BandClust: An Unsupervised Band Reduction Method for Hyperspectral Remote Sensing

Abstract : 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.
Document type :
Journal articles
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-00946927
Contributor : Yolande Sambin <>
Submitted on : Friday, February 14, 2014 - 12:55:25 PM
Last modification on : Friday, November 16, 2018 - 1:28:28 AM

Identifiers

Citation

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

Share

Metrics

Record views

297