Saliency-based ship detection in SAR images

Abstract

Synthetic aperture radar (SAR) on a satellite or a plane is a useful tool for ship target detection because it can work in all weather conditions, day and night. However, speckles of sea clutters and heterogeneous sea regions in SAR images will pose challenges on a task of automatic ship detection. In this paper, we propose a visual saliency based method for ship detection in SAR images. The proposed method is automatic, simple and fast in computation, and has the ability to detect ship targets in SAR data. Experiments conducted over a set of real SAR data show that the proposed method is capable of detecting ships accurately and robust against speckles of sea clutters and heterogeneous sea regions.