Centre de documentation
scientifique

Updating land-cover maps by classification of image time series : A novel change-detection-driven transfer learning approach / Begüm Demir in IEEE Transactions on geoscience and remote sensing, vol 51 n° 1 Tome 1 (January 2013)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 51 n° 1 Tome 1 (January 2013) . - pp 300 - 312 Titre : Updating land-cover maps by classification of image time series : A novel change-detection-driven transfer learning approach Type de document : Article/Communication Auteurs : Begüm Demir, Auteur ; Francesca Bovolo, Auteur ; Lorenzo Bruzzone, Auteur Année de publication : 2013 Article en page(s) : pp 300 - 312 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse diachronique [Termes IGN] apprentissage dirigé [Termes IGN] carte d'occupation du sol [Termes IGN] classification automatique [Termes IGN] détection de changement [Termes IGN] image multitemporelle [Termes IGN] mise à jour de base de données [Termes IGN] série temporelle Résumé : (Auteur) This paper proposes a novel change-detection-driven transfer learning (TL) approach to update land-cover maps by classifying remote-sensing images acquired on the same area at different times (i.e., image time series). The proposed approach requires that a reliable training set is available only for one of the images (i.e., the source domain) in the time series whereas it is not for another image to be classified (i.e., the target domain). Unlike other literature TL methods, no additional assumptions on either the similarity between class distributions or the presence of the same set of land-cover classes in the two domains are required. The proposed method aims at defining a reliable training set for the target domain, taking advantage of the already available knowledge on the source domain. This is done by applying an unsupervised-change-detection method to target and source domains and transferring class labels of detected unchanged training samples from the source to the target domain to initialize the target-domain training set. The training set is then optimized by a properly defined novel active learning (AL) procedure. At the early iterations of AL, priority in labeling is given to samples detected as being changed, whereas in the remaining ones, the most informative samples are selected from changed and unchanged unlabeled samples. Finally, the target image is classified. Experimental results show that transferring the class labels from the source domain to the target domain provides a reliable initial training set and that the priority rule for AL results in a fast convergence to the desired accuracy with respect to Standard AL. Numéro de notice : A2013-015 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2012.2195727 En ligne : https://doi.org/10.1109/TGRS.2012.2195727 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=32153 [article]

Exemplaires(1)

Code-barres	Cote	Support	Localisation	Section	Disponibilité
065-2013011A	RAB	Revue	Centre de documentation	En réserve L003	Disponible