Ship Detection in Polarimetric SAR Based on Support Vector Machine

In this study, we propose a Support Vector Machine (SVM) based method for ship detection in polarimetric SAR (POLSAR). Because of similarities of ship and man-made structures on land in scattering mechanisms, land and sea are first segmented by SVM according to polarimetric features and texture features; The SVM-based Recursive Feature Elimination (RFE-SVM) approach is adopted to improve the performance of the segmentation algorithm. Then ship targets are extracted from sea by SVM classifier; Threshold-based rules and SVM-based rules are established for discriminating ship from non-ship target at last. The experiments are carried out on POLSAR data from Radarsat-2. For the available SAR images, the average accuracy of ship detection is over 95%.