pandoc-slides/all.bib

@techreport{luxey_compte-rendu_2014,
	title = {Compte-rendu informel de stage},
	author = {Luxey, Adrien},
	month = jul,
	year = {2014},
	file = {compte-rendu_adrien-luxey.pdf:/home/florent/.zotero/data/storage/UNQETQ8A/compte-rendu_adrien-luxey.pdf:application/pdf}
}

@misc{bosilj_pattern_2017,
	title = {Pattern {Spectra} as {Region} {Descriptors} for {Image} {Classification} and {Retrieval}},
	author = {Bosilj, Petra},
	month = may,
	year = {2017},
	file = {petra_bosilj_expose_letg_costel_pattern_spectra.pdf:/home/florent/.zotero/data/storage/TTX8EEQH/petra_bosilj_expose_letg_costel_pattern_spectra.pdf:application/pdf}
}

@misc{noauthor_presentation_2017,
	title = {Présentation {OBELIX} au {CNES}},
	abstract = {présentation faite au CNES en janvier (+ une mise à jour de juillet pour un séminaire à Annecy) qui permet d’avoir un aperçu de nos travaux sur les représentations hiérarchiques},
	year = {2017},
	file = {Presentation-OBELIX-CNES-26012017-arbres.pdf:/home/florent/.zotero/data/storage/9HTT8V82/Presentation-OBELIX-CNES-26012017-arbres.pdf:application/pdf;Seminaire-LISTIC-06072017.pdf:/home/florent/.zotero/data/storage/8VSQ64TZ/Seminaire-LISTIC-06072017.pdf:application/pdf}
}

@article{brodu_3d_2012,
	title = {3D terrestrial lidar data classification of complex natural scenes using a multi-scale dimensionality criterion: {Applications} in geomorphology},
	volume = {68},
	shorttitle = {3D terrestrial lidar data classification of complex natural scenes using a multi-scale dimensionality criterion},
	url = {http://www.sciencedirect.com/science/article/pii/S0924271612000330},
	urldate = {2017-09-06},
	journal = {ISPRS Journal of Photogrammetry and Remote Sensing},
	author = {Brodu, Nicolas and Lague, Dimitri},
	year = {2012},
	pages = {121--134},
	file = {02 - canupo_preprint.pdf:/home/florent/.zotero/data/storage/KBK38K2S/02 - canupo_preprint.pdf:application/pdf}
}

@book{soille_mathematical_2011,
	address = {Berlin, Heidelberg},
	series = {Lecture {Notes} in {Computer} {Science}},
	title = {Mathematical {Morphology} and {Its} {Applications} to {Image} and {Signal} {Processing}},
	volume = {6671},
	isbn = {978-3-642-21568-1 978-3-642-21569-8},
	url = {http://link.springer.com/10.1007/978-3-642-21569-8},
	urldate = {2018-04-25},
	publisher = {Springer Berlin Heidelberg},
	editor = {Soille, Pierre and Pesaresi, Martino and Ouzounis, Georgios K.},
	year = {2011},
	doi = {10.1007/978-3-642-21569-8},
	file = {Soille et al. - 2011 - Mathematical Morphology and Its Applications to Im.pdf:/home/florent/.zotero/data/storage/96A5XA2U/Soille et al. - 2011 - Mathematical Morphology and Its Applications to Im.pdf:application/pdf}
}

@article{cavallaro_extended_2015,
	title = {Extended self-dual attribute profiles for the classification of hyperspectral images},
	volume = {12},
	number = {8},
	journal = {IEEE Geoscience and Remote Sensing Letters},
	author = {Cavallaro, Gabriele and Dalla Mura, Mauro and Benediktsson, Jón Atli and Bruzzone, Lorenzo},
	year = {2015},
	pages = {1690--1694},
	file = {Cavallaro et al. - 2015 - Extended self-dual attribute profiles for the clas.pdf:/home/florent/.zotero/data/storage/2FKAWHGC/Cavallaro et al. - 2015 - Extended self-dual attribute profiles for the clas.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/9R5IU6Q7/notes.md:text/plain}
}

@misc{ouzounis_differential_2012,
	title = {Differential {Attribute} {Profiles} in {Remote} {Sensing}},
	author = {Ouzounis, Georgios K.},
	year = {2012},
	file = {Ouzounis - 2012 - Differential Attribute Profiles in Remote Sensing.pdf:/home/florent/.zotero/data/storage/EV6PV7K4/Ouzounis - 2012 - Differential Attribute Profiles in Remote Sensing.pdf:application/pdf}
}

@article{pham_local_2018,
	title = {Local {Feature}-{Based} {Attribute} {Profiles} for {Optical} {Remote} {Sensing} {Image} {Classification}},
	volume = {56},
	issn = {0196-2892, 1558-0644},
	url = {http://ieeexplore.ieee.org/document/8082117/},
	doi = {10.1109/TGRS.2017.2761402},
	number = {2},
	urldate = {2018-03-13},
	journal = {IEEE Transactions on Geoscience and Remote Sensing},
	author = {Pham, Minh-Tan and Lefevre, Sebastien and Aptoula, Erchan},
	month = feb,
	year = {2018},
	pages = {1199--1212},
	file = {notes.md:/home/florent/.zotero/data/storage/MQPKSNCW/notes.md:text/plain;Pham et al. - 2018 - Local Feature-Based Attribute Profiles for Optical.pdf:/home/florent/.zotero/data/storage/FZ48DKIC/Pham et al. - 2018 - Local Feature-Based Attribute Profiles for Optical.pdf:application/pdf}
}

@article{damodaran_attribute_2017,
	title = {Attribute {Profiles} on {Derived} {Features} for {Urban} {Land} {Cover} {Classification}},
	volume = {83},
	issn = {0099-1112},
	url = {http://www.ingentaconnect.com/content/10.14358/PERS.83.3.183},
	doi = {10.14358/PERS.83.3.183},
	language = {en},
	number = {3},
	urldate = {2017-12-15},
	journal = {Photogrammetric Engineering \& Remote Sensing},
	author = {Damodaran, Bharath Bhushan and Höhle, Joachim and Lefèvre, Sébastien},
	month = mar,
	year = {2017},
	keywords = {JURSE},
	pages = {183--193},
	file = {Damodaran et al. - 2017 - Attribute Profiles on Derived Features for Urban L.pdf:/home/florent/.zotero/data/storage/IHQTUNCT/Damodaran et al. - 2017 - Attribute Profiles on Derived Features for Urban L.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/UV7XWQDX/notes.md:text/plain}
}

@article{pedergnana_classification_2012,
	title = {Classification of {Remote} {Sensing} {Optical} and {LiDAR} {Data} {Using} {Extended} {Attribute} {Profiles}},
	volume = {6},
	issn = {1932-4553, 1941-0484},
	url = {http://ieeexplore.ieee.org/document/6237479/},
	doi = {10.1109/JSTSP.2012.2208177},
	number = {7},
	urldate = {2018-02-27},
	journal = {IEEE Journal of Selected Topics in Signal Processing},
	author = {Pedergnana, M. and Marpu, P. R. and Dalla Mura, M. and Benediktsson, J. A. and Bruzzone, L.},
	month = nov,
	year = {2012},
	keywords = {classification, lidar, attribute profiles, JURSE},
	pages = {856--865},
	file = {notes.md:/home/florent/.zotero/data/storage/3ABJQDQR/notes.md:text/plain;Pedergnana et al. - 2012 - Classification of Remote Sensing Optical and LiDAR.pdf:/home/florent/.zotero/data/storage/HDQHFWGU/Pedergnana et al. - 2012 - Classification of Remote Sensing Optical and LiDAR.pdf:application/pdf}
}

@inproceedings{liao_lidar_2016,
	title = {{LiDAR} information extraction by attribute filters with partial reconstruction},
	booktitle = {Geoscience and {Remote} {Sensing} {Symposium} ({IGARSS}), 2016 {IEEE} {International}},
	publisher = {IEEE},
	author = {Liao, Wenzhi and Dalla Mura, Mauro and Huang, Xin and Chanussot, Jocelyn and Gautama, Sidharta and Scheunders, Paul and Philips, Wilfried},
	year = {2016},
	keywords = {classification, lidar, attribute profiles, JURSE},
	pages = {1484--1487},
	file = {Liao et al. - 2016 - LiDAR information extraction by attribute filters .pdf:/home/florent/.zotero/data/storage/XUKQBZZF/Liao et al. - 2016 - LiDAR information extraction by attribute filters .pdf:application/pdf}
}

@article{khodadadzadeh_fusion_2015,
	title = {Fusion of {Hyperspectral} and {LiDAR} {Remote} {Sensing} {Data} {Using} {Multiple} {Feature} {Learning}},
	volume = {8},
	issn = {1939-1404, 2151-1535},
	url = {http://ieeexplore.ieee.org/document/7115053/},
	doi = {10.1109/JSTARS.2015.2432037},
	number = {6},
	urldate = {2018-02-27},
	journal = {IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing},
	author = {Khodadadzadeh, Mahdi and Li, Jun and Prasad, Saurabh and Plaza, Antonio},
	month = jun,
	year = {2015},
	keywords = {classification, lidar, attribute profiles, JURSE},
	pages = {2971--2983},
	file = {Khodadadzadeh et al. - 2015 - Fusion of Hyperspectral and LiDAR Remote Sensing D.pdf:/home/florent/.zotero/data/storage/DXZZZWXA/Khodadadzadeh et al. - 2015 - Fusion of Hyperspectral and LiDAR Remote Sensing D.pdf:application/pdf}
}

@article{ghamisi_automatic_2014,
	title = {Automatic {Spectral}-{Spatial} {Classification} {Framework} {Based} on {Attribute} {Profiles} and {Supervised} {Feature} {Extraction}.},
	volume = {52},
	number = {9},
	journal = {IEEE Trans. Geoscience and Remote Sensing},
	author = {Ghamisi, Pedram and Benediktsson, Jon Atli and Sveinsson, Johannes R.},
	year = {2014},
	pages = {5771--5782},
	file = {Ghamisi et al. - 2014 - Automatic Spectral-Spatial Classification Framewor.pdf:/home/florent/.zotero/data/storage/JSH9KRKC/Ghamisi et al. - 2014 - Automatic Spectral-Spatial Classification Framewor.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/4WT86MQM/notes.md:text/plain}
}

@article{aptoula_vector_2016,
	title = {Vector {Attribute} {Profiles} for {Hyperspectral} {Image} {Classification}},
	volume = {54},
	issn = {0196-2892, 1558-0644},
	url = {http://ieeexplore.ieee.org/document/7387766/},
	doi = {10.1109/TGRS.2015.2513424},
	number = {6},
	urldate = {2018-02-27},
	journal = {IEEE Transactions on Geoscience and Remote Sensing},
	author = {Aptoula, Erchan and Dalla Mura, Mauro and Lefevre, Sebastien},
	month = jun,
	year = {2016},
	keywords = {attribute profiles},
	pages = {3208--3220},
	file = {Aptoula et al. - 2016 - Vector Attribute Profiles for Hyperspectral Image .pdf:/home/florent/.zotero/data/storage/EUUXIHGP/Aptoula et al. - 2016 - Vector Attribute Profiles for Hyperspectral Image .pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/Z9EP8RB8/notes.md:text/plain}
}

@article{souza_iamxt:_2017,
	title = {iamxt: {Max}-tree toolbox for image processing and analysis},
	volume = {6},
	issn = {23527110},
	shorttitle = {iamxt},
	url = {http://linkinghub.elsevier.com/retrieve/pii/S2352711017300079},
	doi = {10.1016/j.softx.2017.03.001},
	language = {en},
	urldate = {2018-02-22},
	journal = {SoftwareX},
	author = {Souza, Roberto and Rittner, Letícia and Machado, Rubens and Lotufo, Roberto},
	year = {2017},
	pages = {81--84},
	file = {Souza et al. - 2017 - iamxt Max-tree toolbox for image processing and a.pdf:/home/florent/.zotero/data/storage/T5GIID2Z/Souza et al. - 2017 - iamxt Max-tree toolbox for image processing and a.pdf:application/pdf}
}

@article{bosilj_partition_2018,
	title = {Partition and {Inclusion} {Hierarchies} of {Images}: {A} {Comprehensive} {Survey}},
	volume = {4},
	issn = {2313-433X},
	shorttitle = {Partition and {Inclusion} {Hierarchies} of {Images}},
	url = {http://www.mdpi.com/2313-433X/4/2/33},
	doi = {10.3390/jimaging4020033},
	language = {en},
	number = {2},
	urldate = {2018-02-20},
	journal = {Journal of Imaging},
	author = {Bosilj, Petra and Kijak, Ewa and Lefèvre, Sébastien},
	month = feb,
	year = {2018},
	keywords = {trees},
	pages = {33},
	file = {Bosilj et al. - 2018 - Partition and Inclusion Hierarchies of Images A C.pdf:/home/florent/.zotero/data/storage/EWAAWITS/Bosilj et al. - 2018 - Partition and Inclusion Hierarchies of Images A C.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/2NCPDDEI/notes.md:text/plain}
}

@misc{vogelgesang_matthias_modern_nodate,
	title = {Modern {Beamer} {Presentations} with the metropolis package},
	author = {Vogelgesang, Matthias},
	file = {metropolistheme.pdf:/home/florent/.zotero/data/storage/A2XS87B2/metropolistheme.pdf:application/pdf}
}

@article{qi_pointnet++:_2017,
	title = {{PointNet}++: {Deep} {Hierarchical} {Feature} {Learning} on {Point} {Sets} in a {Metric} {Space}},
	journal = {arXiv preprint arXiv:1706.02413},
	author = {Qi, Charles R and Yi, Li and Su, Hao and Guibas, Leonidas J},
	year = {2017},
	file = {Qi et al. - 2017 - PointNet++ Deep Hierarchical Feature Learning on .pdf:/home/florent/.zotero/data/storage/3ACDSMID/Qi et al. - 2017 - PointNet++ Deep Hierarchical Feature Learning on .pdf:application/pdf}
}

@article{fernandez-diaz_capability_2016,
	title = {Capability {Assessment} and {Performance} {Metrics} for the {Titan} {Multispectral} {Mapping} {Lidar}},
	volume = {8},
	issn = {2072-4292},
	url = {http://www.mdpi.com/2072-4292/8/11/936},
	doi = {10.3390/rs8110936},
	language = {en},
	number = {11},
	urldate = {2018-01-19},
	journal = {Remote Sensing},
	author = {Fernandez-Diaz, Juan and Carter, William and Glennie, Craig and Shrestha, Ramesh and Pan, Zhigang and Ekhtari, Nima and Singhania, Abhinav and Hauser, Darren and Sartori, Michael},
	month = nov,
	year = {2016},
	keywords = {classification, lidar, titan},
	pages = {936},
	file = {Fernandez-Diaz et al. - 2016 - Capability Assessment and Performance Metrics for .pdf:/home/florent/.zotero/data/storage/V8KI9ZE5/Fernandez-Diaz et al. - 2016 - Capability Assessment and Performance Metrics for .pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/UP2SR4S3/notes.md:text/plain}
}

@inproceedings{lods_learning_2017,
	address = {London, United Kingdom},
	series = {Advances in {Intelligent} {Data} {Analysis} {XVI}},
	title = {Learning {DTW}-{Preserving} {Shapelets}},
	volume = {10584},
	url = {https://hal.archives-ouvertes.fr/hal-01565207},
	doi = {10.1007/978-3-319-68765-0_17},
	booktitle = {{IDA} 2017 - 16th {International} {Symposium} on {Intelligent} {Data} {Analysis}},
	publisher = {springer International Publishing},
	author = {Lods, Arnaud and Malinowski, Simon and Tavenard, Romain and Amsaleg, Laurent},
	month = oct,
	year = {2017},
	keywords = {clustering, dynamic time warping, shapelets, time series},
	pages = {198--209},
	file = {Lods et al. - 2017 - Learning DTW-Preserving Shapelets.pdf:/home/florent/.zotero/data/storage/MJTXM3CP/Lods et al. - 2017 - Learning DTW-Preserving Shapelets.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/R98UAC3V/notes.md:text/plain}
}

@misc{lague_classification_2013,
	title = {Classification of point clouds using the {CANUPO} software suite v1.2},
	author = {Lague, Dimitri and Brodu, Nicolas},
	year = {2013},
	file = {Lague and Brodu - 2013 - Classification of point clouds using the CANUPO so.pdf:/home/florent/.zotero/data/storage/NGS8HIKE/Lague and Brodu - 2013 - Classification of point clouds using the CANUPO so.pdf:application/pdf}
}

@article{qi_pointnet:_2016,
	title = {Pointnet: {Deep} learning on point sets for 3d classification and segmentation},
	journal = {arXiv preprint arXiv:1612.00593},
	author = {Qi, Charles R and Su, Hao and Mo, Kaichun and Guibas, Leonidas J},
	year = {2016},
	file = {notes.md:/home/florent/.zotero/data/storage/SH2KD7M5/notes.md:text/plain;Qi et al. - 2016 - Pointnet Deep learning on point sets for 3d class.pdf:/home/florent/.zotero/data/storage/J5WRAITT/Qi et al. - 2016 - Pointnet Deep learning on point sets for 3d class.pdf:application/pdf}
}

@misc{noauthor_mathstic_nodate,
	title = {{MathStic} - {Catalogue} de formation 2017/2018},
	file = {catalogue-formations-scientifiques-2017-18.v.2017.12.20.pdf:/home/florent/.zotero/data/storage/TF2HQXHC/catalogue-formations-scientifiques-2017-18.v.2017.12.20.pdf:application/pdf}
}

@inproceedings{merciol_fast_2015,
	title = {Fast building extraction by multiscale analysis of digital surface models},
	booktitle = {Geoscience and {Remote} {Sensing} {Symposium} ({IGARSS}), 2015 {IEEE} {International}},
	publisher = {IEEE},
	author = {Merciol, François and Lefèvre, Sébastien},
	year = {2015},
	keywords = {DEM, trees, alpha-tree, extraction},
	pages = {553--556},
	file = {Merciol and Lefèvre - 2015 - Fast building extraction by multiscale analysis of.pdf:/home/florent/.zotero/data/storage/GA98PB7S/Merciol and Lefèvre - 2015 - Fast building extraction by multiscale analysis of.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/82EGVD7J/notes.md:text/markdown}
}

@article{niemeyer_contextual_2014,
	title = {Contextual classification of lidar data and building object detection in urban areas},
	volume = {87},
	issn = {09242716},
	url = {http://linkinghub.elsevier.com/retrieve/pii/S0924271613002359},
	doi = {10.1016/j.isprsjprs.2013.11.001},
	language = {en},
	urldate = {2017-12-14},
	journal = {ISPRS Journal of Photogrammetry and Remote Sensing},
	author = {Niemeyer, Joachim and Rottensteiner, Franz and Soergel, Uwe},
	month = jan,
	year = {2014},
	keywords = {NEXT, classification, lidar},
	pages = {152--165},
	file = {Niemeyer et al. - 2014 - Contextual classification of lidar data and buildi.pdf:/home/florent/.zotero/data/storage/GP7KKTPU/Niemeyer et al. - 2014 - Contextual classification of lidar data and buildi.pdf:application/pdf}
}

@article{tooke_predicting_2014,
	title = {Predicting building ages from {LiDAR} data with random forests for building energy modeling},
	volume = {68},
	issn = {03787788},
	url = {http://linkinghub.elsevier.com/retrieve/pii/S0378778813006506},
	doi = {10.1016/j.enbuild.2013.10.004},
	language = {en},
	urldate = {2017-12-14},
	journal = {Energy and Buildings},
	author = {Tooke, Thoreau Rory and Coops, Nicholas C. and Webster, Jessica},
	month = jan,
	year = {2014},
	pages = {603--610},
	file = {Tooke et al. - 2014 - Predicting building ages from LiDAR data with rand.pdf:/home/florent/.zotero/data/storage/IM9587QM/Tooke et al. - 2014 - Predicting building ages from LiDAR data with rand.pdf:application/pdf}
}

@misc{noauthor_specification_nodate,
	title = {{LAS} {SPECIFICATION} {VERSION} 1.2},
	file = {asprs_las_format_v12.pdf:/home/florent/.zotero/data/storage/K2HVTPZH/asprs_las_format_v12.pdf:application/pdf}
}

@misc{noauthor_specification_nodate-1,
	title = {{LAS} {SPECIFICATION} {VERSION} 1.1},
	file = {asprs_las_format_v11.pdf:/home/florent/.zotero/data/storage/3EAXM8QT/asprs_las_format_v11.pdf:application/pdf}
}

@misc{noauthor_specification_nodate-2,
	title = {{LAS} {SPECIFICATION} {VERSION} 1.0},
	file = {asprs_las_format_v10.pdf:/home/florent/.zotero/data/storage/2Q7Q5DSK/asprs_las_format_v10.pdf:application/pdf}
}

@inproceedings{perret_evaluation_2015,
	title = {Evaluation of morphological hierarchies for supervised segmentation},
	doi = {salembiersalembiersalembier},
	booktitle = {International {Symposium} on {Mathematical} {Morphology} and {Its} {Applications} to {Signal} and {Image} {Processing}},
	publisher = {Springer},
	author = {Perret, Benjamin and Cousty, Jean and Ura, Jean Carlo Rivera and Guimarães, Silvio Jamil F.},
	year = {2015},
	pages = {39--50},
	file = {Perret et al. - 2015 - Evaluation of morphological hierarchies for superv.pdf:/home/florent/.zotero/data/storage/MESFAQ5U/Perret et al. - 2015 - Evaluation of morphological hierarchies for superv.pdf:application/pdf}
}

@article{meng_ground_2010,
	title = {Ground {Filtering} {Algorithms} for {Airborne} {LiDAR} {Data}: {A} {Review} of {Critical} {Issues}},
	volume = {2},
	issn = {2072-4292},
	shorttitle = {Ground {Filtering} {Algorithms} for {Airborne} {LiDAR} {Data}},
	url = {http://www.mdpi.com/2072-4292/2/3/833/},
	doi = {10.3390/rs2030833},
	language = {en},
	number = {3},
	urldate = {2017-12-11},
	journal = {Remote Sensing},
	author = {Meng, Xuelian and Currit, Nate and Zhao, Kaiguang},
	month = mar,
	year = {2010},
	pages = {833--860},
	file = {Meng et al. - 2010 - Ground Filtering Algorithms for Airborne LiDAR Dat.pdf:/home/florent/.zotero/data/storage/I5ETNURI/Meng et al. - 2010 - Ground Filtering Algorithms for Airborne LiDAR Dat.pdf:application/pdf}
}

@article{zeng_entropy-based_2016,
	title = {An entropy-based filtering approach for airborne laser scanning data},
	volume = {75},
	issn = {13504495},
	url = {http://linkinghub.elsevier.com/retrieve/pii/S1350449515300256},
	doi = {10.1016/j.infrared.2015.12.021},
	language = {en},
	urldate = {2017-12-11},
	journal = {Infrared Physics \& Technology},
	author = {Zeng, Zhe and Wan, Jiaxin and Liu, Hui},
	month = mar,
	year = {2016},
	pages = {87--92},
	file = {Zeng et al. - 2016 - An entropy-based filtering approach for airborne l.pdf:/home/florent/.zotero/data/storage/BNNKVNQB/Zeng et al. - 2016 - An entropy-based filtering approach for airborne l.pdf:application/pdf}
}

@article{pingel_improved_2013,
	title = {An improved simple morphological filter for the terrain classification of airborne {LIDAR} data},
	volume = {77},
	issn = {09242716},
	url = {http://linkinghub.elsevier.com/retrieve/pii/S0924271613000026},
	doi = {10.1016/j.isprsjprs.2012.12.002},
	language = {en},
	urldate = {2017-12-11},
	journal = {ISPRS Journal of Photogrammetry and Remote Sensing},
	author = {Pingel, Thomas J. and Clarke, Keith C. and McBride, William A.},
	month = mar,
	year = {2013},
	pages = {21--30},
	file = {Pingel et al. - 2013 - An improved simple morphological filter for the te.pdf:/home/florent/.zotero/data/storage/JXHGSCPU/Pingel et al. - 2013 - An improved simple morphological filter for the te.pdf:application/pdf}
}

@article{cheng_building_2013,
	title = {Building region derivation from {LiDAR} data using a reversed iterative mathematic morphological algorithm},
	volume = {286},
	issn = {00304018},
	url = {http://linkinghub.elsevier.com/retrieve/pii/S0030401812008760},
	doi = {10.1016/j.optcom.2012.08.028},
	language = {en},
	urldate = {2017-12-11},
	journal = {Optics Communications},
	author = {Cheng, Liang and Zhao, Wei and Han, Peng and Zhang, Wen and Shan, Jie and Liu, Yongxue and Li, Manchun},
	month = jan,
	year = {2013},
	pages = {244--250},
	file = {Cheng et al. - 2013 - Building region derivation from LiDAR data using a.pdf:/home/florent/.zotero/data/storage/MQIVUMTA/Cheng et al. - 2013 - Building region derivation from LiDAR data using a.pdf:application/pdf}
}

@article{mongus_ground_2014,
	title = {Ground and building extraction from {LiDAR} data based on differential morphological profiles and locally fitted surfaces},
	volume = {93},
	issn = {09242716},
	url = {http://linkinghub.elsevier.com/retrieve/pii/S0924271613002840},
	doi = {10.1016/j.isprsjprs.2013.12.002},
	language = {en},
	urldate = {2017-12-11},
	journal = {ISPRS Journal of Photogrammetry and Remote Sensing},
	author = {Mongus, Domen and Lukač, Niko and Žalik, Borut},
	month = jul,
	year = {2014},
	keywords = {NEXT, lidar, attribute profiles, hierarchical representation, dem},
	pages = {145--156},
	file = {Mongus et al. - 2014 - Ground and building extraction from LiDAR data bas.pdf:/home/florent/.zotero/data/storage/NU52UAEE/Mongus et al. - 2014 - Ground and building extraction from LiDAR data bas.pdf:application/pdf}
}

@article{silvan-cardenas_multi-resolution_2006,
	title = {A multi-resolution approach for filtering {LiDAR} altimetry data},
	volume = {61},
	issn = {09242716},
	url = {http://linkinghub.elsevier.com/retrieve/pii/S0924271606000633},
	doi = {10.1016/j.isprsjprs.2006.06.002},
	language = {en},
	number = {1},
	urldate = {2017-12-11},
	journal = {ISPRS Journal of Photogrammetry and Remote Sensing},
	author = {Silván-Cárdenas, J.L. and Wang, L.},
	month = oct,
	year = {2006},
	pages = {11--22},
	file = {Silván-Cárdenas and Wang - 2006 - A multi-resolution approach for filtering LiDAR al.pdf:/home/florent/.zotero/data/storage/6NJC3PD3/Silván-Cárdenas and Wang - 2006 - A multi-resolution approach for filtering LiDAR al.pdf:application/pdf}
}

@article{mongus_parameter-free_2012,
	title = {Parameter-free ground filtering of {LiDAR} data for automatic {DTM} generation},
	volume = {67},
	issn = {09242716},
	url = {http://linkinghub.elsevier.com/retrieve/pii/S0924271611001122},
	doi = {10.1016/j.isprsjprs.2011.10.002},
	language = {en},
	urldate = {2017-12-11},
	journal = {ISPRS Journal of Photogrammetry and Remote Sensing},
	author = {Mongus, Domen and Žalik, Borut},
	month = jan,
	year = {2012},
	pages = {1--12},
	file = {Mongus and Žalik - 2012 - Parameter-free ground filtering of LiDAR data for .pdf:/home/florent/.zotero/data/storage/JHXFSDIC/Mongus and Žalik - 2012 - Parameter-free ground filtering of LiDAR data for .pdf:application/pdf}
}

@article{yao_automatic_2010,
	title = {Automatic vehicle extraction from airborne {LiDAR} data of urban areas aided by geodesic morphology},
	volume = {31},
	issn = {01678655},
	url = {http://linkinghub.elsevier.com/retrieve/pii/S0167865510000632},
	doi = {10.1016/j.patrec.2010.02.006},
	language = {en},
	number = {10},
	urldate = {2017-12-11},
	journal = {Pattern Recognition Letters},
	author = {Yao, Wei and Hinz, Stefan and Stilla, Uwe},
	month = jul,
	year = {2010},
	pages = {1100--1108},
	file = {Yao et al. - 2010 - Automatic vehicle extraction from airborne LiDAR d.pdf:/home/florent/.zotero/data/storage/4DWHRK4X/Yao et al. - 2010 - Automatic vehicle extraction from airborne LiDAR d.pdf:application/pdf}
}

@article{bartels_threshold-free_2010,
	title = {Threshold-free object and ground point separation in {LIDAR} data},
	volume = {31},
	issn = {01678655},
	url = {http://linkinghub.elsevier.com/retrieve/pii/S0167865510000887},
	doi = {10.1016/j.patrec.2010.03.007},
	language = {en},
	number = {10},
	urldate = {2017-12-11},
	journal = {Pattern Recognition Letters},
	author = {Bartels, Marc and Wei, Hong},
	month = jul,
	year = {2010},
	pages = {1089--1099},
	file = {Bartels and Wei - 2010 - Threshold-free object and ground point separation .pdf:/home/florent/.zotero/data/storage/Q3DTNKPI/Bartels and Wei - 2010 - Threshold-free object and ground point separation .pdf:application/pdf}
}

@article{hui_improved_2016,
	title = {An {Improved} {Morphological} {Algorithm} for {Filtering} {Airborne} {LiDAR} {Point} {Cloud} {Based} on {Multi}-{Level} {Kriging} {Interpolation}},
	volume = {8},
	issn = {2072-4292},
	url = {http://www.mdpi.com/2072-4292/8/1/35},
	doi = {10.3390/rs8010035},
	language = {en},
	number = {1},
	urldate = {2017-12-11},
	journal = {Remote Sensing},
	author = {Hui, Zhenyang and Hu, Youjian and Yevenyo, Yao and Yu, Xianyu},
	month = jan,
	year = {2016},
	pages = {35},
	file = {Hui et al. - 2016 - An Improved Morphological Algorithm for Filtering .pdf:/home/florent/.zotero/data/storage/2VFVI5FM/Hui et al. - 2016 - An Improved Morphological Algorithm for Filtering .pdf:application/pdf}
}

@article{shan_urban_2005,
	title = {Urban {DEM} generation from raw {LiDAR} data},
	volume = {71},
	number = {2},
	journal = {Photogrammetric Engineering \& Remote Sensing},
	author = {Shan, Jie and Aparajithan, Sampath},
	year = {2005},
	pages = {217--226},
	file = {Shan and Aparajithan - 2005 - Urban DEM generation from raw LiDAR data.pdf:/home/florent/.zotero/data/storage/6SE5ZHZA/Shan and Aparajithan - 2005 - Urban DEM generation from raw LiDAR data.pdf:application/pdf}
}

