基于Hyperion数据的森林类型识别
摘要
森林资源是地球上最大的陆地生态系统,开展森林资源调查,了解和掌握森林资源现状和变化信息对于提高林业发展决策水平,科学合理的经营管理森林资源等都具有极其重要的意义。与传统森林资源调查方式相比,遥感影像解译因其宏观、周期短、动态等优点,被广泛应用于森林资源的调查监测中。随着遥感技术的发展,高光谱遥感是通过遥感方法获取更丰富信息的必然发展趋势,也是当代遥感的前沿和热点之一。高光谱遥感影像将成像技术与细分光谱技术结合,使得高光谱影像在分类技术的应用方面拥有巨大的潜力,高光谱数据能够更好地识别各类地物,但是其庞大的数据量和数据的高维度使数据的传输和存储受到了限制,也给高光谱数据处理方法的探讨带来了不小的挑战。
本文应用Hyperion高光谱数据,对湖南株洲攸县黄丰桥林场作为研究区进行分类研究。针对Hyperion数据波段多和数据量大的特点,对高光谱数据进行了未定标和受水汽影像波段的剔除、像元值与绝对辐射值的转换、坏线的修复、Smile效应的校正、FLAASH大气纠正、几何校正等遥感数据预处理,再利用特征选择与特征提取相结合的基于分段主成分分析和波段指数的高光谱数据降维处理方法,将高光谱数据从高维空间映射到低维空间,然后分别利用最大似然法和光谱角填图法进行森林类型的识别与分析。主要研究结论如下：
(1)对Hyperion数据进行波段剔除、转换以及校正等处理后,高光谱的数据量变小,地物曲线更加趋向于真实的植被光谱特征,使得地物更容易区分。
(2)通过相关矩阵可知,利用分段主成分法对Hyperion数据进行数据源划分,每段的平均相关系数都在0.9以上,表明Hyperion数据相邻波段间的相关性很高。
(3)利用分段主成分分析法结合波段指数法的高光谱降维方法将Hyperion数据的242个原始波段缩减为13个信息量大且相关性弱的波段组合,一方面,分段主成分分析法有效的抑制了全局变换导致局部重要光谱被滤除的可能,另一方面,波段指数法在进行波段选择时兼顾了自适应分段后段与段之间以及各分段中波段间的相关性,有效降低了高光谱数据的维度。
(4)波段选择之前进行子空间划分,本文将Hyperion数据划分为三个子空间,此操作可剔除相关性较大的波段,并能减小数据的计算量,从而达到高维遥感数据优化处理和高效利用的目的。
(5)根据波段指数来选取波段的子集时,选取波段指数的极大值而不是最大值作为降维后波段子集,从而弥补原始数据在分段时产生的误差。
(6)对Hyperion数据进行基于特征空间的最大似然法和基于光谱空间的光谱角填图法两种方式进行森林类型识别,分类误差矩阵结果表明：最大似然法的分类总体精度为85.23%,光谱角填图法的总体精度达到88.94%,说明对于高光谱而言,光谱角填图法针对性的对各类光谱进行识别优于多光谱的传统分类方法。
Forest resources is the world's largest land ecological system, the important component of the national natural resources, the forestry construction foundation, the necessary basis of human survival and development. Developing forest resources survey to understand and grasp the forest resources situation and change information to improve the scientific and reasonable decision-making level of forestry development, management of forest resources has great significance. Compare with the traditional forest resources survey, RS image interpretation for its macroscopic, short cycle, dynamic and other advantages, is widely used in the investigation of the forest resources monitoring.
Along with the development of remote sensing technology, we are able to get and use more and more information, hyperspectral remote sensing through the remote sensing method for more information is the inevitable development trend, as well as the frontier and hotspots. Hyperspectral remote sensing image combined imaging technology and subdividing spectrum technique in one, it make hyperspectral images in the application of classification technology has huge potential, and in imaging process, hyperspectral images can obtain the continuous spectrum of the features of information, and the traditional spectrum than remote sensing data, hyperspectral data is better to recognition and classification of all kinds of features, but the huge amount of data and data of high dimension make the data transmission and storage is limited, also give hyperspectral data processing method discussion bring quite a challenge.
This paper applied Hyperion hyperspectral data, to the hunan zhuzhou YouXian HuangFeng bridge as the forest classification research area. For the bands of Hyperion data and the characteristics of large volumes of data, execute several data processes, uncalibration and suffer lunt images bands weed out, the conversion of DN value and the absolute value, bad line repair, calibration of Smile effect, FLAASH atmosphere effect correction, the remote sensing data pretreatment geometry correction:using mothod combinated with feature selection and feature extraction for hyperspectral data to reduction dimension, process will let data from a high dimensional space mapping to a low dimensional space, then respectively applied maximum likelihood and spectral Angle mapping method for the forest types of recognition and analysis. The main research conclusions are as follows:
(1) After the band removed, conversion and correction processing of Hyperion data, hyperspectral data quantity is small, surface features curves tend to be more real vegetation spectral features, making the surface features easier to distinguish.
(2) The correlation matrix shows the segmented principal component analysis of Hyperion data, the division of data sources, each the average correlation coefficient above0.9, that Hyperion data adjacent to the high correlation between bands.
(3) Use the segmented principal component analysis and band index combining dimensionality reduction method, Hyperion data the original band of242is reduced to the large amount of information and the correlation weak13bands, on the one hand, segmented principal component analysis effectively inhibitglobal transformation leading to the possibility of local important spectral filter, on the other hand, the band index during band selection, taking into account the adaptive segmentation between paragraphs and subparagraphs in the band after the correlation between the effective lowerthe dimension of the hyperspectral data.
(4) Sub-space division, before the band selection can remove larger band, and can reduce the amount of data calculation, so as to achieve high-dimensional remote sensing data to optimize the processing and efficient use of purpose.
(5) Band index to select a subset of the band, select band maxima of the index rather than the maximum value as the drop the Wei Houbo piece set to compensate for the error of the original data in the segment.
(6) Hyperion data in two ways based on the feature space maximum likelihood and spectral angle based on the spectral space mapping method for identification of forest types, classification error matrix:the maximum likelihood classification of the overall accuracy of85.23%, the spectral anglefill in the diagram method, the overall accuracy of88.94%for the high spectral, spectral angle mapping method targeted to identify superior to the traditional multi-spectral classification of various types of spectra.
