Please wait a minute...
img

官方微信

遥感技术与应用  2015, Vol. 30 Issue (4): 616-625    DOI: 10.11873/j.issn.1004-0323.2015.4.0616
综述     
高光谱遥感影像端元提取算法研究进展及分类
王茂芝1,2,徐文皙1,王璐1,郭科1
(1.成都理工大学数学地质四川省重点实验室,四川 成都 610059;
2.电子科技大学航空航天学院,四川 成都 611731)
Research Progress on Endmember Extraction Algorithm and Its Classification of Hyperspectral Remote Sensing Imagery
Wang Maozhi1,2,Xu Wenxi1,Wang Lu1,Guo Ke1
(1.Geomathematics Key Lab.Of Sichuan Province,Chengdu University
of Technology,Chengdu 610059,China;
2.College of Aeronautics and Astronautics,University of Electronic
and Technology of China,Chengdu 611731,China)
 全文: PDF(1134 KB)  
摘要:

在给出端元的物理、代数和几何学解释基础上,对现有端元提取算法从算法设计机理出发,分为基于几何学、基于统计学和信号检测理论以及空间和光谱相结合三大类,并进一步对基于几何学的端元提取算法从技术处理手段差异细分为基于距离、体积、投影变换和最优化4种情况。结合端元提取算法分类,针对算法缺陷及改进思路,介绍了常见端元提取算法PPI、N-FINDR、UOSP、VCA、ICA、NMF和AMEE研究进展。最后,结合解混理论进展和工程应用实际,从技术综合和性能优化的角度指出了端元提取算法的研究展望。

关键词: 高光谱遥感端元提取线性光谱混合模型性能优化    
Abstract:

An explanation of endmember based on physics,algebra and geometry is described.And a classification,with three categories,of endmember extraction algorithms based on algorithm design theory is provided,namely,endmember extraction algorithms designed based on geometry,endmember extraction algorithms designed based on statistics and signal detection theory,and endmember extraction algorithms designed based on combination of spectral and spatial information.Furthmore,the category based on geometry can be subdivided into four conditions according to the different techniques,that is,distance,volume,projection and transformation,optimization.Owing to the classification of endmember extraction algorithms,the defects and improved techniques,research progress of some commonly endmember extraction algorithms including PPI,N\|Findr,UOSP,VCA,ICA,NMF,and AMEE are described.At last,from the point of view on engineering application of hyperspectral remote sensing and the development of unmixing theory,two research prospects on endmember extraction algorithm are pointed out.One prospect is combination of all different techniques used in endmember extraction,and the other is the performance optimization of existing algorithms.
 

Key words: Hyperspectral remote sensing    Endmember extraction    Linear spectral mixing model    Performance optimization
收稿日期: 2013-12-21 出版日期: 2015-09-22
:  TP 751.1  
基金资助:

中国地质调查局地调项目(1212011120226),四川省教育厅自然科学重点项目“基于集群和GPU的高光谱遥感影像并行处理”(13ZA0065)。

作者简介: 王茂芝(1974-),男,江西吉安人,博士,副教授,主要从事高光谱遥感信息处理及地质应用方面的研究。Email:wangmz@cdut.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  
王茂芝
徐文皙
王璐
郭科

引用本文:

王茂芝,徐文皙,王璐,郭科. 高光谱遥感影像端元提取算法研究进展及分类[J]. 遥感技术与应用, 2015, 30(4): 616-625.

Wang Maozhi,Xu Wenxi,Wang Lu,Guo Ke. Research Progress on Endmember Extraction Algorithm and Its Classification of Hyperspectral Remote Sensing Imagery. Remote Sensing Technology and Application, 2015, 30(4): 616-625.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2015.4.0616        http://www.rsta.ac.cn/CN/Y2015/V30/I4/616

[1]Zhang Bing,Gao Lianru.Hyperspectral Image Classification and Target Detection[M].Beijing:Science Press,2011.[张兵,高连如.高光谱图像分类与目标探测[M].北京:科学出版社,2011.]

