Robust Ship Detection in SAR Images from Complex Background

摘要

This paper proposes a novel method for ship detection in complex background from synthetic aperture radar images. It first implements a pixel-level land-sea segmentation with the aid of a global 250-meter water mask. Then, an efficient multi-scale constant false alarm rate detector with generalized Gamma distribution clutter model is designed to detect candidate targets in the sea. At last, Eigen-ellipse discrimination is designed to further exclude false alarm objects in nearshore and harbor area. Finally, experiments undertaken on actual ALOS-2 SAR data show the efficacy of the proposed approach in detecting nearshore ship targets in a complex coastal environment.