Please wait a minute...
 首页  期刊介绍 期刊订阅 联系我们 横山亮次奖 百年刊庆
 
最新录用  |  预出版  |  当期目录  |  过刊浏览  |  阅读排行  |  下载排行  |  引用排行  |  横山亮次奖  |  百年刊庆
清华大学学报(自然科学版)  2015, Vol. 55 Issue (8): 844-848    
  电子工程 本期目录 | 过刊浏览 | 高级检索 |
基于鲁棒主成分分析的SAR舰船检测
宋胜利1,2, 杨健1
1. 清华大学 电子工程系, 北京 100084;
2. 洛阳电子装备试验中心, 洛阳 471000
Ship detection in SAR images by robust principle component analysis
SONG Shengli1,2, YANG Jian1
1. Department of Electronic Engineering, Tsinghua University, Beijing 100084, China;
2. Luoyang Electronic Equipment Test Center, Luoyang 471000, China
全文: PDF(1131 KB)  
输出: BibTeX | EndNote (RIS)      
摘要 针对单极化SAR舰船目标恒虚警检测无标准杂波模型可选,且多目标情况下易发生目标检测不完整和弱目标丢失的问题,该文提出一种基于鲁棒主成分分析(robust principle component analysis, RPCA)的舰船检测方法,通过利用SAR图像中内在的海面低秩属性和舰船目标的稀疏属性,借助推导的增量Lagrange乘子算法,将SAR图像分解为低秩图像、噪声图像(两者之和对应海面)和稀疏图像(对应舰船)的和,从而一次性实现目标检测和杂波抑制,不依赖任何杂波模型和检测统计量。仿真实验验证了增量Lagrange乘子算法的有效性。实测数据处理实验中与平均单元恒虚警检测法和均方误差恒虚警检测法进行了对比,结果表明该方法可以正确从海杂波中检测出舰船目标,具有良好的鲁棒性。
服务
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章
宋胜利
杨健
关键词 合成孔径雷达舰船检测鲁棒主成分分析恒虚警检测    
Abstract:Single polarization SAR ship detection using a constant false alarm rate (CFAR) detector does not have a standard clutter model, so the system often gives incomplete targets and misses weak targets in multitarget detection. A ship detection method was developed based on robust principle component analysis (RPCA) to improve the detection. This method leverages the intrinsic properties of SAR images that the sea area is approximately low rank and there are few ships. SAR images can be decomposed into the sum of a low rank component, a noise component and a sparse component via RPCA, with the sum of the first two corresponding to the sea surface and the third corresponding to ships. Thus, ship detection and clutter suppression are achieved in one step without a clutter model or statistics. The augmented Lagrange multiplier method for RPCA is verified by simulations. For comparison, cell averaging CFAR (CA-CFAR) and mean square error CFAR (MSE-CFAR) are also used. Tests with real data show that this method correctly detects ships from sea clutter with robust detection performance.
Key wordssynthetic aperture radar (SAR)    ship detection    robust principle component analysis (RPCA)    constant false alarm rate (CFAR)
收稿日期: 2014-12-25      出版日期: 2015-09-30
ZTFLH:  TN957.52  
通讯作者: 杨健,教授,E-mail:yangjian_ee@tsinghua.edu.cn     E-mail: yangjian_ee@tsinghua.edu.cn
引用本文:   
宋胜利, 杨健. 基于鲁棒主成分分析的SAR舰船检测[J]. 清华大学学报(自然科学版), 2015, 55(8): 844-848.
SONG Shengli, YANG Jian. Ship detection in SAR images by robust principle component analysis. Journal of Tsinghua University(Science and Technology), 2015, 55(8): 844-848.
链接本文:  
http://jst.tsinghuajournals.com/CN/  或          http://jst.tsinghuajournals.com/CN/Y2015/V55/I8/844
  图1 恢复误差随σ 的变化
  图2 恢复误差随PS 的变化
  图3 恢复误差随r 的变化
  图4 恢复误差随m 的变化
  图5 HH 极化幅度图像
  图6 低秩图像
  图7 稀疏图像(舰船)
  图8 稀疏图像(舰船)
  图9 CAGCFAR 检测结果
  图10 MSE-CFAR 检测结果
[1] Goldstein G B. False-alarm regulation in Log-Normal and Weibull clutter [J]. IEEE Transactions on Aerospace and Electronic Systems, 1973, 9(1): 84-92.