[2]Boardman J W.Automated Spectral Unmixing of AVRIS Data Using Convex Geometry Concepts[C]//Summaries of the Fourth JPL Airborne Geoscience Workshop.California,1993.

[3]Boardman J W,Kruse F A,Green R O.Mapping Target Signatures Via Partial Unmixing of AVRIS Data[C]//Summaries of the VI JPL Airborne Earth Science Workshop.California,1995.

[4]Chang C I,Du Q.Estimation of Number of Spectrally Distinct Signal Sources in Hyperspectral Imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2004,42(3):608-619.

[5]Harsanyi J C,Chang C I.Hyperspectral Image Classification and Dimensionality Reduction:An Orthogonal Subspace Projection Approach[J].IEEE Transactions on Geoscience and Remote Sensing,1994,32(4):779-785.

[6]Craig M D.Minimum-volume Transforms for Remotely Sens-ed Data[J].IEEE Transactions on Geoscience and Remote Sensing,1994,32(3):542-552.

[7]Bowles J,Palmadesso P J,Antoniades,et al.Use of Filter Vectors in Hyperspectral Data Analysis[C]//Infrared Spaceborne Remote Sensing III,SPIE Proceedings.San Diego,CA,1995.

[8]Bayliss J,Gualtieri J A,Cromp R.Analyzing Hyperspectral Data with Independent Component Analysis[C]//26th AIPR Workshop:Exploiting New Image Sources and Sensors,SPIE Proceedings.Washington,DC,1997.

[9]Roberts D A,Gardner R,Church R,et al.Mapping Chaparral in the Santa Monica Mountains Using Multiple Endmember Spectral Mixture Model[J].Remote Sensing of Environment,1998,65(3):267-279.

[10]Winter M E.N-FINDR:An Algorithm for Fast Autonomous Spectral Endmember Determination in Hyperspectral Data[C]//on SPIE Proceedings.Imaging Spectrometry V,Denver,CO,1999.

[11]Neville R.Automatic Endmember Extraction from Hypersp-ectral Data for Mineral Exploration[C]//International Airborne Remote Sensing Conference and Exhibition,Colorado,Ecosystem Management Analysis Center,1999.

[12]Fuhrman D R.Simplex Shrink-wrap Algorithm[C]//on SPIE Proceedings.Automatic Target Recognition IX,Orlando,FL,1999.

[13]Ifarraguerri A,Chang C I.Multispectral and Hyperspectral Imagery Analysis with Convex Cones[J].IEEE Transactions on Geoscience and Remote Sensing,1999,37(2):756-770.

[14]Bateson C A,Asner G P,Wessman C A.Endmember Bundles:a New Approach to Incorporating Endmember Variability into Spectral Mixture Analysis[J].IEEE Transactions on Geoscience and Remote Sensing,2000,38(2):1083-1094.

[15]Plaza A,Martinez P,Perez R,et al.Spatial/Spectral Endmember Extraction by Multidimensional Morphological Operations[J].IEEE Transactions on Geoscience and Remote Sensing,2002,40(9):2025-2041.

[16]Parra L C,Sajda P,Du S.Recovery of Constituent Spectra Using Non-negative Matrix Factorization[C]//Wavelets:Applications in Signal and Image Processing X,SPIE Proceedings.San Diego,CA,2003.

[17]Berman M,Kiiveri H,Lagerstrom R,et al.ICE:A Statistical Approach to Identifying Endmembers in Hyperspectral Images[J].IEEE Transactions on Geoscience and Remote Sensing,2004,42(10):2085-2095.

[18]Bajorski P.Simplex Projection Methods for Selection of Endmembers in Hyperspectral Imagery[C]//IEEE International Geoscience and Remote Sensing Symposium(IGARSS’04),Anchorage,2004.

[19]Gruninger J H,Ratkowski A J,Hoke M L.The Sequential Maximum Angle Convex Cone(SMACC)Endmember Model[C]//Algorithms and Technologies for Multi-spectral,Hyperspectral,and Ultraspectral Imagery X,SPIE Proceedings.Orlando,FL,2004.

