Man-Made Target Detection of SAR Images
SAR图像人造目标检测研究

In the process of SAR (Synthetic Aperture Radar) ATR (Automatic Target Recognition), man-made target detection is very important. In this paper, analyzing the characteristics of SAR images, a new method is proposed to detect man-made targets in SAR images. Firstly, the image is smoothed with the adaptive wavelet filter; the multiple speckles are removed while the edge property of SAR images is sustained. It made the detection easier. Then, the images is segmented with the 2-D C-partition fussy entropy method based on adaptive genetic algorithm. Test results show that the algorithm can detect man-made targets effectively.