Please wait a minute...
img

官方微信

遥感技术与应用  2015, Vol. 30 Issue (2): 292-297    DOI: 10.11873/j.issn.1004-0323.2015.2.0292
图像与数据处理     
基于信噪比估计的波段选择与高光谱异常检测
王晶,王丽姣,崔建涛,厉小润
(浙江大学电气工程学院,浙江 杭州310027)
Band Selection based on Signal-to-noise Ratio Estimation and Hyperspectral Anomaly Detection
Wang Jing,Wang Lijiao,Cui Jiantao,Li Xiaorun
(College of Electrical Engineering,Zhejiang University,Hangzhou 310027,China)
 全文: PDF(5174 KB)  
摘要:

有效的波段选择方法可以极大地提高高光谱图像处理速度的同时改善处理效果。为了自动判断低信噪比波段,提出了一种基于小波变换的图像信噪比估计(SNR estimation,SNRE)方法,利用小波变换后对角方向上的高频成分估计噪声方差并计算信噪比。将该方法分别结合基于方差和相关系数(V_COR)的最优索引指数、最大信息量(MI)、高阶矩(偏度或峰度)结合信息散度(K3_KL)等3种基于信息量的波段选择方法后选择波段。将这些改进后的波段选择方法应用于高光谱异常检测。实验结果表明SNRE预选波段结合MI和K3_KL选择波段用于异常检测能进一步提高检测精度。

关键词: 波段选择信息度量指数高光谱异常检测高阶矩    
Abstract:

Effective band selection algorithms can greatly improve the hyperspectral image processing speed and effect simultaneously.In order to automatically determine low signal\|to\|noise bands,a new image signal\|to\|noise ratio estimation (SNRE) method is proposed based on wavelet transform.Performing wavelet transform on each band image which is assumed to be only corrupted by additive Gaussian noise,and the mid\|value of high frequency component of the wavelet transform is used to estimate the noise variance,then further to calculate the SNR.This method is then integrated with three band selection methods based on information such as optimal index factor defined by variance and correlation coefficient (V_COR),maximal information (MI) and high order moments (kurtosis or skewness) combined with the divergence (K3_KL) to select bands respectively.These improved methods are evaluated by experiments of hyperspectral anomaly detection.Experimental results demonstrate that SNRE combined with MI or K3_KL which can further improve the results of anomaly detection.

Key words: Band selection    Information measure index    Hyperspectral image anomaly detection    High order moment
收稿日期: 2013-09-27 出版日期: 2015-05-08
:  TP 751.1  
基金资助:

浙江省自然科学基金项目(LY13F020044,LZ14F030004),国家自然科学基金项目(61171152)。

通讯作者: 厉小润(1970-),男,浙江东阳人,研究员,主要从事图像处理与模式识别、计算机应用方面的研究。Email:lxr@zju.edu.cn。    
作者简介: 王晶(1988-),男,浙江东阳人,工程师,主要从事图像处理方面的研究。Email:wjaaal@zju.edu.cn。
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  
王晶
王丽姣
崔建涛
厉小润

引用本文:

王晶,王丽姣,崔建涛,厉小润. 基于信噪比估计的波段选择与高光谱异常检测[J]. 遥感技术与应用, 2015, 30(2): 292-297.

Wang Jing,Wang Lijiao,Cui Jiantao,Li Xiaorun. Band Selection based on Signal-to-noise Ratio Estimation and Hyperspectral Anomaly Detection. Remote Sensing Technology and Application, 2015, 30(2): 292-297.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2015.2.0292        http://www.rsta.ac.cn/CN/Y2015/V30/I2/292

[1]Chavez P S,Berlin G L,Sowers B L.Statistical Method for Selecting Landsat MSS Ratios[J].Journal of Applied Photographic Engineering,1982,8(1):23-30.

[2]Liu Chunhong,Zhao Chunhui,Zhang Lingyan.A New Method of Hyperspetral Remote Sensing Imagedimensional Reduction[J].Journal of Image and Graphics,2005,10(2):218-222.[刘春红,赵春晖,张凌雁.一种新的高光谱遥感图像降维方法[J].中国图象图形学报,2005,10(2):218-222.]

[3]Du Q.Band Selection and Its Impact on Target Detection and Classification in Hyperspectral Image Analysis[C]//IEEE Workshop on Advances in Techniques for Analysis of Remotely Sensed Data,2003:374-377.

[4]Liu Xuesong,Ge Liang,Wang Bin,et al.An Unsupervised band Selection Algorithm for Hyperspectral Imagery based on Maximal Information[J].Journal of Infrared and Millimeter Wave,2012,31(2):166-176.[刘雪松,葛亮,王斌,等.基于最大信息量的高光谱遥感图像无监督波段选择方法[J].红外与毫米波学报,2012,31(2):166-176.]

[5]Feng J,Jiao L C,Zhang X G,et al.Hyperspectral Band Selection based on Trivariate Mutual Information and Clonal Selection[J].IEEE Transactions on Geoscience and Remote Sensing,2014,52(7):4092-4105.