[20]Geng Xiurui,Zhang Bing,Zhang Xia,et al.An Unmixing Algorithm of Hyperspectral Imagery based on Cone Simplex Volume of High Dimension Space[J].Progress in Natural Science,2004,14(7):810-814.[耿修瑞,张兵,张霞,等.一种基于高维空间凸集单形体体积的高光谱图像解混算法[J].自然科学进展,2004,14(7):810-814.]

[21]Geng Xiurui.Research on Hyperspectral Remote Sensing Imagery Target Detection and Classification Technology[D].Beijing:Institute of Remote Sensing Application,CAS,2005.[耿修瑞.高光谱遥感图像目标探测与分类技术研究[D].北京:中国科学院遥感应用研究所,2005.]

[22]Geng Xiurui,Zhao Yongchao,Zhou Guanhua.An Automatic Endmember Extraction Algorithm of Hyperspectral Imagery based on Simplex Volume[J].Progress in Natural Science,2006,16(9):1196-1200.[耿修瑞,赵永超,周冠华.一种利用单形体体积自动提取高光谱图像端元的算法[J].自然科学进展,2006,16(9):1196-1200.]

[23]Geng Xiurui,Zhao Yongchao,Liu Suhong,et al.Matrix Calculation of High Dimension Cross Product and Its Application on Endmember Extraction Automatically of Hyperspectral Imgaery[J].China Science:Information Science,2010,40(4):646-652.[耿修瑞,赵永超,刘素红,等.高维叉积的矩阵计算以及在高光谱图像端元自动提取中的应用[J].中国科学:信息科学,2010,40(4):646-652.]

[24]Nascimento J M P,Dias M B.Vertex Component Analysis:A Fast Algorithm to Unmix Hyperspectral Data[J].IEEE Transactions on Geoscience and Remote Sensing,2005,43(4):898-910.

[25]Geng Xiurui,Tong Qingxi,Zheng Lanfeng.Ground Object Extraction Algorithm of Hyperspectral Imagery based on Endmember Projection Vector[J].Progress in Natural Science,2005,15(4):509-512.[耿修瑞,童庆禧,郑兰芬.一种基于端元投影向量的高光谱图像地物提取算法[J].自然科学进展,2005,15(4):509-512.]

[26]Chang C I,Wu C C,Liu W M,et al.A New Growing Method for Simplex-based Endmember Extraction Algorithm[J].IEEE Transactions on Geoscience and Remote Sensing,2006,44(10):2804-2819.

[27]Miao L D,Qi H R.Endmember Extraction from Highly Mixed Data Using Minimum Volume Constrained Nonnegative Matrix Factorization[J].IEEE Transactions on Geoscience and Remote Sensing,2007,45(3):765-777.

[28]Luo Wenfei,Zhong Liang,Zhang Bing,et al.A Spectral Unmixing Algorithm for Hyperspectral Image based on the Distance to Subspace[J].Progress in Natural Science,2008,18(10):1175-1180.[罗文斐,钟亮,张兵,等.基于子空间距离的高光谱图像光谱解混算法[J].自然科学进展,2008,18(10):1175-1180.]

[29]Luo Wenfei,Zhong Liang,Liu Xiang,et al.Endmember Extraction Algorithm of Hyperspectral Imagery based on Maximum Distance of Null Space[J].Progress in Natural Science,2008,18(11):1341-1345.[罗文斐,钟亮,刘翔,等.基于零空间最大距离的高光谱图像端元提取算法[J].自然科学进展,2008,18(11):1341-1345.]

[30]Luo Wenfei,Zhong Liang,Zhang Bing,et al.Null Space Spectral Projection Algorithm for Hyperspectral Image Endmember Extraction[J].Journal of Infrared Millimeter Waves,2010,29(4):307-311.[罗文斐,钟亮,张兵,等.高光谱遥感图像端元提取的零空间光谱投影算法[J].红外与毫米波学报,2010,29(4):307-311.]

