Centre de documentation
scientifique

Active-metric learning for classification of remotely sensed hyperspectral images / Edoardo Pasolli in IEEE Transactions on geoscience and remote sensing, vol 54 n° 4 (April 2016)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 54 n° 4 (April 2016) . - pp 1925 - 1939 Titre : Active-metric learning for classification of remotely sensed hyperspectral images Type de document : Article/Communication Auteurs : Edoardo Pasolli, Auteur ; Hsiuhan Lexie Yang, Auteur ; Melba M. Crawford, Auteur Année de publication : 2016 Article en page(s) : pp 1925 - 1939 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage automatique [Termes IGN] classification barycentrique [Termes IGN] classification dirigée [Termes IGN] extraction automatique [Termes IGN] extraction de traits caractéristiques Résumé : (Auteur) Classification of remotely sensed hyperspectral images via supervised approaches is typically affected by high dimensionality of the spectral data and a limited number of labeled samples. Dimensionality reduction via feature extraction and active learning (AL) are two approaches that researchers have investigated independently to deal with these two problems. In this paper, we propose a new method in which the feature extraction and AL steps are combined into a unique framework. The idea is to learn and update a reduced feature space in a supervised way at each iteration of the AL process, thus taking advantage of the increasing labeled information provided by the user. In particular, the computation of the reduced feature space is based on the large-margin nearest neighbor (LMNN) metric learning principle. This strategy is applied in conjunction with k-nearest neighbor ( k-NN) classification, for which a new sample selection strategy is proposed. The methodology is validated experimentally on four benchmark hyperspectral data sets. Good improvements in terms of classification accuracy and computational time are achieved with respect to the state-of-the-art strategies that do not combine feature extraction and AL. Numéro de notice : A2016-836 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2015.2490482 En ligne : http://dx.doi.org/10.1109/TGRS.2015.2490482 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=82880 [article]

Active learning methods for biophysical parameter estimation / Edoardo Pasolli in IEEE Transactions on geoscience and remote sensing, vol 50 n° 10 Tome 2 (October 2012)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 50 n° 10 Tome 2 (October 2012) . - pp 4071 - 4084 Titre : Active learning methods for biophysical parameter estimation Type de document : Article/Communication Auteurs : Edoardo Pasolli, Auteur ; F. Melgani, Auteur ; N. Alajlan, Auteur ; B. Yakoub, Auteur Année de publication : 2012 Article en page(s) : pp 4071 - 4084 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Intelligence artificielle [Termes IGN] algorithme de Gauss [Termes IGN] apprentissage automatique [Termes IGN] chlorophylle [Termes IGN] régression [Termes IGN] séparateur à vaste marge [Termes IGN] variable biophysique (végétation) Résumé : (Auteur) In this paper, we face the problem of collecting training samples for regression problems under an active learning perspective. In particular, we propose various active learning strategies specifically developed for regression approaches based on Gaussian processes (GPs) and support vector machines (SVMs). For GP regression, the first two strategies are based on the idea of adding samples that are dissimilar from the current training samples in terms of covariance measure, while the third one uses a pool of regressors in order to select the samples with the greater disagreements between the different regressors. Finally, the last strategy exploits an intrinsic GP regression outcome to pick up the most difficult and hence interesting samples to label. For SVM regression, the method based on the pool of regressors and two additional strategies based on the selection of the samples distant from the current support vectors in the kernel-induced feature space are proposed. The experimental results obtained on simulated and real data sets show that the proposed strategies exhibit a good capability to select samples that are significant for the regression process, thus opening the way to the active learning approach for remote-sensing regression problems. Numéro de notice : A2012-528 Affiliation des auteurs : non IGN Thématique : GEOMATIQUE/INFORMATIQUE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2012.2187906 Date de publication en ligne : 17/04/2012 En ligne : https://doi.org/10.1109/TGRS.2012.2187906 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=31974 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-2012101B	MANQUANT	Revue	Centre de documentation	Indéterminé	Disponible