BandClust: An Unsupervised Band Reduction Method for Hyperspectral Remote Sensing - Université de Rennes Accéder directement au contenu
Article Dans Une Revue IEEE Geoscience and Remote Sensing Letters Année : 2011

BandClust: An Unsupervised Band Reduction Method for Hyperspectral Remote Sensing

Résumé

We address the problem of unsupervised band reduction in hyperspectral remote sensing imagery. We propose the use of an information theoretic criterion to automatically separate the sensor's spectral range into disjoint subbands without ground truth knowledge. Our approach, named BandClust, preserves the physical sense of the spectral data and automatically provides relevant spectral subbands, i.e., of maximal informational complementarity. Experiments using real hyperspectral images are conducted to compare BandClust with four other unsupervised approaches. The comparison of the selected dimensionality reduction methods is performed via supervised classification using support vector machines and shows the potential of the proposed approach.
Fichier non déposé

Dates et versions

hal-00946927 , version 1 (14-02-2014)

Identifiants

Citer

Claude Cariou, Kacem Chehdi, Steven Le Moan. BandClust: An Unsupervised Band Reduction Method for Hyperspectral Remote Sensing. IEEE Geoscience and Remote Sensing Letters, 2011, 8 (3), pp.565-569. ⟨10.1109/LGRS.2010.2091673⟩. ⟨hal-00946927⟩
146 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More