[1]曾现灵,张立燕,胡荣华.基于主成分建模的SVDD高光谱图像异常检测[J].智能系统学报,2014,9(03):343-348.[doi:10.3969/j.issn.1673-4785.201309081]
 ZENG Xianling,ZHANG Liyan,HU Ronghua.An SVDD algorithm for hyperspectral anomaly detection based on principal component modeling[J].CAAI Transactions on Intelligent Systems,2014,9(03):343-348.[doi:10.3969/j.issn.1673-4785.201309081]
点击复制

基于主成分建模的SVDD高光谱图像异常检测(/HTML)
分享到:

《智能系统学报》[ISSN:1673-4785/CN:23-1538/TP]

卷:
第9卷
期数:
2014年03期
页码:
343-348
栏目:
出版日期:
2014-06-25

文章信息/Info

Title:
An SVDD algorithm for hyperspectral anomaly detection based on principal component modeling
作者:
曾现灵1 张立燕2 胡荣华1
1. 首都师范大学 资源环境与地理信息系统北京市重点实验室, 北京 100048;
2. 首都师范大学 三维信息获取与应用教育部重点实验室, 北京 100048
Author(s):
ZENG Xianling1 ZHANG Liyan2 HU Ronghua1
1. Key Laboratory of Resource Environment and GIS of Beijing, Capital Normal University, Beijing 100048, China;
2. Key Laboratory of 3D Information Acquisition and Application of the Ministry of Education, Capital Normal University, Beijing 100048, Chi
关键词:
主成分建模SVDD局部邻域聚类光谱角余弦高光谱异常检测
Keywords:
principal component modelingSVDDlocal neighborhood clusteringspectral angle cosinehyperspectral anomaly detection
分类号:
TP751
DOI:
10.3969/j.issn.1673-4785.201309081
摘要:
针对SVDD背景建模时混入异常点造成的检测率下降的问题, 提出了基于主成分建模的SVDD方法并应用于高光谱图像异常检测。利用高光谱图像的光谱特征提取背景的主要成分, 并分别对不同成分构建超球体, 形成单种背景成分SVDD模型, 最后利用综合决策函数对单个SVDD背景模型进行综合判断待检测像元, 从而实现高光谱图像异常像元的检测。用仿真数据和真实数据对算法的性能进行验证, 并将其与SVDD方法进行性能比较。结果表明, 新算法在低虚警概率下较之SVDD模型有更高的检测概率, 实验结果证明了算法的有效性。
Abstract:
An SVDD algorithm based on the principal component modeling is presented for hyperspectral anomaly detection, in order to solve the problem of its low detection rate caused by mixing abnormal points in the process of modeling background. This method extracts the principal components of the background samples by using the hyperspectral image’s spectral signature, and then uses these different components to build different super spheres respectively, forms different single background component SVDD models by these super spheres, finally uses the integrated decision function to judge these SVDD background models to detect any anomalies. The performance of the algorithm is verified by simulated and real data. The results show that the proposed method can obtain a higher detection rate under low false rate than the algorithm based on SVDD, verifying the effectiveness of this proposed method.

参考文献/References:

[1] REED I S, YU X. Adaptive multiple-band CFAR detection of an optical pattern with unknown spectral distribution[J]. IEEE Transactions on Acoustics, Speech and Signal Processing, 1990, 38(10):1760-1770.
[2] THOMAS A M. Extending the rx anomaly detection algorithm to continuous spectral and spatial domains[C]//Proc of IEEE SoutheastCon. Huntsville, Alabama, 2008:557-562.
[3] 史振威, 吴俊, 杨硕, 等. RX及其变种在高光谱图像中的异常检测[J]. 红外与激光工程, 2012, 41(3):796-802. SHI Zhenwei, WU Jun, YANG Shuo, et al. RX and its variants for anomaly detection in hyperspectral images[J]. Infrared and Laser Engineering, 2012, 41(3):796-802.
[4] 刘明, 杜小平, 孙洁. 一种改进的基于正交子空间投影的高光谱图像异常检测算法[J]. 装备学院学报, 2013, 23(4):92-96. LIU Ming, DU Xiaoping, SUN Jie. Anomaly detection based on improved orthogonal subspace projection algorithm in hyperspectral imagery[J]. Journal of Academy of Equipment, 2013, 23(4):92-96.
[5] 肖雄斌, 厉小润, 赵辽英. 基于最小噪声分离变换的高光谱异常检测方法研究[J]. 计算机应用与软件, 2012, 29(4):125-128. XIAO Xiongbin, LI Xiaorun, ZHAO Liaoying. On anomaly detection of hyperspectral image based on minimum noise fraction[J]. Computer Applications and Software, 2012, 29(4):125-128.
[6] 成宝芝, 赵春晖, 王玉磊. 基于四阶累积量的波段子集高光谱图像异常检测[J]. 光电子·激光, 2012, 23(8):1582-1588.CHENG Baozhi, ZHAO Chunhui, WANG Yulei. Anomaly detection of hyperspectral image for band subsets based on fourth order cumulant[J]. Journal of Optoelectronics·Laser, 2012, 23(8):1582-1588.
[7] HARSANYI J C. Detection and classification of subpixel spectral signatures in hyperspectral image sequences[D]. Baltimore:University of Maryland, 1993:116.
[8] 张立燕, 谌德荣, 陶鹏. 基于顶点成分分析的高光谱图像低概率异常检测方法研究[J]. 宇航学报, 2007, 28(5):1262-1265. ZHANG Liyan, CHEN Derong, TAO Peng. Anomaly detection for hyperspectral imagery based on vertex component analysis[J]. Journal of Astronautics, 2007, 28(5):1262-1265.
[9] BANERJEE A, BURLINA P, DIEHL C. A support vector method for anomaly detection in hyperspectral imagery[J]. IEEE Transactions on Geoscience and Remote Sensing, 2006, 44(8):2282-2291.
[10] 谌德荣, 宫久路, 何光林, 等. 高光谱图像全局异常检测RFS-SVDD算法[J]. 宇航学报, 2010, 31(1):228-232. CHEN Derong, GONG Jiulu, HE Guanglin, et al. A RFS-SVDD algorithm for hyperspectral global anomaly detection[J]. Journal of Astronautics, 2010, 31(1):228-232.
[11] 蒲晓丰, 雷武虎, 汤俊杰, 等. 基于带野值的SVDD的高光谱图像异常检测[J]. 光电工程, 2010, 37(12):83-87. PU Xiaofeng, LEI Wuhu, TANG Junjie, et al. Anomaly detection for hyperspectral image based on svdd with negative examples[J]. Opto-Electronic Engineering, 2010, 37(12):83-87.
[12] 谌德荣, 张立燕, 陶鹏, 等. 结合邻域聚类分割的高光谱图像异常检测支持向量数据描述方法[J]. 宇航学报, 2007, 28(3):767-771. CHEN Derong, ZHANG Liyan, TAO Peng, et al. Support vector data description for anomaly detection in hyperspectral imagery combined with neighboring clustering segmentation[J]. Journal of Astronautics, 2007, 28(3):767-771.
[13] 张立燕. 高光谱图像异常检测算法研究[D].北京:北京理工大学, 2007:111.ZHANG Liyan. Hyperspectral image anomaly detection algorithm research[D]. Beijing:Beijing Institute of Technology, 2007:111.
[14] 何守印, 张立燕. 支持向量异常检测在图像有损压缩中的应用[J]. 电子器件, 2008, 31(2):410-413. HE Shouyin, ZHANG Liyan. Research on image compression method based on anomaly detection[J]. Chinese Journal Of Electron Devices, 2008, 31(2):410-413.
[15] 陶鹏, 谌德荣, 范宁军, 等. 基于RFS和ART的高光谱图像主成分提取方法[J]. 中北大学学报:自然科学版, 2010, 31(3):286-290. TAO Peng, CHEN Derong, FAN Ningjun, et al. Hyperspectral image principle component extraction method based on RFS and ART[J]. Journal of North University of China Natural Science Edition, 2010, 31(3):286-290.
[16] 李杰, 赵春晖, 梅锋. 利用背景残差数据检测高光谱图像异常[J]. 红外与毫米波学报, 2010, 29(2):150-155. LI Jie, ZHAO Chunhui, MEI Feng. Detecting hyperspectral anomaly by using background residual error data[J]. Journal of Infrared and Millimeter Waves, 2010, 29(2):150-155.

相似文献/References:

[1]张玉玲,尹传环.依特征频率的安卓恶意软件异常检测的研究[J].智能系统学报,2018,13(02):168.[doi:10.11992/tis.201609016]
 ZHANG Yuling,YIN Chuanhuan.Android malware outlier detection based on feature frequency[J].CAAI Transactions on Intelligent Systems,2018,13(03):168.[doi:10.11992/tis.201609016]

备注/Memo

备注/Memo:
收稿日期:2013-09-27。
基金项目:国家自然科学基金资助项目(41201075);北京市教委科技资助项目(KM201210028012)
作者简介:曾现灵,女,1989年生,硕士研究生,主要研究方向为高光谱图像处理;胡荣华,男,1987年生,硕士研究生,主要研究方向为高光谱遥感图像处理及应用。
通讯作者:张立燕,女,1977年生,讲师,博士后,主要研究方向为高光谱图像处理与应用。近年参与国家"863"计划项目1项、主持北京市教委项目1项,发表学术论文13篇,E-mail:zhangliyan010@126.com。
更新日期/Last Update: 1900-01-01