Improved Classification of SAR Sea Ice Imagery Based on Segmentation

This paper presents a method for semi-supervised classification of polarimetric synthetic aperture radar (PoISAR) sea ice data. The method consists of two steps. In the first stage, a markov random field on region adjacency graph is constructed on the initial watershed oversegmented result. While in the second stage, the Wishart distribution model and maximum a posterior (MAP) are applied as the criterion for obtaining the optimal classification. Good experimental results and less time-consuming are obtained when this method is applied to PoISAR data sets of sea ice in the Beaufort Sea acquired by the airborne AIRSAR.