Unsupervised Segmentation of Polarimetric Sar Data Using the Covariance Matrix

An unsupervised selection of polarimetric features useful for the segmentation and analysis of polarimetric Synthetic Aperture Radar (SAR) data is presented. The technique is based on multidimensional clustering of the parameters composing the polarimetric covariance matrix of the data. Clustering is performed on the logarithm of these quantities. Once the polarimetric cluster centers have been determined segmentation of the polarimetric data into regions is performed using a maximum likelihood polarimetric classifier. Segmentation maps are further improved using a Markov random field to describe the statistics of the regions and computing the maximum of the product of the local conditional densities. Examples with real polarimetric SAR imagery are given to illustrate the potentidl of this rncthod.