基于多特征-多表示融合的SAR图像目标识别  

SAR Target Recognition Based on Multi-feature Multiple Representation Classifier Fusion

作　　者：张新征[1] 谭志颖 王亦坚 Zhang Xinzheng;Tan Zhiying;Wang Yijian(College of Communication Engineering, Chongqing University, Chongqing 400044, Chin)

机构地区：[1]重庆大学通信工程学院,重庆400044

出　　处：《雷达学报（中英文）》2017年第5期492-502,共11页Journal of Radars

基　　金：国家自然科学基金(61301224)~~

摘　　要：针对合成孔径雷达(Synthetic Aperture Radar,SAR)图像目标识别问题,该文提出了一种基于多特征-多表示学习分类器融合的识别算法。首先,该算法提取了SAR图像3种特征,包括主成分(Principle Component Analysis,PCA)特征,小波变换特征和2维切片Zernike矩(2-Dimension Slice Zernike Moments,2DSZM)特征。然后,将测试样本的3类特征分别输入稀疏表示分类器和协同表示分类器进行预分类,得到6个预测标签。对6个预测标签进行分类器融合,得到最终的识别决策。实验中研宄了3种不同的分类器融合算法,实验结果表明利用贝叶斯决策融合得到了最佳的识别性能。基于多特征-多表示学习分类器融合的方法集成了多特征的鉴别能力,也融合了稀疏和协同表示的分类性能,实现优势互补,有效提高了识别精度。基于Moving and Stationary TargetAcquisition and Recognition(MSTAR)公开发布的SAR目标数据库的实验验证了该方法的有效性。In this paper, we present a Synthetic Aperture Radar（SAR） image target recognition algorithm based on multi-feature multiple representation learning classifier fusion. First, it extracts three features from the SAR images, namely principal component analysis, wavelet transform, and Two-Dimensional Slice ZernikeMoments（2 DSZM） features. Second, we harness the sparse representation classifier and the cooperative representation classifier with the above-mentioned features to get six predictive labels. Finally, we adopt classifier fusion to obtain the final recognition decision. We researched three different classifier fusion algorithmsin our experiments, and the results demonstrate th a t using Bayesian decision fusion gives thebest recognition performance. The method based on multi-feature multiple representation learning classifier fusion integrates the discrim ination of m ulti-features and combines the sparse and cooperative representation classificationperformance to gain complementary advantages and to improve recognition accuracy. The experiments are based on th e Moving and Stationary Target Acquisition and Recognition（MSTAR） database,and they demonstrate the effectiveness of the proposed approach.

关 键 词：合成孔径雷达 目标识别 稀疏表示 协同表示 决策融合 

分 类 号：TN959[电子电信—信号与信息处理]