本文应用Hyperion高光谱数据,对湖南株洲攸县黄丰桥林场作为研究区进行分类研究。针对Hyperion数据波段多和数据量大的特点,对高光谱数据进行了未定标和受水汽影像波段的剔除、像元值与绝对辐射值的转换、坏线的修复、Smile效应的校正、FLAASH大气纠正、几何校正等遥感数据预处理,再利用特征选择与特征提取相结合的基于分段主成分分析和波段指数的高光谱数据降维处理方法,将高光谱数据从高维空间映射到低维空间,然后分别利用最大似然法和光谱角填图法进行森林类型的识别与分析。主要研究结论如下：
(1)对Hyperion数据进行波段剔除、转换以及校正等处理后,高光谱的数据量变小,地物曲线更加趋向于真实的植被光谱特征,使得地物更容易区分。
(2)通过相关矩阵可知,利用分段主成分法对Hyperion数据进行数据源划分,每段的平均相关系数都在0.9以上,表明Hyperion数据相邻波段间的相关性很高。
(3)利用分段主成分分析法结合波段指数法的高光谱降维方法将Hyperion数据的242个原始波段缩减为13个信息量大且相关性弱的波段组合,一方面,分段主成分分析法有效的抑制了全局变换导致局部重要光谱被滤除的可能,另一方面,波段指数法在进行波段选择时兼顾了自适应分段后段与段之间以及各分段中波段间的相关性,有效降低了高光谱数据的维度。
(4)波段选择之前进行子空间划分,本文将Hyperion数据划分为三个子空间,此操作可剔除相关性较大的波段,并能减小数据的计算量,从而达到高维遥感数据优化处理和高效利用的目的。
(5)根据波段指数来选取波段的子集时,选取波段指数的极大值而不是最大值作为降维后波段子集,从而弥补原始数据在分段时产生的误差。
(6)对Hyperion数据进行基于特征空间的最大似然法和基于光谱空间的光谱角填图法两种方式进行森林类型识别,分类误差矩阵结果表明：最大似然法的分类总体精度为85.23%,光谱角填图法的总体精度达到88.94%,说明对于高光谱而言,光谱角填图法针对性的对各类光谱进行识别优于多光谱的传统分类方法。
Forest resources is the world's largest land ecological system, the important component of the national natural resources, the forestry construction foundation, the necessary basis of human survival and development. Developing forest resources survey to understand and grasp the forest resources situation and change information to improve the scientific and reasonable decision-making level of forestry development, management of forest resources has great significance. Compare with the traditional forest resources survey, RS image interpretation for its macroscopic, short cycle, dynamic and other advantages, is widely used in the investigation of the forest resources monitoring.
Along with the development of remote sensing technology, we are able to get and use more and more information, hyperspectral remote sensing through the remote sensing method for more information is the inevitable development trend, as well as the frontier and hotspots. Hyperspectral remote sensing image combined imaging technology and subdividing spectrum technique in one, it make hyperspectral images in the application of classification technology has huge potential, and in imaging process, hyperspectral images can obtain the continuous spectrum of the features of information, and the traditional spectrum than remote sensing data, hyperspectral data is better to recognition and classification of all kinds of features, but the huge amount of data and data of high dimension make the data transmission and storage is limited, also give hyperspectral data processing method discussion bring quite a challenge.
This paper applied Hyperion hyperspectral data, to the hunan zhuzhou YouXian HuangFeng bridge as the forest classification research area. For the bands of Hyperion data and the characteristics of large volumes of data, execute several data processes, uncalibration and suffer lunt images bands weed out, the conversion of DN value and the absolute value, bad line repair, calibration of Smile effect, FLAASH atmosphere effect correction, the remote sensing data pretreatment geometry correction:using mothod combinated with feature selection and feature extraction for hyperspectral data to reduction dimension, process will let data from a high dimensional space mapping to a low dimensional space, then respectively applied maximum likelihood and spectral Angle mapping method for the forest types of recognition and analysis. The main research conclusions are as follows:
(1) After the band removed, conversion and correction processing of Hyperion data, hyperspectral data quantity is small, surface features curves tend to be more real vegetation spectral features, making the surface features easier to distinguish.
(2) The correlation matrix shows the segmented principal component analysis of Hyperion data, the division of data sources, each the average correlation coefficient above0.9, that Hyperion data adjacent to the high correlation between bands.
(3) Use the segmented principal component analysis and band index combining dimensionality reduction method, Hyperion data the original band of242is reduced to the large amount of information and the correlation weak13bands, on the one hand, segmented principal component analysis effectively inhibitglobal transformation leading to the possibility of local important spectral filter, on the other hand, the band index during band selection, taking into account the adaptive segmentation between paragraphs and subparagraphs in the band after the correlation between the effective lowerthe dimension of the hyperspectral data.
(4) Sub-space division, before the band selection can remove larger band, and can reduce the amount of data calculation, so as to achieve high-dimensional remote sensing data to optimize the processing and efficient use of purpose.
(5) Band index to select a subset of the band, select band maxima of the index rather than the maximum value as the drop the Wei Houbo piece set to compensate for the error of the original data in the segment.
(6) Hyperion data in two ways based on the feature space maximum likelihood and spectral angle based on the spectral space mapping method for identification of forest types, classification error matrix:the maximum likelihood classification of the overall accuracy of85.23%, the spectral anglefill in the diagram method, the overall accuracy of88.94%for the high spectral, spectral angle mapping method targeted to identify superior to the traditional multi-spectral classification of various types of spectra.
引文
[1]陈述彭,童庆禧,郭华东.遥感信息机理研究[M].科学出版社,1998.
[2]李守乾,安裕伦,朱珂,等.基于高光谱遥感数据提取土地利用信息[J].安徽农业科学,2011,39(4).
[3]陈桂红.高光谱遥感图像纹理分析研究[D].中国科学院研究生院,2003.
[4]刘建贵.高光谱城市地物及人工目标识别与提取[D].中国科学院遥感应用研究所,1999.
[5]童庆禧.电子光学遥感系统的过去、现在和未来.北京：科学出版社,1995,51-60.
[6]Goets A F H, Rowan L C.Geological remote sensing Science[J].1981,211:781-791.
[7]Shippert P.Why use hyperspectral imagery?[J].Photogrammetric Engineering and Remote Sensing,2004,70(1):377-379.
[8]Schowengerdt RA著.李德熊译.遥感中的图像处理和分类技术[M].北京：科学出版社,1991.
[9]徐冠华,田国良,王超,等.遥感信息科学的进展与展望[J].地理学报,1996,51(5)：385-397.
[10]杜培军,陈云浩,王行风,等.遥感科学与进展[M].徐州：中国矿业大学出版社,2007：369-370.
[11]吴培中.星载高光谱成像光谱仪的特性与应用[J].国土资源遥感,1999,(3)：31-39.
[12]Reese H, Nilsson M P, Ahlen TG, Tingelof U.Countrywide estimates of forest variables using satellite data and field data from the national forest inventory[J]. Ambio,2003,32(8):542-548.
[13]路威.面向目标探测的高光谱影像特征提取与分类技术研究[D].郑州：解放军信息工程大学,2005.
[14]Hsieh P, Landgrebe D.Statistics enhancement in hyperspectral data analysis using spectral spatial labeling, the EM algorithm, and the leave-one-out covariance estimator[A].SPIE International Symposium on Optical Science, Engineering, and Instrumentation[C]San Diego, CA,1998.19-24.