[2] 艾加秋, 齐向阳. 一种基于局部K分布的新的SAR图像舰船检测算法[J]. 中国科学院研究生院学报, 2010, 27(1): 36-42. AI Jiaqiu, QI Xiangyang. A novel ship detection method in SAR images based on local K distribution [J]. Journal of the Graduate School of the Chinese Academy of Sciences, 2010, 27(1): 36-42. (in Chinese)
[3] Frery A C, Müller H J, Yanasse C C F, et al. A model for extremely heterogeneous clutter [J]. IEEE Transactions on Geoscience and Remote Sensing, 1997, 35(3): 648-659.
[4] Blacknell D. Target detection in correlated SAR clutter [J]. IEE Proceedings of Radar, Sonar and Navigation, 2000, 147(1): 9-16.
[5] Moser G, Zerubia J, Serpico S B. Dictionary-based stochastic expectation-maximization for SAR amplitude probability density function estimation [J]. IEEE Transactions on Geoscience and Remote Sensing, 2006, 44(1): 188-200.
[6] CUI Yi, YANG Jian, ZHANG Xinzheng. New CFAR target detector for SAR images based on kernel density estimation and mean square error distance [J]. Systems Engineering and Electronics, 2012, 23(1): 40-46.
[7] Candès E J, LI Xiaodong, MA Yi, et al. Robust principal component analysis[J]. Journal of the ACM, 2011, 58(3): 1-34.
[8] ZHOU Zihan, LI Xiaodong, Wright J, et al. Stable principal component pursuit [C]// 2010 IEEE International Symposium on Information Theory Proceedings. Austin, TX, USA: IEEE, 2010: 1518-1522.
[9] ZHOU Chenlin, CHEN Minming, MA Yi. The Augmented Lagrange Multiplier Method for Exact Recovery of Corrupted Low-Rank Matrices, Technical Report UILU-ENG-09-2215 [R]. Champaign, IL, USA: UIUC, 2009.
[10] Candès E J, Plan Y. Matrix completion with noise [J]. Proceedings of the IEEE, 2010, 98(6): 925-936.
[11] Bertsekas P D. Nonlinear Programming [M]. Belmont: Athena Scientic Publishing, 1999.
[12] CAI Jianfeng, Candès E J, ZUO Weishen. A singular value thresholding algorithm for matrix completion [J]. SIAM J OPTIM, 2010, 20(4): 1956-1982.
[13] Oliver C, Quegan S. Understanding Synthetic Aperture Radar Images [M]. Raleigh, NC, USA: SciTech Publishing, 2004.
[1] 杨倩文, 孙富春. 基于泛化空间正则自动编码器的遥感图像识别[J]. 清华大学学报(自然科学版), 2018, 58(2): 113-121.
[2] 刘春, 杨健, 徐丰, 范一大. 基于水域跟踪的极化SAR图像桥梁检测[J]. 清华大学学报(自然科学版), 2017, 57(12): 1303-1309.
[3] 焦智灏, 杨健, 叶春茂, 宋建社. 基于散射成分一致性参数的极化SAR图像分类[J]. 清华大学学报(自然科学版), 2016, 56(8): 908-912.
[4] 杨帆, 杨健, 殷君君, 宋建社. 基于极化SAR分解模型的油膜检测[J]. 清华大学学报(自然科学版), 2015, 55(8): 854-859.
[5] 刘春, 殷君君, 杨健. 基于岸线特征点合并的极化SAR图像小型港口检测[J]. 清华大学学报(自然科学版), 2015, 55(8): 849-853.
[6] 李增辉, 常雯, 杨健. 基于外推陷波滤波的孤立强散射旁瓣抑制[J]. 清华大学学报(自然科学版), 2015, 55(5): 503-507.
[7] 马文婷,杨健,崔一,高伟. 地面高度起伏对SAR图像匹配性能影响的定量分析[J]. 清华大学学报(自然科学版), 2014, 54(4): 432-436.
[8] 游彪,杨健,叶春茂,宋建设. 改进的功率极化交叉熵舰船检测方法[J]. 清华大学学报(自然科学版), 2014, 54(4): 453-457.
[9] 常雯,李增辉,杨健. 基于迭代Radon-Wigner变换的FMCW-ISAR目标速度估计及速度补偿[J]. 清华大学学报(自然科学版), 2014, 54(4): 464-468.
[10] 马文婷, 杨健, 高伟, 周广益. 面向极化SAR图像配准的极化特征[J]. 清华大学学报(自然科学版), 2014, 54(2): 270-274.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
版权所有 © 《清华大学学报(自然科学版)》编辑部
本系统由北京玛格泰克科技发展有限公司设计开发 技术支持:support@magtech.com.cn