Descripteur
Termes IGN > mathématiques > statistique mathématique > analyse de données > classification > classification dirigée
classification dirigéeSynonyme(s)classification superviséeVoir aussi |
Documents disponibles dans cette catégorie (430)
Ajouter le résultat dans votre panier
Visionner les documents numériques
Affiner la recherche Interroger des sources externes
Etendre la recherche sur niveau(x) vers le bas
Titre : Towards operational very high resolution land-cover mapping Titre original : Outils pour des occupations du sol opérationnelles à très haute résolution spatiale Type de document : Thèse/HDR Auteurs : Clément Mallet , Auteur Editeur : Champs/Marne : Université Paris-Est Année de publication : 2016 Importance : 144 p. Format : 21 x 30 cm Note générale : Bibliographie
Synthèse de travaux présentée en vue d’obtenir l’Habilitation à Diriger des Recherches délivrée par l’Université Paris-Est, spécialité « Sciences et Techniques de l’Information Géographique »Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Bases de données localisées
[Termes IGN] base de données d'occupation du sol
[Termes IGN] carte d'occupation du sol
[Termes IGN] classification dirigée
[Termes IGN] détection de changement
[Termes IGN] données localisées 2D
[Termes IGN] données localisées 3D
[Termes IGN] image à très haute résolution
[Termes IGN] image satellite
[Termes IGN] information sémantique
[Termes IGN] reconstruction 3D
[Termes IGN] segmentation d'image
[Termes IGN] sémantisation
[Termes IGN] semis de pointsIndex. décimale : THESE Thèses et HDR Résumé : (Auteur) [Preamble] This document is the manuscript presented in order to obtain the Habilitation à Diriger des Recherches of Paris-Est University, France. My main professional activities, since my PhD defence in 2010, in the MATIS team of the French National Institute of Geographic and Forest Information (IGN), are described here. It may also include recall to previous works of the 2007-2010 period. I was recruited in the research department of IGN in 2005, being a civil servant. I first started as engineer on 3D airborne lidar point cloud processing in urban, natural, and seashore environments during the 2005-2007 period. Then, I focused on the emerging fullwaveform lidar technology during my PhD thesis, with a slight emphasis on urban areas (2007-2010). Since 2010, I took the lead of the research group that deals with land-cover mapping and change detection as well as 2D/3D geodatabase evaluation. Now, it encompasses more generally semantization and reconstruction issues for scene understanding. I naturally moved from airborne lidar data to any kind of geospatial/overhead remote sensing data (mainly satellite and airborne vertical imagery). Some of the developed methods has been eventually specialized to 3D terrestrial point clouds. [...] Note de contenu : PART ONE - SCIENTIFIC SYNTHESIS
1. INTRODUCTION
1.1 Relevance of remote sensing for land-cover mapping
1.2 A fastly evolving context for research in remote sensing
1.3 What is operational land-cover mapping?
1.4 Datasets
2. RESEARCH RESULTS 2011-2016
2.1 Remote sensing data processing
2.2 Feature extraction and selection
2.3 Object extraction/segmentation
2.4 Land-cover classification
2.5 Fusion
3. PERSPECTIVES
3.1 Efficient classifications
3.2 Semantic segmentation
3.3 Humans in the loop
3.4 Optimal data fusion
3.5 Exploitation of existing geospatial databases
3.6 Towards land-use mapping
3.7 Change detection and LC updating
3.8 Land-cover dynamics monitoring
PART TWO - CURRICULUM VITAE
4. EMPLOYEMENT AND EDUCATION
4.1 Civil status
4.2 Employement
4.3 Education
4.4 Awards
5. STUDENT SUPERVISION AND TEACHING
5.1 Supervision
6. CONTENTS
5.2 Teaching
6 Projects and collaborations
6.1 Funded projects
6.2 National and international cooperations
7. SCIENTIFIC ANIMATION
7.1 PhD committee membership
7.2 Editorial work and reviews
7.3 Conference and workshop organisation
