Exploiting spatial correlation features for SAR image analysis

Spatial information is of great importance in Synthetic Aperture Radar (SAR ) image analysis and recently, many methods have been developed that take t his feature into account [38]. This paper deals with a supervised approach to SAR image classification that exploits spatial features within a hierarc hical classification framework. In contrast to the classical approach, which makes the hypothesis about sam ple data independence, in the proposed method, the spatial dependence of ne ighboring pixels is taken into account to estimate relatively simple statis tical features such as sample spatial mean and sample spatial variance, thu s allowing contextual information to he easily handled. The Bhattacharyya distribution distance is used during the training phase, and the generated tree is applied during the test phase. After this, both p hases are based on the proposed features. As a result, second-order statist ics play a major role in the present classification problem, Experimental results on different SAR data sets are reported. It is shown t hat the accuracy of the proposed method is better than that of the ML class ifier and that the new method is also computationally more convenient.