Hyperspectral image segmentation: The butterfly approach

Gorretta Nathalie, Roger Jean-Michel, Rabatel Gilles, Bellon-Maurel Véronique, Fiorio Christophe, Lelong Camille. 2009. Hyperspectral image segmentation: The butterfly approach. In : First Workshop on hyperspectral image and signal processing : evolutions in remote sensing, Grenoble, France, 26-28 august 2009. IEEE-GRS, Gipsa-Lab, INP-Grenoble. s.l. : s.n., 4 p. Workshop on hyperspectral image and signal processing : evolutions in remote sensing. 1, Grenoble, France, 26 Août 2009/28 Août 2009.

Résumé : Few methods are proposed in the litterature for coupling the spectral and the spatial dimension available on hyperspectral images. This paper proposes a generic segmentation scheme named butterfly based on an iterative process and a cross analysis of spectral and spatial information. Indeed, spatial and spatial structures are extracted in spatial and spectral space respectively both taking into account the other one. To apply this layout on hyperspectral imgages, we focus particulary on spatial and spectral structures i.e. topologic concepts and latent variable for the spatial and the spectral space respectively. Moreover, a cooperation scheme with these structures is proposed. Finally, results obtained on real hyperspectral images using this specific implementation of the butterfly approach are presented and discussed.

Classification Agris : U10 - Informatique, mathématiques et statistiques
U30 - Méthodes de recherche

Auteurs et affiliations

• Gorretta Nathalie, CEMAGREF (FRA)
• Roger Jean-Michel, CEMAGREF (FRA)
• Rabatel Gilles, CEMAGREF (FRA)
• Bellon-Maurel Véronique, CEMAGREF (FRA)
• Fiorio Christophe, LIRMM (FRA)
• Lelong Camille, CIRAD-ES-UMR TETIS (FRA) ORCID: 0000-0002-4850-1010

Source : Cirad - Agritrop (https://agritrop.cirad.fr/554218/)

Métriques

[ Page générée et mise en cache le 2024-03-28 ]