基于邻域统计分布变化分析的UWB SAR隐蔽目标变化检测

王广学; 黄晓涛; 周智敏

doi:10.3724/SP.J.1146.2010.00202

基于邻域统计分布变化分析的UWB SAR隐蔽目标变化检测

doi: 10.3724/SP.J.1146.2010.00202

王广学^{* 黄晓涛周智敏,},
黄晓涛,
周智敏

基金项目:

教育部新世纪优秀人才支持计划(NCET-07-0223)，国家自然科学基金(60972121)和国防科大科研计划项目(JC09-04-01)资助课题

计量
- 文章访问数: 4156
- HTML全文浏览量: 118
- PDF下载量: 962
- 被引次数: 0
出版历程
- 收稿日期: 2010-03-09
- 修回日期: 2010-07-05
- 刊出日期: 2011-01-19

UWB SAR Change Detection of Target in Foliage Based on Local Statistic Distribution Change Analysis

Wang Guang-Xue^{* 黄晓涛周智敏
,},
Huang Xiao-Tao,
Zhou Zhi-Min

摘要

摘要: 该文针对载机不同航迹条件下所得多时相UWB SAR图像灰度值存在较大起伏，严重影响了基于像素灰度值差异的变化检测算法性能，提出了一种基于邻域统计分布变化分析的UWB SAR隐蔽目标变化检测方法。该方法将Gram-Charlier展开理论同秩序滤波器相结合对多时相图像中每个像素邻域的统计分布进行估计，进而借助K-L散度理论对多时相图像邻域统计分布变化进行定量分析以检测目标对应的变化区域。实验结果表明，该文方法能够更好地适应不同航迹UWB SAR图像间灰度起伏的影响，取得更好的检测结果。
- 超宽带合成孔径雷达 /
- 叶簇隐蔽目标检测 /
- 变化检测 /
- Gram-Charlier展开 /
- K-L散度
Abstract: Because of large pixel value change between multitemporal UWB SAR images caused by different imaging geometries, the performance of change detection algorithm based on pixel value difference declines quickly. In order to deal with this problem, a new UWB SAR foliage target change detection algorithm based on local statistic distribution is proposed. In the algorithm, the Gram-Charlier expansion theory and rank order filter are combined to estimate local statistic distribution. Then, the K-L divergence is used to measure the change between local statistic distribution of multitemporal UWB SAR image. And the target can be detected because of large K-L divergence value. Finally, the experimental results show that the algorithm can better deal with the pixel value change between multitemporal UWB SAR images with different imaging geometries and an obvious performance improvement on detection can be obtained.
- Ultra-Wide Band SAR (UWB SAR) /
- FOliage PENetration (FOPEN) detection /
- Change detection /
- Gram-Charlier expansion /
- K-L divergence

HTML全文

参考文献(1)

杨志国. 基于ROI的UWB SAR叶簇覆盖目标鉴别方法研究[D]. [博士论文],长沙:国防科技大学, 2007: 17-23.[2]Ulander M H. Modeling of change detection in VHF- and UHF-band SAR [C]. EUSAR2008, Fridrichshafen, 2008, 2: 127-131.[3]Novak L. Target recognition and polarimetric SAR[R]. Tutorial of 2008 IEEE Radar Conference, Rome, 2008, Tutorial #13.[4]Novak L. Algorithms for SAR Change Detection, Compression and super-resolution[R]. Tutorial of 2009 International Radar Conference, 2009, Bordeaux, Tutorial #10.[5]Lundberg M, Ulander M　H, Pierson E, and Gustavsson A. A challenge problem for detection of targets in foliage[C]. Conference on Algorithms for Synthetic Aperture Radar Imagery, Orlando, 2006, SPIE 6237: 1-12.[6]Lundberg M, Ulander M H, PiersonE, and Gustavsson A. Change detection for low-frequency SAR ground surveillance[J].IEE Prodeedings Radar sonar and navigation.2005, 152(6):413-420[7]杨志国, 黄小涛, 周智敏. SAR目标检测中的一种稳健变化检测算法[J].电子与信息学报.2008, 30(9):2094-2098浏览[8]Cavalcante C C, Mota C M, and Romano M T. Polynomial expansion of the probability density function about gaussian mixtures [C]. IEEE Workshop on machine learning for signal processing, Sao Luis, 2004: 163-172.[9]Haykin S. Neural Network: A Comprehensive Foundation. 2nd Edition[M]. New Jersey: Prentice Hall, New Jersey, 1999: 566-567.[10]FOI. CARABAS-II VHF SAR data set[DB/OL], Http:// www. sdms. afrl.af.mil/datasets, 2005.[11]Fung T and Ledrew E. The determination of optimal threshold levels for changes detection using various accuracy indices[J]. Photogrammetric Engineering and Remote Sensing, 1988, 54(10): 1449-1454.

施引文献

资源附件(0)

访问统计