Centre de documentation
scientifique

Satellite image time series classification with pixel-set encoders and temporal self-attention / Vivien Sainte Fare Garnot (2020)    

Public Titre : Satellite image time series classification with pixel-set encoders and temporal self-attention Type de document : Article/Communication Auteurs : Vivien Sainte Fare Garnot , Auteur ; Loïc Landrieu , Auteur ; Sébastien Giordano , Auteur ; Nesrine Chehata , Auteur Editeur : Computer vision foundation CVF Année de publication : 2020 Projets : 1-Pas de projet / Conférence : CVPR 2020, IEEE Conference on Computer Vision and Pattern Recognition 14/06/2020 19/06/2020 en ligne Chine Open Access Proceedings Importance : pp 12325 - 12334 Format : 21 x 30 cm Note générale : bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage automatique [Termes IGN] classification automatique [Termes IGN] classification orientée objet [Termes IGN] classification par forêts d'arbres décisionnels [Termes IGN] classification par réseau neuronal convolutif [Termes IGN] extraction de traits caractéristiques [Termes IGN] géocodage [Termes IGN] image multibande [Termes IGN] image satellite [Termes IGN] parcelle agricole [Termes IGN] politique agricole commune [Termes IGN] série temporelle [Termes IGN] utilisation du sol Résumé : (auteur) Satellite image time series, bolstered by their growing availability, are at the forefront of an extensive effort towards automated Earth monitoring by international institutions. In particular, large-scale control of agricultural parcels is an issue of major political and economic importance. In this regard, hybrid convolutional-recurrent neural architectures have shown promising results for the automated classification of satellite image time series.We propose an alternative approach in which the convolutional layers are advantageously replaced with encoders operating on unordered sets of pixels to exploit the typically coarse resolution of publicly available satellite images. We also propose to extract temporal features using a bespoke neural architecture based on self-attention instead of recurrent networks. We demonstrate experimentally that our method not only outperforms previous state-of-the-art approaches in terms of precision, but also significantly decreases processing time and memory requirements. Lastly, we release a large openaccess annotated dataset as a benchmark for future work on satellite image time series. Numéro de notice : C2020-016 Affiliation des auteurs : UGE-LASTIG+Ext (2020- ) Autre URL associée : vers ArXiv/vers CVF Thématique : IMAGERIE Nature : Communication nature-HAL : ComAvecCL&ActesPubliésIntl DOI : 10.1109/CVPR42600.2020.01234 Date de publication en ligne : 05/08/2020 En ligne : https://doi.org/10.1109/CVPR42600.2020.01234 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=94225

Documents numériques

en open access Satellite image time series classification - pdf préprint Adobe Acrobat PDF