基于光谱角累加的高光谱图像异常检测算法

杜小平; 刘明; 夏鲁瑞; 陈杭

doi:10.3788/CO.20130603.0325

基于光谱角累加的高光谱图像异常检测算法

doi: 10.3788/CO.20130603.0325

中国人民解放军装备学院, 北京 101416

详细信息

作者简介:
杜小平(1966-),女,河北昌黎人,博士,教授,博士生导师,2004年于北京理工大学获得博士学位,主要从事目标光学特性分析、检测与识别等方面的研究。E-mail:dxp8600@163.com;刘明(1987-),男,吉林长春人,硕士,2010年于上海交通大学获得学士学位,2012年于装备学院获得硕士学位,主要从事高光谱图像分类、目标检测等方面的研究。E-mail:270887961@qq.com

杜小平(1966-),女,河北昌黎人,博士,教授,博士生导师,2004年于北京理工大学获得博士学位,主要从事目标光学特性分析、检测与识别等方面的研究。E-mail:dxp8600@163.com;刘明(1987-),男,吉林长春人,硕士,2010年于上海交通大学获得学士学位,2012年于装备学院获得硕士学位,主要从事高光谱图像分类、目标检测等方面的研究。E-mail:270887961@qq.com

通讯作者:
杜小平

中图分类号: TP751.1
计量
- 文章访问数: 2904
- HTML全文浏览量: 403
- PDF下载量: 579
- 被引次数: 0
出版历程
- 收稿日期: 2013-02-16
- 修回日期: 2013-04-17
- 刊出日期: 2013-06-10

Anomaly detection algorithm for hyperspectral imagery based on summation of spectral angles

Academy of Equipment, Chinese People's Liberation Army, Beijing 101416, China

摘要

摘要: 针对传统方法中用作背景的像素中存在干扰像素的问题,提出一种基于光谱角累加的高光谱图像异常检测算法。通过计算测试区域待测像素光谱向量与其他光谱向量之间的夹角,并将其累加,得到图像中每个像素的异常程度;然后使用波段选择预处理方法进一步提高检测性能。HyMap高光谱数据验证表明,在虚警概率设为0.008时,检测概率达到0.73,即在提高异常检测可靠度的同时,降低了虚警概率。
- 高光谱图像 /
- 异常检测 /
- 光谱角 /
- 波段选择
Abstract: As interference pixels influence the background features in traditional methods, a new anomaly detection algorithm for hyperspectral imagery is proposed based on the summation of spectral angles. The anomaly degree of each pixel in the imagery is acquired by calculating the angles between the spectral vector of test pixel and other spectral vectors in the test region, and accumulating the angles. Then, the pretreatment method of band selection is used to further improve detection performance. HyMap hyperspectral data experiments show that the detection probability reaches 0.73 when the probability of false alarm is set to be 0.008. The reliability of anomaly detection is improved, while the probability of false alarm is reduced.
- hyperspectral imagery /
- anomaly detection /
- spectral angle /
- band selection

HTML全文

参考文献(1)

[1] 赵慧洁,秦宝龙,贾国瑞. 高光谱遥感系统调制传递函数的在轨测试[J]. 光学精密工程,2011,19(6):1235-1243. ZHAO H J,QIN B L,JIA G R. On-orbit detection for modulation transfer function of hyperspectral remote sensing system[J]. Opt. Precision Eng.,2011,19(6):1235-1243.(in Chinese) [2] 董超,赵慧洁,王维,等. 局部正交子空间投影高光谱图像异常检测算法[J]. 光学精密工程,2009,17(8):2004-2010. DONg CH,ZHAO H J,WANG W,et al.. Hyperspectral image anomaly detection algorithm based on local orthogonal subspace projection[J]. Opt. Precision Eng.,2009,17(8):2004-2010.(in Chinese). [3] 李欢,周峰. 星载超光谱成像技术发展与展望[J]. 光学与光电技术,2012,10(5):38-44. LI H,ZHOU F. Developments of spaceborne hyperspectral imaging technique[J]. Opt. Optoelectronic Technology,2012,10(5):38-44.(in Chinese). [4] REED I S,YU X. Adaptive multiple-band CFAR detection of an optical pattern with unknown spectral distribution[J]. IEEE T. Acoust., Speech,1990,38(10):1760-1770. [5] ADLER-GOLDEN S M. Improved hyperspectral anomaly detection in heavy-tailed backgrounds [C]//Hyperspectral Image and Signal Processing: Evolution in Remote Sensing,2009 WHISPERS'09. First workshopon,2009:1-4. [6] HARSANYI J C,CHANG C I. Hyperspectral image classification and dimensionality reduction: an orthogonal subspace projection approach[J]. IEEE T. Geosci. Remote,1994,32(4):779-785. [7] BANERJEE A,BURLINA P,DIEHL C. A support vector method for anomaly detection in hyperspectral imagery[J]. IEEE T. Geosci. Remote,2006,44(8):2282-2291. [8] KHAZAI S,HOMAYOUNI S,SAFARI A,et al.. Anomaly detection in hyperspectral images based on an adaptive support vector method[J]. IEEE Geosci. Remote Sensing Lett,,2011,8(4):646-650. [9] 杜培军,谭琨,夏俊士.高光谱遥感影像分类与支持向量机应用研究[M]. 北京.科学出版社,2012:29-31. DU P J,TAN K,XIA J SH. Research on Application of Support Vector Machine and classification of Hyperspectral Remote Sensing Imagery[M]. Beijing:Science Press,2012:29-31. [10] ROGER R E,ARNOLD J F. Reliably estimating the noise in AVIRIS hyperspectral images[J]. International J. Remote Sensing,1996,17(10):1951-1962. [11] AIAZZI B,ALPARONE L,BARONTI F,et al.. Hyperspectral noise modelling and estimation hyperspectral data from airborne imaging spectrometers[J]. Anuals of Geophysics,2006,49(1):3141 [12] 穆治亚, 魏仲慧, 何昕,等. 基于NIOSⅡ的红外弱小目标检测算法实现[J]. 液晶与显示,2012,(6):814-819. MU ZH Y,WEI ZH H,HE X,et al.. Design of dim-small target detection on infrared image based on NIOSⅡ[J]. Chinese J. Liquid Crystals abd Displays,2012,(6):814-819.(in Chinese) [13] 吴君钦,刘昊,罗勇静. 态背景下的运动目标检测算法[J]. 液晶与显示,2012,(5):682-686. WU J Q,LIU H,LUO Y. Algorithm of moving object detection in static background[J]. Chinese J. Liquid Crystals abd Displays,2012,(5):682-686.(in Chinese) [14] 刘翔,周桢. 基于分块背景建模的运动目标检测技术[J]. 液晶与显示,2011,26(6):831-835. LIU X,ZHOU ZH. Moving objectives detecting technology based on block processing of background model establishment[J]. Chinese J. Liquid Crystals abd Displays,2011,26(6):831-835.(in Chinese)

施引文献

附加信息(0)

访问统计