[31]Jun L,Bioucas-Dias J M.Minimum Volume Simplex Analysis:A Fast Algorithm to Unmix Hyperspectral Data[C]//IEEE International Geoscience and Remote Sensing Symposium(IGARSS’08),Boston,2008.

[32]Tao Xuetao,Wang Bin,Zhang Liming.A New Unminxing Method for Remote Sensing Image based on Orthgonal base of Data Space[J].China Science:Information Dcinece,2009,39(4):454-467.[陶雪涛,王斌,张立明.基于数据空间正交基的遥感图像混合像元分解新方法[J].中国科学F辑:信息科学,2009,39(4):454-467.]

[33]Zhu Shulong,Qi Jiancheng,Zhu Baoshan,et al.Fast Extraction of Endmembers from Convex Simplex’s Boundary[J].Journal of Remote Sensing,2010,14(3):482-492.[朱述龙,齐建成,朱宝山,等.以凸面单体边界为搜索空间的端元快速提取算法[J].遥感学报,2010,14(3):482-492.]

[34]Sun Genyun,Zhang Aizhu,Xu Mingming.Research on Endmember Extractraction Algorithm based on Data Field[J].Remote Sensing Technology and Application,2012,27(6):837-843.[孙根云,张爱竹,许明明.基于数据场的端元提取算法研究[J].遥感技术与应用,2012,27(6):837-843.]

[35]Pu Hanye,Wang Bin,Zhang Liming.Simplex Geometry-based Abundance Estimation Algorithm for Hyperspectral Unmixing[J].China Science:Information Science,2012,42(8):1019-1033.[普晗晔,王斌,张立明.基于单形体几何的高光谱遥感图像解混算法[J].中国科学:信息科学,2012,42(8):1019-1033.]

[36]Plaza A,Chang C I.An Improved N-FINDR Algorithm in Implementation[C]//Algorithms and Technologies for Multispectral,Hyperspectral and Untraspectral Imagery XI,SPIE Proceedings.Orlando,FL,2005.

[37]Li Ersen,Zhu Shulong,Zhou Xiaoming,et al.The Development and Comparison of Endmember Extraction Algorithms Using Hyperspectral Imagery[J].Journal of Remote Sensing,2011,15(4):659-679.[李二森,朱述龙,周晓明,等.高光谱图像端元提取算法研究进展与比较[J].遥感学报,2011,15(4):659-679.]

[38]Plaza A,Martínez P,Pérez 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.

[39]Chang C O,Plaza A.A Fast Iterative Algorithm for Implementation of Pixel Purity Index[J].IEEE Transactions on Geoscience and Remote Sensing Letters,2006,3(1):63-67.

[40]Ren H,Chang C I.Automatic Spectral Target Recognition in Hyperspectral Imagery[J].IEEE Transactions on Aerospace and Electronic Systems,2003,39(4):1232-1249.

[41]Zeng F X,Wang M Z,Guo K,et al.Initialization of the N-FINDR Algorithm based on the Max-min Distance Method[C]//Global Congress on Intelligent Systems,Wuhan,2012.

[42]Ding Haiyong,Shi Wenzhong.Fast N-FINDR Algorithm for Endmember Extraction based on Chi-square Distribution[J].Journal of Remote Sensing,2013,17(1):122-137.[丁海勇,史文中.利用卡方分布改进 N-FINDR 端元提取算法[J].遥感学报,2013,17(1):122-137.]

[43]Wu Bo,Zhang Liangpei,Li Pingxiang.Unsupervised Orthogonal Subspace Projection Approach to Unmix Hyperspectral Imagery Automatically[J].Journal of Image and Graphics,2004,9(11):1392-1396.[吴波,张良培,李平湘.非监督正交子空间投影的高光谱混合像元自动分解[J].中国图象图形学报,2004,9(11):1392-1396.]

