Spectral-Spatial Classification of Hyperspectral Images Using Hierarchical Optimization

Abstract : A new spectral-spatial method for hyperspectral data classification is proposed. For a given hyperspectral image, probabilistic pixelwise classification is first applied. Then, hierarchical step-wise optimization algorithm is performed, by iteratively merging neighboring regions with the smallest Dissimilarity Criterion (DC) and recomputing class labels for new regions. The DC is computed by comparing region mean vectors, class labels and a number of pixels in the two regions under consideration. The algorithm is converged when all the pixels get involved in the region merging procedure. Experimental results are presented on two hyperspectral remote sensing images acquired by the AVIRIS and ROSIS sensors. The proposed approach improves classification accuracies and provides maps with more homogeneous regions, when compared to previously proposed classification techniques.
Type de document :
Communication dans un congrès
IEEE Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, Jun 2011, Lisbon, Portugal. pp.1-4, 2011
Liste complète des métadonnées

Littérature citée [10 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-00728881
Contributeur : Yuliya Tarabalka <>
Soumis le : jeudi 6 septembre 2012 - 19:49:57
Dernière modification le : vendredi 7 septembre 2012 - 11:23:38
Document(s) archivé(s) le : vendredi 7 décembre 2012 - 03:43:54

Fichier

2011_WHISPERS_Tarabalka.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00728881, version 1

Citation

Yuliya Tarabalka, James Tilton. Spectral-Spatial Classification of Hyperspectral Images Using Hierarchical Optimization. IEEE Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, Jun 2011, Lisbon, Portugal. pp.1-4, 2011. 〈hal-00728881〉

Partager

Métriques

Consultations de la notice

156

Téléchargements de fichiers

73