联合多层次散射区域的SAR目标识别方法  

SAR Target Recognition Based on Joint Exploitation of Multi-level Scattering Areas

作　　者：王立梅[1] 李金凤[1] 张亚峰 WANG Li-mei;LI Jin-feng;ZHANG Ya-feng(Mudanjiang Normal College,College of Computer and Information Technology,Heilongjiang 157011)

机构地区：[1]牡丹江师范学院,黑龙江157011

出　　处：《中国电子科学研究院学报》2018年第6期690-694,共5页Journal of China Academy of Electronics and Information Technology

基　　金：黑龙江省教育厅科研项目(1353MSYYB006)

摘　　要：本文提出了联合多层次散射区域的合成孔径雷达(SAR)目标识别方法。该方法首先提取原始SAR图像的多层次散射区域,这些散射区域细致地描述了目标散射中心的分布规律和相对强弱。为了充分挖掘各层次散射区域对目标识别的鉴别力,利用联合稀疏表示分类器对多层次散射区域进行联合识别。联合稀疏表示可以有效利用不同层次散射区域的内在关联性,因此可以进一步提高目标识别的性能。采用MSTAR数据集进行了目标识别实验,验证了方法的有效性。This paper proposes a SAR (synthetic aperture radar)target recognition method based on joint sparse representation of multi-level scattering areas.The multi-level scattering areas are first extracted from the original SAR images,which describe the distribution and relative intensities of scattering centers.In order to exploit discriminability of individual scattering areas,the joint spare representation-based classification is employed to classify the multi-level scattering areas.The joint spare representation can effectively exploit the inner correlations among individual scattering areas thus improving the recognition performance.To validate the effeteness of the proposed method,experiments are conducted on public MSTAR (moving and stationary target acquisition and recognition)dataset.

关 键 词：合成孔径雷达 目标识别 散射区域 联合稀疏表示 

分 类 号：TP753[自动化与计算机技术—检测技术与自动化装置]