@misc{noauthor_2015_nodate,
	title = {2015 {Aerial} {Laser} and {Photogrammetry} {Survey} of {Dublin} {City} {Collection} {Record}},
	file = {3489_Dublin_Area_2km2_project_Report.pdf:/home/florent/.zotero/data/storage/Q7V6GRUD/3489_Dublin_Area_2km2_project_Report.pdf:application/pdf;ALSDublin15_documentation.pdf:/home/florent/.zotero/data/storage/UGRTADGF/ALSDublin15_documentation.pdf:application/pdf;bulk-download-instructions.html:/home/florent/.zotero/data/storage/TUHP5Z65/bulk-download-instructions.html:text/html;related_publications.txt:/home/florent/.zotero/data/storage/RJXW2Q9Z/related_publications.txt:text/plain}
}

@article{roynard_paris-lille-3d:_2017,
	title = {Paris-{Lille}-3D: a large and high-quality ground truth urban point cloud dataset for automatic segmentation and classification},
	journal = {ArXiv e-prints},
	author = {Roynard, X. and Deschaud, J.-E. and Goulette, F.},
	month = nov,
	year = {2017},
	keywords = {ISMM},
	file = {dataset_description.pdf:/home/florent/.zotero/data/storage/2CJZ22QZ/dataset_description.pdf:application/pdf;Roynard et al. - 2017 - Paris-Lille-3D a large and high-quality ground tr.pdf:/home/florent/.zotero/data/storage/WXU4TN62/Roynard et al. - 2017 - Paris-Lille-3D a large and high-quality ground tr.pdf:application/pdf}
}

@misc{noauthor_ubl_nodate,
	title = {{UBL} - {Catalogue} de formation 2017/2018},
	file = {catalogueFormationV3.pdf:/home/florent/.zotero/data/storage/AMPKR9MG/catalogueFormationV3.pdf:application/pdf}
}

@article{hofle_urban_2012,
	title = {Urban vegetation detection using radiometrically calibrated small-footprint full-waveform airborne {LiDAR} data},
	volume = {67},
	issn = {09242716},
	url = {http://linkinghub.elsevier.com/retrieve/pii/S0924271611001560},
	doi = {10.1016/j.isprsjprs.2011.12.003},
	language = {en},
	urldate = {2017-12-04},
	journal = {ISPRS Journal of Photogrammetry and Remote Sensing},
	author = {Höfle, Bernhard and Hollaus, Markus and Hagenauer, Julian},
	month = jan,
	year = {2012},
	pages = {134--147},
	file = {Höfle et al. - 2012 - Urban vegetation detection using radiometrically c.pdf:/home/florent/.zotero/data/storage/Z4BVG9JJ/Höfle et al. - 2012 - Urban vegetation detection using radiometrically c.pdf:application/pdf}
}

@article{christiansen_designing_2017,
	title = {Designing and {Testing} a {UAV} {Mapping} {System} for {Agricultural} {Field} {Surveying}},
	volume = {17},
	issn = {1424-8220},
	url = {http://www.mdpi.com/1424-8220/17/12/2703},
	doi = {10.3390/s17122703},
	language = {en},
	number = {12},
	urldate = {2017-12-04},
	journal = {Sensors},
	author = {Christiansen, Martin and Laursen, Morten and Jørgensen, Rasmus and Skovsen, Søren and Gislum, René},
	month = nov,
	year = {2017},
	pages = {2703},
	file = {Christiansen et al. - 2017 - Designing and Testing a UAV Mapping System for Agr.pdf:/home/florent/.zotero/data/storage/9AJIKXCQ/Christiansen et al. - 2017 - Designing and Testing a UAV Mapping System for Agr.pdf:application/pdf}
}

@inproceedings{douillard_segmentation_2011,
	title = {On the segmentation of 3D {LIDAR} point clouds},
	booktitle = {Robotics and {Automation} ({ICRA}), 2011 {IEEE} {International} {Conference} on},
	publisher = {IEEE},
	author = {Douillard, Bertrand and Underwood, James and Kuntz, Noah and Vlaskine, Vsevolod and Quadros, Alastair and Morton, Peter and Frenkel, Alon},
	year = {2011},
	pages = {2798--2805},
	file = {Douillard et al. - 2011 - On the segmentation of 3D LIDAR point clouds.pdf:/home/florent/.zotero/data/storage/HBCCB4KR/Douillard et al. - 2011 - On the segmentation of 3D LIDAR point clouds.pdf:application/pdf}
}

@article{popescu_voxel-based_2008,
	title = {A voxel-based lidar method for estimating crown base height for deciduous and pine trees},
	volume = {112},
	issn = {00344257},
	url = {http://linkinghub.elsevier.com/retrieve/pii/S0034425707002532},
	doi = {10.1016/j.rse.2007.06.011},
	language = {en},
	number = {3},
	urldate = {2017-12-04},
	journal = {Remote Sensing of Environment},
	author = {Popescu, Sorin C. and Zhao, Kaiguang},
	month = mar,
	year = {2008},
	pages = {767--781},
	file = {Popescu and Zhao - 2008 - A voxel-based lidar method for estimating crown ba.pdf:/home/florent/.zotero/data/storage/BZHW42MQ/Popescu and Zhao - 2008 - A voxel-based lidar method for estimating crown ba.pdf:application/pdf}
}

@article{vosselman_recognising_2004,
	title = {Recognising structure in laser scanner point clouds},
	volume = {46},
	number = {8},
	journal = {International archives of photogrammetry, remote sensing and spatial information sciences},
	author = {Vosselman, George and Gorte, Ben GH and Sithole, George and Rabbani, Tahir},
	year = {2004},
	pages = {33--38},
	file = {Vosselman et al. - 2004 - Recognising structure in laser scanner point cloud.pdf:/home/florent/.zotero/data/storage/5U8VCVMJ/Vosselman et al. - 2004 - Recognising structure in laser scanner point cloud.pdf:application/pdf}
}

@article{hebel_automatic_2007,
	title = {Automatic registration of laser point clouds of urban areas},
	volume = {36},
	number = {3/W49A},
	journal = {International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences},
	author = {Hebel, Marcus and Stilla, Uwe},
	year = {2007},
	pages = {13--18},
	file = {Hebel and Stilla - 2007 - Automatic registration of laser point clouds of ur.pdf:/home/florent/.zotero/data/storage/J32GHNDM/Hebel and Stilla - 2007 - Automatic registration of laser point clouds of ur.pdf:application/pdf}
}

@article{rutzinger_detection_2010,
	title = {Detection and modelling of 3D trees from mobile laser scanning data},
	volume = {38},
	journal = {Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci},
	author = {Rutzinger, M. and Pratihast, A. K. and Oude Elberink, S. and Vosselman, George},
	year = {2010},
	pages = {520--525},
	file = {Rutzinger et al. - 2010 - Detection and modelling of 3D trees from mobile la.pdf:/home/florent/.zotero/data/storage/P3ZJ46SC/Rutzinger et al. - 2010 - Detection and modelling of 3D trees from mobile la.pdf:application/pdf}
}

@article{sithole_filtering_2005,
	title = {Filtering of airborne laser scanner data based on segmented point clouds},
	volume = {36},
	number = {part 3},
	journal = {International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences},
	author = {Sithole, George and Vosselman, George},
	year = {2005},
	pages = {W19},
	file = {Sithole and Vosselman - 2005 - Filtering of airborne laser scanner data based on .pdf:/home/florent/.zotero/data/storage/H7BVQ8JV/Sithole and Vosselman - 2005 - Filtering of airborne laser scanner data based on .pdf:application/pdf}
}

@article{wang_lidar_2008,
	title = {A {Lidar} {Point} {Cloud} {Based} {Procedure} for {Vertical} {Canopy} {Structure} {Analysis} {And} 3D {Single} {Tree} {Modelling} in {Forest}},
	volume = {8},
	issn = {1424-8220},
	url = {http://www.mdpi.com/1424-8220/8/6/3938/},
	doi = {10.3390/s8063938},
	language = {en},
	number = {6},
	urldate = {2017-12-04},
	journal = {Sensors},
	author = {Wang, Yunsheng and Weinacker, Holger and Koch, Barbara},
	month = jun,
	year = {2008},
	pages = {3938--3951},
	file = {Wang et al. - 2008 - A Lidar Point Cloud Based Procedure for Vertical C.pdf:/home/florent/.zotero/data/storage/G9TES7J8/Wang et al. - 2008 - A Lidar Point Cloud Based Procedure for Vertical C.pdf:application/pdf}
}

@inproceedings{kammerl_real-time_2012,
	title = {Real-time compression of point cloud streams},
	booktitle = {Robotics and {Automation} ({ICRA}), 2012 {IEEE} {International} {Conference} on},
	publisher = {IEEE},
	author = {Kammerl, Julius and Blodow, Nico and Rusu, Radu Bogdan and Gedikli, Suat and Beetz, Michael and Steinbach, Eckehard},
	year = {2012},
	pages = {778--785},
	file = {Kammerl et al. - 2012 - Real-time compression of point cloud streams.pdf:/home/florent/.zotero/data/storage/UCEV67R5/Kammerl et al. - 2012 - Real-time compression of point cloud streams.pdf:application/pdf}
}

@inproceedings{papon_voxel_2013,
	title = {Voxel {Cloud} {Connectivity} {Segmentation} - {Supervoxels} for {Point} {Clouds}},
	isbn = {978-0-7695-4989-7},
	url = {http://ieeexplore.ieee.org/document/6619108/},
	doi = {10.1109/CVPR.2013.264},
	urldate = {2017-12-04},
	publisher = {IEEE},
	author = {Papon, Jeremie and Abramov, Alexey and Schoeler, Markus and Worgotter, Florentin},
	month = jun,
	year = {2013},
	keywords = {NEXT},
	pages = {2027--2034},
	file = {notes.md:/home/florent/.zotero/data/storage/GACEIB7H/notes.md:text/plain;Papon et al. - 2013 - Voxel Cloud Connectivity Segmentation - Supervoxel.pdf:/home/florent/.zotero/data/storage/45XJESXH/Papon et al. - 2013 - Voxel Cloud Connectivity Segmentation - Supervoxel.pdf:application/pdf}
}

@article{ni-meister_validating_2018,
	title = {Validating modeled lidar waveforms in forest canopies with airborne laser scanning data},
	volume = {204},
	issn = {00344257},
	url = {http://linkinghub.elsevier.com/retrieve/pii/S0034425717304911},
	doi = {10.1016/j.rse.2017.10.028},
	language = {en},
	urldate = {2017-12-01},
	journal = {Remote Sensing of Environment},
	author = {Ni-Meister, Wenge and Yang, Wenze and Lee, Shihyan and Strahler, Alan H. and Zhao, Feng},
	month = jan,
	year = {2018},
	pages = {229--243},
	file = {Ni-Meister et al. - 2018 - Validating modeled lidar waveforms in forest canop.pdf:/home/florent/.zotero/data/storage/UAGP2HI7/Ni-Meister et al. - 2018 - Validating modeled lidar waveforms in forest canop.pdf:application/pdf}
}

@article{collin_benthic_2011,
	title = {Benthic {Classifications} {Using} {Bathymetric} {LIDAR} {Waveforms} and {Integration} of {Local} {Spatial} {Statistics} and {Textural} {Features}},
	volume = {62},
	issn = {0749-0208, 1551-5036},
	url = {http://www.bioone.org/doi/abs/10.2112/SI_62_9},
	doi = {10.2112/SI_62_9},
	language = {en},
	urldate = {2017-12-01},
	journal = {Journal of Coastal Research},
	author = {Collin, Antoine and Long, Bernard and Archambault, Phillippe},
	month = mar,
	year = {2011},
	pages = {86--98},
	file = {Collin et al. - 2011 - Benthic Classifications Using Bathymetric LIDAR Wa.pdf:/home/florent/.zotero/data/storage/TERKBB3P/Collin et al. - 2011 - Benthic Classifications Using Bathymetric LIDAR Wa.pdf:application/pdf}
}

@article{li_estimating_2017,
	title = {Estimating {Leaf} {Area} {Density} of {Individual} {Trees} {Using} the {Point} {Cloud} {Segmentation} of {Terrestrial} {LiDAR} {Data} and a {Voxel}-{Based} {Model}},
	volume = {9},
	issn = {2072-4292},
	url = {http://www.mdpi.com/2072-4292/9/11/1202},
	doi = {10.3390/rs9111202},
	language = {en},
	number = {12},
	urldate = {2017-11-27},
	journal = {Remote Sensing},
	author = {Li, Shihua and Dai, Leiyu and Wang, Hongshu and Wang, Yong and He, Ze and Lin, Sen},
	month = nov,
	year = {2017},
	pages = {1202},
	file = {Li et al. - 2017 - Estimating Leaf Area Density of Individual Trees U.pdf:/home/florent/.zotero/data/storage/529WZ9AX/Li et al. - 2017 - Estimating Leaf Area Density of Individual Trees U.pdf:application/pdf}
}

@article{li_airborne_2017,
	title = {Airborne {LiDAR} {Data} {Filtering} {Based} on {Geodesic} {Transformations} of {Mathematical} {Morphology}},
	volume = {9},
	issn = {2072-4292},
	url = {http://www.mdpi.com/2072-4292/9/11/1104},
	doi = {10.3390/rs9111104},
	language = {en},
	number = {11},
	urldate = {2017-11-27},
	journal = {Remote Sensing},
	author = {Li, Yong and Yong, Bin and van Oosterom, Peter and Lemmens, Mathias and Wu, Huayi and Ren, Liliang and Zheng, Mingxue and Zhou, Jiajun},
	month = oct,
	year = {2017},
	pages = {1104},
	file = {Li et al. - 2017 - Airborne LiDAR Data Filtering Based on Geodesic Tr.pdf:/home/florent/.zotero/data/storage/ADKSGRTU/Li et al. - 2017 - Airborne LiDAR Data Filtering Based on Geodesic Tr.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/IKG42EV7/notes.md:text/plain}
}

@misc{noauthor_biblio_nodate,
	title = {Biblio {LiDAR} {LETG}},
	file = {Biblio LiDAR LETG.pptx:/home/florent/.zotero/data/storage/95ERXXVN/Biblio LiDAR LETG.pptx:application/vnd.openxmlformats-officedocument.presentationml.presentation}
}

@article{simpson_assessment_2017,
	title = {Assessment of {Errors} {Caused} by {Forest} {Vegetation} {Structure} in {Airborne} {LiDAR}-{Derived} {DTMs}},
	volume = {9},
	number = {11},
	journal = {Remote Sensing},
	author = {Simpson, Jake E and Smith, Thomas EL and Wooster, Martin J},
	year = {2017},
	pages = {1101},
	file = {Simpson et al. - 2017 - Assessment of Errors Caused by Forest Vegetation S.pdf:/home/florent/.zotero/data/storage/5JPFR4DZ/Simpson et al. - 2017 - Assessment of Errors Caused by Forest Vegetation S.pdf:application/pdf}
}

@article{ferraz_3-d_2012,
	title = {3-{D} mapping of a multi-layered {Mediterranean} forest using {ALS} data},
	volume = {121},
	journal = {Remote Sensing of Environment},
	author = {Ferraz, António and Bretar, Frédéric and Jacquemoud, Stéphane and Gonçalves, Gil and Pereira, Luisa and Tomé, Margarida and Soares, Paula},
	year = {2012},
	pages = {210--223},
	file = {Ferraz et al. - 2012 - 3-D mapping of a multi-layered Mediterranean fores.pdf:/home/florent/.zotero/data/storage/8GCU77ST/Ferraz et al. - 2012 - 3-D mapping of a multi-layered Mediterranean fores.pdf:application/pdf}
}

@inproceedings{ferraz_3d_2010,
	title = {3D segmentation of forest structure using a mean-shift based algorithm},
	booktitle = {Image {Processing} ({ICIP}), 2010 17th {IEEE} {International} {Conference} on},
	publisher = {IEEE},
	author = {Ferraz, António and Bretar, Frédéric and Jacquemoud, Stéphane and Gonçalves, Gil and Pereira, Luisa},
	year = {2010},
	pages = {1413--1416},
	file = {Ferraz et al. - 2010 - 3D segmentation of forest structure using a mean-s.pdf:/home/florent/.zotero/data/storage/5E8NTMEQ/Ferraz et al. - 2010 - 3D segmentation of forest structure using a mean-s.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/FJ27PJXV/notes.md:text/plain}
}

@misc{noauthor_specification_nodate-3,
	title = {{LAS} {SPECIFICATION} {VERSION} 1.4},
	file = {LAS_1_4_r13.pdf:/home/florent/.zotero/data/storage/QUQDTQDF/LAS_1_4_r13.pdf:application/pdf;LAS_1-4_R6_Annotated.pdf:/home/florent/.zotero/data/storage/XGRGVFVF/LAS_1-4_R6_Annotated.pdf:application/pdf}
}

@misc{noauthor_specification_nodate-4,
	title = {{LAS} {SPECIFICATION} {VERSION} 1.3},
	file = {asprs_las_spec_v13.pdf:/home/florent/.zotero/data/storage/RKXTMZME/asprs_las_spec_v13.pdf:application/pdf}
}

@article{zhu_deep_2017,
	title = {Deep learning in remote sensing: a review},
	journal = {arXiv preprint arXiv:1710.03959},
	author = {Zhu, Xiao Xiang and Tuia, Devis and Mou, Lichao and Xia, Gui-Song and Zhang, Liangpei and Xu, Feng and Fraundorfer, Friedrich},
	year = {2017},
	file = {Zhu et al. - 2017 - Deep learning in remote sensing a review.pdf:/home/florent/.zotero/data/storage/T8T46F9K/Zhu et al. - 2017 - Deep learning in remote sensing a review.pdf:application/pdf}
}

@misc{noauthor_charte_nodate,
	title = {Charte des moyens informatiques de l'{IRISA}},
	file = {ChartemoyensinfoIRISA-V2.5.pdf:/home/florent/.zotero/data/storage/R38US7DH/ChartemoyensinfoIRISA-V2.5.pdf:application/pdf}
}

@misc{noauthor_presentation_nodate,
	title = {Présentation {CNES} de l'{Orféo} {Tool} {Box} ({OTB})},
	file = {otb-general-fr.pdf:/home/florent/.zotero/data/storage/QKC4HEJQ/otb-general-fr.pdf:application/pdf;workshopSlides-fr.pdf:/home/florent/.zotero/data/storage/G58G5HGK/workshopSlides-fr.pdf:application/pdf}
}

@misc{noauthor_open_nodate,
	title = {Open {Source} processing of remote sensing images ({OTB})},
	file = {Develop with OTB.pdf:/home/florent/.zotero/data/storage/E8KAAQSU/Develop with OTB.pdf:application/pdf;Guide d’installation OTB.pdf:/home/florent/.zotero/data/storage/9W2F24H6/Guide d’installation OTB.pdf:application/pdf;workshopSolution-fr.pdf:/home/florent/.zotero/data/storage/62WSNVE6/workshopSolution-fr.pdf:application/pdf}
}

@article{dalla_mura_morphological_2010,
	title = {Morphological attribute profiles for the analysis of very high resolution images},
	volume = {48},
	number = {10},
	journal = {IEEE Transactions on Geoscience and Remote Sensing},
	author = {Dalla Mura, Mauro and Benediktsson, Jón Atli and Waske, Björn and Bruzzone, Lorenzo},
	year = {2010},
	pages = {3747--3762},
	file = {Dalla Mura et al. - 2010 - Morphological attribute profiles for the analysis .pdf:/home/florent/.zotero/data/storage/VFXJ8WQZ/Dalla Mura et al. - 2010 - Morphological attribute profiles for the analysis .pdf:application/pdf;maxtree.png:/home/florent/.zotero/data/storage/9WVGTB3D/maxtree.png:image/png;notes.md:/home/florent/.zotero/data/storage/DU3ZZV4G/notes.md:text/plain}
}

@article{angulo_hypercomplex_2011,
	title = {Hypercomplex mathematical morphology},
	volume = {41},
	number = {1},
	journal = {Journal of Mathematical Imaging and Vision},
	author = {Angulo, Jesús},
	year = {2011},
	pages = {86--108},
	file = {Angulo - 2011 - Hypercomplex mathematical morphology.pdf:/home/florent/.zotero/data/storage/C7V2DV4T/Angulo - 2011 - Hypercomplex mathematical morphology.pdf:application/pdf}
}

@misc{noauthor_vpn_nodate,
	title = {{VPN} {Costel}},
	file = {tuto_vpn.pdf:/home/florent/.zotero/data/storage/MXMGAAEQ/tuto_vpn.pdf:application/pdf}
}

@article{serna_segmentation_2016,
	series = {{ISPRS} {International} {Journal} of {Geo}-{Information}},
	title = {Segmentation of façades from urban 3D point clouds using geometrical and morphological attribute-based operators},
	volume = {5},
	url = {https://hal-mines-paristech.archives-ouvertes.fr/hal-01254284},
	doi = {10.3390/ijgi5010006},
	number = {1},
	journal = {ISPRS International Journal of Geo-Information},
	author = {Serna, Andrés and Marcotegui, Beatriz and Hernández, Jorge},
	year = {2016},
	keywords = {NEXT, mathematical morphology, segmentation, lidar, ISMM},
	pages = {6},
	file = {notes.md:/home/florent/.zotero/data/storage/EKPPL9RA/notes.md:text/markdown;Serna et al. - 2016 - Segmentation of Façades from Urban 3D Point Clouds.pdf:/home/florent/.zotero/data/storage/4R57W3BF/Serna et al. - 2016 - Segmentation of Façades from Urban 3D Point Clouds.pdf:application/pdf}
}

@misc{noauthor_presentation_nodate-1,
	title = {Presentation {OBELIX} {ESA}},
	file = {Presentation-OBELIX-trees-11102017.pdf:/home/florent/.zotero/data/storage/KHHB4987/Presentation-OBELIX-trees-11102017.pdf:application/pdf}
}

@article{koenig_full-waveform_2016,
	title = {Full-{Waveform} {Airborne} {Laser} {Scanning} in {Vegetation} {Studies}—{A} {Review} of {Point} {Cloud} and {Waveform} {Features} for {Tree} {Species} {Classification}},
	volume = {7},
	issn = {1999-4907},
	url = {http://www.mdpi.com/1999-4907/7/9/198},
	doi = {10.3390/f7090198},
	language = {en},
	number = {9},
	urldate = {2017-09-11},
	journal = {Forests},
	author = {Koenig, Kristina and Höfle, Bernhard},
	month = jun,
	year = {2016},
	pages = {198},
	file = {04 - forests-07-00198.pdf:/home/florent/.zotero/data/storage/U7R82Z2K/04 - forests-07-00198.pdf:application/pdf;beech_leafoff.jpg:/home/florent/.zotero/data/storage/DPSEH7VN/beech_leafoff.jpg:image/jpeg;beech_leafon.jpg:/home/florent/.zotero/data/storage/ID2BVMBJ/beech_leafon.jpg:image/jpeg;larch.jpg:/home/florent/.zotero/data/storage/2NE43X36/larch.jpg:image/jpeg}
}

@inproceedings{crozet_first_2014,
	title = {A first parallel algorithm to compute the morphological tree of shapes of {nD} images},
	booktitle = {Image {Processing} ({ICIP}), 2014 {IEEE} {International} {Conference} on},
	publisher = {IEEE},
	author = {Crozet, Sébastien and Géraud, Thierry},
	year = {2014},
	pages = {2933--2937},
	file = {A first parallel algorithm to compute the morphological tree of shapes of nD images.pdf:/home/florent/.zotero/data/storage/EA4RM6RC/A first parallel algorithm to compute the morphological tree of shapes of nD images.pdf:application/pdf}
}

@article{carlinet_comparative_2014,
	title = {A comparative review of component tree computation algorithms},
	volume = {23},
	number = {9},
	journal = {IEEE Transactions on Image Processing},
	author = {Carlinet, Edwin and Géraud, Thierry},
	year = {2014},
	pages = {3885--3895},
	file = {A Comparative Review of Component Tree.pdf:/home/florent/.zotero/data/storage/R25G4HRH/A Comparative Review of Component Tree.pdf:application/pdf}
}

@inproceedings{geraud_quasi-linear_2013,
	title = {A quasi-linear algorithm to compute the tree of shapes of {nD} images},
	booktitle = {International {Symposium} on {Mathematical} {Morphology} and {Its} {Applications} to {Signal} and {Image} {Processing}},
	publisher = {Springer},
	author = {Géraud, Thierry and Carlinet, Edwin and Crozet, Sébastien and Najman, Laurent},
	year = {2013},
	note = {00074},
	pages = {98--110},
	file = {A quasi-linear algorithm to compute the tree of shapes.pdf:/home/florent/.zotero/data/storage/KT9Z2M6X/A quasi-linear algorithm to compute the tree of shapes.pdf:application/pdf}
}

@inproceedings{carlinet_comparison_2013,
	title = {A comparison of many max-tree computation algorithms},
	booktitle = {International {Symposium} on {Mathematical} {Morphology} and {Its} {Applications} to {Signal} and {Image} {Processing}},
	publisher = {Springer},
	author = {Carlinet, Edwin and Géraud, Thierry},
	year = {2013},
	pages = {73--85},
	file = {A comparison of many max-tree computation algorithms.pdf:/home/florent/.zotero/data/storage/3ECBJUWR/A comparison of many max-tree computation algorithms.pdf:application/pdf}
}

@article{havel_efficient_2016,
	title = {Efficient tree construction for multiscale image representation and processing},
	journal = {Journal of Real-Time Image Processing},
	author = {Havel, Jiří and Merciol, François and Lefèvre, Sébastien},
	year = {2016},
	pages = {1--18},
	file = {Efficient tree construction for multiscale image representation and processing.pdf:/home/florent/.zotero/data/storage/NENQF7UR/Efficient tree construction for multiscale image representation and processing.pdf:application/pdf}
}

@book{soille_morphological_2013,
	title = {Morphological image analysis: principles and applications},
	publisher = {Springer Science \& Business Media},
	author = {Soille, Pierre},
	year = {2013}
}

@article{wang_composite_2017,
	title = {Composite {Kernel} {Method} for {PolSAR} {Image} {Classification} {Based} on {Polarimetric}-{Spatial} {Information}},
	volume = {7},
	number = {6},
	journal = {Applied Sciences},
	author = {Wang, Xianyuan and Cao, Zongjie and Ding, Yao and Feng, Jilan},
	year = {2017},
	pages = {612}
}

@article{liu_mapping_2017,
	title = {Mapping urban tree species using integrated airborne hyperspectral and {LiDAR} remote sensing data},
	volume = {200},
	journal = {Remote Sensing of Environment},
	author = {Liu, Luxia and Coops, Nicholas C and Aven, Neal W and Pang, Yong},
	year = {2017},
	pages = {170--182},
	file = {Mapping urban tree species using integrated airborne hyperspectral and LiDAR remote sensing data.pdf:/home/florent/.zotero/data/storage/E65Z3JQX/Mapping urban tree species using integrated airborne hyperspectral and LiDAR remote sensing data.pdf:application/pdf}
}

@article{cao_tree_2016,
	title = {Tree species classification in subtropical forests using small-footprint full-waveform {LiDAR} data},
	volume = {49},
	journal = {International Journal of Applied Earth Observation and Geoinformation},
	author = {Cao, Lin and Coops, Nicholas C and Innes, John L and Dai, Jinsong and Ruan, Honghua and She, Guanghui},
	year = {2016},
	note = {00028},
	pages = {39--51},
	file = {Tree species classification in subtropical forests using small-footprint full-waveform LiDAR data.pdf:/home/florent/.zotero/data/storage/6MHUVPPF/Tree species classification in subtropical forests using small-footprint full-waveform LiDAR data.pdf:application/pdf}
}

@inproceedings{angulo_morphological_2015,
	title = {Morphological {Scale}-{Space} {Operators} for {Images} {Supported} on {Point} {Clouds}},
	booktitle = {International {Conference} on {Scale} {Space} and {Variational} {Methods} in {Computer} {Vision}},
	publisher = {Springer},
	author = {Angulo, Jesus},
	year = {2015},
	pages = {78--89},
	file = {09 - MorphoScaleSpacePointClouds_angulo_v2.pdf:/home/florent/.zotero/data/storage/NA26IVZN/09 - MorphoScaleSpacePointClouds_angulo_v2.pdf:application/pdf}
}

@article{tochon_use_2015,
	title = {On the use of binary partition trees for the tree crown segmentation of tropical rainforest hyperspectral images},
	volume = {159},
	journal = {Remote sensing of environment},
	author = {Tochon, Guillaume and Feret, Jean-Baptiste and Valero, S and Martin, Roberta E and Knapp, David E and Salembier, P and Chanussot, Jocelyn and Asner, Gregory P},
	year = {2015},
	pages = {318--331},
	file = {On_the_use_of_binary_partition_trees_for.pdf:/home/florent/.zotero/data/storage/WEX3WETK/On_the_use_of_binary_partition_trees_for.pdf:application/pdf}
}

@article{soille_advances_2002,
	title = {Advances in mathematical morphology applied to geoscience and remote sensing},
	volume = {40},
	number = {9},
	journal = {IEEE Transactions on Geoscience and Remote Sensing},
	author = {Soille, Pierre and Pesaresi, Martino},
	year = {2002},
	pages = {2042--2055},
	file = {Advances in Mathematical Morphology Applied to Geoscience and Remote Sensing.pdf:/home/florent/.zotero/data/storage/GB2GMDV5/Advances in Mathematical Morphology Applied to Geoscience and Remote Sensing.pdf:application/pdf}
}

@inproceedings{chauve_fullanalyze:_2009,
	title = {Fullanalyze: a research tool for handling, processing and analyzing full-waveform lidar data},
	volume = {4},
	booktitle = {Geoscience and {Remote} {Sensing} {Symposium}, 2009 {IEEE} {International}, {IGARSS} 2009},
	publisher = {IEEE},
	author = {Chauve, Adrien and Bretar, Frédéric and Durrieu, Sylvie and Pierrot-Deseilligny, Marc and Puech, William},
	year = {2009},
	pages = {IV--841},
	file = {Fullanalyze.pdf:/home/florent/.zotero/data/storage/PB7FAHXF/Fullanalyze.pdf:application/pdf}
}

@article{mallet_full-waveform_2009,
	title = {Full-waveform topographic lidar: {State}-of-the-art},
	volume = {64},
	number = {1},
	journal = {ISPRS Journal of photogrammetry and remote sensing},
	author = {Mallet, Clément and Bretar, Frédéric},
	year = {2009},
	pages = {1--16},
	file = {Full waveform topographic lidar  state-of-the-art.pdf:/home/florent/.zotero/data/storage/Q5582ZQK/Full waveform topographic lidar  state-of-the-art.pdf:application/pdf;Le lidar topographique à retour d’onde complète  état de l’art.pdf:/home/florent/.zotero/data/storage/GMH7SGH8/Le lidar topographique à retour d’onde complète  état de l’art.pdf:application/pdf}
}

@misc{corpetti_morphological_nodate,
	title = {Morphological characterization of full waveform airborne {LiDAR} data},
	author = {Corpetti, Thomas},
	file = {sujet_lidar_en.pdf:/home/florent/.zotero/data/storage/4J8CUW94/sujet_lidar_en.pdf:application/pdf;sujet_lidar_fr.pdf:/home/florent/.zotero/data/storage/QCICZC3Q/sujet_lidar_fr.pdf:application/pdf}
}

@article{calderon_point_2014,
	title = {Point {Morphology}},
	journal = {ACM Transactions on Graphics (Proc. SIGGRAPH 2014)},
	author = {Calderon, Stéphane and Boubekeur, Tamy},
	year = {2014},
	note = {00024},
	keywords = {NEXT, morphology, 3D, ISMM},
	file = {Calderon and Boubekeur - 2014 - Point Morphology.pdf:/home/florent/.zotero/data/storage/PV6U24D3/Calderon and Boubekeur - 2014 - Point Morphology.pdf:application/pdf}
}

@article{bosilj_retrieval_2016,
	title = {Retrieval of {Remote} {Sensing} {Images} with {Pattern} {Spectra} {Descriptors}},
	volume = {5},
	issn = {2220-9964},
	url = {http://www.mdpi.com/2220-9964/5/12/228},
	doi = {10.3390/ijgi5120228},
	language = {en},
	number = {12},
	urldate = {2017-09-21},
	journal = {ISPRS International Journal of Geo-Information},
	author = {Bosilj, Petra and Aptoula, Erchan and Lefèvre, Sébastien and Kijak, Ewa},
	month = feb,
	year = {2016},
	pages = {228},
	file = {Retrieval of Remote Sensing Images with Pattern Spectra Descriptors.pdf:/home/florent/.zotero/data/storage/DKRUK3AJ/Retrieval of Remote Sensing Images with Pattern Spectra Descriptors.pdf:application/pdf}
}

@phdthesis{mallet_analyse_2010,
	title = {Analyse des données lidar aéroportées à {Retour} d'{Onde} {Complète} pour la cartographie des milieux urbains},
	school = {Télécom ParisTech},
	author = {Mallet, Clément},
	year = {2010},
	file = {Mallet - 2010 - Analyse des données lidar aéroportées à Retour d'O.pdf:/home/florent/.zotero/data/storage/MQGZNZUV/Mallet - 2010 - Analyse des données lidar aéroportées à Retour d'O.pdf:application/pdf;Vue globale.png:/home/florent/.zotero/data/storage/UEQVSTAK/Vue globale.png:image/png}
}

@inproceedings{chauve_processing_2008,
	title = {Processing full-waveform lidar data: modelling raw signals},
	booktitle = {International archives of photogrammetry, remote sensing and spatial information sciences 2007},
	author = {Chauve, Adrien and Mallet, Clément and Bretar, Frédéric and Durrieu, Sylvie and Pierrot-Deseilligny, Marc and Puech, William},
	year = {2008},
	pages = {102--107},
	file = {Chauve_2007_Laser_scanning.pdf:/home/florent/.zotero/data/storage/X5TTW84J/Chauve_2007_Laser_scanning.pdf:application/pdf}
}

@article{wagner_gaussian_2006,
	title = {Gaussian decomposition and calibration of a novel small-footprint full-waveform digitising airborne laser scanner},
	volume = {60},
	number = {2},
	journal = {ISPRS Journal of Photogrammetry and Remote Sensing},
	author = {Wagner, Wolfgang and Ullrich, Andreas and Ducic, Vesna and Melzer, Thomas and Studnicka, Nick},
	year = {2006},
	pages = {100--112}
}

@book{ose_multispectral_2016,
	title = {Multispectral {Satellite} {Image} {Processing}},
	isbn = {978-1-78548-102-4},
	author = {Ose, Kenji and Corpetti, Thomas and Demagistri, Laurent},
	month = dec,
	year = {2016},
	file = {01 - generalites_classification.pdf:/home/florent/.zotero/data/storage/XM3RUKXK/01 - generalites_classification.pdf:application/pdf}
}

@article{guo_relevance_2011,
	title = {Relevance of airborne lidar and multispectral image data for urban scene classification using {Random} {Forests}},
	volume = {66},
	issn = {09242716},
	url = {http://linkinghub.elsevier.com/retrieve/pii/S0924271610000705},
	doi = {10.1016/j.isprsjprs.2010.08.007},
	language = {en},
	number = {1},
	urldate = {2017-09-11},
	journal = {ISPRS Journal of Photogrammetry and Remote Sensing},
	author = {Guo, Li and Chehata, Nesrine and Mallet, Clément and Boukir, Samia},
	month = jan,
	year = {2011},
	note = {00000},
	keywords = {NEXT, classification, lidar, JURSE},
	pages = {56--66},
	file = {Guo et al. - 2011 - Relevance of airborne lidar and multispectral imag.pdf:/home/florent/.zotero/data/storage/HS8E73EZ/Guo et al. - 2011 - Relevance of airborne lidar and multispectral imag.pdf:application/pdf}
}

@article{mallet_analysis_2008,
	title = {Analysis of full-waveform lidar data for classification of urban areas},
	volume = {5},
	journal = {Photogrammetrie Fernerkundung GeoInformation (PFG)},
	author = {Mallet, Clément and Bretar, Frederic and Soergel, Uwe},
	month = may,
	year = {2008},
	pages = {337--349},
	file = {05 - FWF_pfg_heft5.pdf:/home/florent/.zotero/data/storage/QZXWQD25/05 - FWF_pfg_heft5.pdf:application/pdf}
}

@phdthesis{bosilj_image_2016,
	title = {Image indexing and retrieval using component trees},
	school = {Lorient},
	author = {Bosilj, Petra},
	year = {2016},
	file = {Petra Bosilj - thesis.pdf:/home/florent/.zotero/data/storage/NGZF5T59/Petra Bosilj - thesis.pdf:application/pdf}
}

@article{fehri_segmentation_2018,
	title = {Segmentation hiérarchique faiblement supervisée},
	url = {http://arxiv.org/abs/1802.07008},
	abstract = {Image segmentation is the process of partitioning an image into a set of meaningful regions according to some criteria. Hierarchical segmentation has emerged as a major trend in this regard as it favors the emergence of important regions at different scales. On the other hand, many methods allow us to have prior information on the position of structures of interest in the images. In this paper, we present a versatile hierarchical segmentation method that takes into account any prior spatial information and outputs a hierarchical segmentation that emphasizes the contours or regions of interest while preserving the important structures in the image. An application of this method to the weakly-supervised segmentation problem is presented.},
	language = {fr},
	urldate = {2018-05-25},
	journal = {arXiv:1802.07008 [cs, stat]},
	author = {Fehri, Amin and Velasco-Forero, Santiago and Meyer, Fernand},
	month = feb,
	year = {2018},
	note = {00000 
arXiv: 1802.07008},
	keywords = {segmentation, deep learning},
	file = {Fehri et al. - 2018 - Segmentation hiérarchique faiblement supervisée.pdf:/home/florent/.zotero/data/storage/A9Q6KIFX/Fehri et al. - 2018 - Segmentation hiérarchique faiblement supervisée.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/C5TFCRGV/notes.md:text/markdown}
}

@article{rother_grabcut_2004,
	title = {“{GrabCut}” — {Interactive} {Foreground} {Extraction} using {Iterated} {Graph} {Cuts}},
	abstract = {The problem of efficient, interactive foreground/background segmentation in still images is of great practical importance in image editing. Classical image segmentation tools use either texture (colour) information, e.g. Magic Wand, or edge (contrast) information, e.g. Intelligent Scissors. Recently, an approach based on optimization by graph-cut has been developed which successfully combines both types of information. In this paper we extend the graph-cut approach in three respects. First, we have developed a more powerful, iterative version of the optimisation. Secondly, the power of the iterative algorithm is used to simplify substantially the user interaction needed for a given quality of result. Thirdly, a robust algorithm for “border matting” has been developed to estimate simultaneously the alpha-matte around an object boundary and the colours of foreground pixels. We show that for moderately difficult examples the proposed method outperforms competitive tools.},
	language = {en},
	author = {Rother, Carsten and Kolmogorov, Vladimir and Blake, Andrew},
	year = {2004},
	pages = {6},
	file = {Rother et al. - 2004 - “GrabCut” — Interactive Foreground Extraction usin.pdf:/home/florent/.zotero/data/storage/5SPD68B5/Rother et al. - 2004 - “GrabCut” — Interactive Foreground Extraction usin.pdf:application/pdf}
}

@article{pham_recent_2018,
	title = {Recent {Developments} from {Attribute} {Profiles} for {Remote} {Sensing} {Image} {Classification}},
	language = {en},
	author = {Pham, Minh-Tan and Aptoula, Erchan and Lefevre, Sebastien and Bruzzone, Lorenzo},
	year = {2018},
	pages = {6},
	file = {notes.md:/home/florent/.zotero/data/storage/FJ9I5RIZ/notes.md:text/plain;Pham et al. - 2018 - Recent Developments from Attribute Profiles for Re.pdf:/home/florent/.zotero/data/storage/NKQ3Z9W5/Pham et al. - 2018 - Recent Developments from Attribute Profiles for Re.pdf:application/pdf}
}

@article{bosilj_satellite_2015,
	title = {Satellite {Image} {Retrieval} with {Pattern} {Spectra} {Descriptors}},
	abstract = {The increasing volume of Earth Observation data calls for appropriate solutions in satellite image retrieval. We address this problem by considering morphological descriptors called pattern spectra. Such descriptors are histogram-like structures that contain the information on the distribution of predefined properties (attributes) of image components. They can be computed both at the local and global scale, and are computationally attractive. We demonstrate how they can be embedded in an image retrieval framework and report their promising performances when dealing with a standard satellite image dataset.},
	language = {en},
	author = {Bosilj, Petra and Aptoula, Erchan and Lefevre, Sebastien and Kijak, Ewa},
	year = {2015},
	pages = {4},
	file = {Bosilj et al. - 2015 - Satellite Image Retrieval with Pattern Spectra Des.pdf:/home/florent/.zotero/data/storage/3RVA534X/Bosilj et al. - 2015 - Satellite Image Retrieval with Pattern Spectra Des.pdf:application/pdf}
}

@book{soille_alpha-tree_2012,
	address = {Luxembourg},
	title = {The alpha-tree algorithm: theory, algorithms, and applications.},
	isbn = {978-92-79-26279-1},
	shorttitle = {The alpha-tree algorithm},
	abstract = {A new multi-scale graph-space connectivity framework is presented. It is based upon a measure of dissimilarity between adjacent elements of the graph that is used to construct a hierarchy of partitions. Connected components or partition cells are either preserved or rejected based on a set of attribute criteria that are enumerated through logical predicates. Enforcing attribute constraints generates a dichotomy of the partition hierarchy that can be used for image segmentation and other related applications. The framework is supported by an efficient union-find based algorithm that delivers a tree representation of the totally ordered set of graph-space partitions. It is referred to as the Alpha-Tree. The practical complexity of the algorithm is linear with respect to the number of pixels. Processes on the tree can be launched interactively and in real-time, from a separate module detached from the tree construction phase. The type of attributes and attribute thresholds can be set and adjusted interactively. Timed experiments on highly complicated and massive satellite image tiles are presented, complemented by comparisons to the standard method.},
	language = {en},
	publisher = {Publications Office},
	author = {Soille, Pierre and Ouzounis, Georgios K and {European Commission} and {Joint Research Centre} and {Institute for the Protection and the Security of the Citizen}},
	year = {2012},
	note = {OCLC: 847462885},
	file = {Soille et al. - 2012 - The alpha-tree algorithm theory, algorithms, and .pdf:/home/florent/.zotero/data/storage/HXVA93GX/Soille et al. - 2012 - The alpha-tree algorithm theory, algorithms, and .pdf:application/pdf}
}

@article{zhao_impacts_2016,
	title = {Impacts of {LiDAR} sampling methods and point spacing density on {DEM} generation},
	volume = {2},
	number = {3},
	journal = {Papers in Applied Geography},
	author = {Zhao, Chunhong and Jensen, Jennifer and Deng, Xiangzheng and Dede-Bamfo, Nathaniel},
	year = {2016},
	pages = {261--270},
	file = {notes.md:/home/florent/.zotero/data/storage/VJNHVAC5/notes.md:text/markdown;Zhao et al. - 2016 - Impacts of LiDAR sampling methods and point spacin.pdf:/home/florent/.zotero/data/storage/KZWGNKQL/Zhao et al. - 2016 - Impacts of LiDAR sampling methods and point spacin.pdf:application/pdf}
}

@article{jensen_assessment_2016,
	title = {Assessment of image-based point cloud products to generate a bare earth surface and estimate canopy heights in a woodland ecosystem},
	volume = {8},
	number = {1},
	journal = {Remote Sensing},
	author = {Jensen, Jennifer LR and Mathews, Adam J},
	year = {2016},
	pages = {50},
	file = {Jensen and Mathews - 2016 - Assessment of image-based point cloud products to .pdf:/home/florent/.zotero/data/storage/UNSWERR2/Jensen and Mathews - 2016 - Assessment of image-based point cloud products to .pdf:application/pdf}
}

@inproceedings{drouyer_sparse_2017,
	title = {Sparse stereo disparity map densification using hierarchical image segmentation},
	booktitle = {International {Symposium} on {Mathematical} {Morphology} and {Its} {Applications} to {Signal} and {Image} {Processing}},
	publisher = {Springer},
	author = {Drouyer, Sébastien and Beucher, Serge and Bilodeau, Michel and Moreaud, Maxime and Sorbier, Loïc},
	year = {2017},
	pages = {172--184},
	file = {Drouyer et al. - 2017 - Sparse stereo disparity map densification using hi.pdf:/home/florent/.zotero/data/storage/74M6ACYG/Drouyer et al. - 2017 - Sparse stereo disparity map densification using hi.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/LIPFZA6D/notes.md:text/markdown}
}

@article{min_fast_2014,
	title = {Fast global image smoothing based on weighted least squares},
	volume = {23},
	number = {12},
	journal = {IEEE Transactions on Image Processing},
	author = {Min, Dongbo and Choi, Sunghwan and Lu, Jiangbo and Ham, Bumsub and Sohn, Kwanghoon and Do, Minh N},
	year = {2014},
	keywords = {interpolation},
	pages = {5638--5653},
	file = {Min et al. - 2014 - Fast global image smoothing based on weighted leas.pdf:/home/florent/.zotero/data/storage/6VPNGS7F/Min et al. - 2014 - Fast global image smoothing based on weighted leas.pdf:application/pdf}
}

@article{behan_matching_2000,
	title = {On the matching accuracy of rasterised scanning laser altimeter data},
	volume = {33},
	number = {B2; PART 2},
	journal = {International Archives of Photogrammetry and Remote Sensing},
	author = {Behan, Avril},
	year = {2000},
	pages = {75--80},
	file = {Behan - 2000 - On the matching accuracy of rasterised scanning la.pdf:/home/florent/.zotero/data/storage/CQV5ILCE/Behan - 2000 - On the matching accuracy of rasterised scanning la.pdf:application/pdf}
}

@article{serna_detection_2014,
	title = {Detection, segmentation and classification of 3D urban objects using mathematical morphology and supervised learning},
	volume = {93},
	issn = {09242716},
	url = {http://linkinghub.elsevier.com/retrieve/pii/S0924271614000872},
	doi = {10.1016/j.isprsjprs.2014.03.015},
	abstract = {In this paper, we propose an automatic and robust approach to detect, segment and classify urban objects from 3D point clouds. Processing is carried out using elevation images, called also digital elevation models, and the final result is presented reprojecting the image onto the 3D point cloud. First, the ground is segmented and objects are detected as discontinuities on the ground. Then, connected objects are segmented using a watershed constrained by the significant maxima. Finally, objects are classified in several categories using a support vector machine (SVM) approach with geometrical and contextual features.},
	language = {en},
	urldate = {2018-06-29},
	journal = {ISPRS Journal of Photogrammetry and Remote Sensing},
	author = {Serna, Andrés and Marcotegui, Beatriz},
	month = jul,
	year = {2014},
	keywords = {ISMM},
	pages = {243--255},
	file = {notes.md:/home/florent/.zotero/data/storage/EETSI4UL/notes.md:text/markdown;Serna and Marcotegui - 2014 - Detection, segmentation and classification of 3D u.pdf:/home/florent/.zotero/data/storage/LZH3HXZ6/Serna and Marcotegui - 2014 - Detection, segmentation and classification of 3D u.pdf:application/pdf}
}

@inproceedings{golovinskiy_shape-based_2009,
	title = {Shape-based recognition of 3D point clouds in urban environments},
	isbn = {978-1-4244-4420-5},
	url = {http://ieeexplore.ieee.org/document/5459471/},
	doi = {10.1109/ICCV.2009.5459471},
	abstract = {This paper investigates the design of a system for recognizing objects in 3D point clouds of urban environments. The system is decomposed into four steps: locating, segmenting, characterizing, and classifying clusters of 3D points. Specifically, we first cluster nearby points to form a set of potential object locations (with hierarchical clustering). Then, we segment points near those locations into foreground and background sets (with a graph-cut algorithm). Next, we build a feature vector for each point cluster (based on both its shape and its context). Finally, we label the feature vectors using a classifier trained on a set of manually labeled objects. The paper presents several alternative methods for each step. We quantitatively evaluate the system and tradeoffs of different alternatives in a truthed part of a scan of Ottawa that contains approximately 100 million points and 1000 objects of interest. Then, we use this truth data as a training set to recognize objects amidst approximately 1 billion points of the remainder of the Ottawa scan.},
	language = {en},
	urldate = {2018-06-29},
	publisher = {IEEE},
	author = {Golovinskiy, Aleksey and Kim, Vladimir G and Funkhouser, Thomas},
	month = sep,
	year = {2009},
	pages = {2154--2161},
	file = {Golovinskiy et al. - 2009 - Shape-based recognition of 3D point clouds in urba.pdf:/home/florent/.zotero/data/storage/ET9LYVN7/Golovinskiy et al. - 2009 - Shape-based recognition of 3D point clouds in urba.pdf:application/pdf}
}

@article{antonarakis_object-based_2008,
	title = {Object-based land cover classification using airborne {LiDAR}},
	volume = {112},
	issn = {00344257},
	url = {http://linkinghub.elsevier.com/retrieve/pii/S0034425708000667},
	doi = {10.1016/j.rse.2008.02.004},
	abstract = {Light Detection and Ranging (LiDAR) provides high resolution horizontal and vertical spatial point cloud data, and is increasingly being used in a number of applications and disciplines, which have concentrated on the exploit and manipulation of the data using mainly its three dimensional nature. LiDAR information potential is made even greater though, with its consideration of intensity.},
	language = {en},
	number = {6},
	urldate = {2018-06-29},
	journal = {Remote Sensing of Environment},
	author = {Antonarakis, A.S. and Richards, K.S. and Brasington, J.},
	month = jun,
	year = {2008},
	pages = {2988--2998},
	file = {Antonarakis et al. - 2008 - Object-based land cover classification using airbo.pdf:/home/florent/.zotero/data/storage/C7LPZEY8/Antonarakis et al. - 2008 - Object-based land cover classification using airbo.pdf:application/pdf}
}

@article{ekhtari_classification_2018,
	title = {Classification of {Airborne} {Multispectral} {Lidar} {Point} {Clouds} for {Land} {Cover} {Mapping}},
	issn = {1939-1404, 2151-1535},
	url = {https://ieeexplore.ieee.org/document/8370639/},
	doi = {10.1109/JSTARS.2018.2835483},
	abstract = {Airborne light detection and ranging (lidar) data are widely used for high-resolution land cover mapping. The lidar elevation data are typically used as complementary information to passive multispectral or hyperspectral imagery to enable higher land cover classification accuracy. In this paper, we examine the capabilities of a recently developed multispectral airborne laser scanner, manufactured by Teledyne Optech, for direct classification of multispectral point clouds into ten land cover classes including grass, trees, two classes of soil, four classes of pavement, and two classes of buildings. The scanner, Titan MW, collects point clouds at three different laser wavelengths simultaneously, opening the door to new possibilities in land cover classification using only lidar data. We show that the recorded intensities of laser returns together with spatial metrics calculated from the three-dimensional (3D) locations of laser returns are sufficient for classifying the point cloud into ten distinct land cover classes. Our classification methods achieved an overall accuracy of 94.7\% with a kappa coefficient of 0.94 using the support vector machine (SVM) method to classify single-return points and an overall accuracy of 79.7\% and kappa coefficient of 0.77 using a rule-based classifier on multireturn points. A land cover map is then generated from the classified point cloud. We show that our results outperform the common approach of rasterizing the point cloud prior to classification by ∼4\% in overall accuracy, 0.04 in kappa coefficient, and by up to 16\% in commission and omission errors. This improvement however comes at the price of increased complexity and computational burden.},
	language = {en},
	urldate = {2018-06-29},
	journal = {IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing},
	author = {Ekhtari, Nima and Glennie, Craig and Fernandez-Diaz, Juan Carlos},
	year = {2018},
	note = {00001},
	keywords = {NEXT, classification, lidar, titan},
	pages = {1--11},
	file = {Ekhtari et al. - 2018 - Classification of Airborne Multispectral Lidar Poi.pdf:/home/florent/.zotero/data/storage/D79PDSVP/Ekhtari et al. - 2018 - Classification of Airborne Multispectral Lidar Poi.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/ZNCCYTFD/notes.md:text/markdown}
}

@article{lloyd_deriving_2002,
	title = {Deriving {DSMs} from {LiDAR} data with kriging},
	volume = {23},
	issn = {0143-1161, 1366-5901},
	url = {https://www.tandfonline.com/doi/full/10.1080/01431160110097998},
	doi = {10.1080/01431160110097998},
	abstract = {Light Detection And Ranging (LiDAR) is becoming a widely used source of digital elevation data. LiDAR data are obtained on a point support and it is necessary to interpolate to a regular grid if a digital surface model (DSM) is required. When the data are numerous, and close together in space, simple linear interpolation algorithms are usually considered suYcient. In this letter, inverse distance weighting (IDW), ordinary kriging (OK) and kriging with a trend model ( KT) are assessed for the construction of DSMs from LiDAR data. It is shown that the advantages of KT become more apparent as the number of data points decrease (and the sample spacing increases). It is argued that KT may be advantageous in some instances where the desire is to derive a DSM from LiDAR point data but in many cases a simpler approach, such as IDW, may suYce.},
	language = {en},
	number = {12},
	urldate = {2018-06-29},
	journal = {International Journal of Remote Sensing},
	author = {Lloyd, C. D. and Atkinson, P. M.},
	month = jan,
	year = {2002},
	keywords = {interpolation},
	pages = {2519--2524},
	file = {Lloyd and Atkinson - 2002 - Deriving DSMs from LiDAR data with kriging.pdf:/home/florent/.zotero/data/storage/QM4CRKBM/Lloyd and Atkinson - 2002 - Deriving DSMs from LiDAR data with kriging.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/IN8IBF36/notes.md:text/markdown}
}

@misc{cuturi_primer_nodate,
	title = {A {Primer} on {Optimal} {Transport}},
	language = {en},
	author = {Cuturi, Marco},
	file = {Cuturi - A Primer on Optimal Transport.pdf:/home/florent/.zotero/data/storage/H79IUIRR/Cuturi - A Primer on Optimal Transport.pdf:application/pdf}
}

@article{karydas_evaluation_2009,
	title = {Evaluation of spatial interpolation techniques for mapping agricultural topsoil properties in {Crete}},
	volume = {8},
	number = {1},
	journal = {EARSeL eProceedings},
	author = {Karydas, Christos G and Gitas, Ioannis Z and Koutsogiannaki, Eirini and Lydakis-Simantiris, Nikolaos and Silleos, GN and {others}},
	year = {2009},
	keywords = {interpolation},
	pages = {26--39},
	file = {Karydas et al. - 2009 - Evaluation of spatial interpolation techniques for.pdf:/home/florent/.zotero/data/storage/HPJYBTWG/Karydas et al. - 2009 - Evaluation of spatial interpolation techniques for.pdf:application/pdf}
}

@article{bhattacharjee_spatial_2014,
	title = {Spatial {Interpolation} to {Predict} {Missing} {Attributes} in {GIS} {Using} {Semantic} {Kriging}},
	volume = {52},
	issn = {0196-2892, 1558-0644},
	url = {http://ieeexplore.ieee.org/document/6649977/},
	doi = {10.1109/TGRS.2013.2284489},
	abstract = {Prediction of spatial attributes has attracted significant research interest in recent years. It is challenging especially when spatial data contain errors and missing values. Geostatistical estimators are used to predict the missing attribute values from the observed values of known surrounding data points, a general form of which is referred as kriging in the field of geographic information system and remote sensing. The proposed semantic kriging (SemK) tries to blend the semantics of spatial features (of surrounding data points) with ordinary kriging (OK) method for prediction of the attribute. Experimentation has been carried out with land surface temperature data of four major metropolitan cities in India. It shows that SemK outperforms the OK and most of the existing spatial interpolation methods.},
	language = {en},
	number = {8},
	urldate = {2018-07-02},
	journal = {IEEE Transactions on Geoscience and Remote Sensing},
	author = {Bhattacharjee, Shrutilipi and Mitra, Pabitra and Ghosh, Soumya K.},
	month = aug,
	year = {2014},
	keywords = {interpolation},
	pages = {4771--4780},
	file = {Bhattacharjee et al. - 2014 - Spatial Interpolation to Predict Missing Attribute.pdf:/home/florent/.zotero/data/storage/Z8ILXLPB/Bhattacharjee et al. - 2014 - Spatial Interpolation to Predict Missing Attribute.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/6SG7DT7M/notes.md:text/markdown}
}

@misc{lefevre_recently_2018,
	title = {Recently launched and future {OBELIX} activities in {Deep} {Learning}},
	language = {en},
	author = {Lefèvre, Sébastien},
	month = jun,
	year = {2018},
	file = {Lefèvre - 2018 - Recently launched and future OBELIX activities in .pdf:/home/florent/.zotero/data/storage/GVG4G9QI/Lefèvre - 2018 - Recently launched and future OBELIX activities in .pdf:application/pdf}
}

@article{shi_extraction_2018,
	title = {Extraction of multi-scale landslide morphological features based on local {Gi}* using airborne {LiDAR}-derived {DEM}},
	volume = {303},
	journal = {Geomorphology},
	author = {Shi, Wenzhong and Deng, Susu and Xu, Wenbing},
	year = {2018},
	pages = {229--242},
	file = {notes.md:/home/florent/.zotero/data/storage/GZ7USMU4/notes.md:text/markdown;Shi et al. - 2018 - Extraction of multi-scale landslide morphological .pdf:/home/florent/.zotero/data/storage/ZWVHMAUF/Shi et al. - 2018 - Extraction of multi-scale landslide morphological .pdf:application/pdf}
}

@article{wang_lidar_2018,
	title = {{LiDAR} {Data} {Classification} {Using} {Morphological} {Profiles} and {Convolutional} {Neural} {Networks}},
	volume = {15},
	number = {5},
	journal = {IEEE Geoscience and Remote Sensing Letters},
	author = {Wang, Aili and He, Xin and Ghamisi, Pedram and Chen, Yushi},
	year = {2018},
	pages = {774--778},
	file = {notes.md:/home/florent/.zotero/data/storage/Q8AU4T7J/notes.md:text/markdown;Wang et al. - 2018 - LiDAR Data Classification Using Morphological Prof.pdf:/home/florent/.zotero/data/storage/ERWZANUU/Wang et al. - 2018 - LiDAR Data Classification Using Morphological Prof.pdf:application/pdf}
}

@inproceedings{wang_large-scale_2018,
	title = {Large-scale 3D {Point} {Cloud} {Classification} {Based} {On} {Feature} {Description} {Matrix} {By} {CNN}},
	booktitle = {Proceedings of the 31st {International} {Conference} on {Computer} {Animation} and {Social} {Agents}},
	publisher = {ACM},
	author = {Wang, Lei and Meng, Weiliang and Xi, Runping and Zhang, Yanning and Lu, Ling and Zhang, Xiaopeng},
	year = {2018},
	pages = {43--47},
	file = {Wang et al. - 2018 - Large-scale 3D Point Cloud Classification Based On.pdf:/home/florent/.zotero/data/storage/7828JAPK/Wang et al. - 2018 - Large-scale 3D Point Cloud Classification Based On.pdf:application/pdf}
}

@article{landrieu_large-scale_2017,
	title = {Large-scale {Point} {Cloud} {Semantic} {Segmentation} with {Superpoint} {Graphs}},
	volume = {abs/1711.09869},
	url = {http://arxiv.org/abs/1711.09869},
	journal = {CoRR},
	author = {Landrieu, Loïc and Simonovsky, Martin},
	year = {2017},
	keywords = {segmentation, classification, lidar, deep learning, graphe},
	file = {Landrieu and Simonovsky - 2017 - Large-scale Point Cloud Semantic Segmentation with.pdf:/home/florent/.zotero/data/storage/U83LW9TF/Landrieu and Simonovsky - 2017 - Large-scale Point Cloud Semantic Segmentation with.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/SILE5UI5/notes.md:text/markdown}
}

@article{aptoula_deep_2016,
	title = {Deep {Learning} {With} {Attribute} {Profiles} for {Hyperspectral} {Image} {Classification}},
	volume = {13},
	issn = {1545-598X, 1558-0571},
	url = {http://ieeexplore.ieee.org/document/7733086/},
	doi = {10.1109/LGRS.2016.2619354},
	abstract = {Effective spatial–spectral pixel description is of crucial significance for the classification of hyperspectral remote sensing images. Attribute profiles are considered as one of the most prominent approaches in this regard, since they can capture efficiently arbitrary geometric and spectral properties. Lately though, the advent of deep learning in its various forms has also led to remarkable classification performances by operating directly on hyperspectral input. In this letter, we explore the collaboration potential of these two powerful feature extraction approaches. Specifically, we propose a new strategy for hyperspectral image classification, where attribute filtered images are stacked and provided as input to convolutional neural networks. Our experiments with two real hyperspectral remote sensing data sets show that the proposed strategy leads to a performance improvement, as opposed to using each of the involved approaches individually.},
	language = {en},
	number = {12},
	urldate = {2018-08-29},
	journal = {IEEE Geoscience and Remote Sensing Letters},
	author = {Aptoula, Erchan and Ozdemir, Murat Can and Yanikoglu, Berrin},
	month = dec,
	year = {2016},
	pages = {1970--1974},
	file = {Aptoula et al. - 2016 - Deep Learning With Attribute Profiles for Hyperspe.pdf:/home/florent/.zotero/data/storage/DYKFDBQQ/Aptoula et al. - 2016 - Deep Learning With Attribute Profiles for Hyperspe.pdf:application/pdf}
}

