SAR图像中目标的检测和识别研究进展  

Study evolution of detection and recognition on target in SAR image

作　　者：杨桄[1] 陈克雄[1] 周脉鱼[1] 徐忠林[1] 王宗明[2] 

机构地区：[1]空军航空大学特种专业系,长春130022 [2]中科院东北地理与农业生态研究所,长春130012

出　　处：《地球物理学进展》2007年第2期617-621,共5页Progress in Geophysics

基　　金：国家自然科学基金(40401003);中科院知识创新工程重要方向项目(KZCX3-SW-356)联合资助

摘　　要：SAR图像以其独有的全天时、全天候观测能力、形态探测能力和对地表的穿透性,在地学应用中比光学遥感更具优势.本文结合SAR图像检测和识别应用技术的发展过程,综述了SAR图像在噪声抑制、线状特征和纹理特征提取、图像分割和目标检测等方面的研究进展;介绍SAR图像检测和识别的最新研究情况;最后分析当今国内外SAR图像检测和识别所面临的问题,并对未来发展进行展望.SAR remote-sensing instruments with the capabilities of all weather and all day/night, penetration, and terrain detection, provide unique geological environmental information, quite different from, yet complementary to passive systems such as visible remote sensing. Automatic Target Recognition in SAR imagery becomes popular in recent years. The typical Automatic Target Recognition system consists of three stages： detection, discrimination and classification. Detection, whose role is to find regions in SAR imagery that contains potential targets, will inevitably produce false alarms. Combining detection and identify of SAR imagery this paper summarized study evolution of SAR image on demising, characters of line and texture extraction, image segmentation and target detection; Introduced up to date study progress; ultimately analyzed program about detection and identify of SAR image in inland and overseas thing and prospected development in future.

关 键 词：合成孔径雷达图像 图像去噪 舰船检测 图像分割 目标识别 

分 类 号：P627[天文地球—地质矿产勘探]