期刊文献+

基于稀疏表示与空域金字塔环形描述的SAR目标分类方法(英文) 预览

A SAR target classification method based on sparse representation and spatial pyramid rings
在线阅读 免费下载
分享 导出
摘要 为避免传统SAR图像特征分类算法中所需的目标方位角精确估计,提出了一种新的基于稀疏表示与空域金字塔环形描述相结合的SAR目标分类方法.该方法引入bag of features思想,利用密集采样SIFT描述特征训练过完备字典,对训练集和测试集同时进行稀疏编码并构造空域金字塔环形描述,得到旋转不变特征,最后输入线性SVM分类器进行分类.MSTAR实测数据的对比实验表明,在无需目标方位角估计的前提下,所提出的算法识别率达到96%以上,取得了很好的目标分类效果. Traditional feature based SAR target classification methods require explicit pose angle estimation.To avoid this problem,a SAR target recognition method based on sparse representation and spatial pyramid rings was proposed.The method extended the original bag of features approach to SAR image processing.The dictionary was trained from dense sampled SIFT descriptions.The sparse coding technique and spatial pyramid rings expression were used to gain rotation invariant features.Moving and Stationary Target Acquisition and Recognition public database was used in the classification setup.Results from classifying three categories demonstrate that the performance of the proposed algorithm is superior to the ones using SVM classifier with other dimension reduction techniques,with a classification rate of above 96%.
作者 李雪莹 尹东 张荣 LI Xueying,YIN Dong,ZHANG Rong(School of Information Science & Technology,University of Science and Technology of China,Hefei 230027,China)
出处 《中国科学技术大学学报》 CAS CSCD 北大核心 2013年第4期306-312,共7页 Journal of University of Science and Technology of China
基金 Supported by National Key Basic Research(973)Program of China(2010CB731900)
关键词 SAR 密集采样SIFT 空域金字塔环 bagoffeatures SAR images dense SIFT spatial pyramid ring bag of features
作者简介 LI Xueying, female, born in 1986, master. Research field.. SAP, image processing. E-mail: lixueying@mail, ustc. edu. cn Corresponding author: YIN Dong, associate professor. E-mail: yindong@ ustc. edu. cn
  • 相关文献

参考文献16

  • 1DeVore M D, O'Sullivan J A. A performance complexity study of several approaches to automatic target recognition from synthetic aperture radar images [J]. IEEE Transactions on Aerospace Electronic Systems, 2002, 38(2) :632-648. 被引量:1
  • 2Kaplan L M. Analysis of multiplicative speckle models for template-based SAR ATR[J]. IEEE Transactions on Aerospace and Electronic Systems, 2001, 37(4): 1 424-1 432. 被引量:1
  • 3Patnaik R, Casasent D. MINACE filter classification algorithms for ATR using 'MSTAR data [C]// Proceedings of SPIE Conference on Automatic Target Recognition XV. Orlando, USA: SHE Press, 2005: 100-111. 被引量:1
  • 4Douville P L. Measured and predicted synthetic apemu radar target comparison[J]. IEEE Transactions on Aeros:ce and Hectronic Systems, 2002,38(1) : 25-37. 被引量:1
  • 5Mahalanobis A, Carlson D W, Vijaya Kumar B V K. Evaluation of MACH and DCCF correlation filters for SAR ATR using the MSTAR public database[C]// Proceedings of SHE Conference on Algorithms for Synthetic Aperture Radar Imagery V. Orlando, USA: SHE Press, 1998: 460-468. 被引量:1
  • 6Ross T D, Bradley J J, Hudson L J, et al. SAR ATR: So what's the problem? An MSTAR perspective[C]// Proceedings of SPIE Conference on Algorithms for Synthetic Aperture Radar Imagery VI. Orlando, USA: SHE Press, 1999: 662-672. 被引量:1
  • 7Jones GIII, Bhanu I5. Recognition of articulated and occluded objects [J]. IEEE Transactions on Pattern Analysis and Machine Intelligence, 1999, 21 (7) : 603-613. 被引量:1
  • 8Ryan T W, Pothier S, Pierson W. Search algorithms for vector quantization and nearest-neighbor classification[C]//Proceedings of SHE Conference on Algorithms for Synthetic Aperture Radar Imagery VIII. USA: SPIE Press, 2001: 276-285. 被引量:1
  • 9Zhao Q, Principe J C. Support vector machines for SAR automatic target recognition [J]. IEEE Transactions on Aerospace and Electronic Systems, 2001, 37(2): 643-654. 被引量:1
  • 10Thiagarajan J J, Ramamurthy K N, Knee P, et al. Sparse representations for automatic target classification in SAR images [C]// 4th International Symposium on Communications, Control and Signal Processing. Limassol, Cyprus: IEEE Press, 2010: 1-4. 被引量:1

二级参考文献7

共引文献18

投稿分析

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部 意见反馈