The Segmentation And Target Recognition Of SAR Image

Automatic Target Recognition is a hot topic in the wordwide martial field. With the continuing improvement of modern Radar system,Radar Automatic Target Recognition has come into being and developed,and many new methods were proposed for the increase of the Radar range resolution.Meanwhile, the rapid development of digital technology let ATR come into projects.SAR(Synthetic aperture radar) plays an key role in modern scout errand because of its all-weather,wide,strong penetrable ability and surplying detailed ground mapping material and images in atrocious weather with high resolution.SAR ATR is crucial to the success of battlefield awareness and has become a very hot research topic. In recent years, radar target recognition has made steady progress in many fields,including feature extraction, target classification and recognition. Some ATR systems have been built and have been successfully used in the areas like ground detecting and precision guidance in spaceborne/airborne SAR.This thesis first reviews the ATR fundamentals and the state-of-the-art development of SAR ATR techniques. Main contributions include:First,a SAR image filtering method based median filtering is proposed through traditional fitering valid methods; Secondly,a simple and effective SAR image segmentation method is proposed and three different methods-fixed threshold,local threshold and adaptive threshold are compared,at the same time,a morphologic filter is applied to keeps the target's edge information and removes isolated background image;Thirdly,Two different SAR image feature extraction methods are proposed and their original dimension is descending;Finally,several classic SAR ATR methods are introduced.its efficiency is proved by a lot of valid methods based on MSTAR data surplied by DARPA.