Kernel regression-based background predicting method for target detection in SAR image

Target detection with SAR image is one of important research topics in remote sensing. In this paper, a kernel regression-based predicting method is proposed for target detection in SAR image. Badly speckle noise and background clutter are two main factors which make the target detection with SAR image difficult. In the proposed method, the kernel regression on local image is used to exactly predict the background interferences and make Gaussian assumption in conventional detector better followed after kernel regression-based prediction and suppression of background clutter. Thus, final CFAR detection is performed on the background clutter-removed SAR image. Experiments conducted on real SAR image show that the proposed algorithm can effectively predict and suppress background clutters, and greatly improve the performance of the conventional CFAR detector.