7.4 Program committee membership
7.5 Scientific societies
8. PUBLICATION LIST
8.1 Book chapters
8.2 Journal papers
8.3 Peer-reviewed conference papers
8.4 MiscellaneousNuméro de notice : 22673 Affiliation des auteurs : LASTIG MATIS (2012-2019) Thématique : FORET/IMAGERIE Nature : HDR Note de thèse : HDR : Sciences et Technologies de l’Information Géographique : UPE : 2016 Organisme de stage : MATIS (IGN) nature-HAL : HDR DOI : sans Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=84127 Documents numériques
en open access
22673_Towards operational very high resolution land-cover mapping.pdfAdobe Acrobat PDF Vegetation classification and biogeography of European floodplain forests and alder carrs / Jan Douda in Applied Vegetation Science, vol 19 n° 1 (January 2016)
[article]
Titre : Vegetation classification and biogeography of European floodplain forests and alder carrs Type de document : Article/Communication Auteurs : Jan Douda, Auteur ; Karel Boublík, Auteur ; Michal Slezák, Auteur ; et al., Auteur Année de publication : 2016 Article en page(s) : pp 147 - 163 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Termes IGN] Alnus (genre)
[Termes IGN] Alnus glutinosa
[Termes IGN] Alnus incana
[Termes IGN] analyse de groupement
[Termes IGN] biogéographie
[Termes IGN] classification barycentrique
[Termes IGN] classification dirigée
[Termes IGN] Europe (géographie physique)
[Termes IGN] forêt marécageuse
[Termes IGN] forêt ripicole
[Termes IGN] Fraxinus angustifolia
[Termes IGN] Fraxinus excelsior
[Termes IGN] Platanus orientalis
[Termes IGN] Populus alba
[Termes IGN] Populus nigra
[Vedettes matières IGN] Ecologie forestièreRésumé : (auteur) Aim : Formalized classifications synthesizing vegetation data at the continental scale are being attempted only now, although they are of key importance for nature conservation planning. Therefore, we aim to provide a vegetation classification and to describe the main biogeographical patterns of floodplain forests and alder carrs in Europe.
Location : Europe.
Methods : A database of more than 40 000 vegetation plots of floodplain forests and alder carrs across Europe was compiled. After geographic stratification, 16 392 plots were available for classification, which was performed using the supervised method Cocktail. We also searched for new associations using semi-supervised K-means classification. The main biogeographic patterns and climate-related gradients in species composition were determined using detrended correspondence analysis and cluster analysis.
Results : Thirty associations of floodplain forests and alder carrs were distinguished, which belong to five alliances. The Alnion incanae includes riparian, seepage and hardwood floodplain forests in the nemoral and hemiboreal zones (dominated by Alnus glutinosa and Fraxinus excelsior) and in the boreal zone (dominated by A. incana). The Osmundo-Alnion represents oceanic vegetation dominated by Alnus glutinosa, Fraxinus angustifolia and F. excelsior distributed mostly on the Iberian Peninsula and composed of species with Atlantic distribution and Iberian endemics. The Populion albae comprises floodplain forests frequently dominated by Fraxinus angustifolia, Populus alba and P. nigra that are widespread in floodplains of large rivers under summer-dry climates in the Mediterranean region. The Platanion orientalis represents eastern Mediterranean floodplain forests dominated by Platanus orientalis. The Alnion glutinosae includes forest swamps dominated by Alnus glutinosa distributed mostly in the nemoral and hemiboreal zones. The main biogeographic patterns within European floodplain forests and alder carrs reflect the climatic contrasts between the Mediterranean, nemoral, boreal and mountain regions. Oceanic floodplain forests differ from those in the rest of Europe. The hydrological regime appears to be the most important factor influencing species composition within regions.
