期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

一种新型高光谱实时异常检测算法 被引量：8

A real-time anomaly detection algorithm for hyperspectral imagery based on causal processing
下载PDF
导出
摘要 异常检测是高光谱遥感技术应用的一个重要方向.然而随着高光谱数据量的增大,实时处理成为高光谱异常检测方法所面临的主要问题.基于此,文中提出了一种新型的高光谱图像实时异常检测方法.随着数据的实时下行传输,该异常算子仅仅利用了待检测像元之前已获取的所有像元信息,而并没有用到尚未获取的像元信息,使得数据边传输边处理成为可能;同时,利用卡尔曼滤波器的递归思想,用Woodbury引理从上一时刻的状态更新目前信息,避免了重新计算历史信息及存储所有像元,在大大缩短算法运行时间的同时,大大降低了所需的存储空间.接收机特性曲线显示,与传统异常检测算法相比,这种新型实时算法可获得几乎相同的检测精度.在不影响检测效果的前提下,时间复杂度曲线和算子运行时间可显示提出算法的时效性.与此同时,提出的的状态更新公式不需要重新计算已有像元信息,因此只需两个存储单元存储前一时刻的状态(协方差矩阵或相关矩阵)以及当前的新像元信息,从而大大降低了算法所需的存储空间. Anomaly detection is one of the most important applications in hyperspectral imagery. Real-time processing is the main issue we are facing due to the large data set. Real time causal processing algorithms were developed to perform anomaly detection. It is an innovational kalman filtering based processing by using Woodbury＇s identity to update information which provides the pixel currently being processed without re-processing previous pixels. Experimental results demonstrated the proposed algorithm significantly improves processing efficiency in comparison with conventional anomaly detection without real time causal processing.
作者 赵春晖 王玉磊 李晓慧
机构地区 哈尔滨工程大学信息与通信工程学院 马里兰大学计算机与电机工程系、遥感信号及图像处理实验室 斯特拉斯克莱德大学电子与电气工程系、卓越信号与图像处理中心
出处 《红外与毫米波学报》 SCIE EI CAS CSCD 北大核心 2015年第1期114-121,共8页 Journal of Infrared and Millimeter Waves
基金 国家自然科学基金(61405041) 黑龙江省自然科学基金重点项目(ZD201216) 哈尔滨市优秀学科带头人基金(RC2013XK009003) 中国博士后科学基金(2014M551221) 中央高校基础研究基金(HEUCF1208)~~
关键词 高光谱异常检测 实时算法 Woodbury引理 hyperspectral anomaly detection real-time algorithm Woodbury＇s identity
分类号 TP751.1 [自动化与计算机技术—检测技术与自动化装置]
  • 相关文献

参考文献9

  • 1Chang C-I, Hsueh M. Characterization of anomaly detection for hyperspectral imagery [J]. Sensor Review,2006,26(2): 137-146.
  • 2Reed I S, Yu X. Adaptive multiple-band CFAR detection of an optical pattern with unknown spectral distribution [J]. IEEE Trans. on Acoustic, Speech and Signal Process.1990,38(10): 1760-1770.
  • 3Tarabalka Y, Haavardsholm T V, Kasen I, et al. Real-time anomaly detection in hyperspectral images using multivariate normal mixture, pdels and GPU processing [J]. J. Real Time Image Processing,2009,4(3): 287-300.
  • 4Haavardsholm T V, Arisholm G, Kavara A, et al. Architecture of the real-time target detection processing in an airborne hyperspectral demonstrator system [C]. 2010 2nd Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing (WHISPERS), June 2010.14-16.
  • 5Skauli T, Haavardsholm T, Kasen I, et al. Hyperspectral imaging technology and systems, exemplified by airborne real-time target detection [C]. 2011 Conference on Lasers and Electro-Optics (CLEO), May 2011.1-6.
  • 6Chang C-I Chiang S-S. Anomaly detection and classification for hyperspectral imagery [J].IEEE Trans. on Geoscience and Remote Sensing.2002,40(2),1314-1325.
  • 7Kailath T, Linear Systems [M], Prentice-Hall,1980.655.
  • 8Wang J, Chang C-I . Applications of independent component analysis in endmember extraction and abundance quantification for hyperspectral imagery [J]. IEEE Trans. on Geoscience and Remote Sensing,2006,44(9),2601-2616.
  • 9Chang Y-C. Ren H, Chang, C-I, et al. How to design synthetic images to validate and evaluate hyperspectral imaging algorithms [C], SPIE Conference on Algorithms and Technologies for Multispectral, Hyperspectral, and Ultraspectral Imagery XIV, March 16-20, Orlando, Florida, 2008.

同被引文献37

  • 1Reed I S,Yu X. Adaptive multiple-band CFAR detection of an optical pattern with unknown spectral distribution[J]. IEEE Transaction on Acoustics, Speech and Signal Pro- cessing, 1990,38(10) :1760-1770.
  • 2Borghys D, K. sen I, Achard V, et al. Comparative evalua- tion of hyperspectral anomaly detectors Jn different types of background[A]. Prec. of Algorithms and Technologies for Multispectral Hyperspectral and Ultraspectral Imagery XVIII. International Society for Optics and Photonics[C]. 2012,8390(12) :1106-1112.
  • 3Kwon H, Nasrabadi N M. Kernel RX-algorithm : A nonlinear anomaly detector for hyperspectral imagery [J]. IEEE Transaction on Geoscience and Remote Sensing, 2005,43 (2) :388-397.
  • 4LI Wei, DO Qian. Collaborative representation for hyper- spectral anomaly detection[J]. IEEE Transaction on Gee- science and Remote Sensing,2015,53(3) : 1463-1474.
  • 5YUAN Zong-ze, SUN Hao, JI Ke-feng, et al. Local sparsity divergence for hyperspectral anomaly detection[J]. IEEE Geoscience and Remote Sensing Letters, 2014, 11 (10) : 1697-1701.
  • 6CHEN Yi, Nasrabadi N M, Tran T D. Simultaneous joint sparsity model for target detection in hyperspectral im- agery[J]. IEEE Geoscience and Remote Sensing Letters, 2011,8(4) :676-680.
  • 7Roweis S T, Saul L K. Nonlinear dimensionafity reduction by locally linear embedding[J]. Science, 2000,290 ( 5 ):2323-2326.
  • 8LI Wei, Prasad S, Fowler J E. Decision fusion in kernel- induced spaces for hyperspectral image classification [J]. IEEE Transaction on Geoscience and Remote Sens- ing,2014,52(6): 3399-3411.
  • 9Hoyer P. Non-negative sparse coding [A]. Proc. of the 12th IEEE Workshop on Neural Networks for Signal Pro- cessing[C]. 2002,557-565.
  • 10ZHANG Chun-jie, LIU Jing, LIANG Chao, et al. Image clas- sification by non-negative sparse coding,correlation con- strained low-rank and sparse decomposition[J]. Comput- er Vision and Image Understanding, 2014,123:14-22.

引证文献8

二级引证文献272

红外与毫米波学报
2015年 第1期

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