A superpixel structure based visual attention target detection algorithm for SAR image
shuo liu, Wentao Yu, Mohan Liang · Seventh Asia Pacific Conference on Optics Manufacture and 2021 International Forum of Young Scientists on Advanced Optical Manufacturing (APCOM and YSAOM 2021) · 2022
In this paper, a superpixel structure based visual attention target detection algorithm for synthetic aperture radar (SAR) image is proposed. The proposed algorithm uses visual attention to locate the region of interest (ROI) area, and then uses the corner detection to extract the structural features of the superpixels. Finally, the outlier detection algorithm is used to find the superpixel where the target is located. The proposed algorithm uses superpixel combined with visual attention. Moreover, the proposed algorithm uses superpixel structure information to detect the target. Due to the difference in the superpixel structure of the target and the background, the superpixel structure information can be used to distinguish the target and the background in the SAR image of the complex scene. Experimental results show that the proposed algorithm can effectively complete SAR image target detection in complex scenes.