[1]贾森,钱沄涛,纪震,等.基于光谱和空间特性的高光谱解混方法[J].深圳大学学报理工版,2009,26(3):262-267.
 JIA Sen,QIAN Yun-tao,JI Zhen,et al.Spectral and spatial character-based hyperspectral unmixing[J].Journal of Shenzhen University Science and Engineering,2009,26(3):262-267.
点击复制

基于光谱和空间特性的高光谱解混方法()
分享到:

《深圳大学学报理工版》[ISSN:1000-2618/CN:44-1401/N]

卷:
第26卷
期数:
2009年3期
页码:
262-267
栏目:
光电与信息工程
出版日期:
2009-07-31

文章信息/Info

Title:
Spectral and spatial character-based hyperspectral unmixing
文章编号:
1000-2618(2009)03-0262-06
作者:
贾森1钱沄涛2纪震1沈琳琳1
1)深圳大学德州仪器DSPs实验室,深圳大学计算机与软件学院,深圳 518060;
2)浙江大学计算机学院,杭州 310027
Author(s):
JIA Sen1QIAN Yun-tao2JI Zhen1and SHEN Lin-lin1
1)Texas Instruments DSPs Lab,School of Computer Science and Software Engineering,Shenzhen University,Shenzhen 518060,P.R.China
2)College of Computer Science,Zhejiang University,Hangzhou 310027,P.R.China
关键词:
高光谱解混混合像元线性光谱混合模型非负矩阵分解盲源分离
Keywords:
hyperspectral unmixingmixing pixellinear spectral mixing modelnonnegative matrix factorizationblind source separation
分类号:
TP 753;TP 399
文献标志码:
A
摘要:
为表征高光谱数据的光谱和空间特性,引入光谱的平滑性和地物空间分布的稀疏性约束,提出非负矩阵分解的改进算法,将其应用于高光谱解混.尺度可变的梯度下降算法保证了改进算法的收敛性.实验结果表明,改进后的非负矩阵分解算法能给出地物光谱,并精确估计其分布.
Abstract:
To represent the spectral and spatial character of hyperspectral data,by introducing the smoothness constraint of hyperspectral data and the sparseness constraint of spatial distribution of the materials,an improved nonnegative matrix factorization (INMF) was used for hyperspectral unmixing.Its monotonic convergence is guaranteed by using a gradient-based optimization algorithm.Experiments demonstrate that the INMF algorithm is yielding accurate estimation of both endmember spectra and abundance maps.

参考文献/References:

[1]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.
[2]Nascimento J,Dias J.定点成分分析:一种高光谱解混的快速算法[J].IEEE地球科学与遥感汇刊,2005,43(4):898-910 (英文版).
[3]Wang J,Chang C.独立分量分析在高光谱图像端元提取和丰度量化中的应用[J].IEEE地球科学与遥感汇刊,2006,44(9):2601-2616 (英文版).
[4]Lee D,Seung H.非负矩阵分解算法[C]//第13届高级神经信息处理系统会议.麻省:麻省理工出版社,2000:556-562 (英文版).
[5]Pauca V,Piper J,Plemmons R.非负矩阵分解用于光谱数据分析[J].线性代数及其应用,2006,416(1):29-47(英文版).
[6]Hoyer P.非负稀疏编码[C]//第12届神经网络用于信号处理研讨会.马蒂尼(瑞士):IEEE出版社,2002:557-565 (英文版).
[7]Hoyer P.稀疏约束的非负矩阵分解[J].机器学习研究杂志,2004,5:1457-1469 (英文版).
[8]Chang C,Du Qian.高光谱图像中不同光谱信号源的个数估计[J].IEEE地球科学与遥感汇刊,2004,42(3):608-619 (英文版).
[9]贾森,钱沄涛.基于光谱和空间复杂度的高光谱解混[J].IEEE地球科学与遥感汇刊,2007,45(12):3867-3879 (英文版).
[10]Bethel J,Lee C,Landgrebe D.高光谱数据的几何配准和分类[C]//第19届国际摄影与遥感论坛.阿姆斯特丹:国际摄影与遥感协会,2000:567-571 (英文版).


[1]TONG Qing-xi,ZHANG Bing,ZHENG Lan-fen.Hyperspectral Remote Sensing[M].Beijing:Higher Education Press,2006 (in Chinese).
[2]Nascimento J,Dias J.Vertex component analysis:a fast algorithm to unmix hyperspectral data[J].IEEE Transactions on Geoscience and Remote Sensing,2005,43(4):898-910.
[3]Wang J,Chang C.Applications of independent component analysis in endmember extraction and abundance quantification for hyperspectral imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2006,44(9):2601-2616.
[4]Lee D,Seung H.Algorithms for non-negative matrix factorization[C]//Advances in Neural Information Processing Systems 13.Massachusetts American:MIT Press,2000:556-562.
[5]Pauca V,Piper J,Plemmons R.Nonnegative matrix factorization for spectral data analysis[J].Linear Algebra and Applications,2006,416(1):29-47.
[6]Hoyer P.Non-negative sparse coding[C]// 12th Workshop on Neural Networks for Signal Processing.Martigny(Switzerland):IEEE Press,2002:557-565.
[7]Hoyer P.Non-negative matrix factorization with sparseness constraints[J].Journal of Machine Learning Research,2004,5:1457-1469.
[8]Chang C,Du Qian.Estimation of number of spectrally distinct signal sources in hyperspectral imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2004,42(3):608-619.
[9]JIA Sen,QIAN Yun-tao.Spectral and spatial complexity based hyperspectral unmixing[J].IEEE Transactions on Geoscience and Remote Sensing,2007,45(12):3867-3879.
[10]Bethel J,Lee C,Landgrebe D.Geometric registration and classification of hyperspectral airborne pushbroom data[C]//19th International Symposium on Photogrammetry and Remote Sensing.Amsterdam:Society of Photogrammetry and Remote Sensing,2000:567-571.

备注/Memo

备注/Memo:
收稿日期:2008-10-29;修回日期:2009-05-09
基金项目:国家自然科学基金资助项目(60872071);广东省自然科学基金博士启动资助项目(9451806001002287)
作者简介:贾森(1980-),男(汉族),河南省焦作市人,深圳大学讲师、博士.E-mail:senjia@szu.edu.cn
通讯作者:纪震(1973-),男(汉族),深圳大学教授、博士生导师.E-mail:jizhen@szu.edu.cn
更新日期/Last Update: 2009-08-11