Hyperspectral and multispectral image fusion based on optimal transport

Jamila Mifdal 1, 2, 3 Bartomeu Coll 1 Nicolas Courty 2 Jacques Froment 3 Béatrice Vedel 3
2 OBELIX - Environment observation with complex imagery
UBS - Université de Bretagne Sud, IRISA-D5 - SIGNAUX ET IMAGES NUMÉRIQUES, ROBOTIQUE
3 LMBA_UBS
LMBA - Laboratoire de Mathématiques de Bretagne Atlantique
Abstract : In this work we propose a method for the fusion of hyperspectral (HS) and multispectral (MS) satellite images. The aim of the fusion process is to merge the spectral quality of the HS images with the better spatial resolution of the MS images. The final result is an image having both high spectral and spatial resolution. In order to perform the fusion task, we suggest an approach based on optimal transport theory that highlights the idea of energy transfer from the starting images HS and MS to the resulting final image. In this sense, the map transport can be thought as the transfer of characteristics of one image to another.
Type de document :
Poster
Workshop SIGMA'2016 : SIGNAL, IMAGE, GEOMETRY, MODELLING, APPROXIMATION, Oct 2016, Marseille, France
Liste complète des métadonnées

https://hal.archives-ouvertes.fr/hal-01438955
Contributeur : Jacques Froment <>
Soumis le : mercredi 18 janvier 2017 - 11:25:36
Dernière modification le : vendredi 17 février 2017 - 16:10:59

Identifiants

  • HAL Id : hal-01438955, version 1

Citation

Jamila Mifdal, Bartomeu Coll, Nicolas Courty, Jacques Froment, Béatrice Vedel. Hyperspectral and multispectral image fusion based on optimal transport. Workshop SIGMA'2016 : SIGNAL, IMAGE, GEOMETRY, MODELLING, APPROXIMATION, Oct 2016, Marseille, France. <hal-01438955>

Partager

Métriques

Consultations de la notice

284