基于K-L散度与光谱可分性距离的波段选择算法

杨佳; 华文深; 刘恂; 马左红

基于K-L散度与光谱可分性距离的波段选择算法

杨佳^1, ,,
华文深¹,
刘恂¹,
马左红²

1.
军械工程学院,河北石家庄 050003;
2.
解放军73101部队,江苏徐州 221000

详细信息

通讯作者:
杨佳(1989-)，男，河北石家庄人，硕士研究生，主要从事光电对抗研究工作。 Email: 742811772@qq.com

中图分类号: TN911.73; TP751
计量
- 文章访问数: 1942
- HTML全文浏览量: 97
- PDF下载量: 314
- 被引次数: 0
出版历程
- 刊出日期: 2014-01-15

Band selection algorithm for hyperspectral imagery based on K-L divergence and spectral divisibility distance

1.
Mechanical Engineering College,Shijiazhuang 050003,China;
2.
Unit 73101 of PLA,Xuzhou 221000,China

摘要

摘要: 波段选择是高光谱降维的常用手段，文中从波段选择应遵循的3个原则出发设计了一种基于信息散度与光谱可分性距离的波段选择算法。将高光谱数据中每个波段的光谱分量看作一个一维向量，使用K-L散度表示其相互之间的信息量，选出信息量大且相似性最小的波段组合；根据每个波段中不同地物光谱可分性距离的计算，得到可分性较大的波段组合；将两组波段组合取交集，即得到最优组合波段。为了验证算法的有效性，将选出的最佳3个波段进行伪彩色合成，对其进行光谱角制图分类，分类精度达到92.2%，Kappa系数为0.88.
- 高光谱成像 /
- 波段选择 /
- K-L散度 /
- 光谱可分性 /
- 光谱角制图
Abstract: Band selection is a common approach to reduce data dimensionality of hyperspectral imagery. A new band selection algorithm for hyperspectral imagery based on Kullback-Liebler (K-L) divergence and spectral divisibility was proposed. Firstly by considering every waveband spectral component as the onedimensional vector, the K-L divergence was used to quantify the information amount among them to select the bands combination with maximum information amount and minimum similarity. Then the spectral divisibility distance between two ground objects was calculated to remove redundant bands from the selected bands combination and make the final selected bands combination contain optimal divisibility. Hyperspectral imagery was tested for classification to testify the effectiveness of this band selection algorithm. As shown in the experimental results, the classification accuracy percentage is 92.2% and Kappa coefficient is 0.88, when using spectral angle mapping on the pesudo color synthesis image of 3 selected bands.
- hyperspectral imaging /
- band selection /
- K-L divergence /
- spectral divisibility /
- spectral angle mapping method

HTML全文

参考文献(1)

［1］张良培,张立福.高光谱遥感[M].武汉:武汉大学出版社,2005.
ZHANG Liang-pei, ZHANG Li-fu. Hyperspectral remote sensing [M]. Wuhan: Wuhan University Press, 2005.(in Chinese)
[2]刘建平,赵英时,孙淑玲.高光谱遥感数据最佳波段选择方法试验研究[J].遥感技术与应用, 2001, 16(1):7-13.
LIU Jian-ping, ZHAO Ying-shi, SUN Shu-ling. Experimental studies about methods on optimal bands selection of hyperspectral remote sensing datasets[J]. Remote Sensing Technology and Application. 2001, 16(1):7-13.(in Chinese with an English abstrast)
[3]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.
YANG Jin-hong, YIN Qiu, ZHOU Ning. An improved method of hyperspectral remote sensing data adaptive band selection[J]. Remote Sensing Technology and Application, 2007, 22(4):513~519.(in Chinese with an English abstrast)
[4]DU Qian. Band selection and its impact on target detection and classification in hyperspectral image analysis[C]. Maryland: IEEE Greenbelt, 2003:374-377.
[5]CHANG Chein-I, WANG Su. Constrained band selection for hyperspectral imagery[J]. IEEE Trans. Geosci. Remote Sens, 2006, 44(6):1575-1585.
[6]DU Qian, YANG He. Similarity-based unsupervised band selection for hyperspectral image analysis[J]. IEEE Geosci. Remote Sens. 2008, 5(4):564-568.
[7]杜培军. 高光谱遥感信息中的特征提取与应用研究[J]. 光子学报, 2005, 34(2):293-298.
DU Pei-jun. Spectral feature extraction in hyperspectral RS date and its application to information processing[J]. Acta photonica sinica, 2005, 34(2):293-298.(in Chinese with an English abstract)
[8]SHEFFIELD C. Selecting band combinations from multispectral data[J]. Photogrammetric Engineering & Remote Sensing, 1985, 51(6):681-687.
[9]何元磊,刘代志,易世华.一种新的高光谱图像波段选择方法[J].光电工程, 2009, 37(9):122-126.
HE Yuan-lei, LIU Dai-zhi, YI Shi-hua. A new band selection method for hyperspectral images[J]. Opto-Electronic Engineering, 2009, 37(9):122-126.(in Chinese with an English abstrast)
[10]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):166-170.
LIU Xue-song, GE Liang, WANG Bin, et al. An unsupervised band selection algorithm for hyperspectral imagery based on maximal information[J]. Journal of Infrared and Millimeter Waves, 2012, 31(2):166-170.(in Chinese with an English abstract)

施引文献

资源附件(0)

访问统计