[15]赵锐,赵学军,于嘉喜.地物光谱在林业遥感中的应用[J].内蒙古林业调查设计,1999,3(2)：120-121.
[16]张连蓬.基于投影寻踪和非线性主曲线的高光谱遥感图像特征提取及分类研究[D]. 青岛：山东科技大学,2003.
[17]孙蕾,罗建书.高光谱遥感图像微分域三维混合去噪方法[J].光谱学与光谱分析.2009,29(10)：2717-2720.
[18]Bisun Datt, David Jupp.Hyperion Data Processing Workshop:Handson Processing Instruction[D], CSIRO Earth Observation Centre,2004.
[19]Tan Binxiang, Li Zengyuan, Chen Erxue, etal.EO-1 Hyperion hyperspectral data preprocessing [J]. Remote Sensing Information,2005(6):36-41.
[20]钱乐祥等.遥感数字影像处理与地理特征提取[M].北京：科学出版社.2004：171-172.
[21]Kruse FA, Boardman JW, Huntington JF, etal.Comparison of airborne hyperspectral data and EO-1 Hyperion for mineral mapping[J].IEEE Transactions on Geoscience and Remote Sensing,2003,41(6):1388-1400.
[22]Kumar Shailesh, Ghosh Joydeep, Crawford Melba M.Hierarehical Fusion of Multiple Classifiers for Hyperspectral Data Analysis[J].Pattern Analysis & Applications,2002, 5(2):210-220.
[23]VANE GREGG, GOETZ ALEXANDER F H.Terrestrial imaging spectrometry:current status, future trends[J].Remote Sens.Environ,1993,44:117-126.
[24]LILLESAND T M, KIEFER R W.Remote Sensing and Image Interpretation[A].New York:John Wiley&Sons, Inc.[C],1994,1-750.
[25]HUNT G R.Electromagnetic radiation:the communication link in remote sensing[M].In:Remote Sensing in Geology.Siegal B, Gillespia A.Wiley New York, 1980,702.
[26]Horler DNH, Barber J.P., Ferns D.C., Barringer A.R.Approaches to detection of geochemical stress in vegetation[J].Advanced space Research,1983,3:175-179.
[27]GOETZ ALEXANDER F H, et al. Imaging spectrometry for earth remote sensing[J].Science,1985,228(4702):1147-1153.
[28]Kruse FA.Improved multispectral mapping by spectral modeling with hyperspectral signatures [C].Proceedings, SPIE Symposium on Defense & Security, 9-13 April 2007, Orlando, FL, SPIE, V.6565,2007.
[29]Goodenough DG, Dyk A, Niemann KO, et al.Processing Hyperion and ALI for forest classification[J].IEEE Transactions on Geoscience and Remote Sensing,2003,41(6): 1321-1331.
[30]BOYD, D S, FOODY, et al.Evaluation of approaches for forest cover estimation in the Pacific Northwest, USA, using remote sensing[J].Applied Geography,2002,22: 375-392.
[31]SANDMEIER ST, DEERING D W.Structure Analysis and Classification of Boreal Forests Using Airborne Hyperspectral BRDF Data from AS AS[J].REMOTE SENS.ENVIRON,1999,69:281-295.
[32]MARTIN M E, NEW MAN S D, ABER J D, et al.Determining Forest Species Composition Using High Spectral Resolution Remote Sensing Data[J].REMOTE SENS.ENVIRON,1998,65:249-254.
[33]李智勇.高光谱图像异常检测方法研究[D].长沙：国防科学技术大学,2004.
[34]浦瑞良,宫鹏.高光谱遥感及其应用[M].高等教育出版社,2000.
[35]王学仁,王松桂.实用多元统计分析[M].上海：上海科学技术出版社,1990.
[36]吴昊.高光谱遥感图像数据分类技术研究[D].国防科技大学,2004.
[37]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].中国图像图形学报,2005,1(10)：218-222.
[38]刘勇卫,贺雪鸿.遥感精解第1版[M].北京：测绘出版社,1993,170-220.
[39]童庆禧,张兵,郑兰芬.高光谱遥感—原理、技术与应用第1版[M].北京：高等教育出版社,2006,166-203.
[40]王长耀,牛铮,唐华俊,等.对地观测技术与精细农业[M].北京：科学出版社,2001.
[41]林辉,刘秀英.基于高光谱遥感特征参数的樟树幼林叶绿素a含量估算模型[J].绵阳师范学院学报,2008(8)：1-5.
[42]刘璇.杉木主要生物化学参数的高光谱遥感估算模型研究[D].中南林业科技大学,2010.
[43]宫鹏,浦瑞良,郁彬.不同季相针叶树种高光谱数据识别分析[J].遥感学报,1998：211-217.
[44]卫俊霞,相里斌,段晓峰等.基于EZW的高光谱图像压缩技术研究[J].2011,31(8).
[45]于祥,赵冬至,张丰收,等.红树林高光谱分析技术研究[J].滨州学院学报,2006：53-56.
[46]张丰,熊桢,寇宁.高光谱遥感数据用于水稻精细分类研究[J].武汉理工大学学报,2002,24(10)：36-39.
[47]童庆禧,郑兰芬,王晋年,等.湿地植被成像光谱遥感研究[J].遥感学报,1(1)：50-71.
[48]甘甫平,王润生,郭小方,等.高光谱遥感信息提取与地质应用前景[J].国土资源 遥感,2000：38-44.
[49]甘甫平,王润生,马蔼乃.基于特征谱带的高光谱遥感矿物谱系识别[J].地学前缘,2003(2)：445-454.
[50]王晋年,郑兰芬,童庆禧.成像光谱图像光谱吸收鉴别模型与矿物填图研究[J].环境遥感,1996(1)：20-31.
[51]王青华,王润生,郭小方,等.高光谱遥感技术在岩石识别中的应用[J].国土资源遥感,2000(4)：39-43.
[52]张学霞,葛全胜,郑景云.遥感技术在植物物候研究中的应用综述[J].地球科学进展,2003(4)：534-544.
[53]方红亮,田庆久.高光谱遥感在植被监测中的研究综述[J].遥感技术与应用,1998(1)：62-69.
[54]谭炳香.高光谱遥感森林应用研究探讨[J].世界林业研究,2003(2)：33-37.
[55]申广荣,王人潮.植被光谱遥感数据的研究现状及其展望[J].遥感技术与应用,2001(6)：682-690.
[56]HUNT G R.Electromagnetic radiation:the communication link in remote sensing [M].In:Remote Sensing in Geology.Siegal B, Gillespia A.Wiley New York,1980, 702.
[57]FM Danson.Red edge response to forest leaf area index.lnternational Journal of Remote Sensing,1995,16(1):183-188.
[58]张良培,郑兰芬,童庆禧.利用高光谱对生物变量进行估计[J].遥感学报,1997,1(2)：111-114.