Conclusions : This study is the first applying a formalized classification at the association level for a broad vegetation type at the continental scale. The proposed classification provides the scientific basis for the necessary improvement of the habitat classification systems used in European nature conservation.Numéro de notice : A2016-363 Affiliation des auteurs : non IGN Thématique : FORET Nature : Article DOI : 10.1111/avsc.12201 En ligne : http://dx.doi.org/10.1111/avsc.12201 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=81102
in Applied Vegetation Science > vol 19 n° 1 (January 2016) . - pp 147 - 163[article]Automated annual cropland mapping using knowledge-based temporal features / François Waldner in ISPRS Journal of photogrammetry and remote sensing, vol 110 (December 2015)
[article]
Titre : Automated annual cropland mapping using knowledge-based temporal features Type de document : Article/Communication Auteurs : François Waldner, Auteur ; Guadalupe Sepulcre Canto, Auteur ; Pierre Defourny, Auteur Année de publication : 2015 Article en page(s) : pp 1 – 13 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] Argentine
[Termes IGN] Belgique
[Termes IGN] carte agricole
[Termes IGN] carte d'occupation du sol
[Termes IGN] Chine
[Termes IGN] classification dirigée
[Termes IGN] cultures
[Termes IGN] série temporelle
[Termes IGN] surveillance agricole
[Termes IGN] UkraineRésumé : (auteur) Global, timely, accurate and cost-effective cropland mapping is a prerequisite for reliable crop condition monitoring. This article presented a simple and comprehensive methodology capable to meet the requirements of operational cropland mapping by proposing (1) five knowledge-based temporal features that remain stable over time, (2) a cleaning method that discards misleading pixels from a baseline land cover map and (3) a classifier that delivers high accuracy cropland maps (>>80%). This was demonstrated over four contrasted agrosystems in Argentina, Belgium, China and Ukraine. It was found that the quality and accuracy of the baseline impact more the certainty of the classification rather than the classification output itself. In addition, it was shown that interpolation of the knowledge-based features increases the stability of the classifier allowing for its re-use from year to year without recalibration. Hence, the method shows potential for application at larger scale as well as for delivering cropland map in near real time. Numéro de notice : A2015-889 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2015.09.013 En ligne : http://dx.doi.org/10.1016/j.isprsjprs.2015.09.013 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=79438
in ISPRS Journal of photogrammetry and remote sensing > vol 110 (December 2015) . - pp 1 – 13[article]Semi-supervised SVM for individual tree crown species classification / Michele Dalponte in ISPRS Journal of photogrammetry and remote sensing, vol 110 (December 2015)
[article]
Titre : Semi-supervised SVM for individual tree crown species classification Type de document : Article/Communication Auteurs : Michele Dalponte, Auteur ; Levi Theodor Ene, Auteur ; Mattia Marconcini, Auteur ; et al., Auteur Année de publication : 2015 Article en page(s) : pp 77 – 87 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] classification dirigée
[Termes IGN] classification par séparateurs à vaste marge
[Termes IGN] données laser
[Termes IGN] forêt boréale
[Termes IGN] image hyperspectrale
[Termes IGN] inventaire forestier localRésumé : (auteur) In this paper a novel semi-supervised SVM classifier is presented, specifically developed for tree species classification at individual tree crown (ITC) level. In ITC tree species classification, all the pixels belonging to an ITC should have the same label. This assumption is used in the learning of the proposed semi-supervised SVM classifier (ITC-S3VM). This method exploits the information contained in the unlabeled ITC samples in order to improve the classification accuracy of a standard SVM. The ITC-S3VM method can be easily implemented using freely available software libraries. The datasets used in this study include hyperspectral imagery and laser scanning data acquired over two boreal forest areas characterized by the presence of three information classes (Pine, Spruce, and Broadleaves). The experimental results quantify the effectiveness of the proposed approach, which provides classification accuracies significantly higher (from 2% to above 27%) than those obtained by the standard supervised SVM and by a state-of-the-art semi-supervised SVM (S3VM). Particularly, by reducing the number of training samples (i.e. from 100% to 25%, and from 100% to 5% for the two datasets, respectively) the proposed method still exhibits results comparable to the ones of a supervised SVM trained with the full available training set. This property of the method makes it particularly suitable for practical forest inventory applications in which collection of in situ information can be very expensive both in terms of cost and time. Numéro de notice : A2015-894 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.isprsjprs.2015.10.010 En ligne : http://dx.doi.org/10.1016/j.isprsjprs.2015.10.010 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=79445
in ISPRS Journal of photogrammetry and remote sensing > vol 110 (December 2015) . - pp 77 – 87[article]Urban classification by the fusion of thermal infrared hyperspectral and visible data / Jiayi Li in Photogrammetric Engineering & Remote Sensing, PERS, vol 81 n° 12 (December 2015)
[article]
Titre : Urban classification by the fusion of thermal infrared hyperspectral and visible data Type de document : Article/Communication Auteurs : Jiayi Li, Auteur ; Hongyan Zhang, Auteur ; Min Guo, Auteur ; et al., Auteur Année de publication : 2015 Article en page(s) : pp 901 - 911 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique
[Termes IGN] analyse d'image numérique
[Termes IGN] bande spectrale
[Termes IGN] bande visible
[Termes IGN] classification dirigée
[Termes IGN] fusion de données
[Termes IGN] image hyperspectrale
[Termes IGN] image thermique
[Termes IGN] occupation du solRésumé : (auteur) The 2014 Data Fusion Contest, organized by the Image Analysis and Data Fusion (IADF) Technical Committee of the IEEE Geoscience and Remote Sensing Society, involved two datasets acquired at different spectral ranges and spatial resolutions: a coarser-resolution long-wave infrared (LWIR, thermal infrared) hyperspectral data set and fine-resolution data acquired in the visible (VIS) wavelength range. In this article, a novel multi-level fusion approach is proposed to fully utilize the characteristics of these two different datasets to achieve improved urban land-use and land-cover classification. Specifically, road extraction by fusing the classification result of the TI-HSI dataset and the segmentation result of the VIS dataset is first proposed. Thereafter, a novel gap inpainting method for the VIS data with the guidance of the TI-HSI data is presented to deal with the swath width inconsistency, and to facilitate an accurate spatial feature extraction step. The experimental results with the 2014 Data Fusion Contest datasets suggest that the proposed method can alleviate the multi-spectral-spatial resolution and multi-swath width problem to a great extent, and achieve an improved urban classification accuracy. Numéro de notice : A2015-990 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.14358/PERS.81.12.901 En ligne : https://doi.org/10.14358/PERS.81.12.901 Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=80271
in Photogrammetric Engineering & Remote Sensing, PERS > vol 81 n° 12 (December 2015) . - pp 901 - 911[article]Investigating the robustness of the new Landsat-8 Operational Land Imager derived texture metrics in estimating plantation forest aboveground biomass in resource constrained areas / Timothy Dube in ISPRS Journal of photogrammetry and remote sensing, vol 108 (October 2015)PermalinkMeasuring the effectiveness of various features for thematic information extraction from very high resolution remote sensing imagery / X. Chen in IEEE Transactions on geoscience and remote sensing, vol 53 n° 9 (September 2015)PermalinkDétection à haute résolution spatiale de la desserte forestière en milieu montagneux / António Ferraz in Revue Française de Photogrammétrie et de Télédétection, n° 211 - 212 (juillet - décembre 2015)PermalinkEstimation de la déforestation des forêts humides à Madagascar utilisant une classification multidate d'images Landsat entre 2005, 2010 et 2013 / F.A. Rakotomala in Revue Française de Photogrammétrie et de Télédétection, n° 211 - 212 (juillet - décembre 2015)PermalinkOperationalizing measurement of forest degradation: Identification and quantification of charcoal production in tropical dry forests using very high resolution satellite imagery / K. Dons in International journal of applied Earth observation and geoinformation, vol 39 (July 2015)PermalinkIntegrating user needs on misclassification error sensitivity into image segmentation quality assessment / Hugo Costa in Photogrammetric Engineering & Remote Sensing, PERS, vol 81 n° 6 (June 2015)PermalinkComplementarity of discriminative classifiers and spectral unmixing techniques for the interpretation of hyperspectral images / Jun Li in IEEE Transactions on geoscience and remote sensing, vol 53 n° 5 (mai 2015)PermalinkSupervised spectral–spatial hyperspectral image classification with weighted markov random fields / Le Sun in IEEE Transactions on geoscience and remote sensing, vol 53 n° 3 (March 2015)PermalinkData-driven feature learning for high resolution urban land-cover classification / Piotr Andrzej Tokarczyk (2015)PermalinkDélimitation des parcelles agricoles par classification d'images Pléiades / Nesrine Chehata in Revue Française de Photogrammétrie et de Télédétection, n° 209 (Janvier 2015)Permalink