[44]Mei Shaohui,He Mingyi,Dai Yuchao.A Novel DSSP( Double Signal Subspace Projection)Algorithm for Better VD(Virtual Dimensionality)Estimation[J].Journal of Northwestern Polytechnical University,2012,30(5):640-646.[梅少辉,何明一,戴玉超.基于双向信号子空间投影的高光谱图像虚拟维数估计[J].西北工业大学学报,2012,30(5):640-646.]

[45]Luo Wenfei,Zhong Liang,Zhang Bing,et al.Independent Component Analysis for Spectral Unmixing in Hyperspectral Remote Sensing Image[J].Spectroscopy and Spectral Analysis,2010,30(6):1628-1633.[罗文斐,钟亮,张兵,等.高光谱遥感图像光谱解混的独立成分分析技术[J].光谱学与光谱分析,2010,30(6):1628-1633.]

[46]Xia Wei,Wang Bin,Zhang Liming.Blind Unmixing based on Independent Component Analysis for Hyperspectral Imagery[J].Journal of Infrared Millimeter Waves,2011,30(2):131-137.[夏威,王斌,张立明.基于独立分量分析的高光谱遥感图像混合像元盲分解[J].红外与毫米波学报,2011,30(2):131-137.]

[47]Wu Chen,Du Bo,Zhang Liangpei.Hyperspectral Change Detection based on Independent Component Analysis[J].Journal of Remote Sensing,2012,16(3):545-561.[武辰,杜博,张良培.基于独立成分分析的高光谱变化检测[J].遥感学报,2012,16(3):545-561.]

[48]Li Ersen,Zhang Baoming,Yang Na,et al.Discussion of the NMF’s Application for Hyperspectral Imagery Unmixing[J].Bulletin of Surveying and Mapping,2011,(3):7-10.[李二森,张保明,杨娜,等.非负矩阵分解在高光谱图像解混中的应用探讨[J].测绘通报,2011,(3):7-10.]

[49]Paura V P,Piper J,Plemmons R J.Nonnegative Matrix Factorization for Spectral Data Analysis[J].Linear Algebra and Applications,2006,416(7):29-47.

[50]Zymnis A,Kim S J,Skaf J,et al.Hyperspectral Image Unmixing via Alternating Projected Subgradients[C]//Proceeding of 41st Asilomar Conference on Signals,Systems,and Computers.Pacific Grove,CA,2007.

[51]Li Ersen,Zou Yu,Zhan Fei,et al.Sparseness Constraint MVC-NMF Algorithm[J].Journal of Geomatics Science and Technology,2010,27(6):429-432.[李二森,邹瑜,战飞,等.稀疏约束的MVC-NMF算法[J].测绘科学技术学报,2010,27(6):429-432.]

[52]Lee C A,Gasster S D,Plaza A,et al.Recent Developments in High Performance Computing for Remote Sensing:A Review[J].IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing,2011,4(3):508-527.

[53]Plaza A,Valencia D,Plaza J,et al.Parallel Implementation of Endmember Extraction Algorithms from Hyperspectral Data[J].IEEE Transactions on Geoscience and Remote Sensing Letters,2006,3(3):334-338.

[54]Wang Maozhi,Guo Ke,Xu Wenxi.Hyperspectral Remote Sensing Image Parallel Processing based on Cluster and GPU[J].Infrared and Laser Engineering,2013,42(11):3070-3075.[王茂芝,郭科,徐文皙.基于集群和GPU的高光谱遥感影像并行处理[J].红外与激光工程,2013,42(11):3070-3075.]

[55]Wang M Z,Wang D M,Xu W X,et al.Parallel Computing of Covariance Matrix and its Application on Hyperspectral Data Process[C]//IEEE International Geoscience and Remote Sensing Symposium Remote Sensing for a Dynamic Earth(IGARSS2012),Munich,2012.

[56]Tenenbaum J B,Silva D D,Langford J A.A Global Geometric Framework for Nonlinear Dimensionality Reduction[J].Sience,2000,290(5500):2319-2323.