[59]Horler DNH, Dockray, M.Barber, et al.Red edge measurements for remotely sensing plant chlorophyll content.Advanced space Research,1983,3:273-277.
[60]陈君颖,田庆久.高分辨率遥感植被分类研究[J].遥感学报,2007,11(2)：221-227.
[61]陈桂红,唐伶俐,姜小光.高光谱遥感图像特征选取和提取方法的比较—基于实验区Barrax的HyMap数据[J].干旱区地理,2006,29(1)：143-149.
[62]杨竹青,李勇,胡德文.独立成分分析方法综述[J].自动化学报,2002,5：762-772.
[63]Thenkabail P S, Enclona E A, Ashton M S, et al.Hyperion, IKONOS, ALI and ETM+ sensors in the study of African rainforests. Remote sensing of Environment,2004,90: 23-43.
[64]孙华,林辉,熊育久,莫登奎SPOT5影像统计分析及最佳组合波段选择[J].遥感信息应用技术,2006,4：57-60.
[65]徐冠华,田国良,王超,等.遥感信息科学的进展与展望[J].地理学报,1996,51(5)：385-397.
[66]陈君颖,田庆久.高分辨率遥感植被分类研究[J].遥感学报,2007,11(2)：221-227.
[67]孙家柄,舒宁,关泽群.遥感原理、方法和应用[M].北京：测绘出版社,1997.
[68]骆剑承,王钦敏,马江洪,等.遥感图像最大似然分类方法的EM改进算法[J].测绘学报,2002,31(3)：234-239.
[69]Jia X.Classification techniques for hyperspectral remote sensing image data[D].University of New South Wales,1996.
[70]钱乐祥,等.遥感数字影像处理与地理特征提取[M].北京：科学出版社,2004：171-172.
[71]C R Jung.Multiscale image segmentation using wavelets and watersheds.Proc of XVI Brazilian Symposium on Computer Graphics and Image Processing,2003,278-284.
[72]梁继,等Hyperion高光谱影像的分析与处理[J].冰川冻土,2009.
[73]孙林.多光谱图像获取技术研究[D].西安电子科技大学,2010.
[74]岳跃民.基于光谱和空间领域信息的石漠化遥感评价因子提取研究[D].中国科学院研究生院,2010.
[75]梁亮,杨敏华,李英芳.基于ICA与SVM算法的高光谱遥感影像分类[J].光谱学与光谱分析,2010,30(10).
[76]吴见,彭道黎.高光谱遥感林业信息提取技术研究进展[J].光谱学与光谱分析,2011,3131(9).
[77]李婷.基于图像融合的高光谱遥感图像分类研究[D].中国科学技术大学,2008.
[78]苏红军,盛业华,Yang He, Du Qian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.
[79]陶秋香,赵长胜,张连蓬.植被高光谱遥感分类中一种新的非线性混合光谱模型及其解算方法.矿山测量,2004.
[80]http://datamirror.csdb.cn/eo1/resource/baseIntro.jsp
[81]Manin M.E. et al.Determining forest species composition using high spectral resolution remote sensing data. Remote Sense Environ,1998,65:249-254.
[82]T Han, DG Gondenough, A Dyk, J Love.Detection and correction of abnormal pixels in Hyperion images Proceedings of GARSS,2002, Vol.3, Toronto, ON, Canada, 1327-1330.
[83]McVicar TR, Van Niel TG, Jupp DLB..Geometric Validation of Hyperion Data acquired by Earth Observing Satellite at Coleambally Irrigation Area. CS1RO Land and Water Technical Report 46/01,2001, Canberra, Australia.
[84]Vermote E F, Saleous N EL, Justice C O, et al.Atmosepheric correction of visible to middle infrared EOS-MODIS data over land surface, background, operational algorithm and validation[J].Journal of Geophysical Research,1997,102(17):131-141.
[85]刘建贵.高光谱城市地物及人工目标识别与提取[D].中国科学院遥感应用研究所,1999.
[86]熊祯.高光谱遥感图像分类技术研究[D].中科院遥感应用研究所,2000.
[87]Secker J, Staenz K, Gauthier R, et al.Vicarious calibration of airborne hyperspectral sensors in operational environments.Remote Sensing of Environment,,2001,76(1): 81-92.
[88]Barry P.EO-1 Hyperion Science Data Users Guide[R].Californai:TRW Space, Defense & Information Systems,2001.
[89]Curran PJ, JL Dungan.Estimation of Signal-to-Noise:A New Procedure Applied to AVIRIS data.IEEE Transaction on Geoscience and Remote Sensing,1989,27(5): 620-628.
[90]Goetz AF, WM Calvin.Imaging Spectrometry: Spectral Resolution and Analytical Identification of Spectral Features, in G Vane (Ed.), Imaging Spectroscopy II, Bellingham, WA:Photo-Optical Instrument Engineers,1987,158-165.
[91]Wolfe WL.Introduction to Imaging Spectrometers. Vol.TT25, Bellingham, WA: SPIE Optical Engineering Press,1997,148-149.
[92]Liou K N.An Introduction to Atmospheric Radiation (Second Edition)[M].New York: Academic Press,2002.
[93]谭炳香,李增元,等Hyperion高光谱数据的预处理[J].遥感信息,2005(6)：36-41.
[94]张丰,熊桢,寇宁.高光谱遥感数据用于水稻精细分类研究[J].武汉理工大学学报,2002,24(10)：36-39.
[95]Mustard JF, Staid MI, WJ Fripp.A Semianalytical Approach to the Calibration of AVIRIS Data to Reflectance over Water Application in a Temperate Estuary[J].Remote Sensing of Environment. 2001(75):335-349.
[96]顾名澧.多光谱扫描仪的星上辐射定标系统[J].航天返回与遥感,1998.1(3)：21-25.
[97]Dinguirard M, Slater PN.Caiibration of space-multispectral imaging sensor[J].Remote Sensing of Environment,1999,68(3):194-205.
[98]Richard Beck.EO-1 User Guide v.2.3.http://eo1.usgs.gov & http://eo1.gs fs.nasa.gov, 2003.
[99]张俊华.应用3s技术对帽儿山地区森林水文效应评价的研究[D].东北林业大学,2001：27-40.
[100]孙亮,韩崇昭,康欣.多源遥感影像的集值特征选择与融合分类[J].电波科学学报.2004,9(4)：479-484.
[101]Kruse FA, Boardman JW, Huntington JF, et al.Comparison of airborne hyperspectral data and EO-1 Hyperion for mineral mapping[J].IEEE Transactions on Geoscience and Remote Sensing,2003,41(6):1388-1400.
[102]Kruse FA.Improved multispectral mapping by spectral modeling with hyperspectral signatures [C]// Proceedings, SPIE Symposium on Defense & Security,9-13 April 2007, Orlando, FL, SPIE, V.6565,2007.