@article{yang_convolutional_2017,
	title = {A {Convolutional} {Neural} {Network}-{Based} 3D {Semantic} {Labeling} {Method} for {ALS} {Point} {Clouds}},
	volume = {9},
	issn = {2072-4292},
	url = {http://www.mdpi.com/2072-4292/9/9/936},
	doi = {10.3390/rs9090936},
	language = {en},
	number = {9},
	urldate = {2018-09-01},
	journal = {Remote Sensing},
	author = {Yang, Zhishuang and Jiang, Wanshou and Xu, Bo and Zhu, Quansheng and Jiang, San and Huang, Wei},
	month = sep,
	year = {2017},
	pages = {936},
	file = {Yang et al. - 2017 - A Convolutional Neural Network-Based 3D Semantic L.pdf:/home/florent/.zotero/data/storage/V9AK99HL/Yang et al. - 2017 - A Convolutional Neural Network-Based 3D Semantic L.pdf:application/pdf}
}

@article{yan_urban_2015,
	title = {Urban land cover classification using airborne {LiDAR} data: {A} review},
	volume = {158},
	issn = {00344257},
	shorttitle = {Urban land cover classification using airborne {LiDAR} data},
	url = {http://linkinghub.elsevier.com/retrieve/pii/S0034425714004374},
	doi = {10.1016/j.rse.2014.11.001},
	abstract = {Distribution of land cover has a profound impact on the climate and environment; mapping the land cover patterns from global, regional to local scales are important for scientists and authorities to yield better monitoring of the changing world. Satellite remote sensing has been demonstrated as an efficient tool to monitor the land cover patterns for a large spatial extent. Nevertheless, the demand on land cover maps at a finer scale (especially in urban areas) has been raised with evidence by numerous biophysical and socio-economic studies. This paper reviews the small-footprint LiDAR sensor — one of the latest high resolution airborne remote sensing technologies, and its application on urban land cover classification. While most of the early researches focus on the analysis of geometric components of 3D LiDAR data point clouds, there has been an increasing interest in investigating the use of intensity data, waveform data and multi-sensor data to facilitate land cover classification and object recognition in urban environment. In this paper, the advancement of airborne LiDAR technology, including data configuration, feature spaces, classification techniques, and radiometric calibration/correction is reviewed and discussed. The review mainly focuses on the LiDAR studies conducted during the last decade with an emphasis on identification of the approach, analysis of pros and cons, investigating the overall accuracy of the technology, and how the classification results can serve as an input for different urban environmental analyses. Finally, several promising directions for future LiDAR research are highlighted, in hope that it will pave the way for the applications of urban environmental modeling and assessment at a finer scale and a greater extent.},
	language = {en},
	urldate = {2018-09-01},
	journal = {Remote Sensing of Environment},
	author = {Yan, Wai Yeung and Shaker, Ahmed and El-Ashmawy, Nagwa},
	month = mar,
	year = {2015},
	pages = {295--310},
	file = {Yan et al. - 2015 - Urban land cover classification using airborne LiD.pdf:/home/florent/.zotero/data/storage/NRBYNYV2/Yan et al. - 2015 - Urban land cover classification using airborne LiD.pdf:application/pdf}
}

@article{chen_state---art:_2017,
	title = {State-of-the-{Art}: {DTM} {Generation} {Using} {Airborne} {LIDAR} {Data}},
	volume = {17},
	issn = {1424-8220},
	shorttitle = {State-of-the-{Art}},
	url = {http://www.mdpi.com/1424-8220/17/1/150},
	doi = {10.3390/s17010150},
	abstract = {Digital terrain model (DTM) generation is the fundamental application of airborne Lidar data. In past decades, a large body of studies has been conducted to present and experiment a variety of DTM generation methods. Although great progress has been made, DTM generation, especially DTM generation in specific terrain situations, remains challenging. This research introduces the general principles of DTM generation and reviews diverse mainstream DTM generation methods. In accordance with the filtering strategy, these methods are classified into six categories: surface-based adjustment; morphology-based filtering, triangulated irregular network (TIN)-based refinement, segmentation and classification, statistical analysis and multi-scale comparison. Typical methods for each category are briefly introduced and the merits and limitations of each category are discussed accordingly. Despite different categories of filtering strategies, these DTM generation methods present similar difficulties when implemented in sharply changing terrain, areas with dense non-ground features and complicated landscapes. This paper suggests that the fusion of multi-sources and integration of different methods can be effective ways for improving the performance of DTM generation.},
	language = {en},
	number = {12},
	urldate = {2018-09-01},
	journal = {Sensors},
	author = {Chen, Ziyue and Gao, Bingbo and Devereux, Bernard},
	month = jan,
	year = {2017},
	pages = {150},
	file = {Chen et al. - 2017 - State-of-the-Art DTM Generation Using Airborne LI.pdf:/home/florent/.zotero/data/storage/6F8D9PCW/Chen et al. - 2017 - State-of-the-Art DTM Generation Using Airborne LI.pdf:application/pdf}
}

@article{chehata_airborne_2009,
	title = {Airborne lidar feature selection for urban classification using random forests},
	volume = {38},
	number = {Part 3},
	journal = {International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences},
	author = {Chehata, Nesrine and Guo, Li and Mallet, Clément},
	year = {2009},
	pages = {W8},
	file = {Chehata et al. - 2009 - Airborne lidar feature selection for urban classif.pdf:/home/florent/.zotero/data/storage/HYTZPJVB/Chehata et al. - 2009 - Airborne lidar feature selection for urban classif.pdf:application/pdf}
}

@article{ni_classification_2017,
	title = {Classification of {ALS} {Point} {Cloud} with {Improved} {Point} {Cloud} {Segmentation} and {Random} {Forests}},
	volume = {9},
	issn = {2072-4292},
	url = {http://www.mdpi.com/2072-4292/9/3/288},
	doi = {10.3390/rs9030288},
	abstract = {This paper presents an automated and effective framework for classifying airborne laser scanning (ALS) point clouds. The framework is composed of four stages: (i) step-wise point cloud segmentation, (ii) feature extraction, (iii) Random Forests (RF) based feature selection and classification, and (iv) post-processing. First, a step-wise point cloud segmentation method is proposed to extract three kinds of segments, including planar, smooth and rough surfaces. Second, a segment, rather than an individual point, is taken as the basic processing unit to extract features. Third, RF is employed to select features and classify these segments. Finally, semantic rules are employed to optimize the classification result. Three datasets provided by Open Topography are utilized to test the proposed method. Experiments show that our method achieves a superior classification result with an overall classification accuracy larger than 91.17\%, and kappa coefficient larger than 83.79\%.},
	language = {en},
	number = {3},
	urldate = {2018-09-25},
	journal = {Remote Sensing},
	author = {Ni, Huan and Lin, Xiangguo and Zhang, Jixian},
	month = mar,
	year = {2017},
	keywords = {NEXT, segmentation, lidar, random forests},
	pages = {288},
	file = {Ni et al. - 2017 - Classification of ALS Point Cloud with Improved Po.pdf:/home/florent/.zotero/data/storage/6XBB3K59/Ni et al. - 2017 - Classification of ALS Point Cloud with Improved Po.pdf:application/pdf}
}

@article{jutzi_normalization_2009,
	title = {Normalization of {LiDAR} intensity data based on range and surface incidence angle},
	volume = {38},
	journal = {Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci},
	author = {Jutzi, B and Gross, H},
	year = {2009},
	keywords = {full waveform, lidar, phong, JURSE, intensity calibration},
	pages = {213--218},
	file = {Jutzi and Gross - 2009 - Normalization of LiDAR intensity data based on ran.pdf:/home/florent/.zotero/data/storage/H5XCSJZ2/Jutzi and Gross - 2009 - Normalization of LiDAR intensity data based on ran.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/8GTNXXBH/notes.md:text/markdown}
}

@article{kaasalainen_analysis_2011,
	title = {Analysis of {Incidence} {Angle} and {Distance} {Effects} on {Terrestrial} {Laser} {Scanner} {Intensity}: {Search} for {Correction} {Methods}},
	volume = {3},
	issn = {2072-4292},
	shorttitle = {Analysis of {Incidence} {Angle} and {Distance} {Effects} on {Terrestrial} {Laser} {Scanner} {Intensity}},
	url = {http://www.mdpi.com/2072-4292/3/10/2207},
	doi = {10.3390/rs3102207},
	abstract = {The intensity information from terrestrial laser scanners (TLS) has become an important object of study in recent years, and there are an increasing number of applications that would benefit from the addition of calibrated intensity data to the topographic information. In this paper, we study the range and incidence angle effects on the intensity measurements and search for practical correction methods for different TLS instruments and targets. We find that the range (distance) effect is strongly dominated by instrumental factors, whereas the incidence angle effect is mainly caused by the target surface properties. Correction for both effects is possible, but more studies are needed for physical interpretation and more efficient use of intensity data for target characterization.},
	language = {en},
	number = {10},
	urldate = {2018-09-27},
	journal = {Remote Sensing},
	author = {Kaasalainen, Sanna and Jaakkola, Anttoni and Kaasalainen, Mikko and Krooks, Anssi and Kukko, Antero},
	month = oct,
	year = {2011},
	keywords = {lidar, JURSE, intensity calibration},
	pages = {2207--2221},
	file = {Kaasalainen et al. - 2011 - Analysis of Incidence Angle and Distance Effects o.pdf:/home/florent/.zotero/data/storage/6XV23YG9/Kaasalainen et al. - 2011 - Analysis of Incidence Angle and Distance Effects o.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/EQA8J24P/notes.md:text/markdown}
}

@article{dalla_mura_extended_2010,
	title = {Extended profiles with morphological attribute filters for the analysis of hyperspectral data},
	volume = {31},
	issn = {0143-1161, 1366-5901},
	url = {http://www.tandfonline.com/doi/abs/10.1080/01431161.2010.512425},
	doi = {10.1080/01431161.2010.512425},
	language = {en},
	number = {22},
	urldate = {2018-10-01},
	journal = {International Journal of Remote Sensing},
	author = {Dalla Mura, Mauro and Atli Benediktsson, Jon and Waske, Björn and Bruzzone, Lorenzo},
	month = dec,
	year = {2010},
	keywords = {classification, attribute profiles, JURSE},
	pages = {5975--5991},
	file = {Dalla Mura et al. - 2010 - Extended profiles with morphological attribute fil.pdf:/home/florent/.zotero/data/storage/E6XN6P6Y/Dalla Mura et al. - 2010 - Extended profiles with morphological attribute fil.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/89HE7VTJ/notes.md:text/markdown}
}

@article{cavallaro_automatic_2017,
	title = {Automatic {Attribute} {Profiles}},
	volume = {26},
	issn = {1057-7149, 1941-0042},
	url = {http://ieeexplore.ieee.org/document/7842555/},
	doi = {10.1109/TIP.2017.2664667},
	abstract = {Morphological attribute profiles are multilevel decomposition of images obtained with a sequence of transformations performed by connected operators. They have been extensively employed in performing multi-scale and region-based analysis in a large number of applications. One main, still unresolved, issue is the selection of filter parameters able to provide representative and non-redundant threshold decomposition of the image. This paper presents a framework for the automatic selection of filter thresholds based on Granulometric Characteristic Functions (GCFs). GCFs describe the way that non-linear morphological filters simplify a scene according to a given measure. Since attribute filters rely on a hierarchical representation of an image (e.g., the Tree of Shapes) for their implementation, GCFs can be efficiently computed by taking advantage of the tree representation. Eventually, the study of the GCFs allows the identification of a meaningful set of thresholds. Therefore, a trial and error approach is not necessary for the threshold selection, automating the process and in turn decreasing the computational time. It is shown that the redundant information is reduced within the resulting profiles (a problem of high occurrence, as regards manual selection). The proposed approach is tested on two real remote sensing data sets, and the classification results are compared with strategies present in the literature.},
	language = {en},
	number = {4},
	urldate = {2018-10-11},
	journal = {IEEE Transactions on Image Processing},
	author = {Cavallaro, Gabriele and Falco, Nicola and Dalla Mura, Mauro and Benediktsson, Jon Atli},
	month = apr,
	year = {2017},
	note = {00066},
	keywords = {NEXT, attribute profiles, JURSE},
	pages = {1859--1872},
	file = {Cavallaro et al. - 2017 - Automatic Attribute Profiles.pdf:/home/florent/.zotero/data/storage/I4DJ946V/Cavallaro et al. - 2017 - Automatic Attribute Profiles.pdf:application/pdf}
}

@inproceedings{ghamisi_fusion_2014,
	address = {Quebec City, QC},
	title = {Fusion of hyperspectral and {LiDAR} data in classification of urban areas},
	isbn = {978-1-4799-5775-0},
	url = {http://ieeexplore.ieee.org/document/6946386/},
	doi = {10.1109/IGARSS.2014.6946386},
	language = {en},
	urldate = {2018-10-17},
	booktitle = {2014 {IEEE} {Geoscience} and {Remote} {Sensing} {Symposium}},
	publisher = {IEEE},
	author = {Ghamisi, Pedram and Benediktsson, Jon Atli and Phinn, Stuart},
	month = jul,
	year = {2014},
	keywords = {classification, lidar, attribute profiles, JURSE},
	pages = {181--184},
	file = {Ghamisi et al. - 2014 - Fusion of hyperspectral and LiDAR data in classifi.pdf:/home/florent/.zotero/data/storage/KKA72L2Y/Ghamisi et al. - 2014 - Fusion of hyperspectral and LiDAR data in classifi.pdf:application/pdf}
}

@article{ghamisi_survey_2015,
	title = {A {Survey} on {Spectral}–{Spatial} {Classification} {Techniques} {Based} on {Attribute} {Profiles}},
	volume = {53},
	issn = {0196-2892, 1558-0644},
	url = {http://ieeexplore.ieee.org/document/6945376/},
	doi = {10.1109/TGRS.2014.2358934},
	abstract = {Just over a decade has passed since the concept of morphological profile was defined for the analysis of remote sensing images. From that time, the morphological profile has largely proved to be a powerful tool able to model spatial information (e.g., contextual relations) of the image. However, due to the shortcomings of using the morphological profiles, many variants, extensions and refinements of its definition have appeared stating that the morphological profile is still under continuous development. In this case, recently-introducedtheoretically-sound attribute profiles can be considered as a generalization of the morphological profile, which is a powerful tool to model spatial information existing in the scene. Although the concept of the attribute profile has been introduced in remote sensing only recently, an extensive literature on its use in different applications and on different types of data has appeared. To that end, the great amount of contributions in the literature that address the application of the attribute profile to many tasks (e.g., classification, object detection, segmentation, change detection, etc.) and to different types of images (e.g., panchromatic, multispectral, hyperspectral) proves how the attribute profile is an effective and modern tool. The main objective of this survey paper is to recall the concept of the attribute profiles along with all its modifications and generalizations with a special emphasize on remote sensing image classification and summarize the important aspects of its efficient utilization while also listing potential future works.},
	language = {en},
	number = {5},
	urldate = {2018-10-17},
	journal = {IEEE Transactions on Geoscience and Remote Sensing},
	author = {Ghamisi, Pedram and Dalla Mura, Mauro and Benediktsson, Jon Atli},
	month = may,
	year = {2015},
	note = {00167},
	keywords = {NEXT, attribute profiles, JURSE},
	pages = {2335--2353},
	file = {Ghamisi et al. - 2015 - A Survey on Spectral–Spatial Classification Techni.pdf:/home/florent/.zotero/data/storage/CIXSHII9/Ghamisi et al. - 2015 - A Survey on Spectral–Spatial Classification Techni.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/VNADRL5Q/notes.md:text/markdown}
}

@article{ghamisi_extinction_2016,
	title = {Extinction {Profiles} for the {Classification} of {Remote} {Sensing} {Data}},
	volume = {54},
	issn = {0196-2892, 1558-0644},
	url = {http://ieeexplore.ieee.org/document/7514921/},
	doi = {10.1109/TGRS.2016.2561842},
	abstract = {With respect to recent advances in remote sensing technologies, the spatial resolution of airborne and spaceborne sensors is getting finer, which enables us to precisely analyze even small objects on the Earth. This fact has made the research area of developing efficient approaches to extract spatial and contextual information highly active. Among the existing approaches, morphological profile and attribute profile (AP) have gained great attention due to their ability to classify remote sensing data. This paper proposes a novel approach that makes it possible to precisely extract spatial and contextual information from remote sensing images. The proposed approach is based on extinction filters, which are used here for the first time in the remote sensing community. Then, the approach is carried out on two well-known high-resolution panchromatic data sets captured over Rome, Italy, and Reykjavik, Iceland. In order to prove the capabilities of the proposed approach, the obtained results are compared with the results from one of the strongest approaches in the literature, i.e., APs, using different points of view such as classification accuracies, simplification rate, and complexity analysis. Results indicate that the proposed approach can significantly outperform its alternative in terms of classification accuracies. In addition, based on our implementation, profiles can be generated in a very short processing time. It should be noted that the proposed approach is fully automatic.},
	language = {en},
	number = {10},
	urldate = {2018-10-17},
	journal = {IEEE Transactions on Geoscience and Remote Sensing},
	author = {Ghamisi, Pedram and Souza, Roberto and Benediktsson, Jon Atli and Zhu, Xiao Xiang and Rittner, Leticia and Lotufo, Roberto A.},
	month = oct,
	year = {2016},
	note = {00052},
	keywords = {NEXT},
	pages = {5631--5645},
	file = {Ghamisi et al. - 2016 - Extinction Profiles for the Classification of Remo.pdf:/home/florent/.zotero/data/storage/EDXP9IBE/Ghamisi et al. - 2016 - Extinction Profiles for the Classification of Remo.pdf:application/pdf}
}

@article{ghamisi_land-cover_2015,
	title = {Land-cover classification using both hyperspectral and {LiDAR} data},
	volume = {6},
	issn = {1947-9832, 1947-9824},
	url = {http://www.tandfonline.com/doi/full/10.1080/19479832.2015.1055833},
	doi = {10.1080/19479832.2015.1055833},
	language = {en},
	number = {3},
	urldate = {2018-10-17},
	journal = {International Journal of Image and Data Fusion},
	author = {Ghamisi, Pedram and Benediktsson, Jon Atli and Phinn, Stuart},
	month = jul,
	year = {2015},
	note = {00027},
	keywords = {NEXT, classification, lidar, attribute profiles, JURSE},
	pages = {189--215},
	file = {Ghamisi et al. - 2015 - Land-cover classification using both hyperspectral.pdf:/home/florent/.zotero/data/storage/ME5CYRYR/Ghamisi et al. - 2015 - Land-cover classification using both hyperspectral.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/YEWI2IVB/notes.md:text/markdown}
}

@inproceedings{lodha_aerial_2006,
	address = {Chapel Hill, NC, USA},
	title = {Aerial {LiDAR} {Data} {Classification} {Using} {Support} {Vector} {Machines} ({SVM})},
	isbn = {978-0-7695-2825-0},
	url = {http://ieeexplore.ieee.org/document/4155775/},
	doi = {10.1109/3DPVT.2006.23},
	abstract = {We classify 3D aerial LiDAR scattered height data into buildings, trees, roads, and grass using the Support Vector Machine (SVM) algorithm. To do so we use five features: height, height variation, normal variation, LiDAR return intensity, and image intensity. We also use only LiDARderived features to organize the data into three classes (the road and grass classes are merged). We have implemented and experimented with several variations of the SVM algorithm with soft-margin classification to allow for the noise in the data. We have applied our results to classify aerial LiDAR data collected over approximately 8 square miles. We visualize the classification results along with the associated confidence using a variation of the SVM algorithm producing probabilistic classifications. We observe that the results are stable and robust. We compare the results against the ground truth and obtain higher than 90\% accuracy and convincing visual results.},
	language = {en},
	urldate = {2018-10-17},
	booktitle = {Third {International} {Symposium} on 3D {Data} {Processing}, {Visualization}, and {Transmission} (3DPVT'06)},
	publisher = {IEEE},
	author = {Lodha, Suresh K. and Kreps, Edward J. and Helmbold, David P. and Fitzpatrick, Darren},
	month = jun,
	year = {2006},
	keywords = {classification, lidar, JURSE, rasterization},
	pages = {567--574},
	file = {Lodha et al. - 2006 - Aerial LiDAR Data Classification Using Support Vec.pdf:/home/florent/.zotero/data/storage/BW4Y5HKS/Lodha et al. - 2006 - Aerial LiDAR Data Classification Using Support Vec.pdf:application/pdf}
}

@article{mallet_relevance_2011,
	title = {Relevance assessment of full-waveform lidar data for urban area classification},
	volume = {66},
	issn = {09242716},
	url = {http://linkinghub.elsevier.com/retrieve/pii/S0924271611001055},
	doi = {10.1016/j.isprsjprs.2011.09.008},
	abstract = {Full-waveform lidar data are increasingly being available. Morphological features can be retrieved from the echoes composing the waveforms, and are now extensively used for a large variety of land-cover mapping issues. However, the genuine contribution of these features with respect to those computed from standard discrete return lidar systems has been barely theoretically investigated. This paper therefore aims to study the potential of full-waveform data through the automatic classification of urban areas in building, ground, and vegetation points. Two waveform processing methods, namely a non-linear least squares method and a marked point process approach, are used to fit the echoes both with symmetric and asymmetric modeling functions. The performance of the extracted full-waveform features for the classification problem are then compared to a large variety of multiple-pulse features thanks to three feature selection methods. A support vector machines classifier is finally used to label the point cloud according to various scenarios based on the rank of the features. This allows to find the best classification strategy as well as the minimal feature subsets allowing to achieve the highest classification accuracy possible for each of the three feature selection methods.},
	language = {en},
	number = {6},
	urldate = {2018-10-17},
	journal = {ISPRS Journal of Photogrammetry and Remote Sensing},
	author = {Mallet, Clément and Bretar, Frédéric and Roux, Michel and Soergel, Uwe and Heipke, Christian},
	month = dec,
	year = {2011},
	keywords = {classification, full waveform, lidar},
	pages = {S71--S84},
	file = {Mallet et al. - 2011 - Relevance assessment of full-waveform lidar data f.pdf:/home/florent/.zotero/data/storage/HXA724VY/Mallet et al. - 2011 - Relevance assessment of full-waveform lidar data f.pdf:application/pdf}
}

@article{brennan_object-oriented_2006,
	title = {Object-oriented land cover classification of lidar-derived surfaces},
	volume = {32},
	issn = {0703-8992, 1712-7971},
	url = {http://www.tandfonline.com/doi/abs/10.5589/m06-015},
	doi = {10.5589/m06-015},
	abstract = {Light detection and ranging (lidar) provides high-resolution vertical and horizontal spatial data and has become an important technology for generating digital elevation models (DEMs) and digital surface models (DSMs). The latest terrestrial lidar sensors record intensity and echo information for each pulse in addition to range. In this study, lidar height and intensity data were used to classify land cover using an object-oriented approach. The study area was selected based on the variety of land cover types present and consists of urban, mixed forest, and wetland-estuary coastal environments. Surfaces constructed from the lidar points included DSM, DEM, intensity, multiple echos, and normalized height. These surfaces were segmented and classified using object rule based classification. Ten classes were extracted from the lidar data, including saturated and non-saturated intertidal sediments, saturated or stressed and lush ground cover vegetation, low and tall deciduous and coniferous trees, roads and bare soil, bright-roofed structures, dark-roofed structures, and water. The accuracy of the classification was assessed using independent ground reference polygons interpreted from colour orthophotographs and intensity images. The average accuracy of the 10 classes was 94\%, but improved to 98\% when the classification results were aggregated into seven classes. The results indicate that accurate land cover maps can be generated from a single lidar survey using the derived surfaces, and that image object segmentation and rule-based classification techniques allow the exploitation of spectral and spatial attributes of the lidar data.},
	language = {en},
	number = {2},
	urldate = {2018-10-17},
	journal = {Canadian Journal of Remote Sensing},
	author = {Brennan, R. and Webster, T L},
	month = jan,
	year = {2006},
	keywords = {classification, lidar, JURSE, rasterization},
	pages = {162--172},
	file = {Brennan and Webster - 2006 - Object-oriented land cover classification of lidar.pdf:/home/florent/.zotero/data/storage/UYJMWDK6/Brennan and Webster - 2006 - Object-oriented land cover classification of lidar.pdf:application/pdf}
}

@article{jung_framework_2014,
	title = {A {Framework} for {Land} {Cover} {Classification} {Using} {Discrete} {Return} {LiDAR} {Data}: {Adopting} {Pseudo}-{Waveform} and {Hierarchical} {Segmentation}},
	volume = {7},
	issn = {1939-1404, 2151-1535},
	shorttitle = {A {Framework} for {Land} {Cover} {Classification} {Using} {Discrete} {Return} {LiDAR} {Data}},
	url = {http://ieeexplore.ieee.org/document/6695775/},
	doi = {10.1109/JSTARS.2013.2292032},
	abstract = {Acquiring current, accurate land-use information is criticalformonitoringandunderstandingthe impactofanthropogenic activities on natural environments. Remote sensing technologies are of increasing importance because of their capability to acquire information for large areas in a timely manner, enabling decision makers to be more effectiveincomplex environments. Although optical imagery has demonstrated to be successful for land cover classification, active sensors, such as light detection and ranging (LiDAR), have distinct capabilities that can be exploited to improve classification results. However, utilization of LiDAR data for land cover classification has not been fully exploited. Moreover, spatial–spectral classification has recently gained significant attention since classification accuracy can be improved by extracting additional information from the neighboring pixels. Although spatial information has been widely used for spectral data,lessattentionhas beengiven to LiDARdata.Inthiswork, a new framework for land cover classification using discrete return LiDAR data is proposed. Pseudo-waveforms are generated from the LiDAR data and processed by hierarchical segmentation. Spatial features are extracted in a region-based way using a new unsupervised strategy for multiple pruning of the segmentation hierarchy. The proposed framework is validated experimentally on a real dataset acquired in an urban area. Better classification results are exhibited by the proposed framework compared to the cases in which basic LiDAR products such as digital surface model and intensity image are used. Moreover, the proposed region-based feature extraction strategy results in improved classification accuracies in comparison with a more traditional window-based approach.},
	language = {en},
	number = {2},
	urldate = {2018-10-18},
	journal = {IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing},
	author = {Jung, Jinha and Pasolli, Edoardo and Prasad, Saurabh and Tilton, James C. and Crawford, Melba M.},
	month = feb,
	year = {2014},
	note = {00000},
	keywords = {NEXT, trees, lidar},
	pages = {491--502},
	file = {Jung et al. - 2014 - A Framework for Land Cover Classification Using Di.pdf:/home/florent/.zotero/data/storage/4CXBJW5F/Jung et al. - 2014 - A Framework for Land Cover Classification Using Di.pdf:application/pdf}
}

@article{weinmann_semantic_2015,
	title = {Semantic point cloud interpretation based on optimal neighborhoods, relevant features and efficient classifiers},
	volume = {105},
	issn = {09242716},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S0924271615000349},
	doi = {10.1016/j.isprsjprs.2015.01.016},
	language = {en},
	urldate = {2018-10-18},
	journal = {ISPRS Journal of Photogrammetry and Remote Sensing},
	author = {Weinmann, Martin and Jutzi, Boris and Hinz, Stefan and Mallet, Clément},
	month = jul,
	year = {2015},
	keywords = {NEXT, classification, lidar, features},
	pages = {286--304},
	file = {Weinmann et al. - 2015 - Semantic point cloud interpretation based on optim.pdf:/home/florent/.zotero/data/storage/ST4VWUL4/Weinmann et al. - 2015 - Semantic point cloud interpretation based on optim.pdf:application/pdf}
}

@inproceedings{chauve_processing_2008-1,
	title = {Processing full-waveform lidar data: modelling raw signals},
	booktitle = {International archives of photogrammetry, remote sensing and spatial information sciences 2007},
	author = {Chauve, Adrien and Mallet, Clément and Bretar, Frédéric and Durrieu, Sylvie and Pierrot-Deseilligny, Marc and Puech, William},
	year = {2008},
	note = {00153},
	keywords = {NEXT, full waveform, lidar, features},
	pages = {102--107},
	file = {Chauve et al. - Processing Full-Waveform Lidar Data Modelling Raw.pdf:/home/florent/.zotero/data/storage/VE3YELGB/Chauve et al. - Processing Full-Waveform Lidar Data Modelling Raw.pdf:application/pdf}
}

@article{wagner_radiometric_2010,
	title = {Radiometric calibration of small-footprint full-waveform airborne laser scanner measurements: {Basic} physical concepts},
	volume = {65},
	issn = {09242716},
	shorttitle = {Radiometric calibration of small-footprint full-waveform airborne laser scanner measurements},
	url = {http://linkinghub.elsevier.com/retrieve/pii/S0924271610000626},
	doi = {10.1016/j.isprsjprs.2010.06.007},
	abstract = {Small-footprint (0.2–2 m) airborne laser scanners are lidar instruments originally developed for topographic mapping. While the first airborne laser scanners only allowed determining the range from the sensor to the target, the latest sensor generation records the complete echo waveform. The waveform provides important information about the backscattering properties of the observed targets and may be useful for geophysical parameter retrieval and advanced geometric modelling. However, to fully utilise the potential of the waveform measurements in applications, it is necessary to perform a radiometric calibration. As there are not yet calibration standards, this paper reviews some basic physical concepts commonly used by the remote sensing community for modelling scattering and reflection processes. Based purely on theoretical arguments it is recommended to use the backscattering coefficient γ , which is the backscatter cross-section normalised relative to the laser footprint area, for the radiometric calibration of small-footprint full-waveform airborne laser scanners. The presented concepts are, with some limitations, also applicable to conventional airborne laser scanners that measure the range and intensity of multiple echoes.},
	language = {en},
	number = {6},
	urldate = {2018-10-19},
	journal = {ISPRS Journal of Photogrammetry and Remote Sensing},
	author = {Wagner, Wolfgang},
	month = nov,
	year = {2010},
	keywords = {NEXT, full waveform, lidar, features, brdf},
	pages = {505--513},
	file = {Wagner - 2010 - Radiometric calibration of small-footprint full-wa.pdf:/home/florent/.zotero/data/storage/RS8PYRRQ/Wagner - 2010 - Radiometric calibration of small-footprint full-wa.pdf:application/pdf}
}

