Ship recognition in high resolution SAR imagery based on feature selection

Ship detection and recognition are crucial components of SAR ocean monitoring applications. In the literature, various features have been proposed for ship pattern analysis. However, operators often face the dilemma that they have little knowledge on feature selection. In this paper, we first propose a novel RCS density encoding feature for ship description. A novel two-stage feature selection approach is then presented. Finally, ship recognition experiment conducted with high resolution SAR imagery reveals a percent of correct classification as high as 91.54%.