Centre de documentation
scientifique

Learning sensor-specific spatial-spectral features of hyperspectral images via convolutional neural networks / Shaohui Mei in IEEE Transactions on geoscience and remote sensing, vol 55 n° 8 (August 2017)  

Public [article]  inIEEE Transactions on geoscience and remote sensing > vol 55 n° 8 (August 2017) . - pp 4520 - 4533 Titre : Learning sensor-specific spatial-spectral features of hyperspectral images via convolutional neural networks Type de document : Article/Communication Auteurs : Shaohui Mei, Auteur ; Jingyu Ji, Auteur ; Junhui Hou, Auteur ; et al., Auteur Année de publication : 2017 Article en page(s) : pp 4520 - 4533 Note générale : Bibliographie Langues : Anglais (eng) Descripteur : [Vedettes matières IGN] Traitement d'image optique [Termes IGN] apprentissage dirigé [Termes IGN] apprentissage profond [Termes IGN] extraction de couche [Termes IGN] filtrage numérique d'image [Termes IGN] image AVIRIS [Termes IGN] image hyperspectrale [Termes IGN] image ROSIS [Termes IGN] réseau neuronal convolutif Résumé : (Auteur) Convolutional neural network (CNN) is well known for its capability of feature learning and has made revolutionary achievements in many applications, such as scene recognition and target detection. In this paper, its capability of feature learning in hyperspectral images is explored by constructing a five-layer CNN for classification (C-CNN). The proposed C-CNN is constructed by including recent advances in deep learning area, such as batch normalization, dropout, and parametric rectified linear unit (PReLU) activation function. In addition, both spatial context and spectral information are elegantly integrated into the C-CNN such that spatial-spectral features are learned for hyperspectral images. A companion feature-learning CNN (FL-CNN) is constructed by extracting fully connected feature layers in this C-CNN. Both supervised and unsupervised modes are designed for the proposed FL-CNN to learn sensor-specific spatial-spectral features. Extensive experimental results on four benchmark data sets from two well-known hyperspectral sensors, namely airborne visible/infrared imaging spectrometer (AVIRIS) and reflective optics system imaging spectrometer (ROSIS) sensors, demonstrate that our proposed C-CNN outperforms the state-of-the-art CNN-based classification methods, and its corresponding FL-CNN is very effective to extract sensor-specific spatial-spectral features for hyperspectral application Numéro de notice : A2017-499 Affiliation des auteurs : non IGN Thématique : IMAGERIE Nature : Article nature-HAL : ArtAvecCL-RevueIntern DOI : 10.1109/TGRS.2017.2693346 En ligne : http://dx.doi.org/10.1109/TGRS.2017.2693346 Format de la ressource électronique : URL article Permalink : https://documentation.ensg.eu/index.php?lvl=notice_display&id=86441 [article]