A Curvature-Based Saliency Method for Ship Detection in SAR Images

Abstract

According to the theory and interpretation method of information geometry, this work presents a novel curvature-based saliency method for ship detection in synthetic aperture radar (SAR) images. First, the nonlinear anisotropic diffusive process has been adopted to eliminate clutter while preserving the local ship target structure in SAR images. Then, a novel curvature-based saliency method for super-pixels in the filtered image is presented, which is used to exploit the microstructure feature of statistical manifold. Finally, a statistical classification method is used to realize the location of targets. The experimental results on real SAR images show that the proposed method can achieve good performance.