[103]骆剑承,周成虎,梁怡,等.支持向量机及其遥感影像空间特征提取和应用分类的研究[J].遥感学报,2002,6(1)：50-54.
[104]P Barry.EO-1 Hyperion Science Data User's Guide.Redondo Beach, CA:TRW Space, Defense & Inform.Sys,2001.
[105]刘行华.基于GIS的TM数据分类及辅助制图研究[J].环境遥感,1992(2).
[106]Boardman JW, Kruse FA.Automated spectral analysis:a geological example using ERIM Tenth AVIRIS data, north Grapevine Mountains, Nevada:Thematic Conference on Geologic Remote Sensing, in Proceedings, Environmental Research Institute of Michigan, Ann Arbor, MI,1999,1407-1418.
[107]赵英时.遥感应用分析原理与方法[M].北京：科技出版社,2004.
[108]王秀朋,张洪才,赵永强,等.基于投影寻踪的高光谱图像特征融合算法[J].计算机测量与控制,2006,14(11)：1539-1541.
[109]McVicar TR, Van Niel TG, Jupp DLB.Geometric Validation of Hyperion Data acquired by Earth Observing-1 Satellite at Coleambally Irrigation Area[J].CSIRO Land and Water Technical Report 46/01, Canberra, Australia,2001, pp.70.
[110]Jimenez Luis O, Rivera-Medina Jorge L.Integration of spatial and spectral information homogenous by means of unsupervised extraction and classification for objects applied to multispectral and hyperspectral data[J].IEEE Transactions on Geoscience and Remote Sensing,2005,43(4):844-851.
[111]刘春红,赵春晖,张凌雁.一种新的高光潜遥感图像降维方法[J].中国图象图形学 报,2005,10(2)：218-222.
[112]赵春晖,刘春红.超谱遥感图像降维方法研究现状与分析[J].中国空间科学技术,2004(5)：8-36.
[113]黄睿.高光谱遥感数据特征约简技术研究[D].西安：西北工业大学,2006.
[114]Clark RN, King TVV, Kleijwa M, Swayze.High spectral resolution reflectance spectroscopy of minerals[J].Geophysics,1990,95:12653-12680.
[115]刘建平,赵英时.高光谱遥感数据解译的最佳波段选择方法研究.中国科学院研究生院学报.1999,16(2)：152-161.
[116]李行,张连蓬.高光潜遥感图像最佳波段选择的快速算法研究[J].测绘通报,2004(9)：10-12.
[117]Chavez PS, Berlin GL, Sowers LB.Statistical method for Selecting landsat MSS ratios[J] Journal of applied photographic engineering,1982,1(8):23-30.
[118]姜小光,唐伶俐,王长耀,等.高光谱数据的光谱信息特点及面向对象的特征参数选择—以北京顺义地区为例[J].遥感技术与应用,2002,17(2)：59-65.
[119]Junping Zhang, Ye Zhang, Bin Zou, Tingxian Zhou. Fusion Classification of Hyperspecal Image Based on Adaptive subspace Decomposition [C]. Canada:ICIP 2000 Proceeding. IEEE Signal Processing Society,2000,3:472-475.
[120]杨诸胜,郭雷,罗欣,胡新韬.基于分段主成分分析的高光谱图像波段选择算法研究[J].测绘工程,2006,15(6)：15-18.
[121]赵春晖,刘春红.超谱遥感图像降维方法研究现状与分析[J].中国空间科学技术,2004(5)：28-36.
[122]N Kambhatla, RA Leen.Dimension reduetion by local principal component analysis [J].Neural ComPutation,1997,9(7):1493-1516.
[123]D Manolakis, D Marden.Dimensionality reduetion of hyperspectral imaging data using local Principal components transofmrs[J].Proeeedings of SPIE,2004,5425: 393-401.
[124]DF Miehael, RM Mersereau.On the impact of PCA dimension reduction for hyperspectral detection of difficult targets.IEEE Geoscience and Remote Sensing Letters,2005,2(2):192-195.
[125]HuangRui, HeMingyi.Band selection based on feature weighting for classification of hyperspectral data.IEEE Geoscience and Remote Sensing Letter,2005, 2(2): 156-159.
[126]Jimenez, Luis O, Landgrebe, David A.Hyperspectral data analysis and spuevrised feature reduction via projection pursuit.IEEE Transactions on Geoscience and Remote Sensing, v37, Nov,1999, p2653-2667.
[127]Jia Xiuping, JA Riehards.Segmented principal components transformation for effieient hyperspectral remote-sensing image display and classiflcation.IEEE Geoscience and Remote Sensing,1999,37(1).538-542.
[128]Jimenez LO, Landgrebe DA. Hyperspectral Data Analysis and Supervised Feature Reduction Via Projection Pursuit[J].IEEE Transactions on Geoscience and Remote Sensing,1999,37(6):2653-2667.
[129]田庆久,王世新,王乐意,等.典型地物标准波谱数据库系统设计[J].遥感技术与应用,2003,18(4)：185-190.
[130]Ediriwickrema J, Khorram S.Hieraichical maximum-likelihood classification for improved accuracies[J].IEEE Transactions on Geoscience and Remote Sensing,1997, 35(4):810-816.
[131]Benediktsson J, Swain P, Esroy O.Neural network approaches versus statistical methods in classification of multisource remote sensing data[J].IEEE Transactions on Geoscience and Remote Sensing,1990,28:540-542.
[132]李石华,王金亮,毕艳,等.遥感图像分类方法研究综述[J].国土资源遥感,2005,64(2)：1-6.
[133]王晋年,张兵等.以地物识别和分类为目标的高光谱数据挖掘[J].中国图像图形学报,1999 4(11)：957-964.
[134]Osmar Abilio de Carvalho Jr&Paulo Roberto Meneses.Spectral Correlation Mapper (SCM):An Improvement on the Spectral Angle Mapper(SAM), http: //popo.jpl.nasa.gov/docs/workshops/aviris. proceedings.html
[135]ENVI Tutorials.2003 edition, Research System Inc,2003.
[2]李守乾,安裕伦,朱珂,等.基于高光谱遥感数据提取土地利用信息[J].安徽农业科学,2011,39(4).
[3]陈桂红.高光谱遥感图像纹理分析研究[D].中国科学院研究生院,2003.
[4]刘建贵.高光谱城市地物及人工目标识别与提取[D].中国科学院遥感应用研究所,1999.
[5]童庆禧.电子光学遥感系统的过去、现在和未来.北京：科学出版社,1995,51-60.
[6]Goets A F H, Rowan L C.Geological remote sensing Science[J].1981,211:781-791.
[7]Shippert P.Why use hyperspectral imagery?[J].Photogrammetric Engineering and Remote Sensing,2004,70(1):377-379.
[8]Schowengerdt RA著.李德熊译.遥感中的图像处理和分类技术[M].北京：科学出版社,1991.
