HYPERSPECTRAL AND MULTISPECTRAL WASSERSTEIN BARYCENTER FOR IMAGE FUSION

Jamila Mifdal (1) , Bartomeu Coll (1) , Nicolas Courty (2, 3) , Jacques Froment , Béatrice Vedel (4)

1 Departament de Ciències Matemàtiques et Informàtica
2 VALORIA - Laboratoire de Recherche en Informatique et ses Applications de Vannes et Lorient
3 OBELIX - Environment observation with complex imagery
4 LMBA - Laboratoire de Mathématiques de Bretagne Atlantique

The fusion of hyperspectral and multispectral images is a crucial task nowadays for it allows the extraction of relevant information from the fused image. Fusion consists of the combination of the spectral information of the hypespectral image (h) and the spatial information of the multispectral image (m). The fused image (f) has both good spatial and spectral information. In this paper we suggest a new hyperspectral and multispectral image (h-m) fusion approach based on Optimal Transport (OT) which highlights the idea of energy transfer from the starting images m and h to the resulting image f. The simulations show that the suggested method is effective and compares competitively with other state-of-the-art methods .

Mots clés: Optimal Transport; Wasser- stein Barycenter; Image Fusion

Domaines: Machine Learning [stat.ML]; Traitement du signal et de l'image [eess.SP]

Jamila Mifdal, Bartomeu Coll, Nicolas Courty, Jacques Froment, Béatrice Vedel. HYPERSPECTRAL AND MULTISPECTRAL WASSERSTEIN BARYCENTER FOR IMAGE FUSION. IGARSS 2017, Jul 2017, Houston, United States. ⟨hal-01620601⟩