@inproceedings{dalla_mura_self-dual_2011,
	title = {Self-dual attribute profiles for the analysis of remote sensing images},
	booktitle = {International {Symposium} on {Mathematical} {Morphology} and {Its} {Applications} to {Signal} and {Image} {Processing}},
	publisher = {Springer},
	author = {Dalla Mura, Mauro and Benediktsson, Jon Atli and Bruzzone, Lorenzo},
	year = {2011},
	keywords = {attribute profiles},
	pages = {320--330}
}

@article{liaw_classification_2002,
	title = {Classification and regression by {randomForest}},
	volume = {2},
	number = {3},
	journal = {R news},
	author = {Liaw, Andy and Wiener, Matthew and {others}},
	year = {2002},
	pages = {18--22}
}

@article{le_saux_2018_2018,
	title = {2018 {IEEE} {GRSS} {Data} {Fusion} {Contest}: {Multimodal} {Land} {Use} {Classification} [{Technical} {Committees}]},
	volume = {6},
	issn = {2168-6831, 2473-2397},
	shorttitle = {2018 {IEEE} {GRSS} {Data} {Fusion} {Contest}},
	url = {http://ieeexplore.ieee.org/document/8328995/},
	doi = {10.1109/MGRS.2018.2798161},
	language = {en},
	number = {1},
	urldate = {2018-10-29},
	journal = {IEEE Geoscience and Remote Sensing Magazine},
	author = {Le Saux, Bertrand and Yokoya, Naoto and Hansch, Ronny and Prasad, Saurabh},
	month = mar,
	year = {2018},
	pages = {52--54},
	file = {Le Saux et al. - 2018 - 2018 IEEE GRSS Data Fusion Contest Multimodal Lan.pdf:/home/florent/.zotero/data/storage/KA3WQNEM/Le Saux et al. - 2018 - 2018 IEEE GRSS Data Fusion Contest Multimodal Lan.pdf:application/pdf}
}

@phdthesis{ba_lidar_2017,
	type = {Theses},
	title = {{LiDAR} waveform analysis and high resolution spectrometry remote sensing for sensitive spaces in a coastal environment},
	url = {https://tel.archives-ouvertes.fr/tel-01532088},
	school = {Université de Nantes Faculté des sciences et des techniques},
	author = {Ba, Antoine},
	month = feb,
	year = {2017},
	keywords = {Classification, Coastal dune, Dune côtière, Hyperspectral imaging, Imagerie hyperspectrale, LiDAR, LiDAR imagery, Vegetation},
	file = {Ba - 2017 - LiDAR waveform analysis and high resolution spectr.pdf:/home/florent/.zotero/data/storage/MFVS3EBG/Ba - 2017 - LiDAR waveform analysis and high resolution spectr.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/HT584XQ5/notes.md:text/markdown}
}

@article{persson_visualization_2005,
	title = {Visualization and analysis of full-waveform airborne laser scanner data},
	volume = {36},
	number = {part 3},
	journal = {International Archives of Photogrammetry, Remote Sensing and Spatial Information Sciences},
	author = {Persson, {\textbackslash}AAsa and Söderman, U and Töpel, J and Ahlberg, Simon},
	year = {2005},
	keywords = {NEXT, full waveform, lidar},
	pages = {W19},
	file = {Persson et al. - 2005 - Visualization and analysis of full-waveform airbor.pdf:/home/florent/.zotero/data/storage/ND7KK3HU/Persson et al. - 2005 - Visualization and analysis of full-waveform airbor.pdf:application/pdf}
}

@article{matikainen_object-based_2017,
	title = {Object-based analysis of multispectral airborne laser scanner data for land cover classification and map updating},
	volume = {128},
	issn = {09242716},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S0924271616305305},
	doi = {10.1016/j.isprsjprs.2017.04.005},
	abstract = {During the last 20 years, airborne laser scanning (ALS), often combined with passive multispectral information from aerial images, has shown its high feasibility for automated mapping processes. The main benefits have been achieved in the mapping of elevated objects such as buildings and trees. Recently, the first multispectral airborne laser scanners have been launched, and active multispectral information is for the first time available for 3D ALS point clouds from a single sensor. This article discusses the potential of this new technology in map updating, especially in automated object-based land cover classification and change detection in a suburban area. For our study, Optech Titan multispectral ALS data over a suburban area in Finland were acquired. Results from an object-based random forests analysis suggest that the multispectral ALS data are very useful for land cover classification, considering both elevated classes and ground-level classes. The overall accuracy of the land cover classification results with six classes was 96\% compared with validation points. The classes under study included building, tree, asphalt, gravel, rocky area and low vegetation. Compared to classification of single-channel data, the main improvements were achieved for ground-level classes. According to feature importance analyses, multispectral intensity features based on several channels were more useful than those based on one channel. Automatic change detection for buildings and roads was also demonstrated by utilising the new multispectral ALS data in combination with old map vectors. In change detection of buildings, an old digital surface model (DSM) based on single-channel ALS data was also used. Overall, our analyses suggest that the new data have high potential for further increasing the automation level in mapping. Unlike passive aerial imaging commonly used in mapping, the multispectral ALS technology is independent of external illumination conditions, and there are no shadows on intensity images produced from the data. These are significant advantages in developing automated classification and change detection procedures.},
	language = {en},
	urldate = {2018-10-31},
	journal = {ISPRS Journal of Photogrammetry and Remote Sensing},
	author = {Matikainen, Leena and Karila, Kirsi and Hyyppä, Juha and Litkey, Paula and Puttonen, Eetu and Ahokas, Eero},
	month = jun,
	year = {2017},
	keywords = {NEXT, classification, lidar, rasterization, titan},
	pages = {298--313},
	file = {Matikainen et al. - 2017 - Object-based analysis of multispectral airborne la.pdf:/home/florent/.zotero/data/storage/PE7TECR5/Matikainen et al. - 2017 - Object-based analysis of multispectral airborne la.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/XWPKZU5L/notes.md:text/markdown}
}

@article{leigh_using_2016,
	title = {Using dual-wavelength, full-waveform airborne lidar for surface classification and vegetation characterization},
	volume = {10},
	issn = {1931-3195},
	url = {http://remotesensing.spiedigitallibrary.org/article.aspx?doi=10.1117/1.JRS.10.045001},
	doi = {10.1117/1.JRS.10.045001},
	language = {en},
	number = {4},
	urldate = {2018-10-31},
	journal = {Journal of Applied Remote Sensing},
	author = {Leigh, Holly W. and Magruder, Lori A.},
	month = oct,
	year = {2016},
	note = {00000},
	keywords = {NEXT, classification, full waveform, lidar, voxels, titan},
	pages = {045001},
	file = {Leigh and Magruder - 2016 - Using dual-wavelength, full-waveform airborne lida.pdf:/home/florent/.zotero/data/storage/CBSAT4W3/Leigh and Magruder - 2016 - Using dual-wavelength, full-waveform airborne lida.pdf:application/pdf}
}

@article{teo_analysis_2017,
	title = {Analysis of {Land} {Cover} {Classification} {Using} {Multi}-{Wavelength} {LiDAR} {System}},
	volume = {7},
	issn = {2076-3417},
	url = {http://www.mdpi.com/2076-3417/7/7/663},
	doi = {10.3390/app7070663},
	abstract = {The airborne multi-wavelength light detection and ranging (LiDAR) system measures different wavelengths simultaneously and usually includes two or more active channels in infrared and green to acquire both topographic and hydrographic information. The reflected multi-wavelength energy can also be used to identify different land covers based on physical properties of materials. This study explored the benefits of multi-wavelength LiDAR in object-based land cover classification, focusing on three major issues: (1) the evaluation of single- and multi-wavelength LiDARs for land cover classification; (2) the performance of spectral and geometrical features extracted from multi-wavelength LiDAR; and (3) the comparison of the vegetation index derived from active multi-wavelength LiDAR and passive multispectral images. The three-wavelength test data were acquired by Optech Titan in green, near-infrared, and mid-infrared channels, and the reference data were acquired from Worldview-3 image. The experimental results show that the multi-wavelength LiDAR provided higher accuracy than single-wavelength LiDAR in land cover classification, with an overall accuracy improvement rate about 4–14 percentage points. The spectral features performed better compared to geometrical features for grass, road, and bare soil classes, and the overall accuracy improvement is about 29 percentage points. The results also demonstrated the vegetation indices from Worldview-3 and Optech Titan have similar characteristics, with correlations reaching 0.68 to 0.89. Overall, the multi-wavelength LiDAR system improves the accuracy of land cover classification because this system provides more spectral information than traditional single-wavelength LiDAR.},
	language = {en},
	number = {7},
	urldate = {2018-10-31},
	journal = {Applied Sciences},
	author = {Teo, Tee-Ann and Wu, Hsien-Ming},
	month = jun,
	year = {2017},
	keywords = {NEXT, classification, lidar, rasterization, titan, 2D},
	pages = {663},
	file = {notes.md:/home/florent/.zotero/data/storage/M35L5W8G/notes.md:text/markdown;Teo and Wu - 2017 - Analysis of Land Cover Classification Using Multi-.pdf:/home/florent/.zotero/data/storage/6WIYMMKY/Teo and Wu - 2017 - Analysis of Land Cover Classification Using Multi-.pdf:application/pdf}
}

@article{pauly_multi-scale_2003,
	title = {Multi-scale {Feature} {Extraction} on {Point}-{Sampled} {Surfaces}},
	volume = {22},
	issn = {0167-7055, 1467-8659},
	url = {http://doi.wiley.com/10.1111/1467-8659.00675},
	doi = {10.1111/1467-8659.00675},
	abstract = {We present a new technique for extracting line-type features on point-sampled geometry. Given an unstructured point cloud as input, our method first applies principal component analysis on local neighborhoods to classify points according to the likelihood that they belong to a feature. Using hysteresis thresholding, we then compute a minimum spanning graph as an initial approximation of the feature lines. To smooth out the features while maintaining a close connection to the underlying surface, we use an adaptation of active contour models. Central to our method is a multi-scale classification operator that allows feature analysis at multiple scales, using the size of the local neighborhoods as a discrete scale parameter. This significantly improves the reliability of the detection phase and makes our method more robust in the presence of noise. To illustrate the usefulness of our method, we have implemented a non-photorealistic point renderer to visualize point-sampled surfaces as line drawings of their extracted feature curves.},
	language = {en},
	number = {3},
	urldate = {2018-10-31},
	journal = {Computer Graphics Forum},
	author = {Pauly, Mark and Keiser, Richard and Gross, Markus},
	month = sep,
	year = {2003},
	keywords = {NEXT, point cloud, features},
	pages = {281--289},
	file = {Pauly et al. - 2003 - Multi-scale Feature Extraction on Point-Sampled Su.pdf:/home/florent/.zotero/data/storage/Z3795SCZ/Pauly et al. - 2003 - Multi-scale Feature Extraction on Point-Sampled Su.pdf:application/pdf}
}

@article{wang_airborne_2014,
	title = {Airborne {Dual}-{Wavelength} {LiDAR} {Data} for {Classifying} {Land} {Cover}},
	volume = {6},
	issn = {2072-4292},
	url = {http://www.mdpi.com/2072-4292/6/1/700},
	doi = {10.3390/rs6010700},
	abstract = {This study demonstrated the potential of using dual-wavelength airborne light detection and ranging (LiDAR) data to classify land cover. Dual-wavelength LiDAR data were acquired from two airborne LiDAR systems that emitted pulses of light in near-infrared (NIR) and middle-infrared (MIR) lasers. The major features of the LiDAR data, such as surface height, echo width, and dual-wavelength amplitude, were used to represent the characteristics of land cover. Based on the major features of land cover, a support vector machine was used to classify six types of suburban land cover: road and gravel, bare soil, low vegetation, high vegetation, roofs, and water bodies. Results show that using dual-wavelength LiDAR-derived information (e.g., amplitudes at NIR and MIR wavelengths) could compensate for the limitations of using single-wavelength LiDAR information (i.e., poor discrimination of low vegetation) when classifying land cover.},
	language = {en},
	number = {1},
	urldate = {2018-10-31},
	journal = {Remote Sensing},
	author = {Wang, Cheng-Kai and Tseng, Yi-Hsing and Chu, Hone-Jay},
	month = jan,
	year = {2014},
	keywords = {NEXT, classification, lidar, rasterization, titan, 2D},
	pages = {700--715},
	file = {Wang et al. - 2014 - Airborne Dual-Wavelength LiDAR Data for Classifyin.pdf:/home/florent/.zotero/data/storage/PYJJKH5D/Wang et al. - 2014 - Airborne Dual-Wavelength LiDAR Data for Classifyin.pdf:application/pdf}
}

@article{zou_3d_2016,
	title = {3D {LAND} {COVER} {CLASSIFICATION} {BASED} {ON} {MULTISPECTRAL} {LIDAR} {POINT} {CLOUDS}},
	volume = {XLI-B1},
	issn = {2194-9034},
	url = {http://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLI-B1/741/2016/isprs-archives-XLI-B1-741-2016.pdf},
	doi = {10.5194/isprsarchives-XLI-B1-741-2016},
	abstract = {Multispectral Lidar System can emit simultaneous laser pulses at the different wavelengths. The reflected multispectral energy is captured through a receiver of the sensor, and the return signal together with the position and orientation information of sensor is recorded. These recorded data are solved with GNSS/IMU data for further post-processing, forming high density multispectral 3D point clouds. As the first commercial multispectral airborne Lidar sensor, Optech Titan system is capable of collecting point clouds data from all three channels at 532nm visible (Green), at 1064 nm near infrared (NIR) and at 1550nm intermediate infrared (IR). It has become a new source of data for 3D land cover classification. The paper presents an Object Based Image Analysis (OBIA) approach to only use multispectral Lidar point clouds datasets for 3D land cover classification. The approach consists of three steps. Firstly, multispectral intensity images are segmented into image objects on the basis of multi-resolution segmentation integrating different scale parameters. Secondly, intensity objects are classified into nine categories by using the customized features of classification indexes and a combination the multispectral reflectance with the vertical distribution of object features. Finally, accuracy assessment is conducted via comparing random reference samples points from google imagery tiles with the classification results. The classification results show higher overall accuracy for most of the land cover types. Over 90\% of overall accuracy is achieved via using multispectral Lidar point clouds for 3D land cover classification.},
	language = {en},
	urldate = {2018-10-31},
	journal = {ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences},
	author = {Zou, Xiaoliang and Zhao, Guihua and Li, Jonathan and Yang, Yuanxi and Fang, Yong},
	month = jun,
	year = {2016},
	keywords = {NEXT, classification, lidar, titan, 3D},
	pages = {741--747},
	file = {Zou et al. - 2016 - 3D LAND COVER CLASSIFICATION BASED ON MULTISPECTRA.pdf:/home/florent/.zotero/data/storage/JZEZD9CJ/Zou et al. - 2016 - 3D LAND COVER CLASSIFICATION BASED ON MULTISPECTRA.pdf:application/pdf}
}

@article{bakula_testing_2016,
	title = {{TESTING} {OF} {LAND} {COVER} {CLASSIFICATION} {FROM} {MULTISPECTRAL} {AIRBORNE} {LASER} {SCANNING} {DATA}},
	volume = {XLI-B7},
	issn = {2194-9034},
	url = {http://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLI-B7/161/2016/isprs-archives-XLI-B7-161-2016.pdf},
	doi = {10.5194/isprsarchives-XLI-B7-161-2016},
	abstract = {Multispectral Airborne Laser Scanning provides a new opportunity for airborne data collection. It provides high-density topographic surveying and is also a useful tool for land cover mapping. Use of a minimum of three intensity images from a multiwavelength laser scanner and 3D information included in the digital surface model has the potential for land cover/use classification and a discussion about the application of this type of data in land cover/use mapping has recently begun. In the test study, three laser reflectance intensity images (orthogonalized point cloud) acquired in green, near-infrared and short-wave infrared bands, together with a digital surface model, were used in land cover/use classification where six classes were distinguished: water, sand and gravel, concrete and asphalt, low vegetation, trees and buildings. In the tested methods, different approaches for classification were applied: spectral (based only on laser reflectance intensity images), spectral with elevation data as additional input data, and spectro-textural, using morphological granulometry as a method of texture analysis of both types of data: spectral images and the digital surface model. The method of generating the intensity raster was also tested in the experiment. Reference data were created based on visual interpretation of ALS data and traditional optical aerial and satellite images. The results have shown that multispectral ALS data are unlike typical multispectral optical images, and they have a major potential for land cover/use classification. An overall accuracy of classification over 90\% was achieved. The fusion of multi-wavelength laser intensity images and elevation data, with the additional use of textural information derived from granulometric analysis of images, helped to improve the accuracy of classification significantly. The method of interpolation for the intensity raster was not very helpful, and using intensity rasters with both first and last return numbers slightly improved the results.},
	language = {en},
	urldate = {2018-10-31},
	journal = {ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences},
	author = {Bakuła, K. and Kupidura, P. and Jełowicki, ł.},
	month = jun,
	year = {2016},
	note = {00014},
	keywords = {NEXT, classification, lidar, titan},
	pages = {161--169},
	file = {Bakuła et al. - 2016 - TESTING OF LAND COVER CLASSIFICATION FROM MULTISPE.pdf:/home/florent/.zotero/data/storage/RZ9SQ8LL/Bakuła et al. - 2016 - TESTING OF LAND COVER CLASSIFICATION FROM MULTISPE.pdf:application/pdf}
}

@article{karila_feasibility_2017,
	title = {Feasibility of {Multispectral} {Airborne} {Laser} {Scanning} {Data} for {Road} {Mapping}},
	volume = {14},
	issn = {1545-598X, 1558-0571},
	url = {http://ieeexplore.ieee.org/document/7829363/},
	doi = {10.1109/LGRS.2016.2631261},
	abstract = {Multispectral airborne laser scanning (ALS) data have recently become available. The objective of this letter is to study the feasibility of these data for road mapping—for road detection and road surface classification. The results are compared with the results of traditional aerial ortho images using object-based image analysis and Random Forest classification. The results demonstrate that the multispectral ALS data are feasible for automatic road detection and a significant improvement compared to the use of optical aerial imagery is obtained. In a test using ALS data, 80.5\% points representing roads were classified correctly. When aerial images were used, the percentage decreased to 71.6\%.},
	language = {en},
	number = {3},
	urldate = {2018-10-31},
	journal = {IEEE Geoscience and Remote Sensing Letters},
	author = {Karila, Kirsi and Matikainen, Leena and Puttonen, Eetu and Hyyppa, Juha},
	month = mar,
	year = {2017},
	note = {00000},
	keywords = {NEXT, classification, lidar, titan},
	pages = {294--298},
	file = {Karila et al. - 2017 - Feasibility of Multispectral Airborne Laser Scanni.pdf:/home/florent/.zotero/data/storage/EGXVR6IX/Karila et al. - 2017 - Feasibility of Multispectral Airborne Laser Scanni.pdf:application/pdf}
}

@incollection{lane_playing_2017,
	title = {Playing {With} {Virtual} {Blocks}: {Minecraft} as a {Learning} {Environment} for {Practice} and {Research}},
	isbn = {978-0-12-809481-5},
	shorttitle = {Playing {With} {Virtual} {Blocks}},
	url = {https://linkinghub.elsevier.com/retrieve/pii/B9780128094815000079},
	language = {en},
	urldate = {2018-11-02},
	booktitle = {Cognitive {Development} in {Digital} {Contexts}},
	publisher = {Elsevier},
	author = {Lane, H. Chad and Yi, Sherry},
	year = {2017},
	doi = {10.1016/B978-0-12-809481-5.00007-9},
	pages = {145--166},
	file = {Lane and Yi - 2017 - Playing With Virtual Blocks Minecraft as a Learni.pdf:/home/florent/.zotero/data/storage/WTZ46PJU/Lane and Yi - 2017 - Playing With Virtual Blocks Minecraft as a Learni.pdf:application/pdf}
}

@incollection{felsberg_use_2017,
	address = {Cham},
	title = {On the {Use} of the {Tree} {Structure} of {Depth} {Levels} for {Comparing} 3D {Object} {Views}},
	volume = {10424},
	isbn = {978-3-319-64688-6 978-3-319-64689-3},
	url = {http://link.springer.com/10.1007/978-3-319-64689-3_21},
	abstract = {Today the simple availability of 3D sensory data, the evolution of 3D representations, and their application to object recognition and scene analysis tasks promise to improve autonomy and flexibility of robots in several domains. However, there has been little research into what can be gained through the explicit inclusion of the structural relations between parts of objects when quantifying similarity of their shape, and hence for shape-based object category recognition. We propose a Mathematical Morphology inspired hierarchical decomposition of 3D object views into peak components at evenly spaced depth levels, casting the 3D shape similarity problem to a tree of more elementary similarity problems. The matching of these trees of peak components is here compared to matching the individual components through optimal and greedy assignment in a simple feature space, trying to find the maximum-weight-maximal-match assignments. The matching thus achieved provides a metric of total shape similarity between object views. The three matching strategies are evaluated and compared through the category recognition accuracy on objects from a public set of 3D models. It turns out that all three methods yield similar accuracy on the simple features we used, while the greedy method is fastest.},
	language = {en},
	urldate = {2018-11-11},
	booktitle = {Computer {Analysis} of {Images} and {Patterns}},
	publisher = {Springer International Publishing},
	author = {Bracci, Fabio and Hillenbrand, Ulrich and Marton, Zoltan-Csaba and Wilkinson, Michael H. F.},
	editor = {Felsberg, Michael and Heyden, Anders and Krüger, Norbert},
	year = {2017},
	doi = {10.1007/978-3-319-64689-3_21},
	note = {00000 },
	keywords = {NEXT, ISMM},
	pages = {251--263},
	file = {Bracci et al. - 2017 - On the Use of the Tree Structure of Depth Levels f.pdf:/home/florent/.zotero/data/storage/S498LTII/Bracci et al. - 2017 - On the Use of the Tree Structure of Depth Levels f.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/BCTMZGBF/notes.md:text/plain}
}

@inproceedings{wang_voxelization_2013,
	address = {Melbourne, Australia},
	title = {Voxelization of full waveform {LiDAR} data for fusion with {Hyperspectral} {Imagery}},
	isbn = {978-1-4799-1114-1},
	url = {http://ieeexplore.ieee.org/document/6723560/},
	doi = {10.1109/IGARSS.2013.6723560},
	abstract = {Current research into the fusion of Hyperspectral Imagery (HI) and full waveform LiDAR (Light detection and ranging) has relied on fIrst processing the full waveform LiDAR (FWL) data to a set of discrete returns before combining. However, more information about target properties can potentially be recovered if the raw waveform is preserved in the fusion with HI. This paper proposes a voxelization method to fuse raw FWL data with HI by dividing the waveform data into voxels, and then synthesizing all waveforms which intersect a voxel into one 3D superposition waveform. The effIcacy of this method is evaluated by comparing the synthesized waveform with an actual nadir LiDAR waveform from the voxel of interest. Results show that this method of voxelizing and fusion of FWL data can preserve raw waveform characteristics while effectively representing the FWL data on a 3D raster basis that can be directly co-registered with the HI.},
	language = {en},
	urldate = {2018-11-26},
	booktitle = {2013 {IEEE} {International} {Geoscience} and {Remote} {Sensing} {Symposium} - {IGARSS}},
	publisher = {IEEE},
	author = {Wang, Hongzhou and Glennie, Craig and Prasad, Saurabh},
	month = jul,
	year = {2013},
	keywords = {NEXT, full waveform, lidar, voxels, fusion},
	pages = {3407--3410},
	file = {notes.md:/home/florent/.zotero/data/storage/P3FW8LQU/notes.md:text/markdown;Wang et al. - 2013 - Voxelization of full waveform LiDAR data for fusio.pdf:/home/florent/.zotero/data/storage/BGHJSFRQ/Wang et al. - 2013 - Voxelization of full waveform LiDAR data for fusio.pdf:application/pdf}
}

@article{wang_fusion_2015,
	title = {Fusion of waveform {LiDAR} data and hyperspectral imagery for land cover classification},
	volume = {108},
	issn = {09242716},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S0924271615001495},
	doi = {10.1016/j.isprsjprs.2015.05.012},
	abstract = {Current research into the fusion of hyperspectral imagery (HI) and full waveform LiDAR (Light Detection And Ranging) has relied on first processing the full waveform LiDAR (FWL) data to a set of discrete returns before merging because the data structure and sampling interval of HI and FWL are distinctly different. However, additional information about target properties can potentially be recovered if the waveform shape is preserved in the fusion process. This paper proposes a ‘‘voxelization’’ method to register FWL data to HI by dividing the waveform data into voxels, and then synthesizing all waveforms which intersect a voxel column into one three-dimensional superposition waveform: the synthesized waveform (SWF). A vertical energy distribution coefficients (VEDC) feature is proposed for extracting features from SWF, and then the SWF and HI are fused to form a complete feature space for classification. A pairwise classifier was adapted and completed using both Maximum Likelihood and Support Vector Machine classifiers for the combined SWF/HI features. Results show that this method of generating SWF from FWL data can effectively preserve information from the original waveforms, and the fusion of SWF and HI enhanced land cover classification compared to both using either data set alone or the merging of HI with a discrete LiDAR return point cloud.},
	language = {en},
	urldate = {2018-11-26},
	journal = {ISPRS Journal of Photogrammetry and Remote Sensing},
	author = {Wang, Hongzhou and Glennie, Craig},
	month = oct,
	year = {2015},
	keywords = {NEXT, full waveform, lidar, voxels, fusion},
	pages = {1--11},
	file = {Wang and Glennie - 2015 - Fusion of waveform LiDAR data and hyperspectral im.pdf:/home/florent/.zotero/data/storage/TTBZNDHM/Wang and Glennie - 2015 - Fusion of waveform LiDAR data and hyperspectral im.pdf:application/pdf}
}

@article{gorte_structuring_2004,
	title = {Structuring laser-scanned trees using 3D mathematical morphology},
	volume = {35},
	number = {B5},
	journal = {International Archives of Photogrammetry and Remote Sensing},
	author = {Gorte, Ben and Pfeifer, Norbert},
	year = {2004},
	keywords = {ISMM},
	pages = {929--933},
	file = {Gorte and Pfeifer - 2004 - Structuring laser-scanned trees using 3D mathemati.pdf:/home/florent/.zotero/data/storage/FFF3GEKD/Gorte and Pfeifer - 2004 - Structuring laser-scanned trees using 3D mathemati.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/BP6NTW2L/notes.md:text/markdown}
}

@article{stelling_voxel_2016,
	title = {{VOXEL} {BASED} {REPRESENTATION} {OF} {FULL}-{WAVEFORM} {AIRBORNE} {LASER} {SCANNER} {DATA} {FOR} {FORESTRY} {APPLICATIONS}},
	volume = {XLI-B8},
	issn = {2194-9034},
	url = {http://www.int-arch-photogramm-remote-sens-spatial-inf-sci.net/XLI-B8/755/2016/isprs-archives-XLI-B8-755-2016.pdf},
	doi = {10.5194/isprsarchives-XLI-B8-755-2016},
	abstract = {The advantages of using airborne full-waveform laser scanner data in forest applications, e.g. for the description of the vertical vegetation structure or accurate biomass estimation, have been emphasized in many publications. To exploit the full potential offered by airborne full-waveform laser scanning data, the development of voxel based methods for data analysis is essential. In contrast to existing approaches based on the extraction of discrete 3D points by a Gaussian decomposition, it is very promising to derive the voxel attributes from the digitised waveform directly. For this purpose, the waveform data have to be transferred into a 3D voxel representation. This requires a series of radiometric and geometric transformations of the raw full-waveform laser scanner data. Thus, the paper deals with the geometric aspects and describes a processing chain from the raw waveform data to an attenuationcorrected volumetric forest stand reconstruction.},
	language = {en},
	urldate = {2018-11-27},
	journal = {ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences},
	author = {Stelling, N. and Richter, K.},
	month = jun,
	year = {2016},
	keywords = {NEXT, lidar, voxels},
	pages = {755--762},
	file = {Stelling and Richter - 2016 - VOXEL BASED REPRESENTATION OF FULL-WAVEFORM AIRBOR.pdf:/home/florent/.zotero/data/storage/RZB7R27P/Stelling and Richter - 2016 - VOXEL BASED REPRESENTATION OF FULL-WAVEFORM AIRBOR.pdf:application/pdf}
}

@incollection{wettergreen_segmentation_2016,
	address = {Cham},
	title = {Segmentation and {Classification} of 3D {Urban} {Point} {Clouds}: {Comparison} and {Combination} of {Two} {Approaches}},
	volume = {113},
	isbn = {978-3-319-27700-4 978-3-319-27702-8},
	shorttitle = {Segmentation and {Classification} of 3D {Urban} {Point} {Clouds}},
	url = {http://link.springer.com/10.1007/978-3-319-27702-8_14},
	abstract = {Segmentation and classification of 3D urban point clouds is a complex task, making it very difficult for any single method to overcome all the diverse challenges offered. This sometimes requires the combination of several techniques to obtain the desired results for different applications. This work presents and compares two different approaches for segmenting and classifying 3D urban point clouds. In the first approach, detection, segmentation and classification of urban objects from 3D point clouds, converted into elevation images, are performed by using mathematical morphology. First, the ground is segmented and objects are detected as discontinuities on the ground. Then, connected objects are segmented using a watershed approach. Finally, objects are classified using SVM (Support Vector Machine) with geometrical and contextual features. The second method employs a super-voxel based approach in which the 3D urban point cloud is first segmented into voxels and then converted into super-voxels. These are then clustered together using an efficient link-chain method to form objects. These segmented objects are then classified using local descriptors and geometrical features into basic object classes. Evaluated on a common dataset (real data), both these methods are thoroughly compared on three different levels: detection, segmentation and classification. After analyses, simple strategies are also presented to combine the two methods, exploiting their complementary strengths and weaknesses, to improve the overall segmentation and classification results.},
	language = {en},
	urldate = {2018-11-27},
	booktitle = {Field and {Service} {Robotics}},
	publisher = {Springer International Publishing},
	author = {Aijazi, A. K. and Serna, A. and Marcotegui, B. and Checchin, P. and Trassoudaine, L.},
	editor = {Wettergreen, David S. and Barfoot, Timothy D.},
	year = {2016},
	note = {00000},
	keywords = {NEXT, segmentation, morphology, classification, lidar, ISMM},
	pages = {201--216},
	file = {Aijazi et al. - 2016 - Segmentation and Classification of 3D Urban Point .pdf:/home/florent/.zotero/data/storage/GGUKKIC3/Aijazi et al. - 2016 - Segmentation and Classification of 3D Urban Point .pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/DKKGFT3P/notes.md:text/markdown}
}