[9]徐冠华,田国良,王超,等.遥感信息科学的进展与展望[J].地理学报,1996,51(5)：385-397.
[10]杜培军,陈云浩,王行风,等.遥感科学与进展[M].徐州：中国矿业大学出版社,2007：369-370.
[11]吴培中.星载高光谱成像光谱仪的特性与应用[J].国土资源遥感,1999,(3)：31-39.
[12]Reese H, Nilsson M P, Ahlen TG, Tingelof U.Countrywide estimates of forest variables using satellite data and field data from the national forest inventory[J]. Ambio,2003,32(8):542-548.
[13]路威.面向目标探测的高光谱影像特征提取与分类技术研究[D].郑州：解放军信息工程大学,2005.
[14]Hsieh P, Landgrebe D.Statistics enhancement in hyperspectral data analysis using spectral spatial labeling, the EM algorithm, and the leave-one-out covariance estimator[A].SPIE International Symposium on Optical Science, Engineering, and Instrumentation[C]San Diego, CA,1998.19-24.
[15]赵锐,赵学军,于嘉喜.地物光谱在林业遥感中的应用[J].内蒙古林业调查设计,1999,3(2)：120-121.
[16]张连蓬.基于投影寻踪和非线性主曲线的高光谱遥感图像特征提取及分类研究[D]. 青岛：山东科技大学,2003.
[17]孙蕾,罗建书.高光谱遥感图像微分域三维混合去噪方法[J].光谱学与光谱分析.2009,29(10)：2717-2720.
[18]Bisun Datt, David Jupp.Hyperion Data Processing Workshop:Handson Processing Instruction[D], CSIRO Earth Observation Centre,2004.
[19]Tan Binxiang, Li Zengyuan, Chen Erxue, etal.EO-1 Hyperion hyperspectral data preprocessing [J]. Remote Sensing Information,2005(6):36-41.
[20]钱乐祥等.遥感数字影像处理与地理特征提取[M].北京：科学出版社.2004：171-172.
[21]Kruse FA, Boardman JW, Huntington JF, etal.Comparison of airborne hyperspectral data and EO-1 Hyperion for mineral mapping[J].IEEE Transactions on Geoscience and Remote Sensing,2003,41(6):1388-1400.
[22]Kumar Shailesh, Ghosh Joydeep, Crawford Melba M.Hierarehical Fusion of Multiple Classifiers for Hyperspectral Data Analysis[J].Pattern Analysis & Applications,2002, 5(2):210-220.
[23]VANE GREGG, GOETZ ALEXANDER F H.Terrestrial imaging spectrometry:current status, future trends[J].Remote Sens.Environ,1993,44:117-126.
[24]LILLESAND T M, KIEFER R W.Remote Sensing and Image Interpretation[A].New York:John Wiley&Sons, Inc.[C],1994,1-750.
[25]HUNT G R.Electromagnetic radiation:the communication link in remote sensing[M].In:Remote Sensing in Geology.Siegal B, Gillespia A.Wiley New York, 1980,702.
[26]Horler DNH, Barber J.P., Ferns D.C., Barringer A.R.Approaches to detection of geochemical stress in vegetation[J].Advanced space Research,1983,3:175-179.
[27]GOETZ ALEXANDER F H, et al. Imaging spectrometry for earth remote sensing[J].Science,1985,228(4702):1147-1153.
[28]Kruse FA.Improved multispectral mapping by spectral modeling with hyperspectral signatures [C].Proceedings, SPIE Symposium on Defense & Security, 9-13 April 2007, Orlando, FL, SPIE, V.6565,2007.
[29]Goodenough DG, Dyk A, Niemann KO, et al.Processing Hyperion and ALI for forest classification[J].IEEE Transactions on Geoscience and Remote Sensing,2003,41(6): 1321-1331.
[30]BOYD, D S, FOODY, et al.Evaluation of approaches for forest cover estimation in the Pacific Northwest, USA, using remote sensing[J].Applied Geography,2002,22: 375-392.
[31]SANDMEIER ST, DEERING D W.Structure Analysis and Classification of Boreal Forests Using Airborne Hyperspectral BRDF Data from AS AS[J].REMOTE SENS.ENVIRON,1999,69:281-295.
[32]MARTIN M E, NEW MAN S D, ABER J D, et al.Determining Forest Species Composition Using High Spectral Resolution Remote Sensing Data[J].REMOTE SENS.ENVIRON,1998,65:249-254.
[33]李智勇.高光谱图像异常检测方法研究[D].长沙：国防科学技术大学,2004.
[34]浦瑞良,宫鹏.高光谱遥感及其应用[M].高等教育出版社,2000.
[35]王学仁,王松桂.实用多元统计分析[M].上海：上海科学技术出版社,1990.
[36]吴昊.高光谱遥感图像数据分类技术研究[D].国防科技大学,2004.
[37]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].中国图像图形学报,2005,1(10)：218-222.
[38]刘勇卫,贺雪鸿.遥感精解第1版[M].北京：测绘出版社,1993,170-220.
[39]童庆禧,张兵,郑兰芬.高光谱遥感—原理、技术与应用第1版[M].北京：高等教育出版社,2006,166-203.
[40]王长耀,牛铮,唐华俊,等.对地观测技术与精细农业[M].北京：科学出版社,2001.
[41]林辉,刘秀英.基于高光谱遥感特征参数的樟树幼林叶绿素a含量估算模型[J].绵阳师范学院学报,2008(8)：1-5.
[42]刘璇.杉木主要生物化学参数的高光谱遥感估算模型研究[D].中南林业科技大学,2010.
[43]宫鹏,浦瑞良,郁彬.不同季相针叶树种高光谱数据识别分析[J].遥感学报,1998：211-217.
[44]卫俊霞,相里斌,段晓峰等.基于EZW的高光谱图像压缩技术研究[J].2011,31(8).
[45]于祥,赵冬至,张丰收,等.红树林高光谱分析技术研究[J].滨州学院学报,2006：53-56.
[46]张丰,熊桢,寇宁.高光谱遥感数据用于水稻精细分类研究[J].武汉理工大学学报,2002,24(10)：36-39.
[47]童庆禧,郑兰芬,王晋年,等.湿地植被成像光谱遥感研究[J].遥感学报,1(1)：50-71.
[48]甘甫平,王润生,郭小方,等.高光谱遥感信息提取与地质应用前景[J].国土资源 遥感,2000：38-44.
[49]甘甫平,王润生,马蔼乃.基于特征谱带的高光谱遥感矿物谱系识别[J].地学前缘,2003(2)：445-454.
[50]王晋年,郑兰芬,童庆禧.成像光谱图像光谱吸收鉴别模型与矿物填图研究[J].环境遥感,1996(1)：20-31.
[51]王青华,王润生,郭小方,等.高光谱遥感技术在岩石识别中的应用[J].国土资源遥感,2000(4)：39-43.