[57]Roweis S T,Saul L K.Nonlinear Dimensionality Reduction by Locally Linear Embedding[J].Sience,2000,290(5500):2323-2326.

[58]Tang Xiaoyan,Gao Kun,Ni Guoqing.Advances in Nonlinear Spectral Unmixing of Hyperspectral Images[J].Remote Sensing Technology and Application,2013,28(4):731-738.[唐晓燕,高昆,倪国强.高光谱图像百线性解混方法的研究进展[J].遥感技术与应用,2013,28(4):731-738.]

[59]Xu Rong,Jiang Feng,Yao Hongxun.Overview of Manifold Learning[J].CAAI Transactions on Intelligent Systems,2006,1(1):44-51.[徐蓉,姜峰,姚鸿勋.流形学习概述[J].智能系统学报,2006,1(1):44-51.]

[60]Li F,Ng M,Plemmons R.Coupled Segmentation and Denoising/Deblurring Models for Hyperspectral Material Identification[J].Numerical Linear Algebra,2012,19(1):53-73.

[61]Li C,Sun T,Kelly K,et al.A Compressive Sensing and Unmixing Scheme for Hyperspectral Data Processing[J].IEEE Transactions on Image Process,2012,21(3):1200-1210.

[1] 秦振涛,杨茹,张靖,杨武年. 基于聚类结构自适应稀疏表示的高光谱遥感图像修复研究[J]. 遥感技术与应用, 2018, 33(2): 212-215.
[2] 郭宇柏,卓莉,陶海燕,曹晶晶,王芳. 基于空谱初始化的非负矩阵光谱混合像元盲分解[J]. 遥感技术与应用, 2018, 33(2): 216-226.
[3] 吴兴,张霞,孙雪剑,张立福,戚文超. SPARK卫星高光谱数据辐射质量评价[J]. 遥感技术与应用, 2018, 33(2): 233-240.
[4] 刘慧珺,苏红军,赵-波. 基于改进萤火虫算法的高光谱遥感多特征优化方法[J]. 遥感技术与应用, 2018, 33(1): 110-118.
[5] 唐超,邵龙义. 高光谱遥感地物目标识别算法及其在岩性特征提取中的应用[J]. 遥感技术与应用, 2017, 32(4): 691-697.
[6] 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.
[7] 史飞飞,高小红,杨灵玉,何林华,贾伟. 基于HJ-1A高光谱遥感数据的湟水流域典型农作物分类研究[J]. 遥感技术与应用, 2017, 32(2): 206-217.
[8] 朱济帅,尹作霞,谭琨,王雪,李二珠,杜培军. 基于空间邻域信息的高光谱遥感影像半监督协同训练[J]. 遥感技术与应用, 2016, 31(6): 1122-1130.
[9] 张霞,戚文超,孙伟超. 基于数学形态滤波的植被光谱去噪方法研究[J]. 遥感技术与应用, 2016, 31(5): 846-854.
[10] 苏远超,孙旭,高连如,陈晓宁. 高光谱影像端元提取算法的进展分析与比较[J]. 遥感技术与应用, 2015, 30(6): 1195-1205.
[11] 周玉洁,王卷乐,郭海会. 基于谐波分析和线性光谱模型的耕地信息提取[J]. 遥感技术与应用, 2015, 30(4): 706-713.
[12] 贺军亮,张淑媛,查勇,蒋建军. 高光谱遥感反演土壤重金属含量研究进展[J]. 遥感技术与应用, 2015, 30(3): 407-412.
[13] 钱进,罗鼎. 基于成对约束半监督降维的高光谱遥感影像特征提取[J]. 遥感技术与应用, 2014, 29(4): 681-688.
[14] 周子勇. 高光谱遥感油气勘探进展[J]. 遥感技术与应用, 2014, 29(2): 352-36.
[15] 吕晓凯,李传荣,马灵玲,苑馨方,李晓辉. 一种基于物理机理的高光谱遥感图像真彩色校正模型[J]. 遥感技术与应用, 2013, 28(3): 467-473.