@incollection{angulo_brain_2017,
	address = {Cham},
	title = {Brain {Lesion} {Detection} in 3D {PET} {Images} {Using} {Max}-{Trees} and a {New} {Spatial} {Context} {Criterion}},
	volume = {10225},
	isbn = {978-3-319-57239-0 978-3-319-57240-6},
	url = {http://link.springer.com/10.1007/978-3-319-57240-6_37},
	abstract = {In this work, we propose a new criterion based on spatial context to select relevant nodes in a max-tree representation of an image, dedicated to the detection of 3D brain tumors for 18F -FDG PET images. This criterion prevents the detected lesions from merging with surrounding physiological radiotracer uptake. A complete detection method based on this criterion is proposed, and was evaluated on five patients with brain metastases and tuberculosis, and quantitatively assessed using the true positive rates and positive predictive values. The experimental results show that the method detects all the lesions in the PET images.},
	language = {en},
	urldate = {2018-12-03},
	booktitle = {Mathematical {Morphology} and {Its} {Applications} to {Signal} and {Image} {Processing}},
	publisher = {Springer International Publishing},
	author = {Urien, Hélène and Buvat, Irène and Rougon, Nicolas and Soussan, Michaël and Bloch, Isabelle},
	editor = {Angulo, Jesús and Velasco-Forero, Santiago and Meyer, Fernand},
	year = {2017},
	doi = {10.1007/978-3-319-57240-6_37},
	keywords = {voxels, ISMM, hierarchical representation},
	pages = {455--466},
	file = {notes.md:/home/florent/.zotero/data/storage/XME9ZGUL/notes.md:text/markdown;Urien et al. - 2017 - Brain Lesion Detection in 3D PET Images Using Max-.pdf:/home/florent/.zotero/data/storage/E22SPADW/Urien et al. - 2017 - Brain Lesion Detection in 3D PET Images Using Max-.pdf:application/pdf}
}

@book{jesus_angulo_mathematical_2017,
	edition = {1},
	series = {Lecture {Notes} in {Computer} {Science} 10225},
	title = {Mathematical {Morphology} and {Its} {Applications} to {Signal} and {Image} {Processing}: 13th {International} {Symposium}, {ISMM} 2017, {Fontainebleau}, {France}, {May} 15–17, 2017, {Proceedings}},
	isbn = {978-3-319-57239-0 978-3-319-57240-6},
	url = {http://gen.lib.rus.ec/book/index.php?md5=6c0abdf9e828221efeb237bbb44fdc6c},
	publisher = {Springer International Publishing},
	author = {Jesús Angulo, Santiago Velasco-Forero, Fernand Meyer (eds.)},
	year = {2017},
	file = {2017 - Mathematical morphology and its applications to si.pdf:/home/florent/.zotero/data/storage/NFS87DVN/2017 - Mathematical morphology and its applications to si.pdf:application/pdf}
}

@inproceedings{marcotegui_ultimate_2017,
	address = {Cham},
	title = {Ultimate {Opening} {Combined} with {Area} {Stability} {Applied} to {Urban} {Scenes}},
	isbn = {978-3-319-57240-6},
	abstract = {This paper explores the use of ultimate opening in urban analysis context. It demonstrates the efficiency of this approach for street level elevation images, derived from 3D point clouds acquired by terrestrial mobile mapping systems. An area-stability term is introduced in the residual definition, reducing the over-segmentation of the vegetation while preserving small significant regions.},
	booktitle = {Mathematical {Morphology} and {Its} {Applications} to {Signal} and {Image} {Processing}},
	publisher = {Springer International Publishing},
	author = {Marcotegui, Beatriz and Serna, Andrés and Hernández, Jorge},
	editor = {Angulo, Jesús and Velasco-Forero, Santiago and Meyer, Fernand},
	year = {2017},
	keywords = {morphology, urban, ISMM},
	pages = {261--268},
	file = {notes.md:/home/florent/.zotero/data/storage/GKX84N56/notes.md:text/markdown}
}

@inproceedings{kazemier_connected_2017,
	address = {Cham},
	title = {Connected {Morphological} {Attribute} {Filters} on {Distributed} {Memory} {Parallel} {Machines}},
	isbn = {978-3-319-57240-6},
	abstract = {We present a new algorithm for attribute filtering of extremely large images, using a forest of modified max-trees, suitable for distributed memory parallel machines. First, max-trees of tiles of the image are computed, after which messages are exchanged to modify the topology of the trees and update attribute data, such that filtering the modified trees on each tile gives exactly the same results as filtering a regular max-tree of the entire image. On a cluster, a speed-up of up to 53\$\${\textbackslash}backslashtimes \$\$is obtained on 64, and up to 100\$\${\textbackslash}backslashtimes \$\$on 128 single CPU nodes. On a shared memory machine a peak speed-up of 50\$\${\textbackslash}backslashtimes \$\$on 64 cores was obtained.},
	booktitle = {Mathematical {Morphology} and {Its} {Applications} to {Signal} and {Image} {Processing}},
	publisher = {Springer International Publishing},
	author = {Kazemier, Jan J. and Ouzounis, Georgios K. and Wilkinson, Michael H. F.},
	editor = {Angulo, Jesús and Velasco-Forero, Santiago and Meyer, Fernand},
	year = {2017},
	keywords = {hierarchical representation, algo},
	pages = {357--368},
	file = {notes.md:/home/florent/.zotero/data/storage/TTGB4NXH/notes.md:text/markdown}
}

@inproceedings{bosilj_attribute_2017,
	address = {Cham},
	title = {Attribute {Profiles} from {Partitioning} {Trees}},
	isbn = {978-3-319-57240-6},
	abstract = {Morphological attribute profiles are among the most prominent spatial-spectral pixel description tools. They can be calculated efficiently from tree based representations of an image. Although widely and successfully used with various inclusion trees (i.e., component trees and tree of shape), in this paper, we investigate their implementation through partitioning trees, and specifically \$\${\textbackslash}backslashalpha \$\$- and \$\$({\textbackslash}backslashomega )\$\$-trees. Our preliminary findings show that they are capable of comparable results to the state-of-the-art, while possessing additional properties rendering them suitable for the analysis of multivariate images.},
	booktitle = {Mathematical {Morphology} and {Its} {Applications} to {Signal} and {Image} {Processing}},
	publisher = {Springer International Publishing},
	author = {Bosilj, Petra and Damodaran, Bharath Bhushan and Aptoula, Erchan and Mura, Mauro Dalla and Lefèvre, Sébastien},
	editor = {Angulo, Jesús and Velasco-Forero, Santiago and Meyer, Fernand},
	year = {2017},
	keywords = {trees, attribute profiles},
	pages = {381--392},
	file = {notes.md:/home/florent/.zotero/data/storage/G39WGQVZ/notes.md:text/markdown}
}

@article{lefebvre_monitoring_2017,
	title = {Monitoring the {Morphological} {Transformation} of {Beijing} {Old} {City} {Using} {Remote} {Sensing} {Texture} {Analysis}},
	volume = {10},
	issn = {1939-1404, 2151-1535},
	url = {http://ieeexplore.ieee.org/document/7782832/},
	doi = {10.1109/JSTARS.2016.2627545},
	abstract = {This paper is concerned with the morphological analysis of Beijing old city’s dynamics from 1966 to 2015. This area has been continuously submitted to internal transformations since the opening of China to a market economy. In particular, districts of small traditional houses are being replaced by large buildings, entailing a fast reorganization of the inner city. To monitor this phenomenon, we propose to characterize urban patterns with veryhigh-resolution images using texture analysis. To this end, dedicated urban descriptors at various scales (based on local variance, cooccurrence matrices, and wavelets) are evaluated and selected to highlight informations related to different urban patterns. These features, whose scales are essential for a reliable description, are used to highlight changes in the city of Beijing in 21 images from 1969 to 2015. The experimental results show good performances and are in accordance with expert knowledge issued from Beijing urban planning studies. About 50\% of the old urban pattern has been destroyed and most of these changes occurred before 2001.},
	language = {en},
	number = {2},
	urldate = {2018-12-03},
	journal = {IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing},
	author = {Lefebvre, Antoine and Corpetti, Thomas},
	month = feb,
	year = {2017},
	pages = {539--548},
	file = {Lefebvre and Corpetti - 2017 - Monitoring the Morphological Transformation of Bei.pdf:/home/florent/.zotero/data/storage/G5RVAYP2/Lefebvre and Corpetti - 2017 - Monitoring the Morphological Transformation of Bei.pdf:application/pdf}
}

@article{rottensteiner_new_2001,
	title = {A {New} {Method} for {Building} {Extraction} in {Urban} {Areas} from {High}-resolution {LIDAR} {Data}},
	volume = {34},
	journal = {Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci},
	author = {Rottensteiner, Franz and Briese, Ch},
	year = {2001},
	file = {Rottensteiner and Briese - 2001 - A New Method for Building Extraction in Urban Area.pdf:/home/florent/.zotero/data/storage/PQCIER74/Rottensteiner and Briese - 2001 - A New Method for Building Extraction in Urban Area.pdf:application/pdf}
}

@article{ramdani_extraction_2013,
	title = {Extraction of {Urban} {Vegetation} in {Highly} {Dense} {Urban} {Environment} with {Application} to {Measure} {Inhabitants}’ {Satisfaction} of {Urban} {Green} {Space}},
	volume = {05},
	issn = {2151-1950, 2151-1969},
	url = {http://www.scirp.org/journal/doi.aspx?DOI=10.4236/jgis.2013.52012},
	doi = {10.4236/jgis.2013.52012},
	abstract = {Urban environment has functioned not only for ecological reason but also for socioeconomic function, due to this reason extraction of urban vegetation in highly dense urban environment becomes more important to understand the inhabitants’ satisfaction of urban green space. With a medium resolution of satellite imagery, the precision is very low. We used high resolution of WorldView-2 satellite to raise the accuracy. We chose Depok City in West Java as a case study area, analyse four multispectral bands, and apply TCT algorithm for getting vegetation density. The relationship between vegetation density and inhabitants’ satisfaction was calculated by Geo-statistical technique based on administrative boundary. We extracted three types of urban vegetation density: good, mid and low. The final result shows that the inhabitants are mostly satisfied with good density of urban vegetation in the city forest inside Campus University of Indonesia.},
	language = {en},
	number = {02},
	urldate = {2018-12-03},
	journal = {Journal of Geographic Information System},
	author = {Ramdani, Fatwa},
	year = {2013},
	pages = {117--122},
	file = {Ramdani - 2013 - Extraction of Urban Vegetation in Highly Dense Urb.pdf:/home/florent/.zotero/data/storage/HV9W6WK4/Ramdani - 2013 - Extraction of Urban Vegetation in Highly Dense Urb.pdf:application/pdf}
}

@incollection{aujol_morphological_2015,
	address = {Cham},
	title = {Morphological {Scale}-{Space} {Operators} for {Images} {Supported} on {Point} {Clouds}},
	volume = {9087},
	isbn = {978-3-319-18460-9 978-3-319-18461-6},
	url = {http://link.springer.com/10.1007/978-3-319-18461-6_7},
	abstract = {The aim of this paper is to develop the theory, and to propose an algorithm, for morphological processing of images painted on point clouds, viewed as a length metric measure space (X, d, µ). In order to extend morphological operators to process point cloud supported images, one needs to de ne dilation and erosion as semigroup operators on (X, d). That corresponds to a supremal convolution (and in mal convolution) using admissible structuring function on (X, d). From a more theoretical perspective, we introduce the notion of abstract structuring functions formulated on length metric Maslov idempotent measurable spaces, which is the appropriate setting for (X, d). In practice, computation of Maslov structuring function is approached by a random walks framework to estimate heat kernel on (X, d, µ), followed by the logarithmic trick.},
	language = {en},
	urldate = {2018-12-03},
	booktitle = {Scale {Space} and {Variational} {Methods} in {Computer} {Vision}},
	publisher = {Springer International Publishing},
	author = {Angulo, Jesús},
	editor = {Aujol, Jean-François and Nikolova, Mila and Papadakis, Nicolas},
	year = {2015},
	doi = {10.1007/978-3-319-18461-6_7},
	keywords = {ISMM},
	pages = {78--89},
	file = {Angulo - 2015 - Morphological Scale-Space Operators for Images Sup.pdf:/home/florent/.zotero/data/storage/DMQIL6I9/Angulo - 2015 - Morphological Scale-Space Operators for Images Sup.pdf:application/pdf}
}

@article{elmoataz_morphological_2016,
	title = {Morphological {PDEs} on {Graphs} for {Image} {Processing} on {Surfaces} and {Point} {Clouds}},
	volume = {5},
	copyright = {http://creativecommons.org/licenses/by/3.0/},
	url = {https://www.mdpi.com/2220-9964/5/11/213},
	doi = {10.3390/ijgi5110213},
	abstract = {Partial Differential Equations (PDEs)-based morphology offers a wide range of continuous operators to address various image processing problems. Most of these operators are formulated as Hamilton–Jacobi equations or curve evolution level set and morphological flows. In our previous works, we have proposed a simple method to solve PDEs on point clouds using the framework of PdEs (Partial difference Equations) on graphs. In this paper, we propose to apply a large class of morphological-based operators on graphs for processing raw 3D point clouds and extend their applications for the processing of colored point clouds of geo-informatics 3D data. Through illustrations, we show that this simple framework can be used in the resolution of many applications for geo-informatics purposes.},
	language = {en},
	number = {11},
	urldate = {2018-12-03},
	journal = {ISPRS International Journal of Geo-Information},
	author = {Elmoataz, Abderrahim and Lozes, François and Talbot, Hugues},
	month = nov,
	year = {2016},
	note = {00000},
	keywords = {NEXT},
	pages = {213},
	file = {Elmoataz et al. - 2016 - Morphological PDEs on Graphs for Image Processing .pdf:/home/florent/.zotero/data/storage/RPIHYZLC/Elmoataz et al. - 2016 - Morphological PDEs on Graphs for Image Processing .pdf:application/pdf;Snapshot:/home/florent/.zotero/data/storage/L5K5N9RB/213.html:text/html}
}

@article{passat_rigid_2018,
	title = {Rigid motions in the cubic grid: {A} discussion on topological issues},
	abstract = {Rigid motions on 2D digital images were recently investigated with the purpose of preserving geometric and topological properties. From the application point of view, such properties are crucial in image processing tasks, for instance image registration. The known ideas behind preserving geometry and topology rely on connections between the 2D continuous and 2D digital geometries that were established via multiple notions of regularity on digital and continuous sets. We start by recalling these results; then we discuss the difficulties that arise when extending them from Z2 to Z3. On the one hand, we aim to provide a discussion on strategies that proved to be successful in Z2 and remain valid in Z3; on the other hand, we explain why certain strategies cannot be extended to the 3D framework of digitized rigid motions. We also emphasize the relationships that may exist between certain concepts initially proposed in Z2. Overall, our objective is to initiate an investigation about the most promising approaches for extending the 2D results to higher dimensions.},
	language = {en},
	author = {Passat, Nicolas and Kenmochi, Yukiko and Ngo, Phuc and Pluta, Kacper},
	year = {2018},
	keywords = {NEXT},
	pages = {13},
	file = {Passat et al. - 2018 - Rigid motions in the cubic grid A discussion on t.pdf:/home/florent/.zotero/data/storage/7JJHTBD2/Passat et al. - 2018 - Rigid motions in the cubic grid A discussion on t.pdf:application/pdf}
}

@inproceedings{padilla_hierarchical_2018,
	address = {Washington, DC},
	title = {Hierarchical forest attributes for multimodal tumor segmentation on {FDG}-{PET}/contrast-enhanced {CT}},
	isbn = {978-1-5386-3636-7},
	url = {https://ieeexplore.ieee.org/document/8363546/},
	doi = {10.1109/ISBI.2018.8363546},
	abstract = {Accurate tumor volume delineation is a crucial step for disease assessment, treatment planning and monitoring of several kinds of cancers. However, this process is complex due to variations in tumors properties. Recently, some methods have been proposed for taking advantage of the spatial and spectral information carried by coupled modalities (e.g., PETCT, MRI-PET). Simultaneously, the development of attributebased approaches has contributed to improve PET image analysis. In this work, we aim at developing a coupled multimodal / attribute-based approach for image segmentation. Our proposal is to take advantage of hierarchical image models for determining relevant and specific attribute from each modality. These attributes then allow us to define a unique, semantic vectorial image. Sequentially, this image can be processed by a standard segmentation method, in our case a randomwalker approach, for segmenting tumors based on their intrinsic attribute-based properties. Experimental results emphasize the relevance of computing region-based attributes from both modalities.},
	language = {en},
	urldate = {2018-12-03},
	booktitle = {2018 {IEEE} 15th {International} {Symposium} on {Biomedical} {Imaging} ({ISBI} 2018)},
	publisher = {IEEE},
	author = {Padilla, Francisco Javier Alvarez and Romaniuk, Barbara and Naegel, Benoit and Servagi-Vernat, Stephanie and Morland, David and Papathanassiou, Dimitri and Passat, Nicolas},
	month = apr,
	year = {2018},
	keywords = {NEXT, ISMM},
	pages = {163--167},
	file = {Padilla et al. - 2018 - Hierarchical forest attributes for multimodal tumo.pdf:/home/florent/.zotero/data/storage/A8RPIY7I/Padilla et al. - 2018 - Hierarchical forest attributes for multimodal tumo.pdf:application/pdf}
}

@inproceedings{grossiord_hierarchies_2015,
	address = {Brooklyn, NY, USA},
	title = {Hierarchies and shape-space for pet image segmentation},
	isbn = {978-1-4799-2374-8},
	url = {http://ieeexplore.ieee.org/document/7164068/},
	doi = {10.1109/ISBI.2015.7164068},
	abstract = {Positron Emission Tomography (PET) image segmentation is essential for detecting lesions and quantifying their metabolic activity. Due to the spatial and spectral properties of PET images, most methods rely on intensity-based strategies. Recent methods also propose to integrate anatomical priors to improve the segmentation process. In this article, we show how the hierarchical approaches proposed in mathematical morphology can efficiently handle these different strategies. Our contribution is twofold. First, we present the component-tree as a relevant data-structure for developing interactive, real-time, intensity-based segmentation of PET images. Second, we prove that thanks to the recent concept of shaping, we can efficiently involve a priori knowledge for lesion segmentation, while preserving the good properties of component-tree segmentation. Preliminary experiments on synthetic and real PET images of lymphoma demonstrate the relevance of our approach.},
	language = {en},
	urldate = {2018-12-03},
	booktitle = {2015 {IEEE} 12th {International} {Symposium} on {Biomedical} {Imaging} ({ISBI})},
	publisher = {IEEE},
	author = {Grossiord, E. and Talbot, H. and Passat, N. and Meignan, M. and Terve, P. and Najman, L.},
	month = apr,
	year = {2015},
	keywords = {ISMM},
	pages = {1118--1121},
	file = {Grossiord et al. - 2015 - Hierarchies and shape-space for pet image segmenta.pdf:/home/florent/.zotero/data/storage/WE6BBSKV/Grossiord et al. - 2015 - Hierarchies and shape-space for pet image segmenta.pdf:application/pdf}
}

@incollection{hutchison_quasi-linear_2013,
	address = {Berlin, Heidelberg},
	title = {A {Quasi}-linear {Algorithm} to {Compute} the {Tree} of {Shapes} of {nD} {Images}},
	volume = {7883},
	isbn = {978-3-642-38293-2 978-3-642-38294-9},
	url = {http://link.springer.com/10.1007/978-3-642-38294-9_9},
	abstract = {To compute the morphological self-dual representation of images, namely the tree of shapes, the state-of-the-art algorithms do not have a satisfactory time complexity. Furthermore the proposed algorithms are only effective for 2D images and they are far from being simple to implement. That is really penalizing since a self-dual representation of images is a structure that gives rise to many powerful operators and applications, and that could be very useful for 3D images. In this paper we propose a simple-to-write algorithm to compute the tree of shapes; it works for nD images and has a quasi-linear complexity when data quantization is low, typically 12 bits or less. To get that result, this paper introduces a novel representation of images that has some amazing properties of continuity, while remaining discrete.},
	language = {en},
	urldate = {2018-12-03},
	booktitle = {Mathematical {Morphology} and {Its} {Applications} to {Signal} and {Image} {Processing}},
	publisher = {Springer Berlin Heidelberg},
	author = {Géraud, Thierry and Carlinet, Edwin and Crozet, Sébastien and Najman, Laurent},
	editor = {Hutchison, David and Kanade, Takeo and Kittler, Josef and Kleinberg, Jon M. and Mattern, Friedemann and Mitchell, John C. and Naor, Moni and Nierstrasz, Oscar and Pandu Rangan, C. and Steffen, Bernhard and Sudan, Madhu and Terzopoulos, Demetri and Tygar, Doug and Vardi, Moshe Y. and Weikum, Gerhard and Hendriks, Cris L. Luengo and Borgefors, Gunilla and Strand, Robin},
	year = {2013},
	note = {00000},
	keywords = {NEXT, ISMM},
	pages = {98--110},
	file = {Géraud et al. - 2013 - A Quasi-linear Algorithm to Compute the Tree of Sh.pdf:/home/florent/.zotero/data/storage/TFR3K66Z/Géraud et al. - 2013 - A Quasi-linear Algorithm to Compute the Tree of Sh.pdf:application/pdf}
}

@book{wilkinson_mathematical_2009,
	title = {Mathematical morphology and its application to signal and image processing},
	publisher = {Springer},
	author = {Wilkinson, Michael HF and Roerdink, JBTM},
	year = {2009},
	keywords = {NEXT},
	file = {Wilkinson and Roerdink - 2009 - Mathematical morphology and its application to sig.pdf:/home/florent/.zotero/data/storage/GERIGII5/Wilkinson and Roerdink - 2009 - Mathematical morphology and its application to sig.pdf:application/pdf}
}

@incollection{kiwanuka_surface-area-based_2009,
	title = {Surface-area-based attribute filtering in 3d},
	booktitle = {International {Symposium} on {Mathematical} {Morphology} and {Its} {Applications} to {Signal} and {Image} {Processing}},
	publisher = {Springer},
	author = {Kiwanuka, Fred N and Ouzounis, Georgios K and Wilkinson, Michael HF},
	year = {2009},
	keywords = {ISMM},
	pages = {70--81},
	file = {Kiwanuka et al. - 2009 - Surface-area-based attribute filtering in 3d.pdf:/home/florent/.zotero/data/storage/RH6ZTEIG/Kiwanuka et al. - 2009 - Surface-area-based attribute filtering in 3d.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/6CHBEB4T/notes.md:text/markdown}
}

@article{zhengnan_zhang_estimating_2017,
	title = {Estimating {Forest} {Structural} {Parameters} {Using} {Canopy} {Metrics} {Derived} from {Airborne} {LiDAR} {Data} in {Subtropical} {Forests}},
	volume = {9},
	issn = {2072-4292},
	url = {http://www.mdpi.com/2072-4292/9/9/940},
	doi = {10.3390/rs9090940},
	abstract = {Accurate and timely estimation of forest structural parameters plays a key role in the management of forest resources, as well as studies on the carbon cycle and biodiversity. Light Detection and Ranging (LiDAR) is a promising active remote sensing technology capable of providing highly accurate three dimensional and wall-to-wall forest structural characteristics. In this study, we evaluated the utility of standard metrics and canopy metrics derived from airborne LiDAR data for estimating plot-level forest structural parameters individually and in combination, over a subtropical forest in Yushan forest farm, southeastern China. Standard metrics, i.e., height-based and density-based metrics, and canopy metrics extracted from canopy vertical profiles, i.e., canopy volume profile (CVP), canopy height distribution (CHD), and foliage profile (FP), were extracted from LiDAR point clouds. Then the standard metrics and canopy metrics were used for estimating forest structural parameters individually and in combination by multiple regression models, including forest type-specific (coniferous forest, broad-leaved forest, mixed forest) models and general models. Additionally, the synergy of standard metrics and canopy metrics for estimating structural parameters was evaluated using field measured data. Finally, the sensitivity of vertical and horizontal resolution of voxel size for estimating forest structural parameters was assessed. The results showed that, in general, the accuracies of forest type-specific models (Adj-R2 = 0.44–0.88) were relatively higher than general models (Adj-R2 = 0.39–0.77). For forest structural parameters, the estimation accuracies of Lorey’s mean height (Adj-R2 = 0.61–0.88) and aboveground biomass (Adj-R2 = 0.54–0.81) models were the highest, followed by volume (Adj-R2 = 0.42–0.78), DBH (Adj-R2 = 0.48–0.74), basal area (Adj-R2 = 0.41–0.69), whereas stem density (Adj-R2 = 0.39–0.64) models were relatively lower. The combination models (Adj-R2 = 0.45–0.88) had higher performance compared with models developed using standard metrics (only) (Adj-R2 = 0.42–0.84) and canopy metrics (only) (Adj-R2 = 0.39–0.83). The results also demonstrated that the optimal voxel size was 5 × 5 × 0.5 m3 for estimating most of the parameters. This study demonstrated that canopy metrics based on canopy vertical profiles can be effectively used to enhance the estimation accuracies of forest structural parameters in subtropical forests.},
	language = {en},
	number = {9},
	urldate = {2018-12-13},
	journal = {Remote Sensing},
	author = {{Zhengnan Zhang} and {Lin Cao} and {Guanghui She}},
	month = sep,
	year = {2017},
	keywords = {NEXT, lidar, voxels, vegetation},
	pages = {940},
	file = {Zhengnan Zhang et al. - 2017 - Estimating Forest Structural Parameters Using Cano.pdf:/home/florent/.zotero/data/storage/8AIAJ7Z9/Zhengnan Zhang et al. - 2017 - Estimating Forest Structural Parameters Using Cano.pdf:application/pdf}
}

@article{westenberg_volumetric_2007,
	title = {Volumetric {Attribute} {Filtering} and {Interactive} {Visualization} {Using} the {Max}-{Tree} {Representation}},
	volume = {16},
	issn = {1057-7149},
	url = {http://ieeexplore.ieee.org/document/4376245/},
	doi = {10.1109/TIP.2007.909317},
	abstract = {The Max-Tree designed for morphological attribute filtering in image processing, is a data structure in which the nodes represent connected components for all threshold levels in a data set. Attribute filters compute some attribute describing the shape or size of each connected component and then decide which components to keep or to discard. In this paper, we augment the basic Max-Tree data structure such that interactive volumetric filtering and visualization becomes possible. We introduce extensions that allow 1) direct, splatting-based, volume rendering; 2) representation of the Max-Tree on graphics hardware; and 3) fast active cell selection for isosurface generation. In all three cases, we can use the Max-Tree representation for visualization directly, without needing to reconstruct the volumetric data explicitly. We show that both filtering and visualization can be performed at interactive frame rates, ranging between 2.4 and 32 frames per seconds. In contrast, a standard texture-based volume visualization method manages only between 0.5 and 1.8 frames per second. For isovalue browsing, the experimental results show that the performance is comparable to the performance of an interval tree, where our method has the advantage that both filter threshold browsing and isolevel browsing are fast. It is shown that the methods using graphics hardware can be extended to other connected filters.},
	language = {en},
	number = {12},
	urldate = {2018-12-13},
	journal = {IEEE Transactions on Image Processing},
	author = {Westenberg, Michel A. and Roerdink, Jos B. T. M. and Wilkinson, Michael H. F.},
	month = dec,
	year = {2007},
	keywords = {NEXT, voxels, ISMM, hierarchical representation},
	pages = {2943--2952},
	file = {notes.md:/home/florent/.zotero/data/storage/YGQYZKZK/notes.md:text/markdown;Westenberg et al. - 2007 - Volumetric Attribute Filtering and Interactive Vis.pdf:/home/florent/.zotero/data/storage/9GGUWBG2/Westenberg et al. - 2007 - Volumetric Attribute Filtering and Interactive Vis.pdf:application/pdf}
}

@article{ouzounis_differential_2012-1,
	title = {Differential {Area} {Profiles}: {Decomposition} {Properties} and {Efficient} {Computation}},
	volume = {34},
	issn = {0162-8828, 2160-9292},
	shorttitle = {Differential {Area} {Profiles}},
	url = {http://ieeexplore.ieee.org/document/6109269/},
	doi = {10.1109/TPAMI.2011.245},
	abstract = {Differential area profiles (DAPs) are point-based multiscale descriptors used in pattern analysis and image segmentation. They are defined through sets of size-based connected morphological filters that constitute a joint area opening top-hat and area closing bottom-hat scale-space of the input image. The work presented in this paper explores the properties of this image decomposition through sets of area zones. An area zone defines a single plane of the DAP vector field and contains all the peak components of the input image, whose size is between the zone’s attribute extrema. Area zones can be computed efficiently from hierarchical image representation structures, in a way similar to regular attribute filters. Operations on the DAP vector field can then be computed without the need for exporting it first, and an example with the leveling-like convex/concave segmentation scheme is given. This is referred to as the one-pass method and it is demonstrated on the Max-Tree structure. Its computational performance is tested and compared against conventional means for computing differential profiles, relying on iterative application of area openings and closings. Applications making use of the area zone decomposition are demonstrated in problems related to remote sensing and medical image analysis.},
	language = {en},
	number = {8},
	urldate = {2018-12-13},
	journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
	author = {Ouzounis, G. K. and Pesaresi, M. and Soille, P.},
	month = aug,
	year = {2012},
	keywords = {NEXT},
	pages = {1533--1548},
	file = {Ouzounis et al. - 2012 - Differential Area Profiles Decomposition Properti.pdf:/home/florent/.zotero/data/storage/J8JNHF35/Ouzounis et al. - 2012 - Differential Area Profiles Decomposition Properti.pdf:application/pdf}
}

@article{salembier_connected_2009,
	title = {Connected operators},
	volume = {26},
	issn = {1053-5888},
	url = {http://ieeexplore.ieee.org/document/5230812/},
	doi = {10.1109/MSP.2009.934154},
	language = {en},
	number = {6},
	urldate = {2018-12-13},
	journal = {IEEE Signal Processing Magazine},
	author = {Salembier, Philippe and Wilkinson, Michael},
	month = nov,
	year = {2009},
	keywords = {NEXT},
	pages = {136--157},
	file = {Salembier and Wilkinson - 2009 - Connected operators.pdf:/home/florent/.zotero/data/storage/3WZCMY8S/Salembier and Wilkinson - 2009 - Connected operators.pdf:application/pdf}
}