[6]He Yuanlei,Liu Daizhi,Yi Shihua,et al.Band Selection based on Hierarchical Clustering for Hyperspectral Target Detection[J].Chinese Journal of Scientific Instrument,2011,32(4):825-830.[何元磊,刘代志,易世华,等.面向目标探测的高光谱图像层次聚类波段选择[J].仪器仪表学报,2011,32(4):825-830.]

[7]Feng J,Jiao L C,Liu F,et al.Mutual-Information-based Semi-Supervised Hypers-pectral Band Selection with High Discrimination,High Information,and Low Redundancy[J].IEEE Transactions on Geoscience and Remote Sensing,2015,53(5):2956-2969.

[8]Jia S,Ji Z,Qian Y T,et al.Unsupervised Band Selection for 〖JP2〗Hyperspectral Imagery Classification without Manual Band Removal[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2012,5(2):531-543.

[9]Yang H,Du Q,Chen G.Unsupervised Hyperspectral Band Selection Using Graphics Processing Units[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2011,4(3):660-668.

[10]Zhou Y,Li X R,Cui J T.High-efficiency Hyperspectral Unmixing based on Band Selection[C]//Third Global Congress on Intelligent Systems,2012:140-143.

[11]Plaza A,Martinez P,Perez R,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.

[12]Corner B R.Noise Estimation in Remote Sensing Imagery Using Data Masking[J].International Journal of Remote Sensing,2003,24(4):689-702.

[13]Gao Lianru,Zhang Bing,Zhang Xia,et al.Study on the Method for Estimating the Noise in Remote Sensing Images based on Local Standard Deviations[J].Journal of Remote Sensing,2007,11(2):201-208.[高连如,张兵,张霞,等.基于局部标准差的遥感图像噪声评估方法研究[J].遥感学报,2007,11(2):201-208.]

[14]Donoho D L,Johnstone I M.Ideal Spatial Adaptation Via Wavelet Shrinkage[J].Biometrika,1994,81(3):425-455.

[15]Lin Zhemin,Kang Xuelei,Zhang Liming.EM Algorithm for Estimating the Noise Deviationof the Image in the Wavelet Domain[J].Journal of Infrared and Millimeter Wave,2001,20(3):199-202.[林哲民,康学雷,张立明.小波域中进行图像噪声方差估计的EM 方法[J].红外与毫米波学报,2001,20(3):199-202.]

[16]Li Tianyi,Wang Minghui,Chang Huawen,et al.An Entropy-based Estimation of Noise Variance in Wavelet Domain[J].Journal of Beijing University of Posts and Telecommunications,2001,34(5):2-5.[李天翼,王明辉,常化文,等.基于熵检测的图像噪声方差小波域估计[J].北京邮电大学学报,2001,34(5):2-5.]

[17]Zhao Wenji,Duan Fuzhou,Liu Xiaomeng,et al.ENVI Remote Sensing Image Processing Project and Practice[M].Beijing:China Environmental Science Press,2007.[赵文吉,段福州,刘晓萌,等.ENVI遥感影像处理专题与实践[M].北京:中国环境科学出版社,2007.]

[18]AVIRIS.NW Indiana’s Indian Pines 1992 Data Set[EB/OL].https://engineering.purdue.edu/biehl/MultiSpec/hyperspectral.html,1992,2013-4.

[1] 苏红军,赵波. 基于共形几何代数的高光谱遥感波段选择方法[J]. 遥感技术与应用, 2017, 32(3): 539-545.
[2] 张路,刘良云,高建威,焦全军,贾建华. 基于蚁群优化算法的遥感器波段设置探究[J]. 遥感技术与应用, 2016, 31(3): 488-496.
[3] 丁小辉,李华朋,张树清. 基于多态蚁群算法的高光谱遥感影像最优波段选择[J]. 遥感技术与应用, 2016, 31(2): 275-284.
[4] 李茜楠,苏红军. 基于萤火虫算法的高光谱遥感波段选择方法[J]. 遥感技术与应用, 2014, 29(5): 761-770.
[5] 张汉奎,黄 波,俞 乐. SVM-RFE高光谱数据波段选择中核函数的研究[J]. 遥感技术与应用, 2013, 28(5): 747-752.
[6] 黄长平, 刘 波, 张 霞, 童庆禧. 土壤重金属Cu含量遥感反演的波段选择与最佳光谱分辨率研究[J]. 遥感技术与应用, 2010, 25(3): 353-357.
[7] 周旭, 安裕伦, 张斌, 蒋良群. BERS-CCD数据土地利用/覆盖信息 提取最佳波段选择——以贵州喀斯特山区为例[J]. 遥感技术与应用, 2009, 24(6): 743-748.
[8] 杨金红,尹 球,周 宁. 一种改进的高光谱数据自适应波段选择方法[J]. 遥感技术与应用, 2007, 22(4): 513-519.