High resolution SAR-image classification - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Rapport (Rapport De Recherche) Année : 2009

High resolution SAR-image classification

Résumé

In this report we propose a novel classification algorithm for high and very high resolution synthetic aperture radar (SAR) amplitude images that combines the Markov random field approach to Bayesian image classification and a finite mixture technique for probability density function estimation. The finite mixture modeling is done by dictionary-based stochastic expectation maximization amplitude histogram estimation approach. The developed semiautomatic algorithm is extended to an important case of multi-polarized SAR by modeling the joint distributions of channels via copulas. The accuracy of the proposed algorithm is validated for the application of wet soil classification on several high resolution SAR images acquired by TerraSAR-X and COSMO-SkyMed.
Fichier principal
Vignette du fichier
RR-7108.pdf (1.09 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

inria-00433036 , version 1 (11-12-2009)
inria-00433036 , version 2 (13-12-2009)
inria-00433036 , version 3 (18-01-2010)

Identifiants

  • HAL Id : inria-00433036 , version 2

Citer

Vladimir Krylov, Josiane Zerubia. High resolution SAR-image classification. [Research Report] RR-7108, 2009. ⟨inria-00433036v2⟩

Collections

INRIA-RRRT
441 Consultations
238 Téléchargements

Partager

Gmail Facebook X LinkedIn More