一种联合阴影和目标区域图像的SAR目标识别方法

发布时间：2019-03-06 08:04

【摘要】：地面目标的SAR图像中除了包含目标散射回波形成的区域,还包括由目标遮挡地面形成的阴影区域。但是由于这两种区域中的图像特性不相同,所以传统的SAR图像自动目标识别主要利用目标区域信息进行目标识别,或者单独使用阴影区域进行识别。该文提出一种阴影区域与目标区域图像联合的稀疏表示模型。通过使用l1\l2范数最小化方法求解该模型得到联合的稀疏表示,然后根据联合重构误差最小准则进行SAR图像目标识别。在运动和静止目标获取与识别(MSTAR)数据集上的识别实验结果表明,通过联合稀疏表示模型可以有效地将目标区域与阴影区域信息进行融合,相对于采用单独区域图像的稀疏表示识别方法性能更好。
[Abstract]:The SAR image of the ground target includes not only the area formed by the scattering echo of the target, but also the shaded area formed by the target occluding the ground. However, because the image characteristics of the two regions are different, the traditional SAR image automatic target recognition mainly uses the target region information to recognize the target, or uses the shadow region to recognize the target separately. In this paper, a sparse representation model of image association between shaded region and target region is proposed. The joint sparse representation is obtained by solving the model by using L1\ L2 norm minimization method, and then the target recognition of SAR image is carried out according to the minimum error criterion of joint reconstruction. The experimental results on moving and stationary target acquisition and recognition (MSTAR) data sets show that the joint sparse representation model can effectively fuse the information of target region and shaded area. The performance of the sparse representation recognition method is better than that of the sparse representation method based on a single region image.
【作者单位】：西安电子科技大学雷达信号处理国家重点实验室;
【基金】：国家自然科学基金(61201292,61322103,61372132) 全国优秀博士学位论文作者专项资金(FANEDD-201156) 国家部委基金中央高校基本科研业务费专项资金资助课题
【分类号】：TN957.52

【参考文献】