Morphological Band Selection for Hyperspectral Imagery

J. Wang X. Wang K. Zhang K. Madani 1 C. Sabourin 1
1 SYNAPSE
LISSI - Laboratoire Images, Signaux et Systèmes Intelligents
Abstract : In this letter, a novel morphological band selection method is proposed to obtain the most representative bands from hyperspectral image (HSI) in an unsupervised manner. In order to sufficiently process the HSI, we propose to use only a small set of data instead of using the original full data. For the obtained clusters, the differences of spectral response curves are applied to measure the local discrimination capability of bands, of which the local maximum value point is yielded based on the morphological processing. To verify the performance of the proposed method, the robustness of the parameters has been evaluated, while the effectiveness and superiority have been tested on three popular hyperspectral data sets. The experiment results have shown that the proposed method outperforms other methods.
Type de document :
Article dans une revue
IEEE Geoscience and Remote Sensing Letters, IEEE - Institute of Electrical and Electronics Engineers, 2018, 15 (8), pp.1259-1263. 〈10.1109/LGRS.2018.2830795〉
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01865219
Contributeur : Lab Lissi <>
Soumis le : vendredi 31 août 2018 - 10:37:01
Dernière modification le : mardi 12 février 2019 - 15:29:08

Identifiants

Collections

Citation

J. Wang, X. Wang, K. Zhang, K. Madani, C. Sabourin. Morphological Band Selection for Hyperspectral Imagery. IEEE Geoscience and Remote Sensing Letters, IEEE - Institute of Electrical and Electronics Engineers, 2018, 15 (8), pp.1259-1263. 〈10.1109/LGRS.2018.2830795〉. 〈hal-01865219〉

Partager

Métriques

Consultations de la notice

34