Centre dedocumentation
scientifique

Effect of training class label noise on classification performances for land cover mapping with satellite image time series / Charlotte Pelletier in Remote sensing, vol 9 n° 2 (February 2017)  

Public [article]  inRemote sensing > vol 9 n° 2 (February 2017) . - pp 1 - 24 Titre : Effect of training class label noise on classification performances for land cover mapping with satellite image time series Type de document : Article/Communication Auteurs : Charlotte Pelletier, Auteur ; Silvia Valero, Auteur ; Jordi Inglada, Auteur ; Nicolas Champion , Auteur ; Claire Marais-Sicre, Auteur ; Gérard Dedieu, Auteur Année de publication : 2017 Projets : 1-Pas de projet / Article en page(s) : pp 1 - 24 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] base de données d'occupation du sol [Termes IGN] classification par forêts aléatoires [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] image Landsat-8 [Termes IGN] image SPOT 4 [Termes IGN] série temporelle Résumé : (auteur) Supervised classification systems used for land cover mapping require accurate reference databases. These reference data come generally from different sources such as field measurements, thematic maps, or aerial photographs. Due to misregistration, update delay, or land cover complexity, they may contain class label noise, i.e., a wrong label assignment. This study aims at evaluating the impact of mislabeled training data on classification performances for land cover mapping. Particularly, it addresses the random and systematic label noise problem for the classification of high resolution satellite image time series. Experiments are carried out on synthetic and real datasets with two traditional classifiers: Support Vector Machines (SVM) and Random Forests (RF). A synthetic dataset has been designed for this study, simulating vegetation profiles over one year. The real dataset is composed of Landsat-8 and SPOT-4 images acquired during one year in the south of France. The results show that both classifiers are little influenced for low random noise levels up to 25%–30%, but their performances drop down for higher noise levels. Different classification configurations are tested by increasing the number of classes, using different input feature vectors, and changing the number of training instances. Algorithm complexities are also analyzed. The RF classifier achieves high robustness to random and systematic label noise for all the tested configurations; whereas the SVM classifier is more sensitive to the kernel choice and to the input feature vectors. Finally, this work reveals that the cross-validation procedure is impacted by the presence of class label noise. Numéro de notice : A2017-896 Affiliation des auteurs : LaSTIG MATIS+Ext (2012-2019) Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : doi.org/10.3390/rs9020173 Date de publication en ligne : 18/02/2017 En ligne : https://doi.org/10.3390/rs9020173 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=91880 [article]

Automatic production of large-scale cloud-free orthomosaics from multitemporal satellite images / Nicolas Champion (2017)  

Public Titre : Automatic production of large-scale cloud-free orthomosaics from multitemporal satellite images Type de document : Article/Communication Auteurs : Nicolas Champion , Auteur ; Emilie Le Hir, Auteur ; Stéphane Massera , Auteur ; Nicolas Bellaiche, Auteur Editeur : New York : Institute of Electrical and Electronics Engineers IEEE Année de publication : 2017 Projets : 2-Pas d'info accessible - article non ouvert / Conférence : Multitemp 2017, 9th International Workshop on the Analysis of Multitemporal Remote Sensing Images 27/06/2017 29/06/2017 Brugge Belgique Proceedings IEEE Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] chaîne de traitement [Termes IGN] continuité cartographique [Termes IGN] harmonisation des données [Termes IGN] image Pléiades-HR [Termes IGN] image SPOT 6 [Termes IGN] image SPOT 7 [Termes IGN] masque [Termes IGN] orthophotoplan numérique Résumé : (auteur) The main goal of this paper is to present the automatic pipeline designed at IGN-France to produce automatic large-scale cloud-free orthomosaics from multiple Spot 6/7 and Pléiades-HR satellite images. Our pipeline is composed of three steps: the radiometric harmonisation of satellite images, the automatic production of cloud masks and the stitching procedure. Our evaluation shows that our pipeline is capable to remove all clouds in a given scene and produce seamless orthomosaics. Numéro de notice : C2017-058 Affiliation des auteurs : LaSTIG MATIS (2012-2019) Thématique : IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1109/Multi-Temp.2017.8035214 Date de publication en ligne : 14/09/2017 En ligne : https://doi.org/10.1109/Multi-Temp.2017.8035214 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97496

