Unsupervised Band Selection using Block Diagonal Sparsity for Hyperspectral Image Classification

J. Wang K. Zhang P. Pei K. Madani 1 C. Sabourin 1
1 SYNAPSE
LISSI - Laboratoire Images, Signaux et Systèmes Intelligents
Abstract : In order to alleviate the negative effect of curse of dimensionality, band selection is a crucial step for hyperspectral image (HSI) processing. In this letter, we propose a novel unsupervised band selection approach to reduce the dimensionality for hyperspectral imagery. In order to obtain the most representative bands, the correlation matrix computed from the original HSI is used to describe the correlation characteristics among bands, while the block-diagonal structure is measured to segment all bands into a series of subspace. After applying the spectral clustering algorithm, the optimal combination of band is finally selected. To verify the effectiveness and superiority of the proposed band selection method, experiments have been conducted on three widely used real-world hyperspectral data. The results have shown that the proposed method outperforms other methods in HSI classification application.
Keywords : Correlation Hyperspectral imaging Feature extraction Sparse matrices Optimization Matrix decomposition
Type de document :
Article dans une revue
IEEE Geoscience and Remote Sensing Letters, IEEE - Institute of Electrical and Electronics Engineers, 2017, 14 (11), pp.2062-2066. 〈10.1109/LGRS.2017.2751082〉
Liste complète des métadonnées
https://hal.archives-ouvertes.fr/hal-01681969
Contributeur : Lab Lissi <>
Soumis le : jeudi 11 janvier 2018 - 22:38:35
Dernière modification le : vendredi 15 février 2019 - 09:38:39

Identifiants

Collections

INSMI | TDS-MACS | UPEC-UPEM | LISSI

Citation

J. Wang, K. Zhang, P. Pei, K. Madani, C. Sabourin. Unsupervised Band Selection using Block Diagonal Sparsity for Hyperspectral Image Classification. IEEE Geoscience and Remote Sensing Letters, IEEE - Institute of Electrical and Electronics Engineers, 2017, 14 (11), pp.2062-2066. 〈10.1109/LGRS.2017.2751082〉. 〈hal-01681969〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

69

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD