基于光谱相似度量的高光谱图像异常检测算法

吉林大学学报(工学版) ›› 2013, Vol. 43 ›› Issue (增刊1): 148-153.

基于光谱相似度量的高光谱图像异常检测算法

王玉磊, 赵春晖, 齐滨

哈尔滨工程大学信息与通信工程学院,哈尔滨 150001

收稿日期:2012-05-25 发布日期:2013-06-01
通讯作者: 赵春晖(1965-),男,教授,博士生导师.研究方向:遥感图像处理.E-mail:zhaochunhui@hrbev.edu.cn E-mail:zhaochunhui@hrbev.edu.cn
作者简介:王玉磊(1986-),女,博士研究生.研究方向:高光谱图像处理.E-mail:wangyulei@hrbeu.edu.cn
基金资助:
国家自然科学基金项目(61077079);教育部博士学科点专项科研基金项目(20102304110013);黑龙江省自然科学基金重点项目(ZD201216).

Hyperspectral anomaly detection algorithm based on spectral similarity scale

WANG Yu-lei, ZHAO Chun-hui, QI Bin

College of Information and Communication Engineering, Harbin Engineering University, Harbin 150001, China

Received:2012-05-25 Published:2013-06-01

摘要/Abstract

摘要：

针对传统异常检测算法需要建立在一定的假设模型下,提出了一种新的高光谱图像异常检测算法。该算法无需假设背景模型,首先运用迭代误差分析方法对高光谱图像数据进行处理,得到高光谱图像数据的异常端元。然后以选取出的端元为参考,对高光谱数据进行相似度量,通过计算与参考端元的核光谱角余弦,找到与异常端元相似的光谱向量,得到异常检测结果。仿真实验结果表明,该算法能够准确的检测出异常目标,并且具有运算时间短、效率高的特点。

关键词: 高光谱, 异常检测, 相似度量, 光谱角余弦, 核方法

Abstract:

Because conventional anomaly detection algorithms are based on special assumptions,a new algorithm of hyperspectral imagery anomaly detection was presented.Without assuming the background model,first,iterative error analysis (IEA) was used for endmember extraction.Then the Spectral Similarity Scale (SSS) was measured.Through computing the kernel spectral angel cosine (KSAC),the anomaly detection result was obtained.The simulation result shows that the new algorithm can detect the anomalies exactly,and what's more,the new algorithm has the advantages of little computation time and high efficiency.

Key words: hyperspectral, anomaly detection, spectral similarity scale, spectral angel cosine, kernel method

中图分类号:

TP751.1

王玉磊, 赵春晖, 齐滨. 基于光谱相似度量的高光谱图像异常检测算法[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 148-153.

WANG Yu-lei, ZHAO Chun-hui, QI Bin. Hyperspectral anomaly detection algorithm based on spectral similarity scale[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 148-153.

参考文献

[1] Irving S Reed,Yu Xiao-li.Adaptive multiple-band cfar detection of an optical pattern with unknown spectral distribution [J].EEE Transactions on Acoustics Speech and Signal Processing,1990,38(10):1760-1769.

[2] Heesung K,Nasrabadi N M.Kernel RX-algorithm:A nonlinear anomaly detector for hyperspectral imagery [J].IEEE Transactions on Geoscience and Remote Sensing,2005,43(2):388-397.

[3] 梅锋,赵春晖.基于空域滤波的核RX高光谱图像异常检测算法[J].哈尔滨工程大学学报,2009,30(6):697-702. Mei Feng,Zhao Chun-hui.Spatial filter based anomaly detection algorithm for hyperspectral imagery kernel RX detectors [J].Journal of Harbin Engineering University,2009,30(6):697-702.

[4] Zhao Chun-hui,Wang Yu-lei,Mei Feng.Kernel ICA feature extraction for anomaly detection in hyperspectral imagery [J].Chinese Journal of Electronics,2012,21(2):265-269.

[5] 赵春晖,胡春梅.基于目标正交子空间投影加权的高光谱图像异常检测算法[J].吉林大学学报:工学版,2011,41(5):1468-1474. Zhao Chun-hui,Hu Chun-mei.Weighted anomaly detection algorithm for hyperspectral image based on target orthogonal subspace projection [J].Journal of Jilin University(Engineering and Technology Edition),2011,41(5):1468-1474.