[52]张学霞,葛全胜,郑景云.遥感技术在植物物候研究中的应用综述[J].地球科学进展,2003(4)：534-544.
[53]方红亮,田庆久.高光谱遥感在植被监测中的研究综述[J].遥感技术与应用,1998(1)：62-69.
[54]谭炳香.高光谱遥感森林应用研究探讨[J].世界林业研究,2003(2)：33-37.
[55]申广荣,王人潮.植被光谱遥感数据的研究现状及其展望[J].遥感技术与应用,2001(6)：682-690.
[56]HUNT G R.Electromagnetic radiation:the communication link in remote sensing [M].In:Remote Sensing in Geology.Siegal B, Gillespia A.Wiley New York,1980, 702.
[57]FM Danson.Red edge response to forest leaf area index.lnternational Journal of Remote Sensing,1995,16(1):183-188.
[58]张良培,郑兰芬,童庆禧.利用高光谱对生物变量进行估计[J].遥感学报,1997,1(2)：111-114.
[59]Horler DNH, Dockray, M.Barber, et al.Red edge measurements for remotely sensing plant chlorophyll content.Advanced space Research,1983,3:273-277.
[60]陈君颖,田庆久.高分辨率遥感植被分类研究[J].遥感学报,2007,11(2)：221-227.
[61]陈桂红,唐伶俐,姜小光.高光谱遥感图像特征选取和提取方法的比较—基于实验区Barrax的HyMap数据[J].干旱区地理,2006,29(1)：143-149.
[62]杨竹青,李勇,胡德文.独立成分分析方法综述[J].自动化学报,2002,5：762-772.
[63]Thenkabail P S, Enclona E A, Ashton M S, et al.Hyperion, IKONOS, ALI and ETM+ sensors in the study of African rainforests. Remote sensing of Environment,2004,90: 23-43.
[64]孙华,林辉,熊育久,莫登奎SPOT5影像统计分析及最佳组合波段选择[J].遥感信息应用技术,2006,4：57-60.
[65]徐冠华,田国良,王超,等.遥感信息科学的进展与展望[J].地理学报,1996,51(5)：385-397.
[66]陈君颖,田庆久.高分辨率遥感植被分类研究[J].遥感学报,2007,11(2)：221-227.
[67]孙家柄,舒宁,关泽群.遥感原理、方法和应用[M].北京：测绘出版社,1997.
[68]骆剑承,王钦敏,马江洪,等.遥感图像最大似然分类方法的EM改进算法[J].测绘学报,2002,31(3)：234-239.
[69]Jia X.Classification techniques for hyperspectral remote sensing image data[D].University of New South Wales,1996.
[70]钱乐祥,等.遥感数字影像处理与地理特征提取[M].北京：科学出版社,2004：171-172.
[71]C R Jung.Multiscale image segmentation using wavelets and watersheds.Proc of XVI Brazilian Symposium on Computer Graphics and Image Processing,2003,278-284.
[72]梁继,等Hyperion高光谱影像的分析与处理[J].冰川冻土,2009.
[73]孙林.多光谱图像获取技术研究[D].西安电子科技大学,2010.
[74]岳跃民.基于光谱和空间领域信息的石漠化遥感评价因子提取研究[D].中国科学院研究生院,2010.
[75]梁亮,杨敏华,李英芳.基于ICA与SVM算法的高光谱遥感影像分类[J].光谱学与光谱分析,2010,30(10).
[76]吴见,彭道黎.高光谱遥感林业信息提取技术研究进展[J].光谱学与光谱分析,2011,3131(9).
[77]李婷.基于图像融合的高光谱遥感图像分类研究[D].中国科学技术大学,2008.
[78]苏红军,盛业华,Yang He, Du Qian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.
[79]陶秋香,赵长胜,张连蓬.植被高光谱遥感分类中一种新的非线性混合光谱模型及其解算方法.矿山测量,2004.
[80]http://datamirror.csdb.cn/eo1/resource/baseIntro.jsp
[81]Manin M.E. et al.Determining forest species composition using high spectral resolution remote sensing data. Remote Sense Environ,1998,65:249-254.
[82]T Han, DG Gondenough, A Dyk, J Love.Detection and correction of abnormal pixels in Hyperion images Proceedings of GARSS,2002, Vol.3, Toronto, ON, Canada, 1327-1330.
[83]McVicar TR, Van Niel TG, Jupp DLB..Geometric Validation of Hyperion Data acquired by Earth Observing Satellite at Coleambally Irrigation Area. CS1RO Land and Water Technical Report 46/01,2001, Canberra, Australia.
[84]Vermote E F, Saleous N EL, Justice C O, et al.Atmosepheric correction of visible to middle infrared EOS-MODIS data over land surface, background, operational algorithm and validation[J].Journal of Geophysical Research,1997,102(17):131-141.
[85]刘建贵.高光谱城市地物及人工目标识别与提取[D].中国科学院遥感应用研究所,1999.
[86]熊祯.高光谱遥感图像分类技术研究[D].中科院遥感应用研究所,2000.
[87]Secker J, Staenz K, Gauthier R, et al.Vicarious calibration of airborne hyperspectral sensors in operational environments.Remote Sensing of Environment,,2001,76(1): 81-92.
[88]Barry P.EO-1 Hyperion Science Data Users Guide[R].Californai:TRW Space, Defense & Information Systems,2001.
[89]Curran PJ, JL Dungan.Estimation of Signal-to-Noise:A New Procedure Applied to AVIRIS data.IEEE Transaction on Geoscience and Remote Sensing,1989,27(5): 620-628.
[90]Goetz AF, WM Calvin.Imaging Spectrometry: Spectral Resolution and Analytical Identification of Spectral Features, in G Vane (Ed.), Imaging Spectroscopy II, Bellingham, WA:Photo-Optical Instrument Engineers,1987,158-165.
[91]Wolfe WL.Introduction to Imaging Spectrometers. Vol.TT25, Bellingham, WA: SPIE Optical Engineering Press,1997,148-149.
[92]Liou K N.An Introduction to Atmospheric Radiation (Second Edition)[M].New York: Academic Press,2002.
[93]谭炳香,李增元,等Hyperion高光谱数据的预处理[J].遥感信息,2005(6)：36-41.
[94]张丰,熊桢,寇宁.高光谱遥感数据用于水稻精细分类研究[J].武汉理工大学学报,2002,24(10)：36-39.
[95]Mustard JF, Staid MI, WJ Fripp.A Semianalytical Approach to the Calibration of AVIRIS Data to Reflectance over Water Application in a Temperate Estuary[J].Remote Sensing of Environment. 2001(75):335-349.
[96]顾名澧.多光谱扫描仪的星上辐射定标系统[J].航天返回与遥感,1998.1(3)：21-25.
[97]Dinguirard M, Slater PN.Caiibration of space-multispectral imaging sensor[J].Remote Sensing of Environment,1999,68(3):194-205.