@article{dufour_filtering_2013,
	title = {Filtering and segmentation of 3D angiographic data: {Advances} based on mathematical morphology},
	volume = {17},
	issn = {13618415},
	shorttitle = {Filtering and segmentation of 3D angiographic data},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S1361841512001119},
	doi = {10.1016/j.media.2012.08.004},
	abstract = {In the last 20 years, 3D angiographic imaging has proven its usefulness in the context of various clinical applications. However, angiographic images are generally difficult to analyse due to their size and the complexity of the data that they represent, as well as the fact that useful information is easily corrupted by noise and artifacts. Therefore, there is an ongoing necessity to provide tools facilitating their visualisation and analysis, while vessel segmentation from such images remains a challenging task. This article presents new vessel segmentation and filtering techniques, relying on recent advances in mathematical morphology. In particular, methodological results related to spatially variant mathematical morphology and connected filtering are stated, and included in an angiographic data processing framework. These filtering and segmentation methods are evaluated on real and synthetic 3D angiographic data.},
	language = {en},
	number = {2},
	urldate = {2018-12-13},
	journal = {Medical Image Analysis},
	author = {Dufour, A. and Tankyevych, O. and Naegel, B. and Talbot, H. and Ronse, C. and Baruthio, J. and Dokládal, P. and Passat, N.},
	month = feb,
	year = {2013},
	note = {00059},
	keywords = {NEXT, ISMM},
	pages = {147--164},
	file = {Dufour et al. - 2013 - Filtering and segmentation of 3D angiographic data.pdf:/home/florent/.zotero/data/storage/6JM53J8U/Dufour et al. - 2013 - Filtering and segmentation of 3D angiographic data.pdf:application/pdf}
}

@article{ouzounis_hyperconnected_2011,
	title = {Hyperconnected {Attribute} {Filters} {Based} on k-{Flat} {Zones}},
	volume = {33},
	issn = {0162-8828},
	url = {http://ieeexplore.ieee.org/document/5432219/},
	doi = {10.1109/TPAMI.2010.74},
	abstract = {In this paper, we present a new method for attribute filtering, combining contrast and structural information. Using hyperconnectivity based on k-flat zones, we improve the ability of attribute filters to retain internal details in detected objects. Simultaneously, we improve the suppression of small, unwanted detail in the background. We extend the theory of attribute filters to hyperconnectivity and provide a fast algorithm to implement the new method. The new version is only marginally slower than the standard Max-Tree algorithm for connected attribute filters, and linear in the number of pixels or voxels. It is two orders of magnitude faster than anisotropic diffusion. The method is implemented in the form of a filtering rule suitable for handling both increasing (size) and nonincreasing (shape) attributes. We test this new framework on nonincreasing shape filters on both 2D images from astronomy, document processing, and microscopy, and 3D CT scans, and show increased robustness to noise while maintaining the advantages of previous methods.},
	language = {en},
	number = {2},
	urldate = {2018-12-13},
	journal = {IEEE Transactions on Pattern Analysis and Machine Intelligence},
	author = {Ouzounis, G K and Wilkinson, M H F},
	month = feb,
	year = {2011},
	keywords = {NEXT},
	pages = {224--239},
	file = {Ouzounis and Wilkinson - 2011 - Hyperconnected Attribute Filters Based on k-Flat Z.pdf:/home/florent/.zotero/data/storage/XWQR54FX/Ouzounis and Wilkinson - 2011 - Hyperconnected Attribute Filters Based on k-Flat Z.pdf:application/pdf}
}

@article{passat_interactive_2011,
	title = {Interactive segmentation based on component-trees},
	volume = {44},
	issn = {00313203},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S0031320311001294},
	doi = {10.1016/j.patcog.2011.03.025},
	abstract = {Component-trees associate to a discrete grey-level image a descriptive data structure induced by the inclusion relation between the binary components obtained at successive level-sets. This article presents an original interactive segmentation methodology based on component-trees. It consists of the extraction of a subset of the image component-tree, enabling the generation of a binary object which fits at best (with respect to the grey-level structure of the image) a given binary target selected beforehand in the image. A proof of the algorithmic efficiency of this methodological scheme is proposed. Concrete application examples on magnetic resonance imaging (MRI) data emphasise its actual computational efficiency and its usefulness for interactive segmentation of real images.},
	language = {en},
	number = {10-11},
	urldate = {2018-12-13},
	journal = {Pattern Recognition},
	author = {Passat, Nicolas and Naegel, Benoît and Rousseau, François and Koob, Mériam and Dietemann, Jean-Louis},
	month = oct,
	year = {2011},
	keywords = {NEXT},
	pages = {2539--2554},
	file = {Passat et al. - 2011 - Interactive segmentation based on component-trees.pdf:/home/florent/.zotero/data/storage/JDRM27TF/Passat et al. - 2011 - Interactive segmentation based on component-trees.pdf:application/pdf}
}

@inproceedings{ferdosi_finding_2010,
	address = {Salt Lake City, UT, USA},
	title = {Finding and visualizing relevant subspaces for clustering high-dimensional astronomical data using connected morphological operators},
	isbn = {978-1-4244-9488-0},
	url = {http://ieeexplore.ieee.org/document/5652450/},
	doi = {10.1109/VAST.2010.5652450},
	abstract = {Data sets in astronomy are growing to enormous sizes. Modern astronomical surveys provide not only image data but also catalogues of millions of objects (stars, galaxies), each object with hundreds of associated parameters. Exploration of this very high-dimensional data space poses a huge challenge. Subspace clustering is one among several approaches which have been proposed for this purpose in recent years. However, many clustering algorithms require the user to set a large number of parameters without any guidelines. Some methods also do not provide a concise summary of the datasets, or, if they do, they lack additional important information such as the number of clusters present or the significance of the clusters. In this paper, we propose a method for ranking subspaces for clustering which overcomes many of the above limitations. First we carry out a transformation from parametric space to discrete image space where the data are represented by a grid-based density field. Then we apply so-called connected morphological operators on this density field of astronomical objects that provides visual support for the analysis of the important subspaces. Clusters in subspaces correspond to high-intensity regions in the density image. The importance of a cluster is measured by a new quality criterion based on the dynamics of local maxima of the density. Connected operators are able to extract such regions with an indication of the number of clusters present. The subspaces are visualized during computation of the quality measure, so that the user can interact with the system to improve the results. In the result stage, we use three visualization toolkits linked within a graphical user interface so that the user can perform an in-depth exploration of the ranked subspaces. Evaluation based on synthetic as well as real astronomical datasets demonstrates the power of the new method. We recover various known astronomical relations directly from the data with little or no a priori assumptions. Hence, our method holds good prospects for discovering new relations as well.},
	language = {en},
	urldate = {2018-12-13},
	booktitle = {2010 {IEEE} {Symposium} on {Visual} {Analytics} {Science} and {Technology}},
	publisher = {IEEE},
	author = {Ferdosi, Bilkis J. and Buddelmeijer, Hugo and Trager, Scott and Wilkinson, Michael H. F. and Roerdink, Jos B. T. M.},
	month = oct,
	year = {2010},
	note = {00036},
	keywords = {NEXT, ISMM},
	pages = {35--42},
	file = {Ferdosi et al. - 2010 - Finding and visualizing relevant subspaces for clu.pdf:/home/florent/.zotero/data/storage/CYXV6YJG/Ferdosi et al. - 2010 - Finding and visualizing relevant subspaces for clu.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/7H4EJ5WG/notes.md:text/markdown}
}

@incollection{goos_shape_2001,
	address = {Berlin, Heidelberg},
	title = {Shape {Preserving} {Filament} {Enhancement} {Filtering}},
	volume = {2208},
	isbn = {978-3-540-42697-4 978-3-540-45468-7},
	url = {http://link.springer.com/10.1007/3-540-45468-3_92},
	abstract = {Morphological connected set filters for extraction of filamentous details from medical images are developed. The advantages of these filters are that they are shape preserving and do not amplify noise. Two approaches are compared: (i) multi-scale filtering (ii) single-step shape filtering using connected set (or attribute) thinnings. The latter method highlights all filamentous structure in a single filtering stage, regardless of the scale. The second approach is an order of magnitude faster than the first, filtering a 2563 volume in 41.65 s on a 400 MHz Pentium II.},
	language = {en},
	urldate = {2018-12-13},
	booktitle = {Medical {Image} {Computing} and {Computer}-{Assisted} {Intervention} – {MICCAI} 2001},
	publisher = {Springer Berlin Heidelberg},
	author = {Wilkinson, Michael H. F. and Westenberg, Michel A.},
	editor = {Goos, Gerhard and Hartmanis, Juris and van Leeuwen, Jan and Niessen, Wiro J. and Viergever, Max A.},
	year = {2001},
	doi = {10.1007/3-540-45468-3_92},
	note = {00000 },
	keywords = {NEXT, ISMM},
	pages = {770--777},
	file = {notes.md:/home/florent/.zotero/data/storage/SRRGZ4QV/notes.md:text/markdown;Wilkinson and Westenberg - 2001 - Shape Preserving Filament Enhancement Filtering.pdf:/home/florent/.zotero/data/storage/8HC4F2PU/Wilkinson and Westenberg - 2001 - Shape Preserving Filament Enhancement Filtering.pdf:application/pdf}
}

@inproceedings{guiotte_rasterization_2019,
	title = {Rasterization strategies for airborne {LiDAR} classification using attribute profiles},
	abstract = {This paper evaluates rasterization strategies and the benefit of hierarchical representations, in particular attribute profiles, to classify urban scenes issued from multispectral LiDAR acquisitions. In recent years it has been found that rasterized LiDAR provides a reliable source of information on its own or for fusion with multispectral/hyperspectral imagery. However previous works using attribute profiles on LiDAR rely on elevation data only. Our approach focuses on several LiDAR features rasterized with multilevel description to produce precise land cover maps over urban areas. Our experimental results obtained with LiDAR data from university of Houston indicate good classification results for alternative rasters and even more when multilevel image descriptions are used.},
	author = {Guiotte, Florent and Lefevre, Sebastien and Corpetti, Thomas},
	year = {2019},
	keywords = {ISMM},
	file = {Guiotte et al. - Rasterization strategies for airborne LiDAR classi.pdf:/home/florent/.zotero/data/storage/RCPIJU9B/Guiotte et al. - Rasterization strategies for airborne LiDAR classi.pdf:application/pdf}
}

@inproceedings{meijster_interactive_2002,
	title = {Interactive shape preserving filtering and visualization of volumetric data},
	booktitle = {Proc. 4th {IASTED} {Conf}. {Comp}. {Signal} {Image} {Processing}},
	author = {Meijster, Arnold and Westenberg, Michel A and Wilkinson, Michael HF},
	year = {2002},
	keywords = {NEXT, trees, voxels, ISMM},
	pages = {12--14},
	file = {Meijster et al. - 2002 - Interactive shape preserving filtering and visuali.pdf:/home/florent/.zotero/data/storage/PQF6TL2Q/Meijster et al. - 2002 - Interactive shape preserving filtering and visuali.pdf:application/pdf}
}

@book{kothe_applications_2012,
	address = {Berlin, Heidelberg},
	series = {Lecture {Notes} in {Computer} {Science}},
	title = {Applications of {Discrete} {Geometry} and {Mathematical} {Morphology}},
	volume = {7346},
	isbn = {978-3-642-32312-6 978-3-642-32313-3},
	url = {http://link.springer.com/10.1007/978-3-642-32313-3},
	language = {en},
	urldate = {2018-12-14},
	publisher = {Springer Berlin Heidelberg},
	editor = {Köthe, Ullrich and Montanvert, Annick and Soille, Pierre and Hutchison, David and Kanade, Takeo and Kittler, Josef and Kleinberg, Jon M. and Mattern, Friedemann and Mitchell, John C. and Naor, Moni and Nierstrasz, Oscar and Pandu Rangan, C. and Steffen, Bernhard and Sudan, Madhu and Terzopoulos, Demetri and Tygar, Doug and Vardi, Moshe Y. and Weikum, Gerhard},
	year = {2012},
	doi = {10.1007/978-3-642-32313-3},
	file = {Köthe et al. - 2012 - Applications of Discrete Geometry and Mathematical.pdf:/home/florent/.zotero/data/storage/FV23JAWE/Köthe et al. - 2012 - Applications of Discrete Geometry and Mathematical.pdf:application/pdf}
}

@inproceedings{kiwanuka_radial_2012,
	address = {Berlin, Heidelberg},
	title = {Radial {Moment} {Invariants} for {Attribute} {Filtering} in 3D},
	isbn = {978-3-642-32313-3},
	abstract = {The edge or shape preservation property of connected attribute filters is a desirable feature for biomedical imaging and makes them a suitable tool for problems in which accurate shape analysis is of importance. However, there are still comparatively few attributes for 3D filtering upon which to select features of interest besides, efficient and fast computation of attributes from volumetric data is still a daunting challenge. In particular, whereas a vast literature on 2D moment invariants exist, far fewer 3D moment invariants are available. In this study we introduce a new, radial-moment based roundness attribute in 3D, and provide a memory-efficient algorithm to compute it, even for very high moment orders. It satisfies similarity transformations of translation, rotation and scaling invariance and be generalised to higher order moments without performance degradation. We show the utility of the new attribute in the isolation of kidney stones and other structures in 3D CT and MRI images.},
	booktitle = {Applications of {Discrete} {Geometry} and {Mathematical} {Morphology}},
	publisher = {Springer Berlin Heidelberg},
	author = {Kiwanuka, Fred N. and Wilkinson, Michael H. F.},
	editor = {Köthe, Ullrich and Montanvert, Annick and Soille, Pierre},
	year = {2012},
	note = {00000},
	keywords = {NEXT, ISMM},
	pages = {68--81},
	file = {Kiwanuka and Wilkinson - 2012 - Radial Moment Invariants for Attribute Filtering i.pdf:/home/florent/.zotero/data/storage/9FQX9XJJ/Kiwanuka and Wilkinson - 2012 - Radial Moment Invariants for Attribute Filtering i.pdf:application/pdf}
}

@incollection{goos_sequential_2001,
	address = {Berlin, Heidelberg},
	title = {A {Sequential} 3D {Thinning} {Algorithm} and {Its} {Medical} {Applications}},
	volume = {2082},
	isbn = {978-3-540-42245-7 978-3-540-45729-9},
	url = {http://link.springer.com/10.1007/3-540-45729-1_42},
	abstract = {Skeleton is a frequently applied shape feature to represent the general form of an object. Thinning is an iterative object reduction technique for producing a reasonable approximation to the skeleton in a topology preserving way. This paper describes a sequential 3D thinning algorithm for extracting medial lines of objects in (26, 6) pictures. Our algorithm has been successfully applied in medical image analysis. Three of the emerged applications (analysing airways, blood vessels, and colons) are also presented.},
	language = {en},
	urldate = {2018-12-17},
	booktitle = {Information {Processing} in {Medical} {Imaging}},
	publisher = {Springer Berlin Heidelberg},
	author = {Palágyi, Kálmán and Balogh, Emese and Kuba, Attila and Halmai, Csongor and Erdőhelyi, Balázs and Sorantin, Erich and Hausegger, Klaus},
	editor = {Goos, Gerhard and Hartmanis, Juris and van Leeuwen, Jan and Insana, Michael F. and Leahy, Richard M.},
	year = {2001},
	doi = {10.1007/3-540-45729-1_42},
	keywords = {morphology, voxels, ISMM},
	pages = {409--415},
	file = {Palágyi et al. - 2001 - A Sequential 3D Thinning Algorithm and Its Medical.pdf:/home/florent/.zotero/data/storage/CY8D7I92/Palágyi et al. - 2001 - A Sequential 3D Thinning Algorithm and Its Medical.pdf:application/pdf}
}

@article{aijazi_segmentation_2013,
	title = {Segmentation {Based} {Classification} of 3D {Urban} {Point} {Clouds}: {A} {Super}-{Voxel} {Based} {Approach} with {Evaluation}},
	volume = {5},
	issn = {2072-4292},
	shorttitle = {Segmentation {Based} {Classification} of 3D {Urban} {Point} {Clouds}},
	url = {http://www.mdpi.com/2072-4292/5/4/1624},
	doi = {10.3390/rs5041624},
	abstract = {Segmentation and classification of urban range data into different object classes have several challenges due to certain properties of the data, such as density variation, inconsistencies due to missing data and the large data size that require heavy computation and large memory. A method to classify urban scenes based on a super-voxel segmentation of sparse 3D data obtained from LiDAR sensors is presented. The 3D point cloud is first segmented into voxels, which are then characterized by several attributes transforming them into super-voxels. These are joined together by using a link-chain method rather than the usual region growing algorithm to create objects. These objects are then classified using geometrical models and local descriptors. In order to evaluate the results, a new metric that combines both segmentation and classification results simultaneously is presented. The effects of voxel size and incorporation of RGB color and laser reflectance intensity on the classification results are also discussed. The method is evaluated on standard data sets using different metrics to demonstrate its efficacy.},
	language = {en},
	number = {4},
	urldate = {2018-12-17},
	journal = {Remote Sensing},
	author = {Aijazi, Ahmad and Checchin, Paul and Trassoudaine, Laurent},
	month = mar,
	year = {2013},
	note = {00114},
	keywords = {NEXT, urban, voxels, ISMM},
	pages = {1624--1650},
	file = {Aijazi et al. - 2013 - Segmentation Based Classification of 3D Urban Poin.pdf:/home/florent/.zotero/data/storage/K6VGF33X/Aijazi et al. - 2013 - Segmentation Based Classification of 3D Urban Poin.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/ZCTVXB2U/notes.md:text/markdown}
}

@article{yang_hierarchical_2015,
	title = {Hierarchical extraction of urban objects from mobile laser scanning data},
	volume = {99},
	issn = {09242716},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S092427161400255X},
	doi = {10.1016/j.isprsjprs.2014.10.005},
	abstract = {Point clouds collected in urban scenes contain a huge number of points (e.g., billions), numerous objects with significant size variability, complex and incomplete structures, and variable point densities, raising great challenges for the automated extraction of urban objects in the field of photogrammetry, computer vision, and robotics. This paper addresses these challenges by proposing an automated method to extract urban objects robustly and efficiently. The proposed method generates multi-scale supervoxels from 3D point clouds using the point attributes (e.g., colors, intensities) and spatial distances between points, and then segments the supervoxels rather than individual points by combining graph based segmentation with multiple cues (e.g., principal direction, colors) of the supervoxels. The proposed method defines a set of rules for merging segments into meaningful units according to types of urban objects and forms the semantic knowledge of urban objects for the classification of objects. Finally, the proposed method extracts and classifies urban objects in a hierarchical order ranked by the saliency of the segments. Experiments show that the proposed method is efficient and robust for extracting buildings, streetlamps, trees, telegraph poles, traffic signs, cars, and enclosures from mobile laser scanning (MLS) point clouds, with an overall accuracy of 92.3\%.},
	language = {en},
	urldate = {2018-12-17},
	journal = {ISPRS Journal of Photogrammetry and Remote Sensing},
	author = {Yang, Bisheng and Dong, Zhen and Zhao, Gang and Dai, Wenxia},
	month = jan,
	year = {2015},
	keywords = {NEXT},
	pages = {45--57},
	file = {Yang et al. - 2015 - Hierarchical extraction of urban objects from mobi.pdf:/home/florent/.zotero/data/storage/86AACYF3/Yang et al. - 2015 - Hierarchical extraction of urban objects from mobi.pdf:application/pdf}
}

@article{yang_voxel-based_2018,
	title = {Voxel-{Based} {Extraction} of {Transmission} {Lines} {From} {Airborne} {LiDAR} {Point} {Cloud} {Data}},
	volume = {11},
	issn = {1939-1404, 2151-1535},
	url = {https://ieeexplore.ieee.org/document/8472117/},
	doi = {10.1109/JSTARS.2018.2869542},
	abstract = {The safety of the electricity infrastructure significantly affects both our daily life and industrial activities. Timely and accurate monitoring of the safety of electricity network can prevent dangerous situations effectively. Thus, we, in this paper, develop a voxel-based method for automatically extracting the transmission lines from airborne LiDAR point cloud data. The method proposed in this paper uses three-dimensional (3-D) voxels as primitives and consist of the following steps: First, skeleton structure extraction using Laplacian smoothing; second, feature construction of a 3-D voxel using Latent Dirichlet allocation topic model; and third Markov random field model-based extraction for generating locally continuous and globally optimal results. To evaluate the effectiveness and robustness of the proposed method, experiments were conducted on four different types of power line scenes with flat and complex terrains from helicopter-borne LiDAR point cloud data. Experimental results demonstrate that our proposed method is efficient and robust for automatically detecting both the single conductor and the bundled conductors, with precision, recall, and quality of over 96.78\%, 98.67\%, and 96.66\%, respectively. Moreover, compared with other existing methods, our proposed method provides higher detection correctness rate.},
	language = {en},
	number = {10},
	urldate = {2018-12-17},
	journal = {IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing},
	author = {Yang, Juntao and Kang, Zhizhong},
	month = oct,
	year = {2018},
	keywords = {NEXT},
	pages = {3892--3904},
	file = {Yang and Kang - 2018 - Voxel-Based Extraction of Transmission Lines From .pdf:/home/florent/.zotero/data/storage/Z7WKI6NT/Yang and Kang - 2018 - Voxel-Based Extraction of Transmission Lines From .pdf:application/pdf}
}

@article{salembier_antiextensive_1998,
	title = {Antiextensive connected operators for image and sequence processing},
	volume = {7},
	issn = {10577149},
	url = {http://ieeexplore.ieee.org/document/663500/},
	doi = {10.1109/83.663500},
	abstract = {This paper deals with a class of morphological operators called connected operators. These operators filter the signal by merging its flat zones. As a result, they do not create any new contours and are very attractive for filtering tasks where the contour information has to be preserved. This paper shows that connected operators work implicitly on a structured representation of the image made of flat zones. The max-tree is proposed as a suitable and efficient structure to deal with the processing steps involved in antiextensive connected operators. A formal definition of the various processing steps involved in the operator is proposed and, as a result, several lines of generalization are developed. First, the notion of connectivity and its definition are analyzed. Several modifications of the traditional approach are presented. They lead to connected operators that are able to deal with texture. They also allow the definition of connected operators with less leakage than the classical ones. Second, a set of simplification criteria are proposed and discussed. They lead to simplicity-, entropy-, and motion-oriented operators. The problem of using a nonincreasing criterion is analyzed. Its solution is formulated as an optimization problem that can be very efficiently solved by a Viterbi algorithm. Finally, several implementation issues are discussed showing that these operators can be very efficiently implemented.},
	language = {en},
	number = {4},
	urldate = {2018-12-17},
	journal = {IEEE Transactions on Image Processing},
	author = {Salembier, P. and Oliveras, A. and Garrido, L.},
	month = apr,
	year = {1998},
	keywords = {NEXT, morphology, trees, ISMM},
	pages = {555--570},
	file = {Salembier et al. - 1998 - Antiextensive connected operators for image and se.pdf:/home/florent/.zotero/data/storage/HYJBL44E/Salembier et al. - 1998 - Antiextensive connected operators for image and se.pdf:application/pdf}
}

@article{salembier_binary_2000,
	title = {Binary partition tree as an efficient representation for image processing, segmentation, and information retrieval},
	volume = {9},
	issn = {10577149},
	url = {http://ieeexplore.ieee.org/document/841934/},
	doi = {10.1109/83.841934},
	abstract = {This paper discusses the interest of Binary Partition Trees as a region-oriented image representation. Binary Partition Trees concentrate in a compact and structured representation a set of meaningful regions that can be extracted from an image. They offer a multi-scale representation of the image and define a translation invariant 2-connectivity rule among regions. As shown in the paper, this representation can be used for a large number of processing goals such as filtering, segmentation, information retrieval and visual browsing. Furthermore, the processing of the tree representation leads to very efficient algorithms. Finally, for some applications, it may be interesting to compute the Binary Partition Tree once and to store it for subsequent use for various applications. In this context, the last section of the paper will show that the amount of bits necessary to encode a Binary Partition Tree remains moderate.},
	language = {en},
	number = {4},
	urldate = {2018-12-17},
	journal = {IEEE Transactions on Image Processing},
	author = {Salembier, P. and Garrido, L.},
	month = apr,
	year = {2000},
	pages = {561--576},
	file = {Salembier and Garrido - 2000 - Binary partition tree as an efficient representati.pdf:/home/florent/.zotero/data/storage/A4BFYVJ5/Salembier and Garrido - 2000 - Binary partition tree as an efficient representati.pdf:application/pdf}
}

@article{souza_hands-morphological_nodate,
	title = {Hands-on morphological processing using the max-tree},
	language = {en},
	author = {Souza, Roberto and Tavares, Luıs and Rittner, Letıcia and Lotufo, Roberto},
	pages = {9},
	file = {Souza et al. - Hands-on morphological processing using the max-tr.pdf:/home/florent/.zotero/data/storage/AYSPU45R/Souza et al. - Hands-on morphological processing using the max-tr.pdf:application/pdf}
}

@article{vayer_fused_2018,
	title = {Fused {Gromov}-{Wasserstein} distance for structured objects: theoretical foundations and mathematical properties},
	shorttitle = {Fused {Gromov}-{Wasserstein} distance for structured objects},
	url = {http://arxiv.org/abs/1811.02834},
	abstract = {Optimal transport theory has recently found many applications in machine learning thanks to its capacity for comparing various machine learning objects considered as distributions. The Kantorovitch formulation, leading to the Wasserstein distance, focuses on the features of the elements of the objects but treat them independently, whereas the Gromov-Wasserstein distance focuses only on the relations between the elements, depicting the structure of the object, yet discarding its features. In this paper we propose to extend these distances in order to encode simultaneously both the feature and structure informations, resulting in the Fused Gromov-Wasserstein distance. We develop the mathematical framework for this novel distance, prove its metric and interpolation properties and provide a concentration result for the convergence of finite samples. We also illustrate and interpret its use in various contexts where structured objects are involved.},
	language = {en},
	urldate = {2018-12-20},
	journal = {arXiv:1811.02834 [cs, stat]},
	author = {Vayer, Titouan and Chapel, Laetita and Flamary, Rémi and Tavenard, Romain and Courty, Nicolas},
	month = nov,
	year = {2018},
	note = {00000 
arXiv: 1811.02834},
	keywords = {NEXT},
	file = {Vayer et al. - 2018 - Fused Gromov-Wasserstein distance for structured o.pdf:/home/florent/.zotero/data/storage/UH3Z72IM/Vayer et al. - 2018 - Fused Gromov-Wasserstein distance for structured o.pdf:application/pdf}
}

@article{morales_semantic_nodate,
	title = {Semantic analysis of 3D point clouds from urban environments: ground, facades, urban objects and accessibility},
	language = {en},
	author = {Morales, Andrés Felipe Serna},
	keywords = {NEXT},
	pages = {175},
	file = {Morales - Semantic analysis of 3D point clouds from urban en.pdf:/home/florent/.zotero/data/storage/LW985EQH/Morales - Semantic analysis of 3D point clouds from urban en.pdf:application/pdf}
}

@book{talbot_mathematical_2002,
	address = {Collingwood, Victoria [Australia]},
	title = {Mathematical morphology: proceedings of the {VIth} {International} {Symposium}--{ISMM} 2002: {Sydney}, 3-5 {April}, 2002},
	isbn = {978-0-643-06804-9},
	shorttitle = {Mathematical morphology},
	language = {en},
	publisher = {CSIRO Pub},
	editor = {Talbot, Hugues and Beare, Richard},
	year = {2002},
	note = {OCLC: ocm51244501},
	keywords = {Congresses, Digital filters (Mathematics), Image processing, Mathematics, Signal processing}
}

@inproceedings{urbach_shape-only_2002,
	title = {Shape-{Only} {Granulometries} and {Grey}-{Scale} {Shape} {Filters}},
	booktitle = {Proc. {Int}. {Symp}. {Math}. {Morphology} ({ISMM}) 2002},
	author = {Urbach, Erik and Wilkinson, Michael},
	year = {2002},
	keywords = {trees, ISMM, max-tree},
	pages = {305--314},
	file = {Urbach and Wilkinson - 2002 - Shape-Only Granulometries and Grey-Scale Shape Fil.pdf:/home/florent/.zotero/data/storage/DYGGPF24/Urbach and Wilkinson - 2002 - Shape-Only Granulometries and Grey-Scale Shape Fil.pdf:application/pdf}
}

@article{peternell_minkowski_2007,
	title = {Minkowski sum boundary surfaces of 3D-objects},
	volume = {69},
	issn = {15240703},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S1524070307000021},
	doi = {10.1016/j.gmod.2007.01.001},
	abstract = {Given two objects A and B with piecewise smooth boundary we discuss the computation of the boundary C of the Minkowski sum A + B. This boundary surface C is part of the envelope when B is moved by translations defined by vectors a 2 A, or vice versa. We present an efficient algorithm working for dense point clouds or for triangular meshes. Besides this the global self-intersections of the boundary C are detected and resolved. Additionally we point to some relations between Minkowski sums and kinematics, and compute local quadratic approximations of the envelope.},
	language = {en},
	number = {3-4},
	urldate = {2019-01-16},
	journal = {Graphical Models},
	author = {Peternell, Martin and Steiner, Tibor},
	month = may,
	year = {2007},
	keywords = {NEXT, ISMM},
	pages = {180--190},
	file = {Peternell and Steiner - 2007 - Minkowski sum boundary surfaces of 3D-objects.pdf:/home/florent/.zotero/data/storage/77SYNTU9/Peternell and Steiner - 2007 - Minkowski sum boundary surfaces of 3D-objects.pdf:application/pdf}
}

@inproceedings{nelaturi_configuration_2009,
	address = {San Francisco, California},
	title = {Configuration products in geometric modeling},
	isbn = {978-1-60558-711-0},
	url = {http://portal.acm.org/citation.cfm?doid=1629255.1629286},
	doi = {10.1145/1629255.1629286},
	abstract = {The six-dimensional space SE(3) is traditionally associated with the space of configurations of a rigid solid (a subset of Euclidean three-dimensional space E3). But a solid can be also considered to be a set of configurations, and therefore a subset of SE(3). This observation removes the artificial distinction between shapes and their configurations, and allows formulation and solution of a large class of problems in mechanical design and manufacturing. In particular, the configuration product of two subsets of configuration space is the set of all configurations obtained when one of the sets is transformed by all configurations of the other. The usual definitions of various sweeps, Minkowski sum, and other motion related operations are then realized as projections of the configuration product into E3 . Similarly, the dual operation of configuration quotient subsumes the more common operations of unsweep and Minkowski difference. We identify the formal properties of these operations that are instrumental in formulating and solving both direct and inverse problems in computer aided design and manufacturing. Finally, we show that all required computations may be implemented using a fast parallel sampling method on a GPU.},
	language = {en},
	urldate = {2019-01-16},
	booktitle = {2009 {SIAM}/{ACM} {Joint} {Conference} on {Geometric} and {Physical} {Modeling} on - {SPM} '09},
	publisher = {ACM Press},
	author = {Nelaturi, Saigopal and Shapiro, Vadim},
	year = {2009},
	keywords = {NEXT},
	pages = {247},
	file = {Nelaturi and Shapiro - 2009 - Configuration products in geometric modeling.pdf:/home/florent/.zotero/data/storage/WHZZBGIC/Nelaturi and Shapiro - 2009 - Configuration products in geometric modeling.pdf:application/pdf}
}

