Accéder directement au contenu Accéder directement à la navigation
Communication dans un congrès

Optimized Class-Separability in Hyperspectral Images

Abstract : Image visualization techniques are mostly based on three bands as RGB color composite channels for human eye to characterize the scene. This, however, is not effective in case of hyper-spectral images (HSI) because they contain dozens of informative spectral bands. To eliminate redundancy of spectral information among these bands, dimensionality reduction (DR) is applied while at the same trying to retain maximum information. In this paper, we propose a new method of information-preserved hyper-spectral satellite image visualization that is based on fusion of unsupervised band selection techniques and color matching function (CMF) stretching. The results show consistent, edge-preserved and pre-attentive feature less images with high class separability. Different visualization techniques are compared to demonstrate the effectiveness of our scheme that can prompt an important advancement in the field.
Liste complète des métadonnées

https://hal-univ-bourgogne.archives-ouvertes.fr/hal-01497281
Contributeur : Le2i - Université de Bourgogne <>
Soumis le : mardi 28 mars 2017 - 14:54:04
Dernière modification le : vendredi 17 juillet 2020 - 14:54:11

Lien texte intégral

Identifiants

Citation

Sumera Sattar,, Haris Ahmad Khan,, Khurram Khurshid,. Optimized Class-Separability in Hyperspectral Images. 36th IEEE International Geoscience and Remote Sensing Symposium (IGARSS), Jul 2016, Beijing, China. pp.2711-2714, ⟨10.1109/IGARSS.2016.7729700⟩. ⟨hal-01497281⟩

Partager

Métriques

Consultations de la notice

290