基于改进的子类判决分析的SAR目标特征提取与识别

胡利平; 刘宏伟; 吴顺君

doi:10.3724/SP.J.1146.2008.01135

基于改进的子类判决分析的SAR目标特征提取与识别

doi: 10.3724/SP.J.1146.2008.01135

基金项目:

教育部长江学者和创新团队支持计划(IRT0645)，国家自然科学基金(60772140)资助课题

计量
- 文章访问数: 3575
- HTML全文浏览量: 69
- PDF下载量: 865
- 被引次数: 0
出版历程
- 收稿日期: 2008-09-09
- 修回日期: 2009-05-11
- 刊出日期: 2009-09-19

SAR Target Feature Extraction and Recognition Based on Improved Clustering-based Discriminant Analysis

摘要

摘要: 针对大多文献中假设合成孔径雷达(SAR)数据服从单模分布带来的问题，该文提出改进的子类判决分析(ICDA)，它假设SAR目标数据服从更合理更实际的多模分布。首先采用快速全局k-均值聚类算法找到每类目标的子类划分，然后基于子类判决分析(CDA)准则寻找最优的投影矢量，使得投影后不同类别的子类样本之间距离最大而每个子类内部的样本散布最小。用美国运动和静止目标获取与识别(MSTAR)计划录取的SAR地面静止目标数据的实验结果表明，ICDA可获得较好的对真实目标的分类性能和对干扰目标的拒判能力。
- 合成孔径雷达; 自动目标识别; 子类判决分析; 快速全局k-均值聚类算法
Abstract: In many literatures, Synthetic Aperture Radar (SAR) data is usually supposed to obey the unimodal distribution, unsuitable in the applications. To overcome the limitation, an Improved Clustering-based Discriminant Analysis (ICDA) method is proposed, which assumes the distribution of each class for SAR data is multimodal, a more reasonable and practical assumption. The detailed procedure of ICDA is to first partition each class of the SAR data into multiple clusters via the fast global k-means clustering algorithm, and then try to find the projection vectors such that the projections of every pair of clusters from different classes are well separated while the within-cluster scatter is minimized. Experimental results performing on SAR ground stationary targets based the Moving and Stationary Target Acquisition and Recognition (MSTAR) public database show that ICDA has better classification capabilities of three true objects classes and rejection capabilities of two confusers classes.

HTML全文

参考文献(1)

Ross T D, Worrell S W, and Velten V J, et al.. Standard SARATR evaluation experiments using the MSTAR publicrelease data set. Proc. of SPIE on SAR Imagery V, Orlando,Florida, 1998, 3370: 566-573.[2]Bryant M L and Garber F D. SVM classifier applied to theMSTAR public data set. Proc. of SPIE on SAR Imagery VI,Orlando, Florida, 1999, 3721: 355-360.[3]Zhao Q and Principe J C. Support vector machines for SARautomatic target recognition[J].IEEE Trans. on Aerospace andElectronic Systems.2001, 37(2):643-654[4]Yuan C and Casasent D P. A new SVM for distorted SARobject classification. Proc. of SPIE on Optical PatternRecognition XVI, Bellingham WA, 2005, 5816: 10-22.[5]Ramamoorthy L D and Casasent D P. Classification andrejection of MSTAR data. Proc. of SPIE on Optical PatternRecognition XV, Orlando, Florida, 2004, 5437: 265-276.[6]Bryant M L. Target signature manifold methods applied tothe MSTAR database: preliminary results. Proc. of SPIE onSAR Imagery VIII, USA: SPIE, 2001, 4382: 389-394.[7]Patnaik R and Casasent D. MSTAR object classification andconfuser and clutter rejection using minace filters. Proc. ofSPIE on ATR XVI, Bellingham, 2006, 6234: 1-13.[8]Sun Y J, Liu Z P, and Todorovic S, et al.. Adaptive boostingfor SAR automatic target recognition. IEEE Trans. onAerospace and Electronic Systems, 2007: 43(1): 112-125.[9]宦若虹, 杨汝良, 岳晋. 一种合成孔径雷达图像特征提取与目标识别的新方法[J].电子与信息学报.2008, 30(3):554-558浏览[10]宦若虹, 杨汝良, 岳晋. SVM和HMM相结合的合成孔径雷达图像目标识别. 系统工程与电子技术, 2008, 30(3): 447-451.Huan Ruo-hong, Yang Ru-liang, and Yue Jin. Syntheticaperture radar images target recognition combined SVM withHMM. Systems Engineering and Electronics, 2008, 30(3):447-451.[11]宦若虹, 杨汝良. 基于ICA和SVM的SAR图像特征提取与目标识别.计算机工程, 2008, 34(13): 24-28.Huan Ruo-hong and Yang Ru-liang. SAR images featureextraction and target recognition based on ICA and SVM.Computer Engineering, 2008, 34(13): 24-28.[12]Belhumeur P N, Hespanha J P, and Kriegman D J.Eigenfaces vs. fisherfaces: recognition using class specificlinear projection. IEEE Trans. on Pattern Analysis andMachine Intelligence, 1997, 19(7): 711-720.[13]Chen X W and Huang T. Facial expression recognition: Aclustering-based approach[J].Pattern Recognition Letters.2003,24:1295-1302[14]Likas A, Vlassis N, and Verbeek J J. The global k-meansclustering algorithm[J].Pattern Recognition.2003, 36:451-461[15]Gonzalez R C and Woods R E. Digital image processing. NewYork: Prentice-Hall, 2003: 75-147.[16]Musman S and Kerr D. Automatic recognition of ISAR shipimages[J].IEEE Transactions on Aerospace and ElectronicSystems.1996, 32(4):1392-1404

施引文献

资源附件(0)

访问统计