Filtering mislabeled data for improving time series classification / Charlotte Pelletier (2017)  

Public Titre : Filtering mislabeled data for improving time series classification Type de document : Article/Communication Auteurs : Charlotte Pelletier, Auteur ; Silvia Valero, Auteur ; Jordi Inglada, Auteur ; Gérard Dedieu, Auteur ; Nicolas Champion , Auteur Editeur : New York : Institute of Electrical and Electronics Engineers IEEE Année de publication : 2017 Projets : 2-Pas d'info accessible - article non ouvert / Conférence : Multitemp 2017, 9th International Workshop on the Analysis of Multitemporal Remote Sensing Images 27/06/2017 29/06/2017 Brugge Belgique Proceedings IEEE Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] base d'apprentissage [Termes IGN] classification par forêts aléatoires [Termes IGN] image Sentinel-MSI [Termes IGN] série temporelle [Termes IGN] végétation Résumé : (auteur) The supervised classification of optical image time series allow the production of accurate land cover maps over large areas. However, the precision yielded by learning algorithms strongly depends on the quality of the reference data. The reference databases covering a large geographical area usually contain noisy data with an important number of mislabeled instances. These labeling errors result in longer training time, less accurate classifiers, and ultimately poorer results. To address this issue, we proposed a new iterative learning framework that removes mislabeled data from the training set. Specifically, a preliminary outlier rejection procedure based on the well-known Random Forest algorithm is proposed. The presented strategy is tested with the classification of Sentinel-2 image time series acquired on 2016 by using an out-of-date reference dataset collected on 2014. Numéro de notice : C2017-059 Affiliation des auteurs : LaSTIG MATIS+Ext (2012-2019) Thématique : IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1109/Multi-Temp.2017.8035217 Date de publication en ligne : 14/09/2017 En ligne : https://doi.org/10.1109/Multi-Temp.2017.8035217 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=97497

New iterative learning strategy to improve classification systems by using outlier detection techniques / Charlotte Pelletier (2017)  

Public Titre : New iterative learning strategy to improve classification systems by using outlier detection techniques Type de document : Article/Communication Auteurs : Charlotte Pelletier, Auteur ; Silvia Valero, Auteur ; Jordi Inglada, Auteur ; Gérard Dedieu, Auteur ; Nicolas Champion , Auteur Editeur : New York : Institute of Electrical and Electronics Engineers IEEE Année de publication : 2017 Conférence : IGARSS 2017, IEEE International Geoscience And Remote Sensing Symposium 23/07/2017 28/07/2017 Fort Worth Texas - Etats-Unis Proceedings IEEE Importance : pp 3676 - 3679 Format : 21 x 30 cm Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image [Termes IGN] apprentissage automatique [Termes IGN] classification dirigée [Termes IGN] classification par forêts aléatoires [Termes IGN] détection d'anomalie [Termes IGN] itération [Termes IGN] valeur aberrante Résumé : (auteur) The supervised classification of satellite image time series allows obtaining reliable land cover maps over large areas. However, their quality depends on the reference datasets used for training the classifier. In remote sensing, reference data may lack of timeliness and accuracy which leads to the presence of mislabeled data degrading the classification performances. This work presents an iterative learning framework to deal with noisy instances, that can be seen as outliers. Several outlier detection strategies, based on the well-known Random Forests (RF) ensemble classifier, are proposed, evaluated quantitatively, and then compared with traditional methods. Experimental results have been carried out by using synthetic and real datasets representing annual vegetation profiles. Numéro de notice : C2017-042 Affiliation des auteurs : IGN+Ext (2012-2019) Thématique : IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1109/IGARSS.2017.8127796 Date de publication en ligne : 04/12/2017 En ligne : https://doi.org/10.1109/IGARSS.2017.8127796 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=91925

Assessing the robustness of Random Forests to map land cover with high resolution satellite image time series over large areas / Charlotte Pelletier in Remote sensing of environment, vol 187 (15 December 2016)  

