Centre de documentation
scientifique

Unsupervised feature learning for land-use scene recognition / Jiayuan Fan in IEEE Transactions on geoscience and remote sensing, vol 55 n° 4 (April 2017)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 55 n° 4 (April 2017) . - pp 2250 - 2261 Titre : Unsupervised feature learning for land-use scene recognition Type de document : Article/Communication Auteurs : Jiayuan Fan, Auteur ; Tao Chen, Auteur ; Shijian Lu, Auteur Année de publication : 2017 Article en page(s) : pp 2250 - 2261 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Applications de télédétection [Termes IGN] algorithme d'apprentissage [Termes IGN] analyse discriminante [Termes IGN] codage [Termes IGN] image proche infrarouge [Termes IGN] image RVB [Termes IGN] invariant [Termes IGN] pouvoir de résolution géométrique [Termes IGN] reconnaissance automatique [Termes IGN] Singapour [Termes IGN] utilisation du sol Résumé : (Auteur) This paper proposes a novel unsupervised feature learning algorithm for land-use scene recognition on very high resolution remote sensing imagery. The proposed technique utilizes a multipath sparse coding architecture in order to capture multiple aspects of discriminative structures within complex remote sensing sceneries. Unlike the previous sparse coding and bag-of-visual-words-based techniques that rely on the handcrafted feature descriptors such as scale-invariant feature transform, the proposed technique extracts dense low-level features from the raw data, including the visual (RGB) data and near-infrared (NIR) data, using image patches of varying sizes at different layers. The proposed technique has been evaluated on three data sets, including the 21-category UC Merced landuse RGB data set with a 1-ft spatial resolution, the 9-category ground scene RGB-NIR data set, and the 10-category Singapore land-use RGB-NIR data set with a 0.5-m spatial resolution. The experimental results show that the proposed technique outperforms the state-of-the-art methods. Numéro de notice : A2107-174 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2016.2640186 En ligne : https://doi.org/10.1109/TGRS.2016.2640186 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=84723 [article]