Hyperspectral unmixing with material variability using social sparsity - Archive ouverte HAL
Communication Dans Un Congrès Année : 2016

Hyperspectral unmixing with material variability using social sparsity

Lucas Drumetz
Jocelyn Chanussot
Andrea Bertozzi
  • Fonction : Auteur
  • PersonId : 866731

Résumé

We apply social-norms for the first time to the problem of hyperspectral unmixing while modeling spectral variability. These norms are built with inter-group penalties which are combined in a global intra-group penalization that can enforce selection of entire endmember bundles; this results in the selection of a few representative materials even in the presence of large endmembers bundles capturing each material's variability. We demonstrate improvements quantitatively on synthetic data and qualitatively on real data for three cases of social norms: group, elitist, and a fractional social norm, respectively. We find that the greatest improvements arise from using either the group or fractional flavor.
Fichier principal
Vignette du fichier
meyer_ICIP2016.pdf (445.44 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01364247 , version 1 (12-09-2016)

Identifiants

Citer

Travis Meyer, Lucas Drumetz, Jocelyn Chanussot, Andrea Bertozzi, Christian Jutten. Hyperspectral unmixing with material variability using social sparsity. ICIP 2016 - 23rd IEEE International Conference on Image Processing, IEEE, Sep 2016, Phoenix, United States. ⟨10.1109/ICIP.2016.7532746⟩. ⟨hal-01364247⟩
430 Consultations
232 Téléchargements

Altmetric

Partager

More