Centre de documentation
scientifique

Semi-supervised label propagation for multi-source remote sensing image change detection / Fan Hao in Computers & geosciences, vol 170 (January 2023)  

Public [article]  inComputers & geosciences > vol 170 (January 2023) . - n° 105249 Titre : Semi-supervised label propagation for multi-source remote sensing image change detection Type de document : Article/Communication Auteurs : Fan Hao, Auteur ; Zong-Fang Ma, Auteur ; Hong Peng Tian, Auteur ; et al., Auteur Année de publication : 2023 Article en page(s) : n° 105249 Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] analyse de groupement [Termes IGN] classification barycentrique [Termes IGN] classification pixellaire [Termes IGN] détection de changement [Termes IGN] données d'entrainement (apprentissage automatique) [Termes IGN] étiquette [Termes IGN] filtrage du bruit [Termes IGN] image multi sources Résumé : (auteur) Remote sensing image change detection remains a challenging task. Most existing approaches are based on fully supervised learning, but labeled data are so scarce for change detection. It is difficult to exhibit high detection performance with a limited amount of labeled data. In this paper, we propose a semi-supervised Label Propagation (SSLP) approach for multi-source remote sensing image change detection. First, a clustering label propagation (CLP) method is designed to cluster pre and post images, respectively, and assign pseudo labels to unlabeled pixel pairs that have similar mapping relationships to labeled pixel pairs. Second, a pixel density metric is investigated to filter out the data with low density and retain the data with high density, which can ensure the reliability of the propagated data. Third, a secondary expansion method based on pixel neighborhood is used to generate enough training data for training a classifier. Finally, the effectiveness of SSLP is validated on three real datasets by comparing to other related methods. Numéro de notice : A2023-032 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article DOI : 10.1016/j.cageo.2022.105249 Date de publication en ligne : 19/10/2022 En ligne : https://doi.org/10.1016/j.cageo.2022.105249 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=102292 [article]