Please wait a minute...
J4  2011, Vol. 45 Issue (4): 607-613    DOI: 10.3785/j.issn.1008-973X.2011.04.004
自动化技术、电信技术     
非监督的高光谱混合像元非线性分解方法
厉小润1, 伍小明1, 赵辽英2
1.浙江大学 电气工程学院,浙江 杭州 310027; 2.杭州电子科技大学 计算机应用技术研究所,浙江 杭州 310018
Unsupervised nonlinear decomposing method of
hyperspectral imagery
LI Xiao-run1, WU Xiao-ming1, ZHAO Liao-ying2
1. College of Electrical Engineering,Zhejiang University,Hangzhou 310027, China; 2. Institute of Computer
Application Technology, Hangzhou Dianzi University, Hangzhou 310018, China
 全文: PDF  HTML
摘要:

在进行高光谱混合像元非线性分解应用中,提出一种非监督的高光谱混合像元非线性分解方法.通过核函数把原始高光谱数据映射到高维特征空间中,揭示数据之间的高阶性质.通过非线性映射,原始数据在高维特征空间中变得线性可分.在高维特征空间中运用线性的非负矩阵分解(NMF)算法进行光谱解混,挖掘出数据间更多的特征.解混结果以端元相关系数、光谱角距离、光谱信息散度和均方根误差作为质量评价指标.进行模拟数据仿真实验和真实高光谱遥感数据分解实验,结果表明,采用该算法得到的分解结果优于非负矩阵分解算法.

Abstract:

An unsupervised nonlinear decomposing algorithm for hyperspectral imagery was introduced to solve the nonlinear decomposing problem of hyperspectral imagery. The original data were mapped into a high-dimensional feature space by a nonlinear mapping, which was associated with a kernel function. Then the higher order relationships between the data were exploited. The mapped data became linearly separable in the high-dimensional feature space by using an appropriate nonlinear mapping. Then a linear nonnegative matrix factorization (NMF) method can be applied to extract more useful features. Endmember correlation coefficient, spectral angle distance, spectral information divergence and root mean square error were used to estimate the quality of the results. The experimental results of synthetic mixtures and a real image scene demonstrated that the method outperformed the nonnegative matrix factorization approach.

出版日期: 2011-05-05
:  TP 751  
基金资助:

浙江省自然科学基金资助项目(Y1100196).

作者简介: 厉小润(1970—),男,浙江东阳人,副教授,从事模式识别和遥感图像分析的研究.E-mail: lxr@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  

引用本文:

厉小润, 伍小明, 赵辽英. 非监督的高光谱混合像元非线性分解方法[J]. J4, 2011, 45(4): 607-613.

LI Xiao-run, WU Xiao-ming, ZHAO Liao-ying. Unsupervised nonlinear decomposing method of
hyperspectral imagery. J4, 2011, 45(4): 607-613.

链接本文:

http://www.zjujournals.com/eng/CN/10.3785/j.issn.1008-973X.2011.04.004        http://www.zjujournals.com/eng/CN/Y2011/V45/I4/607

[1] 陶雪涛,王斌,张立明.基于NMF的遥感图像混合像元分解新方法[J].信息与电子工程,2008,6(1): 34-39.
TAO Xuetao, WANG Bin, ZHANG Liming. New scheme for decomposition of mixed pixels of remote sensing images based on nonnegative matrix factorization [J]. Information and Electronic Engineering, 2008, 6(1): 34-39.
[2] KWON H, NASRABADI N M. Kernel orthogonal subspace projection for hyperspectral signal classification [J]. Geoscience and Remote Sensing, 2005, 43(12): 2952-2962.
[3] 童庆禧,张兵,郑兰芬.高光谱遥感:原理、技术与应用[M].北京:高等教育出版社,2006: 255-262.
[4] SJOHN S T, NELLO C. Kernel methods for pattern analysis [M]. Beijing: China Machine Press, 2005: 15-27.
[5] 吴波,张良培,李平湘.基于支撑向量回归的高光谱混合像元非线性分解[J].遥感学报,2006,10(3): 312-318.
WU Bo, ZHANG Liangpei, LI Pingxiang. Unmixing hyperspectral imagery based on support vector nonlinear approximating regression [J]. Journal of Remote Sensing, 2006, 10(3): 312-318.
[6] 贾森.非监督的高光谱图像解混技术研究[D].杭州:浙江大学,2007.
JIA Sen. Unsupervised hyperspectral unmixing theory and techniques [D]. Hangzhou: Zhejiang University, 2007.
[7] LEE D D, SEUNG H S. Algorithms for nonnegative matrix factorization [J]. Advances in Neural Information Processing Systems, 2001, 3(13): 556-562.
[8]  PAURA V P, PIPER J, PLEMMONS R J. Nonnegative matrix factorization for spectral data analysis [J]. Linear Algebra Applications,2006, 416(1): 29-47.
[9]  TAO Xuetao,WANG Bin, ZHANG Liming, et al. A new scheme for decomposition of mixed pixels based on nonnegative matrix factorization [C]∥ International Conference on Geoscience and Remote Sensing Symposium. Barcelona: IEEE, 2007: 1759-1762.
[10] MIAO L D, QI H R. Endmember extraction from highly mixed data using minimum volumn constrained nonnegative matrix factorization [J]. IEEE Transactions on Geoscience and Remote Sensing,2007, 45(3): 765-777.
[11] ZHANG Daoqiang, ZHOU Zhihua, CHEN Songcan. Nonnegative matrix factorization on kernels [C]∥ 9th Pacific Rim International Conference on Artificial Intelligence. Guilin, China: \
[s.n.\], 2006: 404-412.
[12] United States Geological Survey Spectroscopy Lab [EB/OL]. \
[2009-08-20\]. http:∥speclab.cr.usgs.gov.
[13] CLARK R N, SWAYZE G A, GALLAGHER A. Mapping minerals with imaging spectroscopy [EB/OL]. \
[2009-08-20\]. http:∥speclab.cr.usgs.gov/cuprite.html.
[14] CHANG C I, DU Q. Estimation of number of spectrally distinct signal sources in hyperspectral imagery [J]. IEEE Transaction on Geoscience and Remote Sensing, 2004, 42(3): 608-619.
[15] SWAYZE G. The hydrothermal and structural history of the cuprite mining district,southwestern Nevada: an integrated geological and geophysical approach [D]. Boulder: University of Colorado, 1997.
[16] GRANT M, BOY S, YE Y. Matlab software for disciplined convex programming [EB/OL]. \
[2009-08-20\]. http:∥www stanford.edu/~boyd/-cvx.

[1] 崔建涛,王晶,厉小润,赵辽英. 基于空间像素纯度指数的端元提取算法[J]. J4, 2013, 47(9): 1517-1523.
[2] 崔建涛, 厉小润, 赵辽英. 高光谱图像亚像元级地物端元提取方法[J]. J4, 2012, 46(10): 1857-1865.
[3] 张登荣, 俞乐, 张汉奎, 等. 光学遥感影像快速镶嵌方法[J]. J4, 2009, 43(11): 1988-1993.