Improved Ship Detection for High Resolution SAR Images Based on Kernel Density Estimation

Ship detection is an important application of global monitoring of ocean environment and maritime traffic. Synthetic aperture radar (SAR) has the good ability to detect ships at high resolution over wide swath and in all weather conditions. This paper proposes an improved fast CFAR detection for high resolution SAR image based on K-distribution and Kernel Density Estimation processing. One scene of COSMO-SkyMed SAR image is adopted for investigating the proposed algorithm. Experiment results illustrate that the method can achieve good performance.