Nonlinear unmixing of vegetated areas: a model comparison based on simulated and real hyperspectral data

Abstract : When analyzing remote sensing hyperspectral images, numerous works dealing with spectral unmixing assume the pixels result from linear combinations of the endmember signatures. However, this assumption cannot be fulfilled, in particular when considering images acquired over vegetated areas. As a consequence, several nonlinear mixing models have been recently derived to take various nonlinear effects into account when unmixing hyperspectral data. Unfortunately, these models have been empirically proposed and without thorough validation. This paper attempts to fill this gap by taking advantage of two sets of real and physical-based simulated data. The accuracy of various linear and nonlinear models and the corresponding unmixing algorithms is evaluated with respect to their ability of fitting the sensed pixels and of providing accurate estimates of the abundances.
Type de document :
Communication dans un congrès
IEEE Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing - WHISPERS 2014, Jun 2014, Lausanne, Switzerland. pp. 1-4, 2014
Liste complète des métadonnées

Littérature citée [20 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-01136112
Contributeur : Open Archive Toulouse Archive Ouverte (oatao) <>
Soumis le : jeudi 26 mars 2015 - 15:20:52
Dernière modification le : mercredi 12 septembre 2018 - 17:46:02
Document(s) archivé(s) le : jeudi 2 juillet 2015 - 08:05:29

Fichier

Dobigeon_13066.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01136112, version 1
  • OATAO : 13066

Collections

Citation

Nicolas Dobigeon, Laurent Tits, Ben Somers, Yoann Altmann, Pol Coppin. Nonlinear unmixing of vegetated areas: a model comparison based on simulated and real hyperspectral data. IEEE Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing - WHISPERS 2014, Jun 2014, Lausanne, Switzerland. pp. 1-4, 2014. 〈hal-01136112〉

Partager

Métriques

Consultations de la notice

164

Téléchargements de fichiers

65