@inproceedings{lien_point-based_2007,
	address = {Maui, HI, USA},
	title = {Point-{Based} {Minkowski} {Sum} {Boundary}},
	isbn = {978-0-7695-3009-3},
	url = {http://ieeexplore.ieee.org/document/4392736/},
	doi = {10.1109/PG.2007.49},
	language = {en},
	urldate = {2019-01-16},
	booktitle = {15th {Pacific} {Conference} on {Computer} {Graphics} and {Applications} ({PG}'07)},
	publisher = {IEEE},
	author = {Lien, Jyh-Ming},
	month = oct,
	year = {2007},
	note = {00000},
	keywords = {NEXT},
	pages = {261--270},
	file = {Lien - 2007 - Point-Based Minkowski Sum Boundary.pdf:/home/florent/.zotero/data/storage/9KR7V6EN/Lien - 2007 - Point-Based Minkowski Sum Boundary.pdf:application/pdf}
}

@inproceedings{alexa_point_2001,
	address = {San Diego, CA, USA},
	title = {Point set surfaces},
	isbn = {978-0-7803-7200-9},
	url = {http://ieeexplore.ieee.org/document/964489/},
	doi = {10.1109/VISUAL.2001.964489},
	abstract = {We advocate the use of point sets to represent shapes. We provide a definition of a smooth manifold surface from a set of points close to the original surface. The definition is based on local maps from differential geometry, which are approximated by the method of moving least squares (MLS). We present tools to increase or decrease the density of the points, thus, allowing an adjustment of the spacing among the points to control the fidelity of the representation.},
	language = {en},
	urldate = {2019-01-19},
	booktitle = {Proceedings {Visualization}, 2001. {VIS} '01.},
	publisher = {IEEE},
	author = {Alexa, M. and Behr, J. and Cohen-Or, D. and Fleishman, S. and Levin, D. and Silva, C.T.},
	year = {2001},
	keywords = {morphology, point cloud},
	pages = {21--537},
	file = {Alexa et al. - 2001 - Point set surfaces.pdf:/home/florent/.zotero/data/storage/R9LUNT7C/Alexa et al. - 2001 - Point set surfaces.pdf:application/pdf}
}

@article{audebert_classification_2018,
	title = {Classification de données massives de télédétection},
	language = {fr},
	author = {Audebert, Nicolas},
	month = dec,
	year = {2018},
	pages = {221},
	file = {Audebert - 2018 - Classification de données massives de télédétectio.pdf:/home/florent/.zotero/data/storage/RXRIKVB9/Audebert - 2018 - Classification de données massives de télédétectio.pdf:application/pdf}
}

@phdthesis{boulch_reconstruction_2014,
	title = {Reconstruction automatique de maquettes numériques},
	author = {Boulch, Alexandre},
	month = dec,
	year = {2014},
	file = {Boulch - 2014 - Reconstruction automatique de maquettes numériques.pdf:/home/florent/.zotero/data/storage/ZH7RY9ZK/Boulch - 2014 - Reconstruction automatique de maquettes numériques.pdf:application/pdf}
}

@inproceedings{guiotte_attribute_2019,
	title = {Attribute filtering of urban point clouds using max-tree on voxel data},
	author = {Guiotte, Florent and Lefèvre, Sébastien and Corpetti, Thomas},
	year = {2019},
	file = {Guiotte et al. - 2019 - Attribute filtering of urban point clouds using ma.pdf:/home/florent/.zotero/data/storage/M92S96E2/Guiotte et al. - 2019 - Attribute filtering of urban point clouds using ma.pdf:application/pdf}
}

@inproceedings{guiotte_voxel-based_2019,
	title = {Voxel-based attribute profiles on {LiDAR} data for land conver mapping},
	author = {Guiotte, Florent and Lefèvre, Sébastien and Corpetti, Thomas},
	year = {2019},
	file = {Guiotte et al. - 2019 - Voxel-based attribute profiles on LiDAR data for l.pdf:/home/florent/.zotero/data/storage/65K47AUD/Guiotte et al. - 2019 - Voxel-based attribute profiles on LiDAR data for l.pdf:application/pdf}
}

@article{trier_using_2018,
	title = {Using deep neural networks on airborne laser scanning data: {Results} from a case study of semi-automatic mapping of archaeological topography on {Arran}, {Scotland}},
	issn = {10752196},
	shorttitle = {Using deep neural networks on airborne laser scanning data},
	url = {http://doi.wiley.com/10.1002/arp.1731},
	doi = {10.1002/arp.1731},
	abstract = {This article presents results of a case study within a project that seeks to develop heavily automated analysis of digital topographic data to extract archaeological information and to expedite large area mapping. Drawing on developments in computer vision and machine learning, this has the potential to fundamentally recast the capacity of archaeological prospection to cover large areas and deal with mass data, breaking a dependency on human resource. Without such developments, the potential of the vast amount of archaeological information embedded in large topographic and image‐based datasets cannot be realized. The purpose of the case study reported on here is to assess existing developments in a Norwegian study against digital topographic data for the island of Arran, Scotland, examining the transferability of the approach and providing a proof of concept in a Scottish context. For Arran, three monument classes were assessed – prehistoric roundhouses, shieling huts of medieval or post‐medieval date, and small clearance cairns. These present different challenges to detection, with preliminary results ranging from a manageable mix of false positives and true identifications to the chaotic. The influence of variable morphology and the occurrence of other, largely natural, objects of confusion in the landscape is discussed, highlighting the potential improvements in automated detection routines offered by adding anthropogenic and natural false positives to additional confusion classes.},
	language = {en},
	urldate = {2019-01-30},
	journal = {Archaeological Prospection},
	author = {Trier, Øivind Due and Cowley, David C. and Waldeland, Anders Ueland},
	month = nov,
	year = {2018},
	keywords = {lidar, deep learning, 2D},
	file = {notes.md:/home/florent/.zotero/data/storage/G5RSB5PK/notes.md:text/markdown;Trier et al. - 2018 - Using deep neural networks on airborne laser scann.pdf:/home/florent/.zotero/data/storage/Y7F3CLLK/Trier et al. - 2018 - Using deep neural networks on airborne laser scann.pdf:application/pdf}
}

@article{huo_supervised_2018,
	title = {Supervised spatial classification of multispectral {LiDAR} data in urban areas},
	volume = {13},
	issn = {1932-6203},
	url = {http://dx.plos.org/10.1371/journal.pone.0206185},
	doi = {10.1371/journal.pone.0206185},
	language = {en},
	number = {10},
	urldate = {2019-02-20},
	journal = {PLOS ONE},
	author = {Huo, Lian-Zhi and Silva, Carlos Alberto and Klauberg, Carine and Mohan, Midhun and Zhao, Li-Jun and Tang, Ping and Hudak, Andrew Thomas},
	editor = {Shah, Tayyab Ikram},
	month = oct,
	year = {2018},
	note = {00000},
	keywords = {NEXT, classification, lidar, multispectral},
	pages = {e0206185},
	file = {Huo et al. - 2018 - Supervised spatial classification of multispectral.pdf:/home/florent/.zotero/data/storage/2PU9LAXP/Huo et al. - 2018 - Supervised spatial classification of multispectral.pdf:application/pdf}
}

@article{ezuz_gwcnn:_2017,
	title = {{GWCNN}: {A} {Metric} {Alignment} {Layer} for {Deep} {Shape} {Analysis}},
	volume = {36},
	issn = {01677055},
	shorttitle = {{GWCNN}},
	url = {http://doi.wiley.com/10.1111/cgf.13244},
	doi = {10.1111/cgf.13244},
	abstract = {Deep neural networks provide a promising tool for incorporating semantic information in geometry processing applications. Unlike image and video processing, however, geometry processing requires handling unstructured geometric data, and thus data representation becomes an important challenge in this framework. Existing approaches tackle this challenge by converting point clouds, meshes, or polygon soups into regular representations using, e.g., multi-view images, volumetric grids or planar parameterizations. In each of these cases, geometric data representation is treated as a fixed pre-process that is largely disconnected from the machine learning tool. In contrast, we propose to optimize for the geometric representation during the network learning process using a novel metric alignment layer. Our approach maps unstructured geometric data to a regular domain by minimizing the metric distortion of the map using the regularized Gromov–Wasserstein objective. This objective is parameterized by the metric of the target domain and is differentiable; thus, it can be easily incorporated into a deep network framework. Furthermore, the objective aims to align the metrics of the input and output domains, promoting consistent output for similar shapes. We show the effectiveness of our layer within a deep network trained for shape classification, demonstrating state-of-the-art performance for nonrigid shapes.},
	language = {en},
	number = {5},
	urldate = {2019-03-01},
	journal = {Computer Graphics Forum},
	author = {Ezuz, Danielle and Solomon, Justin and Kim, Vladimir G. and Ben-Chen, Mirela},
	month = aug,
	year = {2017},
	note = {00011},
	keywords = {NEXT, classification, voxels, transport},
	pages = {49--57},
	file = {Ezuz et al. - 2017 - GWCNN A Metric Alignment Layer for Deep Shape Ana.pdf:/home/florent/.zotero/data/storage/UECNDSEM/Ezuz et al. - 2017 - GWCNN A Metric Alignment Layer for Deep Shape Ana.pdf:application/pdf}
}

@article{thomas_semantic_2018,
	title = {Semantic {Classification} of 3D {Point} {Clouds} with {Multiscale} {Spherical} {Neighborhoods}},
	url = {http://arxiv.org/abs/1808.00495},
	abstract = {This paper introduces a new definition of multiscale neighborhoods in 3D point clouds. This definition, based on spherical neighborhoods and proportional subsampling, allows the computation of features with a consistent geometrical meaning, which is not the case when using k-nearest neighbors. With an appropriate learning strategy, the proposed features can be used in a random forest to classify 3D points. In this semantic classification task, we show that our multiscale features outperform state-of-the-art features using the same experimental conditions. Furthermore, their classification power competes with more elaborate classification approaches including Deep Learning methods.},
	language = {en},
	urldate = {2019-03-25},
	journal = {arXiv:1808.00495 [cs]},
	author = {Thomas, Hugues and Deschaud, Jean-Emmanuel and Marcotegui, Beatriz and Goulette, François and Gall, Yann Le},
	month = aug,
	year = {2018},
	note = {00000 
arXiv: 1808.00495},
	keywords = {NEXT, point cloud, classification, deep learning},
	file = {Thomas et al. - 2018 - Semantic Classification of 3D Point Clouds with Mu.pdf:/home/florent/.zotero/data/storage/GN84EWUB/Thomas et al. - 2018 - Semantic Classification of 3D Point Clouds with Mu.pdf:application/pdf}
}

@article{pham_feature_2018,
	title = {Feature {Profiles} from {Attribute} {Filtering} for {Classification} of {Remote} {Sensing} {Images}},
	volume = {11},
	issn = {1939-1404, 2151-1535},
	url = {http://ieeexplore.ieee.org/document/8118175/},
	doi = {10.1109/JSTARS.2017.2773367},
	abstract = {This paper proposes a novel extension of morphological attribute profiles (APs) for classification of remote sensing data. In standard AP-based approaches, an input image is characterized by a set of filtered images achieved from the sequential application of attribute filters based on the image tree representation. Hence, only pixel values (i.e. gray levels) are employed to form the output profiles. In this paper, during the attribute filtering process, instead of outputting the gray levels, we propose to extract both statistical and geometrical features from the connected components (w.r.t. tree nodes) to build the so-called feature profiles (FPs). These features are expected to better characterize the object or region encoded by each connected component. They are then exploited to classify remote sensing images. To evaluate the effectiveness of the proposed approach, supervised classification using the random forest classifier is conducted on the panchromatic Reykjavik image as well as the hyperspectral Pavia University data. Experimental results show the FPs provide a competitive performance compared against standard APs and thus constitute a promising alternative. Index Terms—Attribute profiles (APs), feature profiles (FPs), random forest, remote sensing imagery, supervised classification.},
	language = {en},
	number = {1},
	urldate = {2019-03-25},
	journal = {IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing},
	author = {Pham, Minh-Tan and Aptoula, Erchan and Lefevre, Sebastien},
	month = jan,
	year = {2018},
	keywords = {NEXT, AP},
	pages = {249--256},
	file = {Pham et al. - 2018 - Feature Profiles from Attribute Filtering for Clas.pdf:/home/florent/.zotero/data/storage/3FCRJ6IA/Pham et al. - 2018 - Feature Profiles from Attribute Filtering for Clas.pdf:application/pdf}
}

@article{breen_attribute_1996,
	title = {Attribute {Openings}, {Thinnings}, and {Granulometries}},
	volume = {64},
	issn = {10773142},
	url = {http://linkinghub.elsevier.com/retrieve/pii/S1077314296900661},
	doi = {10.1006/cviu.1996.0066},
	language = {en},
	number = {3},
	urldate = {2019-04-04},
	journal = {Computer Vision and Image Understanding},
	author = {Breen, Edmond J. and Jones, Ronald},
	month = nov,
	year = {1996},
	note = {00446},
	keywords = {NEXT, hierarchical representation, ORASIS},
	pages = {377--389},
	file = {Breen and Jones - 1996 - Attribute Openings, Thinnings, and Granulometries.pdf:/home/florent/.zotero/data/storage/KYGVSMIR/Breen and Jones - 1996 - Attribute Openings, Thinnings, and Granulometries.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/N6H6XC3L/notes.md:text/markdown}
}

@article{mongus_computationally_2014,
	title = {Computationally {Efficient} {Method} for the {Generation} of a {Digital} {Terrain} {Model} {From} {Airborne} {LiDAR} {Data} {Using} {Connected} {Operators}},
	volume = {7},
	issn = {1939-1404, 2151-1535},
	url = {http://ieeexplore.ieee.org/document/6521401/},
	doi = {10.1109/JSTARS.2013.2262996},
	abstract = {This paper proposes a new mapping schema, named mapping, for filtering nonground objects from LiDAR data, and the generation of a digital terrain model. By extending the CSL model, mapping extracts the most contrasted connected-components from top-hat scale-space and attributes them for an adaptive multicriterion filter definition. Areas of the most contrasted connected-components and the standard deviations of contained points’ levels are considered for this purpose. Computational efficiency is achieved by arranging the input LiDAR data into a grid, represented by a Max-Tree. Since a constant number of passes over the grid is required, the time complexity of the proposed method is linear according to the number of grid-cells. As confirmed by the experiments, the average CPU execution time decreases by nearly 98\%, while the average accuracy improves by up to 10\% in comparison with the related method.},
	language = {en},
	number = {1},
	urldate = {2019-04-04},
	journal = {IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing},
	author = {Mongus, Domen and Zalik, Borut},
	month = jan,
	year = {2014},
	keywords = {NEXT, lidar, hierarchical representation, ORASIS, dem},
	pages = {340--351},
	file = {Mongus and Zalik - 2014 - Computationally Efficient Method for the Generatio.pdf:/home/florent/.zotero/data/storage/KQ8NR5JF/Mongus and Zalik - 2014 - Computationally Efficient Method for the Generatio.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/L6GFQCGQ/notes.md:text/markdown}
}

@article{lomenie_point_2012,
	title = {Point set morphological filtering and semantic spatial configuration modeling: {Application} to microscopic image and bio-structure analysis},
	volume = {45},
	issn = {00313203},
	shorttitle = {Point set morphological filtering and semantic spatial configuration modeling},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S003132031200060X},
	doi = {10.1016/j.patcog.2012.01.021},
	abstract = {High-level spatial relation and configuration modeling issues are gaining momentum in the image analysis and pattern recognition fields. In particular, it is deemed important whenever one needs to mine high-content images or large scale image databases in a more expressive way than a purely statistically one. Continuing previous efforts to incorporate structural analysis by developing specific efficient morphological tools performing on mesh representations like Delaunay triangulations, we propose to formalize spatial relation modeling techniques dedicated to unorganized point sets. We provide an original mesh lattice framework which is more convenient for structural representations of large image data by means of interest point sets and their morphological analysis. The set of designed numerical operators is based on a specific dilation operator that makes it possible to handle concepts like ‘‘between’’ or ‘‘left of’’ over sparse representations of image data such as graphs. Based on this new theoretical framework for reasoning about images, we are able to process high-level queries over large histopathological images, knowing that digitized histopathology is a new challenge in the field of bioimaging due to the high-content nature and large size of these images.},
	language = {en},
	number = {8},
	urldate = {2019-04-04},
	journal = {Pattern Recognition},
	author = {Loménie, Nicolas and Racoceanu, Daniel},
	month = aug,
	year = {2012},
	note = {00000},
	keywords = {NEXT, hierarchical representation, ORASIS},
	pages = {2894--2911},
	file = {Loménie and Racoceanu - 2012 - Point set morphological filtering and semantic spa.pdf:/home/florent/.zotero/data/storage/2LZHZKEN/Loménie and Racoceanu - 2012 - Point set morphological filtering and semantic spa.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/ZRUBICBM/notes.md:text/markdown}
}

@article{fournier_automatic_2010,
	title = {Automatic {Grid} {Resolution} and {Efficient} {Triangulation} of {Implicit} {Vector} {Field}},
	volume = {3},
	issn = {1936-4954},
	url = {http://epubs.siam.org/doi/10.1137/090772149},
	doi = {10.1137/090772149},
	abstract = {In this paper we propose an automatic grid resolution to compute the vector field distance transform of triangle meshes. This implicit representation is useful in performing many mesh processing operations such as mesh fusion and mesh filtering in object surface reconstruction. Setting an appropriate grid resolution is mandatory for obtaining good quality results from these operations. Grid resolution is usually set experimentally by operators until satisfying results are obtained. An automated process is demonstrated that improves this parameter setting step. We also introduce a new marching cube triangulation adaptation to the vector field distance transform. Unlike the previous adaptation, our algorithm allows vertex interpolation on cube faces instead of only on cube edges. We compare our new design to the previous one using a reliable error metric evaluation. Results show our triangulation outperforms the previous one in terms of mesh quality and runtime performances. The new algorithm takes advantage of the more accurate vector field definition to better approximate the implicit isosurface.},
	language = {en},
	number = {3},
	urldate = {2019-04-04},
	journal = {SIAM Journal on Imaging Sciences},
	author = {Fournier, Marc},
	month = jan,
	year = {2010},
	note = {00003},
	keywords = {NEXT, voxels, ORASIS, mesh},
	pages = {564--577},
	file = {Fournier - 2010 - Automatic Grid Resolution and Efficient Triangulat.pdf:/home/florent/.zotero/data/storage/MLDYWWVW/Fournier - 2010 - Automatic Grid Resolution and Efficient Triangulat.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/HTNIHWS6/notes.md:text/markdown}
}

@article{fournier_mesh_2011,
	title = {Mesh filtering algorithm using an adaptive 3D convolution kernel applied to a volume-based vector distance field},
	volume = {35},
	issn = {00978493},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S0097849311000586},
	doi = {10.1016/j.cag.2011.03.019},
	abstract = {This paper addresses the problem of feature preserving mesh filtering, which occurs in surface reconstruction of scanned objects, which include acquisition noise to be removed without altering sharp edges. We propose a method based on a vector field distance transform of the mesh to process. It is a volume-based implicit surface modeling, which provides an alternative representation of meshes. We use an adaptive 3D convolution kernel applied to the voxels of the distance transform model. Weights of the kernel elements are determined according to the angle between the vectors of the implicit field. We also propose a new adaptation of the Marching Cubes algorithm in order to extract the isosurface from the vector implicit field after the filtering process. We compare our method to the previous one introduced using the vector field representation and to other feature preserving adaptive filtering algorithms. According to error metric evaluations, we show that our new design provides high quality filtering results while better preserving geometric features.},
	language = {en},
	number = {3},
	urldate = {2019-04-04},
	journal = {Computers \& Graphics},
	author = {Fournier, Marc},
	month = jun,
	year = {2011},
	note = {00006},
	keywords = {NEXT, voxels, ORASIS, mesh},
	pages = {668--676},
	file = {Fournier - 2011 - Mesh filtering algorithm using an adaptive 3D conv.pdf:/home/florent/.zotero/data/storage/K3R3FG3V/Fournier - 2011 - Mesh filtering algorithm using an adaptive 3D conv.pdf:application/pdf;notes.md:/home/florent/.zotero/data/storage/3P3TZGQA/notes.md:text/markdown}
}

@inproceedings{pesaresi_new_2012,
	address = {Baltimore, Maryland},
	title = {A new compact representation of morphological profiles: report on first massive {VHR} image processing at the {JRC}},
	shorttitle = {A new compact representation of morphological profiles},
	url = {http://proceedings.spiedigitallibrary.org/proceeding.aspx?articleid=1354593},
	doi = {10.1117/12.920291},
	abstract = {A new compact representation of differential morphological profile (DMP) vector fields is presented. It is referred to as the CSL model and is conceived to radically reduce the dimensionality of the DMP descriptors. The model maps three characteristic parameters, namely scale, saliency and level, into the RGB space through a HSV transform. The result is a a medium abstraction semantic layer used for visual exploration, image information mining and pattern classification. Fused with the PANTEX built-up presence index, the CSL model converges to an approximate building footprint representation layer in which color represents building class labels. This process is demonstrated on the first high resolution (HR) global human settlement layer (GHSL) computed from multi-modal HR and VHR satellite images. Results of the first massive processing exercise involving several thousands of scenes around the globe are reported along with validation figures.},
	language = {en},
	urldate = {2019-04-08},
	author = {Pesaresi, Martino and Ouzounis, Georgios K. and Gueguen, Lionel},
	editor = {Shen, Sylvia S. and Lewis, Paul E.},
	month = may,
	year = {2012},
	note = {00022},
	keywords = {NEXT, attribute profiles, hierarchical representation},
	pages = {839025--839025--6},
	file = {Pesaresi et al. - 2012 - A new compact representation of morphological prof.pdf:/home/florent/.zotero/data/storage/65GQJBVH/Pesaresi et al. - 2012 - A new compact representation of morphological prof.pdf:application/pdf}
}

@article{chaplot_accuracy_2006,
	title = {Accuracy of interpolation techniques for the derivation of digital elevation models in relation to landform types and data density},
	volume = {77},
	issn = {0169555X},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S0169555X06000079},
	doi = {10.1016/j.geomorph.2005.12.010},
	language = {en},
	number = {1-2},
	urldate = {2019-04-08},
	journal = {Geomorphology},
	author = {Chaplot, Vincent and Darboux, Frédéric and Bourennane, Hocine and Leguédois, Sophie and Silvera, Norbert and Phachomphon, Konngkeo},
	month = jul,
	year = {2006},
	note = {00368},
	keywords = {interpolation, dem},
	pages = {126--141},
	file = {Chaplot et al. - 2006 - Accuracy of interpolation techniques for the deriv.pdf:/home/florent/.zotero/data/storage/ZPIPWLNV/Chaplot et al. - 2006 - Accuracy of interpolation techniques for the deriv.pdf:application/pdf}
}

@article{mongus_efficient_2015,
	title = {An efficient approach to 3D single tree-crown delineation in {LiDAR} data},
	volume = {108},
	issn = {09242716},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S0924271615001951},
	doi = {10.1016/j.isprsjprs.2015.08.004},
	abstract = {This paper proposes a new method for 3D delineation of single tree-crowns in LiDAR data by exploiting the complementaries of treetop and tree trunk detections. A unified mathematical framework is provided based on the graph theory, allowing for all the segmentations to be achieved using marker-controlled watersheds. Treetops are defined by detecting concave neighbourhoods within the canopy height model using locally fitted surfaces. These serve as markers for watershed segmentation of the canopy layer where possible oversegmentation is reduced by merging the regions based on their heights, areas, and shapes. Additional tree crowns are delineated from mid- and under-storey layers based on tree trunk detection. A new approach for estimating the verticalities of the points’ distributions is proposed for this purpose. The watershed segmentation is then applied on a density function within the voxel space, while boundaries of delineated trees from the canopy layer are used to prevent the overspreading of regions. The experiments show an approximately 6\% increase in the efficiency of the proposed treetop definition based on locally fitted surfaces in comparison with the traditionally used local maxima of the smoothed canopy height model. In addition, 4\% increase in the efficiency is achieved by the proposed tree trunk detection. Although the tree trunk detection alone is dependent on the data density, supplementing it with the treetop detection the proposed approach is efficient even when dealing with low density point-clouds.},
	language = {en},
	urldate = {2019-04-08},
	journal = {ISPRS Journal of Photogrammetry and Remote Sensing},
	author = {Mongus, Domen and Žalik, Borut},
	month = oct,
	year = {2015},
	note = {00037},
	pages = {219--233},
	file = {Mongus and Žalik - 2015 - An efficient approach to 3D single tree-crown deli.pdf:/home/florent/.zotero/data/storage/92L7RAR8/Mongus and Žalik - 2015 - An efficient approach to 3D single tree-crown deli.pdf:application/pdf}
}

@article{horvat_context-dependent_2016,
	title = {Context-dependent detection of non-linearly distributed points for vegetation classification in airborne {LiDAR}},
	volume = {116},
	issn = {09242716},
	url = {https://linkinghub.elsevier.com/retrieve/pii/S092427161600054X},
	doi = {10.1016/j.isprsjprs.2016.02.011},
	abstract = {This paper proposes a new method for the detection of vegetation in LiDAR data. As vegetation points are characterised by non-linear distributions, they are efficiently recognised based-on large errors obtained when applying the local fitting of planar surfaces. In addition, three contextual filters are introduced capable of dealing with those exceptions that do not conform with previous interpretations. Namely, they are designed for detecting overgrowing vegetation, small objects attached to the planar surfaces (such as balconies, chimneys, and noise within the buildings) and small objects that do not belong to vegetation (vehicles, statues, fences). During the validation, the proposed method achieved over 97\% correctness as well as completeness of vegetation recognition in rural areas while its average accuracy in urban settings was 90.7\% in terms of F1-scores. The method uses only three input parameters and allows for efficient compensation between completeness and correctness, without significantly affecting the F1-score. Sensitivity analysis of the method also confirmed the robustness against a sub-optimal definition of the input parameters.},
	language = {en},
	urldate = {2019-04-08},
	journal = {ISPRS Journal of Photogrammetry and Remote Sensing},
	author = {Horvat, Denis and Žalik, Borut and Mongus, Domen},
	month = jun,
	year = {2016},
	note = {00014},
	pages = {1--14},
	file = {Horvat et al. - 2016 - Context-dependent detection of non-linearly distri.pdf:/home/florent/.zotero/data/storage/UPGU9H49/Horvat et al. - 2016 - Context-dependent detection of non-linearly distri.pdf:application/pdf}
}

@article{najman_building_2006,
	title = {Building the {Component} {Tree} in {Quasi}-{Linear} {Time}},
	volume = {15},
	issn = {1057-7149},
	url = {http://ieeexplore.ieee.org/document/1709995/},
	doi = {10.1109/TIP.2006.877518},
	abstract = {The level sets of a map are the sets of points with level above a given threshold. The connected components of the level sets, thanks to the inclusion relation, can be organized in a tree structure, that is called the component tree. This tree, under several variations, has been used in numerous applications. Various algorithms have been proposed in the literature for computing the component tree. The fastest ones (considering the worst-case complexity) have been proven to run in ( ln( )). In this paper, we propose a simple to implement quasi-linear algorithm for computing the component tree on symmetric graphs, based on Tarjan’s union-find procedure. We also propose an algorithm that computes the most significant lobes of a map.},
	language = {en},
	number = {11},
	urldate = {2019-04-08},
	journal = {IEEE Transactions on Image Processing},
	author = {Najman, L. and Couprie, M.},
	month = nov,
	year = {2006},
	note = {00237},
	keywords = {NEXT, hierarchical representation},
	pages = {3531--3539},
	file = {Najman and Couprie - 2006 - Building the Component Tree in Quasi-Linear Time.pdf:/home/florent/.zotero/data/storage/7PLWE8PE/Najman and Couprie - 2006 - Building the Component Tree in Quasi-Linear Time.pdf:application/pdf}
}

@article{matas_connected_2014,
	title = {Connected {Component} {Tree} {Construction} for {Embedded} {Systems}},
	language = {en},
	author = {Matas, Petr},
	month = jun,
	year = {2014},
	note = {00000},
	keywords = {NEXT, hierarchical representation, attribute filter},
	pages = {102},
	file = {Matas - 2014 - Connected Component Tree Construction for Embedded.pdf:/home/florent/.zotero/data/storage/HI5JPN3B/Matas - 2014 - Connected Component Tree Construction for Embedded.pdf:application/pdf}
}

@article{salembier_ship_2018,
	title = {Ship {Detection} in {SAR} {Images} {Based} on {Maxtree} {Representation} and {Graph} {Signal} {Processing}},
	issn = {0196-2892, 1558-0644},
	url = {https://ieeexplore.ieee.org/document/8529215/},
	doi = {10.1109/TGRS.2018.2876603},
	abstract = {This paper discusses an image processing architecture and tools to address the problem of ship detection in synthetic-aperture radar images. The detection strategy relies on a tree-based representation of images, here a Maxtree, and graph signal processing tools. Radiometric as well as geometric attributes are evaluated and associated with the Maxtree nodes. They form graph attribute signals which are processed with graph filters. The goal of this filtering step is to exploit the correlation existing between attribute values on neighboring tree nodes. Considering that trees are specific graphs where the connectivity toward ancestors and descendants may have a different meaning, we analyze several linear, nonlinear, and morphological filtering strategies. Beside graph filters, two new filtering notions emerge from this analysis: tree and branch filters. Finally, we discuss a ship detection architecture that involves graph signal filters and machine learning tools. This architecture demonstrates the interest of applying graph signal processing tools on the treebased representation of images and of going beyond classical graph filters. The resulting approach significantly outperforms state-of-the-art algorithms. Finally, a MATLAB toolbox allowing users to experiment with the tools discussed in this paper on Maxtree or Mintree has been created and made public.},
	language = {en},
	urldate = {2019-04-10},
	journal = {IEEE Transactions on Geoscience and Remote Sensing},
	author = {Salembier, Philippe and Liesegang, Sergi and Lopez-Martinez, Carlos},
	year = {2018},
	note = {00000},
	keywords = {NEXT, hierarchical representation},
	pages = {1--16},
	file = {Salembier et al. - 2018 - Ship Detection in SAR Images Based on Maxtree Repr.pdf:/home/florent/.zotero/data/storage/V36M2PTB/Salembier et al. - 2018 - Ship Detection in SAR Images Based on Maxtree Repr.pdf:application/pdf}
}