光电工程, 2012, 39 (6): 71, 网络出版: 2012-06-25   

基于矩阵模式的高光谱波段选择方法

An Efficient Hyperspectral Band Selection Method Based on Matrix Mode
作者单位
1 中国科学院安徽光学精密机械研究所环境光学与技术重点实验室,合肥 230031
2 合肥师范学院数学系,合肥 230061
摘要
去除冗余信息,进行特征提取是当前高光谱数据处理的一个重要课题。本文根据波段选择的基本准则,结合离散系数和相关系数对高光谱影像空间维和光谱维的可分性及相关性进行分析,提出了基于矩阵模式的高光谱波段选择方法 -BSMM,并且定义了一个矩阵因子。在计算空间信息量时比较了标准差和离散系数的量化结果,除此之外,采用区间映射有效地消除了离散系数和相关系数变换区间不一致的情况。最后利用 AVIRIS高光谱数据,通过与最佳指数因子的比较验证了该方法的有效性。
Abstract
It is an important task to remove the redundant information in hyperspectral images. In this work, a band selection method for hyperspectral data based on matrix mode (BSMM) is proposed by combining the coefficient of variance and the correlation coefficient and a matrix factor is defined. By using the coefficient of variance and the correlation coefficient, we analyze the separability and correlation of hyperspectral images and compare the standard deviation and coefficient of variation when the measurement of spatial dimension information is discussed. In addition, interval mapping is adopted to remove the difference of variation interval between the coefficient of variation and the correlation coefficient. The efficiency of this method is demonstrated by the analysis of AVIRIS hyperspectral data.
参考文献

[1] 姜小光,王长耀,王成. 成像光谱数据的光谱信息特点及最佳波段选择 -以北京顺义区为例 [J]. 干旱区地理,2003,2(3): 214-220. JIANG Xiao-guang,WANG Chang-yao,WANG Cheng. Optimum band selection of hyperspectral remote sensing data [J]. Arid Land Geography,2003,2(3):214-220.

[2] CHACVEZ P S,BERLN G L,SOWERS L B. Statistical method for selecting Landsat MSS ratios [J]. Journal of Applied Photographic Engineering (S0098-7298),1982,8(1):23-30.

[3] ARZUAGA-CRUZ E,JIMENEZ-RODRIGUEZ L O,VELEZ-REYES M. Unsupervised feature extraction and band subset selection techniques based on relative entropy criteria for hyperspectral data analysis [C]// Proc of SPIE Algorithm and Technologies for Multispectral,Hyperspectral,and Ultrospectral Imagery,Orlando,FL,USA,April 21,2003:462-473.

[4] BAJCSY P,GROVES P. Methodology for hyperspectral band selection [J]. Photogrammetric Engineering and Remote Sensing (S0099-1112),2004,70(7):793-802.

[5] SHEFFIELD C. Selecting band combinations from multispectral data [J]. Photogrammetric Engineering & Remote Sensing (S0099-1112),1985,51(6):681-687.

[6] 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. LIU Chun-hong,ZHAO Chun-hui,ZHANG Ling-yan. A new method of hyperspectral remote sensing image dimensional reduction [J]. China Journal of Image and Graphics,2005,10(2):218-222.

[7] 苏红军,杜培军,盛业华 . 高光谱遥感数据光谱特征提取算法与分类研究 [J]. 计算机应用研究,2008,25(4):1093-1096. SU Hong-jun,DU Pei-jun,SHENG Ye-hua. Study on feature extraction and experiment of hyperspectral data [J]. Application Research of Computers,2008,25(4):1093-1096.

[8] 苏红军,盛业华, YANG He,等. 基于正交投影散度的高光谱遥感波段选择算法 [J].光谱学与光谱分析, 2011,31(5): 1309-1313. SU Hong-jun,SHENG Ye-hua,YANG He,et al. Orthogonal projection divergence-based hyperspectral band selection [J]. Spectroscopy and Spectral Analysis,2011,31(5):1309-1313.

[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,2010,37(9):122-126. HE Yuan-lei,LIU Dai-zhi,YI Shi-hua. A new band selection method for Hyperspectral images [J]. Opto-Electronic Engineering,2010,37(9):122-126.

[10] KWAK N,CHOI C-H. Input feature selection for classification problems [J]. IEEE Trans. Neural Networks(S0893-6080), 2002,13(1):143-159.

[11] CHANG C I. An information-theoretic approach to spectral variability,similarity,and discrimination for hyperspectral image analysis [J]. IEEE Transactions on Information Theory(S0018-9448),2000,46(5):1927-1932.

[12] KRUSE F A,LEFKOFF A B,BOARDMAN J W,et al. The Spectral Image Processing System (SIPS)-Interactive Visualization and Analysis of Imaging Spectrometer Data [J]. Remote Sensing Environment(S0034-4257),1993,44(2):145-163.

[13] KESHAVA N. Best bands selection for detection in hyperspectral Processing [C]// Proceedings of the IEEE International Conference in Acoustics,Speech,and Signal Processing,Salt Lake City,UT,USA,May 7-11,2001,5:3149-3152.

于绍慧, 张玉钧, 赵南京, 肖雪, 王欢博. 基于矩阵模式的高光谱波段选择方法[J]. 光电工程, 2012, 39(6): 71. YU Shao-hui, ZHANG Yu-jun, ZHAO Nan-jing, XIAO Xue, WANG Huan-bo. An Efficient Hyperspectral Band Selection Method Based on Matrix Mode[J]. Opto-Electronic Engineering, 2012, 39(6): 71.

本文已被 1 篇论文引用
被引统计数据来源于中国光学期刊网
引用该论文: TXT   |   EndNote

相关论文

加载中...

关于本站 Cookie 的使用提示

中国光学期刊网使用基于 cookie 的技术来更好地为您提供各项服务,点击此处了解我们的隐私策略。 如您需继续使用本网站,请您授权我们使用本地 cookie 来保存部分信息。
全站搜索
您最值得信赖的光电行业旗舰网络服务平台!