基于改进的稀疏保持投影的SAR目标特征提取与识别

韩萍; 王欢

doi:10.12000/JR15068

基于改进的稀疏保持投影的SAR目标特征提取与识别

DOI: 10.12000/JR15068

韩萍^,,
王欢

1.
(中国民航大学智能信号与图像处理天津市重点实验室天津 300300)
2.
(江西省机场集团公司九江机场分公司九江 332000)

基金项目:

国家自然科学基金(61571442, 61471365),国家自然科学基金重点项目(61231017),中央高校基金(3122014C004)

详细信息

作者简介:
韩萍(1966–),女,天津人,教授,硕士生导师,中国民航大学智能信号与图像处理天津市重点实验室,研究方向为图像处理与模式识别、SAR目标检测与识别等。E-mail:hanpingcauc@163.com;王欢(1990–),女,安徽安庆人,硕士生,江西省机场集团公司九江机场分公司,研究方向为合成孔径雷达目标识别。E-mail:tianjinwanghuan@126.com

通讯作者:
韩萍hanpingcauc@163.com

计量
- 文章访问数: 2311
- HTML全文浏览量: 415
- PDF下载量: 1509
- 被引次数: 0
出版历程
- 收稿日期: 2015-05-28
- 修回日期: 2015-09-16
- 网络出版日期: 2015-12-28

Synthetic Aperture Radar Target Feature Extraction and Recognition Based on Improved Sparsity Preserving Projections

HAN Ping^,,
WANG Huan

1.
(Tianjin Key Laboratory for Advanced Signal Processing, Civil Aviation University of China, Tianjin 300300, China)
2.
(Jiujiang Airport Branch, Jiangxi Airports Group Company, Jiujiang 332000, China)

Funds:

The National Natural Science Foundation of China (61571442, 61471365), The State Key Program of National Natural Science Foundation of China (61231017), The Fundamental Research Funds for the Central Universities (3122014C004)

摘要

摘要: 提出了一种改进的稀疏保持投影(Sparsity Preserving Projections, SPP)特征提取方法。该方法将SPP特征提取与局部保持投影(Locality Preserving Projection, LPP)特征提取思想相结合,构造新的目标函数求解投影向量,保证了投影空间内样本的稀疏重构误差达到最小的同时使同类样本间距最小。利用美国运动和静止目标获取与识别(Moving and Stationary Target Acquisition and Recognition, MSTAR)实测SAR数据进行实验,实验结果表明在不利用目标成像方位信息情况下平均识别率最高可达97.81%,明显地提高了目标的识别结果,是一种有效的SAR目标识别方法。
- 合成孔径雷达 /
- 自动目标识别 /
- 稀疏保持投影 /
- 特征提取
Abstract: We have proposed an improved Sparsity Preserving Projection (SPP) method to implement target feature extraction. It combines the SPP feature extraction using the idea of the Locality Preserving Projection (LPP) scheme to build a new objective function, which can not only maintain the relationship of sparse reconstruction between the samples but also minimize the distance between similar sample types in the projection space. Experimental results with Moving and Stationary Target Acquisition and Recognition (MSTAR) Synthetic Aperture Radar (SAR) data sets show that the average recognition rate using the proposed method is up to 97.81% without knowing the target to be azimuth, which can improve the target recognition result even further for obvious reasons. The proposed method is an effective one for SAR target recognition.
- Synthetic Aperture Radar (SAR) /
- Automatic target recognition /
- Sparsity Preserving Projections (SPP) /
- Feature extraction

HTML全文

参考文献(15)

[1]	Alpert B K. A class of bases in L2 for sparse representation of integral operators[J]. SIAM Journal on Mathematical Analysis, 1993, 24(1): 246-262.
[2]	Olshausen B A, Sallee P, and Lewicki M S. Learning Sparse Image Codes Using a Wavlet Pyramid Architecture[C]. Advances in Neural Information Processing Systems, 2001: 887-893.
[3]	邓承志, 曹汉强. 多尺度脊波字典的构造及其在图像编码中的应用[J]. 中国图象图形学报, 2009, 14(7): 1273-1278.DENG Chengzhi and CAO Hanqiang. Construction of multiscale ridgelet dictionary and its application for image coding[J]. Journal of Image and Graphics, 2009, 14(7): 1273-1278.
[4]	LI S T, YIN H T, and FANG L Y. Group sparse representation with dictionary learning for medical image denoising and fusion[J]. IEEE Transactions on Biomedical Engineering, 2012, 59(12): 3450-3459.
[5]	马路, 邓承志, 汪胜前, 等. 特征保留的稀疏表示图像去噪[J]. 计算机应用, 2013, 33(5): 1416-1419.MA Lu, DENG Chengzhi, WANG Shengqian, et al. Feature-retained image de-noising via sparse representation[J]. Journal of Computer Applications, 2013, 33(5): 1416-1419.
[6]	Wright J, Yang A Y, Ganesh A, et al.. Robust face recognition via sparse representation[J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2009, 31(2): 210-227.
[7]	胡正平, 赵淑欢. 分辨性分解块稀疏表示遮挡人脸识别算法[J]. 信号处理, 2014, 30(2): 214-220.HU Zhengping and ZHAO Shuhuan. Discriminative decomposition structure sparse representation for face recognition with occlusion[J]. Journal of Signal Processing, 2014, 30(2): 214-220.
[8]	刘中杰, 庄丽葵, 曹云峰, 等. 基于主元分析和稀疏表示的SAR图像目标识别[J]. 系统工程与电子技术, 2013, 35(2): 282-286.LIU Zhongjie, ZHUANG Likui, CAO Yunfeng, et al. Target recognition of SAR images using principal component analysis and sparse representation[J]. Systems Engineering and Electronics, 2013, 35(2): 282-286.
[9]	王燕霞, 张弓. 基于特征参数稀疏表示的SAR图像目标识别[J]. 重庆邮电大学学报(自然科学版), 2012, 24(3): 308-313.WANG Yanxia and ZHANG Gong. Target recognition in SAR images using sparse representation based on feature space[J]. Journal of Chongqing University of Posts and Telecommunications National Science Edition (Natural Science Edition), 2012, 24(3): 308-313.
[10]	LIU M, WU Y, and ZHANG Q, et al. Dempster-shafer fusion of multiple sparse representation and statistical property for SAR target configuration recognition[J]. IEEE Geoscience and Remote Sensing Letters, 2014, 11(6): 1106-1110.
[11]	韩萍, 王欢. 结合KPCA和稀疏表示的SAR目标识别方法研究[J]. 信号处理, 2013, 29(12): 1696-1701.HAN Ping and WANG Huan. Research on the synthetic aperture radar target recognition based on KPCA and sparse representation[J]. Journal of Signal Processing, 2013, 29(12): 1696-1701.
[12]	QIAO L S, CHEN S C, and TAN X Y. Sparsity preserving projections with applications to face recognition[J]. Pattern Recognition, 2010, 43(1): 331-341.
[13]	He X F and Niyogi P. Local Preserving Projections[C]. Proceedings of Conference on Advances in Neural Information Processing Systems, 2003: 153-160.
[14]	Figueiredo M A T, Nowak R D, and Wright S J. Gradient projection for sparse reconstruction: application to compressed sensing and other inverse problems[J]. IEEE Journals of Selected Topics in Signal Processing, 2007, 1(4): 586-597.
[15]	Bryant M and Garber F. SVM classifier applied to the MSTAR public data set[C]. SPIE Algorithm for Synthetic Aperture Rader Imagery, Orlando, FL, 1999, 3721: 662-672.