Public [article]  inRemote sensing of environment > vol 187 (15 December 2016) . - pp 156 - 168 Titre : Assessing the robustness of Random Forests to map land cover with high resolution satellite image time series over large areas Type de document : Article/Communication Auteurs : Charlotte Pelletier, Auteur ; Silvia Valero, Auteur ; Jordi Inglada, Auteur ; Nicolas Champion , Auteur ; Gérard Dedieu, Auteur Année de publication : 2016 Article en page(s) : pp 156 - 168 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] caractérisation [Termes IGN] carte d'occupation du sol [Termes IGN] classification par forêts aléatoires [Termes IGN] classification par séparateurs à vaste marge [Termes IGN] France (administrative) [Termes IGN] image Landsat-8 [Termes IGN] image Sentinel [Termes IGN] image SPOT 4 [Termes IGN] méthode robuste [Termes IGN] précision de la classification [Termes IGN] série temporelle Résumé : (Auteur) New remote sensing sensors will acquire High spectral, spatial and temporal Resolution Satellite Image Time Series (HR-SITS). These new data are of great interest to map land cover thanks to the combination of the three high resolutions that will allow a depiction of scene dynamics. However, their efficient exploitation involves new challenges, especially for adapting traditional classification schemes to data complexity. More specifically, it requires: (1) to determine which classifier algorithms can handle the amount and the variability of data; (2) to evaluate the stability of classifier parameters; (3) to select the best feature set used as input data in order to find the good trade-off between classification accuracy and computational time; and (4) to establish the classifier accuracy over large areas. This work aims at studying these different issues, and more especially at demonstrating the ability of state-of-the-art classifiers, such as Random Forests (RF) or Support Vector Machines (SVM), to classify HR-SITS. For this purpose, several studies are carried out by using SPOT-4 and Landsat-8 HR-SITS in the south of France. Firstly, the choice of the classifier is discussed by comparing RF and SVM algorithms on HR-SITS. Both classifiers show their ability to tackle the classification problem with an Overall Accuracy (OA) of 83.3 % for RF and 77.1 % for SVM. But RF have some advantages such as a small training time, and an easy parameterization. Secondly, the stability of RF parameters is appraised. RF parameters appear to cause little influence on the classification accuracy, about 1% OA difference between the worst and the best parameter configuration. Thirdly, different input data – composed of spectral bands with or without spectral and/or temporal features – are proposed in order to enhance the characterization of land cover. The addition of features improves the classification accuracy, but the gain in OA is weak compared with the increase in the computational cost. Eventually, the classifier accuracy is assessed on a larger area where the landscape variabilities affect the classification performances. Numéro de notice : A2016--109 Affiliation des auteurs : IGN+Ext (2012-2019) Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1016/j.rse.2016.10.010 Date de publication en ligne : 15/10/2016 En ligne : http://doi.org/10.1016/j.rse.2016.10.010 Format de la ressource électronique : URL Article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=84726 [article]

An assessment of image features and random forest for land cover mapping over large areas using high resolution Satellite Image Time Series / Charlotte Pelletier (2016)  

Permalink

Automatic detection of clouds and shadows using high resolution satellite image time series / Nicolas Champion (2016)  

Permalink

Pinastéréo, estimation de la hauteur dominante et de la biomasse forestière dans le massif des Landes de Gascogne à partir d'images stéréoscopiques Pléiades / Thierry Bélouard in Revue Française de Photogrammétrie et de Télédétection, n° 209 (Janvier 2015)  

Permalink

Extracting polygonal building footprints from digital surface models: A fully-automatic global optimization framework / Mathieu Brédif in ISPRS Journal of photogrammetry and remote sensing, vol 77 (March 2013)  

Permalink

Automatic cloud detection from multi-temporal satellite images: towards the use of Pléiades time series / Nicolas Champion (2012)  

Permalink

2D change detection from satellite imagery: Performance analysis and impact of the spatial resolution of input images / Nicolas Champion (2011)  

Permalink

Détection de changement 2D à partir d’imagerie satellitaire : Application à la mise à jour des bases de données géographiques / Nicolas Champion (2011)  

Permalink

2D building change detection from high resolution satellite imagery: A two-step hierarchical method based on 3D invariant primitives / Nicolas Champion in Pattern recognition letters, vol 31 n° 10 (15 July 2010)  

Permalink

Detection of unregistered buildings for updating 2D databases / Nicolas Champion (01/12/2009)

Permalink

Automatic GIS updating from high resolution satellite images / Nicolas Champion (22/05/2009)  

Permalink