[98]Richard Beck.EO-1 User Guide v.2.3.http://eo1.usgs.gov & http://eo1.gs fs.nasa.gov, 2003.
[99]张俊华.应用3s技术对帽儿山地区森林水文效应评价的研究[D].东北林业大学,2001：27-40.
[100]孙亮,韩崇昭,康欣.多源遥感影像的集值特征选择与融合分类[J].电波科学学报.2004,9(4)：479-484.
[101]Kruse FA, Boardman JW, Huntington JF, et al.Comparison of airborne hyperspectral data and EO-1 Hyperion for mineral mapping[J].IEEE Transactions on Geoscience and Remote Sensing,2003,41(6):1388-1400.
[102]Kruse FA.Improved multispectral mapping by spectral modeling with hyperspectral signatures [C]// Proceedings, SPIE Symposium on Defense & Security,9-13 April 2007, Orlando, FL, SPIE, V.6565,2007.
[103]骆剑承,周成虎,梁怡,等.支持向量机及其遥感影像空间特征提取和应用分类的研究[J].遥感学报,2002,6(1)：50-54.
[104]P Barry.EO-1 Hyperion Science Data User's Guide.Redondo Beach, CA:TRW Space, Defense & Inform.Sys,2001.
[105]刘行华.基于GIS的TM数据分类及辅助制图研究[J].环境遥感,1992(2).
[106]Boardman JW, Kruse FA.Automated spectral analysis:a geological example using ERIM Tenth AVIRIS data, north Grapevine Mountains, Nevada:Thematic Conference on Geologic Remote Sensing, in Proceedings, Environmental Research Institute of Michigan, Ann Arbor, MI,1999,1407-1418.
[107]赵英时.遥感应用分析原理与方法[M].北京：科技出版社,2004.
[108]王秀朋,张洪才,赵永强,等.基于投影寻踪的高光谱图像特征融合算法[J].计算机测量与控制,2006,14(11)：1539-1541.
[109]McVicar TR, Van Niel TG, Jupp DLB.Geometric Validation of Hyperion Data acquired by Earth Observing-1 Satellite at Coleambally Irrigation Area[J].CSIRO Land and Water Technical Report 46/01, Canberra, Australia,2001, pp.70.
[110]Jimenez Luis O, Rivera-Medina Jorge L.Integration of spatial and spectral information homogenous by means of unsupervised extraction and classification for objects applied to multispectral and hyperspectral data[J].IEEE Transactions on Geoscience and Remote Sensing,2005,43(4):844-851.
[111]刘春红,赵春晖,张凌雁.一种新的高光潜遥感图像降维方法[J].中国图象图形学 报,2005,10(2)：218-222.
[112]赵春晖,刘春红.超谱遥感图像降维方法研究现状与分析[J].中国空间科学技术,2004(5)：8-36.
[113]黄睿.高光谱遥感数据特征约简技术研究[D].西安：西北工业大学,2006.
[114]Clark RN, King TVV, Kleijwa M, Swayze.High spectral resolution reflectance spectroscopy of minerals[J].Geophysics,1990,95:12653-12680.
[115]刘建平,赵英时.高光谱遥感数据解译的最佳波段选择方法研究.中国科学院研究生院学报.1999,16(2)：152-161.
[116]李行,张连蓬.高光潜遥感图像最佳波段选择的快速算法研究[J].测绘通报,2004(9)：10-12.
[117]Chavez PS, Berlin GL, Sowers LB.Statistical method for Selecting landsat MSS ratios[J] Journal of applied photographic engineering,1982,1(8):23-30.
[118]姜小光,唐伶俐,王长耀,等.高光谱数据的光谱信息特点及面向对象的特征参数选择—以北京顺义地区为例[J].遥感技术与应用,2002,17(2)：59-65.
[119]Junping Zhang, Ye Zhang, Bin Zou, Tingxian Zhou. Fusion Classification of Hyperspecal Image Based on Adaptive subspace Decomposition [C]. Canada:ICIP 2000 Proceeding. IEEE Signal Processing Society,2000,3:472-475.
[120]杨诸胜,郭雷,罗欣,胡新韬.基于分段主成分分析的高光谱图像波段选择算法研究[J].测绘工程,2006,15(6)：15-18.
[121]赵春晖,刘春红.超谱遥感图像降维方法研究现状与分析[J].中国空间科学技术,2004(5)：28-36.
[122]N Kambhatla, RA Leen.Dimension reduetion by local principal component analysis [J].Neural ComPutation,1997,9(7):1493-1516.
[123]D Manolakis, D Marden.Dimensionality reduetion of hyperspectral imaging data using local Principal components transofmrs[J].Proeeedings of SPIE,2004,5425: 393-401.
[124]DF Miehael, RM Mersereau.On the impact of PCA dimension reduction for hyperspectral detection of difficult targets.IEEE Geoscience and Remote Sensing Letters,2005,2(2):192-195.
[125]HuangRui, HeMingyi.Band selection based on feature weighting for classification of hyperspectral data.IEEE Geoscience and Remote Sensing Letter,2005, 2(2): 156-159.
[126]Jimenez, Luis O, Landgrebe, David A.Hyperspectral data analysis and spuevrised feature reduction via projection pursuit.IEEE Transactions on Geoscience and Remote Sensing, v37, Nov,1999, p2653-2667.
[127]Jia Xiuping, JA Riehards.Segmented principal components transformation for effieient hyperspectral remote-sensing image display and classiflcation.IEEE Geoscience and Remote Sensing,1999,37(1).538-542.
[128]Jimenez LO, Landgrebe DA. Hyperspectral Data Analysis and Supervised Feature Reduction Via Projection Pursuit[J].IEEE Transactions on Geoscience and Remote Sensing,1999,37(6):2653-2667.
[129]田庆久,王世新,王乐意,等.典型地物标准波谱数据库系统设计[J].遥感技术与应用,2003,18(4)：185-190.
[130]Ediriwickrema J, Khorram S.Hieraichical maximum-likelihood classification for improved accuracies[J].IEEE Transactions on Geoscience and Remote Sensing,1997, 35(4):810-816.
[131]Benediktsson J, Swain P, Esroy O.Neural network approaches versus statistical methods in classification of multisource remote sensing data[J].IEEE Transactions on Geoscience and Remote Sensing,1990,28:540-542.
[132]李石华,王金亮,毕艳,等.遥感图像分类方法研究综述[J].国土资源遥感,2005,64(2)：1-6.
[133]王晋年,张兵等.以地物识别和分类为目标的高光谱数据挖掘[J].中国图像图形学报,1999 4(11)：957-964.
[134]Osmar Abilio de Carvalho Jr&Paulo Roberto Meneses.Spectral Correlation Mapper (SCM):An Improvement on the Spectral Angle Mapper(SAM), http: //popo.jpl.nasa.gov/docs/workshops/aviris. proceedings.html
[135]ENVI Tutorials.2003 edition, Research System Inc,2003.