Inshore Ship Detection with High-Resolution SAR Data Using Salience Map and Kernel Density

Ship detection is a key topic for surveillance of coastal areas. In this paper, a new method based on salience map and kernel density is proposed to detect inshore ships with high-resolution Synthetic Aperture Radar (SAR) images. Firstly, two-dimensional wavelet transform is employed to extract the salience map of SAR image, and the difference between targets and background is effectively enhanced. Secondly with the Constant False Alarm Rate (CFAR) detector, we achieve the suspected ship targets. Finally, combining geometric features and kernel density, the false alarm targets are removed. The proposed method can effectively detect the inshore ship targets with the high correct detection rate and quality factor. Experiments on real high-resolution SAR images demonstrate the performance of the proposed method.