Correlation based joint CFAR ship detector in SAR images

摘要

The characteristic difference between targets and clutter is analyzed. Considering the ship target's gray intensity distribution and its shape difference compared to the clutter, in this paper, a new algorithm is proposed based on correlation. The algorithm utilizes the strong gray intensity correlation in the ship target, and the joint gray intensity distribution (JPDF) using 2D joint Gaussian distribution of neighboring pixels in the clutter is modeled, which realizes joint CFAR detection. Using this algorithm, the false alarms caused by speckle and local background non-homogeneity can be greatly reduced.