HAL: inria-00516333, version 1

DOI: 10.1117/12.865023

See detailed view

BibTeX,EndNote,... BibTeX - EndNote - TEI - RefWorks -

SPIE Remote Sensing, Toulouse : France (2010)

Classification of very high resolution SAR images of urban areas by dictionary-based mixture models, copulas and Markov random fields using textural features

Aurélie Voisin (  Author to contact preferably ) 1, Gabriele Moser 2, Vladimir Krylov 1, 3, Sebastiano B. Serpico 2, Josiane Zerubia 1

(2010)

This paper addresses the problem of the classification of very high resolution (VHR) SAR amplitude images of urban areas. The proposed supervised method combines a finite mixture technique to estimate class-conditional probability density functions, Bayesian classification, and Markov random fields (MRFs). Textural features, such as those extracted by the greylevel co-occurrency method, are also integrated in the technique, as they allow to improve the discrimination of urban areas. Copulas are applied to estimate bivariate joint class-conditional statistics, merging the marginal distributions of both textural and SAR amplitude features. The resulting joint distribution estimates are plugged into a hidden MRF model, endowed with a modified Metropolis dynamics scheme for energy minimization. Experimental results with COSMO-SkyMed and TerraSAR-X images point out the accuracy of the proposed method, also as compared with previous contextual classifiers.

1:	ARIANA (INRIA Sophia Antipolis / Laboratoire I3S)
	INRIA – Université Nice Sophia Antipolis [UNS] – CNRS : UMR7271
2:	Department of Biophysical and Electronic Engineering [Genoa] (DIBE)
	University of Genoa
3:	Faculty of Computational Mathematics and Cybernetics (Lomonosov Moscow State University)
	Moscow State University

Domain

:

Computer Science/Signal and Image Processing Mathematics/Statistics Statistics/Statistics Theory Engineering Sciences/Signal and Image processing

inria-00516333, version 1

http://hal.inria.fr/inria-00516333

oai:hal.inria.fr:inria-00516333

From: Aurélie Voisin <>

Submitted on: Thursday, 9 September 2010 11:50:44

Updated on: Monday, 19 November 2012 10:35:19