SAR场景图像中车辆目标的自动识别

Journal of Systems Engineering and Electronics ›› 2009, Vol. 31 ›› Issue (7): 1596-1601,1638.

SAR场景图像中车辆目标的自动识别

潘卓^1,2, 高鑫¹, 王岩飞¹, 王宾辉³, 谢建红^1,2

1. 中国科学院电子学研究所, 北京, 100190;
2. 中国科学院研究生院, 北京, 100039;
3. 北京师范大学数学科学学院, 北京, 100875

收稿日期:2008-03-18 修回日期:2008-09-03 出版日期:2009-07-20 发布日期:2010-01-03
作者简介:潘卓(1980- ),女,博士研究生,主要研究方向为SAR图像解译与目标识别.E-mail:panzhuo-iecas@163.com

Automatic vehicle target recognition in full SAR image scenes

PAN Zhuo^1,2, GAO Xin¹, WANG Yan-fei¹, WANG Bin-hui³, XIE Jian-hong^1,2

1. Inst. of Electronics, Chinese Academy of Sciences, Beijing 100190, China;
2. Graduate School of the Chinese Academy of Sciences, Beijing 100039, China;
3. School of Mathematical Sciences, Beijing Normal Univ., Beijing 100875, China

Received:2008-03-18 Revised:2008-09-03 Online:2009-07-20 Published:2010-01-03

摘要/Abstract

摘要： 提出一种在合成孔径雷达(synthetic aperture radar,SAR)场景图像中进行自动目标识别的方法,并针对识别流程中分类阶段对目标方位角敏感的问题,基于相关滤波器理论与核特征分析方法,提出一种对SAR目标方位角具有较强鲁棒性的非线性相关滤波器。该滤波器使用特征向量降低对训练图像的依赖性,并将特征空间进行非线性扩展,大大提高了目标的正确分类率,同时利用核函数避免了因为高维矢量而造成的计算问题。MSTAR实测SAR图像数据的实验结果表明,方法切实有效,所提出的滤波器对目标方位角失真具有较强的容忍性,不需要存储目标模板和估计目标方位角就能够实现高效率、高准确率的目标分类。

Abstract: A new method is presented for automatic target recognition in full synthetic aperture radar(SAR) image scenes.As SAR target classification is sensitive to target’s azimuth,based on correlation filter theory and kernel feature analysis,a nonlinear correlation filter is provided,it can tolerate a distortion of target’s azimuth.The novel filter exploits eigenvectors to reduce the dependence of the training set and extends the linear combination of eigenvectors nonlinearly to improve the classification performance.Moreover,to keep the computation tractable in high dimensional space,the kernel function is employed.The tests using MSTAR database demonstrate the scheme is practical and the novel filter implements target classification efficiently and accurately without templates and target poses estimation.

中图分类号:

TP753

潘卓, 高鑫, 王岩飞, 王宾辉, 谢建红. SAR场景图像中车辆目标的自动识别[J]. Journal of Systems Engineering and Electronics, 2009, 31(7): 1596-1601,1638.

PAN Zhuo, GAO Xin, WANG Yan-fei, WANG Bin-hui, XIE Jian-hong. Automatic vehicle target recognition in full SAR image scenes[J]. Journal of Systems Engineering and Electronics, 2009, 31(7): 1596-1601,1638.

参考文献

[1] Novak L M,Halversen S D,Owirka G J,et al.Effects of polarization and resolution on SAR ATR[J] ,IEEE Trans.on Aerospace and Electronic Systems,1997,33(1):102-116.
[2] Novak L M,Owirka G J,Brower W S,et al.The automatic target-recognition system in SAIP[J].The Lincoln Laboratory Journal,1997,10(2):187-202.
[3] Ross T D,Bradley J J,Hudson L J,et al.SAR ATR-So What's the problem?-An MSTAR perspective[C]//Proc.of SPIE-Algorithms for Sythetic Aperture Radar Imagery Ⅵ,Orlando,Florida,1999,3721:662-672.
[4] Devore M D,O'Sullivan J A.Performance complexity study of several approaches to automatic target recognition from SAR im ages[J].IEEE Trans.on Aerospace and Electronic Systems,2002,38(2):632-648.
[5] Shenoy R K.The design and use of unconstrained image filters and features for SAR detection and recognition[D].Carnegie Mellon University,2001.
[6] Singh R.Advanced correlation filter for multi-class synthetic aperture radar detection and classification[D] ,Carnegie Mellon University,2002.
[7] Casasent D,Patnaik R.Automated synthesis of distortion-invariant filters:AutoMinace[C]//Proc.of SPIE-Intelligent Robots and Computer Vision ⅩⅩⅣ,Boston,USA,2006,6384:638401.
[8] Patnaik R,Casasent D.MSTAR object classification and confu-ser and clutter rejection using minace filters[C]//Proc.of SP IE-Automatic Target Recognition ⅩⅥ,Orlando,Florida,2006,6234:62340S1.
[9] Vijaya Kumar B V K.Tutorial survey of composite filter designs for optical correlators[J].Applied Optics,1992,31:4773-4801.
[10] Mahalanobis A,Vijaya Kumar B V K,Casasent D.Minimum average correlation energy filter[J].Applied Optics,1986,26:3633-3640.
[11] Rsvichandran G,Casasent D.Minimum noise and correlation energy filter[J].Applied Optics,1992,31:1823-1833.
[12] Isaacs J C,Foo S Y,Bases A M.Novel kernels and kernel PCA for patten recognition[C]//Proc.of the IEEE International sumposium on Computational Intelligence in Robotics and Automation,FL,USA,2007:438-443.
[13] Vijaya Kumar B V K,Xie C Y.Correlation pattern recognition for face recognition[C]//Proc.of the IEEE,2006,94(11):1963-1975.
[14] MSTAR public release dataset[oL].hups://www.sdms.afrl.af.mill/datasets/mstar/.
[15] Maria Petrou,Panagiota Bosdogianni.数字图像处理疑难解析[M].赖剑煌,冯国灿,等.译.北京:机械工业出版社,2005.