Clustering of fully polarimetric SAR data using finite G(p)(0) mixture model and SEM algorithm

Autor(es)

Horta, Michelle M. ; Mascarenhas, Nelson D. A. ; Frery, Alejandro C. ; Levada, Alexandre L. M. ; Rozinaj, G ; Cepko, J ; Truchly, P ; Vrabec, J ; Vojtko, J

• Tipo de documento: Artigo Científico
• Fonte: PROCEEDINGS OF IWSSIP 2008: 15TH INTERNATIONAL CONFERENCE ON SYSTEMS, SIGNALS AND IMAGE PROCESSING; v. N/A, p. 2-pg., 2008-01-01.

Resumo

This paper presents a novel method for clustering multilook polarimetric SAR images by combining the stochastic expectation-maximization (SEM) algorithm with the mixture of G(p)(0) distributions, using the method of moments for parameter estimation. The pixel values of multilook SAR data are complex covariance matrices, and they are described by mixtures of G(p)(0) laws. This distribution can describe different type of targets; like urban areas, forest and pasture. The proposed clustering technique can be applied to unsupervised classification and segmentation process. Experiments with real image data provide good results. http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=4604372 (AU)

• Processo FAPESP: 04/09334-0 - Modelos de mistura de distribuicoes na segmentacao de imagens. sar polarimetricas multilook
• Beneficiário: Michelle Matos Horta Tenca
• Modalidade de apoio: Bolsas no Brasil - Doutorado