[6] 王斯博,杨春玲.基于RX算法的高光谱红外弱小目标检测[J].红外技术,2010,32(4)::204-208. Wang Si-bo,Yang Chun-ling.Detection of dim small target based oil rx algorithm for hyperspectral ir imagery[J].Infrared Technology,2010,32(4):204-208.

[7] James Norman Sweet.The spectral similarity scale and its application to the classification of hyperspectral remote sensing data[D].New York:State university of New York,College of Environmental Science and Forestry,2002.

[8] Antonio Plaza,Pablo Martínez,Rosa Pérez,et al.A quantitative and comparative analysis of endmember extraction algorithms from hyperspectral data[J].IEEE Transactions on Geoscience and Remote Sensing,2004,42(3):650-663.

[9] Sun Li-xin,Zhang Ying,Bert Guindon.Improved iterative error analysis for endmember extraction from hyperspectral imagery[J].Processing of SPIE,2008,7086:11-18.

[10] 李智勇,郁文贤,赵和鹏.迭代误差分析方法在高光谱异常检测中的应用[J].系统工程与电子技术,2008,30( 12):2340-2344. Li Zhi-yong,Yu Wen-xian,Zhao He-peng.Application of iterative error analysis in hyperspectral anomaly detection[J].Systems Engineering and Electronics,2008,30( 12):2340-2344.

[11] 谌德荣,孙波,陶鹏,等.基于核光谱角余弦的高光谱图像空间邻域聚类方法[J].电子学报,2008,36(10):1992-1995. Chen De-rong,Sun Bo,Tao Peng,et al.Spatial neighboring clustering method for hyperspectral imagery based on kernel spectral angel cosine[J].Acta Electronica Sinia,2008,36(10):1992-1995.

相关文章 12

[1]	王柯俨, 李云松, 宋娟, 廖惠琳, 吴宪云. 基于局部边缘预测的空谱联合高光谱图像无损压缩[J]. 吉林大学学报(工学版), 2017, 47(2): 677-685.
[2]	于赫, 秦贵和, 孙铭会, 闫鑫, 王璇喆. 车载CAN总线网络安全问题及异常检测方法[J]. 吉林大学学报(工学版), 2016, 46(4): 1246-1253.
[3]	齐滨, 赵春晖, 王玉磊. 基于支持向量机与相关向量机的高光谱图像分类[J]. 吉林大学学报(工学版), 2013, 43(增刊1): 143-147.
[4]	王瀛, 郭雷, 梁楠. 基于核熵成分分析的高光谱遥感图像分类算法[J]. , 2012, (06): 1597-1601.
[5]	柴争义, 吴慧欣, 吴勇. 用于异常检测的免疫实值检测器优化生成算法[J]. , 2012, 42(05): 1251-1256.
[6]	柴争义, 王献荣, 王亮. 用于异常检测的实值否定选择算法[J]. 吉林大学学报(工学版), 2012, 42(01): 176-181.
[7]	张朝柱,左国辉. 基于核方法的二维线性判决分析的人脸识别算法[J]. 吉林大学学报(工学版), 2011, 41(4): 1167-1170.
[8]	赵春晖,胡春梅. 基于目标正交子空间投影加权的高光谱图像异常检测算法[J]. 吉林大学学报(工学版), 2011, 41(05): 1468-1474.
[9]	付朝阳,郭雷,常威威. 网络的高光谱图像融合[J]. 吉林大学学报(工学版), 2011, 41(03): 838-843.
[10]	王自强，段爱玲，张德贤 . 基于支持向量数据描述的高效异常数据检测算法[J]. 吉林大学学报(工学版), 2009, 39(02): 499-0503.
[11]	王立国，赵春晖，毕晓君 . 端元选择算法在波段选择中的应用[J]. 吉林大学学报(工学版), 2007, 37(04): 915-919.
[12]	张君；张国英；刘玉树. 基于属性相似度云模型的网络异常检测[J]. 吉林大学学报(工学版), 2006, 36(06): 954-0957.

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed