An Automatic Ship Detection Method for PolSAR Data Based on K-Wishart Distribution

For polarimetric synthetic aperture radar (PolSAR) data, abundant structure and textural information significantly enhance the ability of ship detection. This paper presents an automatic ship detection algorithm for PolSAR data, termed K-Wishart detector, which utilizes non-Gaussian K-Wishart classifier and incorporates the polarimetric SPAN parameter to identify the ships. The fundamental assumption is that the PolSAR data could be well characterized by the non-Gaussian K-Wishart distribution. The automatic ship detection scheme mainly consists of two steps. First, the PolSAR data are divided into different unlabeled clusters by the automatic non-GaussianK-Wishart classifier. Then, the SPAN information is used to extract ships among multiple unlabeled clusters considering the energy difference with ambient environment. Finally, the proposed method is validated using real measured NASA/JPL AIRSAR and UAVSAR datasets by comparing the performance with modified CFAR detector, SPAN Wishart (SPWH) detector, and Wishart detector. The comparison results show that the proposed algorithm could improve the ability of target detection while reduces the rate of false alarm and miss detections.