基于支持向量机的超谱图像分类技术研究
|
摘要
随着数字信号处理技术、计算机技术以及通信技术的迅猛发展,遥感图像处理技术在军事、民用等领域发挥着越来越重要的作用。与多光谱遥感相比,超谱遥感具有更高的光谱分辨率。超谱图像分类的研究是超谱遥感应用的主要内容之一。硬分类是将复杂的现象简化为少量的类别,是提取超谱图像中有用信息的重要处理方法之一。另一方面,超谱图像的空间分辨率一般较低,从而导致混合像素广泛存在,而处理混合像素相对于处理纯像素更加困难且更具重要意义。作为混合像元处理主要技术的光谱分离,就是要去求解光谱分离后像元内各混合成分所占的比例,是一种更为精确的软分类技术。目前硬分类方法较多,但分类效果不够理想或是方法本身有待提升;传统软分类方法由于在光谱分离中无关类别的参与以及光谱分离模型本身的不足导致分离效果不够理想。为此,本文以支持向量机为主要理论,对超谱图像硬、软分类(光谱分离)及相关技术进行研究。
第一,研究基于相似特征逐步删除的超谱图像波段选择和高斯低通滤波预处理方法。该波段选择方法建立在特征相似性计算之上,具有无监督性并且计算复杂度很小。所提出的高斯低通滤波方法旨在减弱或消除超谱遥感图像的高频分量但不影响低频分量,使得图像平滑且平滑后的图像类内距离变小而类间距离变大,以便有利于后续分类处理。
第二,系统研究支持向量机相关理论,包括理论基础、分类原理、线性分类到非线性分类的推广、二类分类到多类分类的扩展、主要实现技术等,并且对其分类性能进行了实验测试。理论基础和主要原理的研究有利于理解支持向量机所具有的独特优势;发展类型和优化算法的研究旨在提高支持向量机的应用效率;多类实现方法的研究使得该技术能够更为方便地处理类别较多的分类问题。这部分内容的研究为后文开展奠定了必要的理论基础。
第三,研究提高支持向量机分类精度的方法,包括分类前的模糊方法的应用,训练过程中加权方法的应用,以及初次训练完成后对于部分子分类器的二次训练思想等。模糊方法在模糊聚类的基础上选择训练样本,并采用支持向量机分类算法对图像进行最终的分类,用以克服样本选择的盲目性;加权方法采用距离尺度对最小二乘支持向量机惩罚项进行加权,以克服训练过程中噪声点的不良干扰;二次训练思想对两种类型的支持向量机和全部参数均进行有效的二次调整,通过对分类效果最差的几个子分类器进行二次参数调整,最后整合利用两次获得的最优参数赋予相应的子分类器构成新的总体分类器。
第四,研究支持向量机应用于光谱分离即软分类的可行性和方法,以及光谱分离中有效的类别子集的选择方法。一方面,介绍了线性支持向量机应用于光谱分离的原理,应用的非线性扩展,并对其应用效果进行了论证;另一方面在光谱分离中分别根据空间相关性和感兴趣类别进行相关类别子集的选择,利用相关类别对混合像元进行更为精确的光谱分离。
实验结果表明,支持向量机对于超谱图像的软、硬分类有着非常良好的效果;而恰当的预处理方法、支持向量机性能提升方法和类别子集选择有助于获得更好的分析效果。
With the development of digital signal processing technology, computer technology and communication technology, remote sensing imagery processing takes increasingly important effects in the fields of military and civil applications. Compared with multispectral remote sensing, the hyperspectral remote sensing has a higher spectral resolution. The research of hyperspectral images (HSI) classification is one of the main contents of the hyperspectral remote sensing application. Hard classification which aims at simplifying the complex phenomenon is one of the significant processing methods in the interest information extraction of hyperspectral images. On the other hand, mixed pixels are widely existent in hyperspectral images for its low spatial resolution. The analysis and processing of mixed pixels are of more importance and significance. As a main technique of mixed pixel processing, spectral unmixing is to work out the mixing proportion of each class included in mixed pixel. It is a more accurate soft classification technique. At present, there are lots of hard classification methods, but their classification performances are not very perfect, or some methods themselves are to be improved. Traditional spectral unmixing methods are inefficient for the participation of unrelated classes and for the deficiency of spectral unmixing model. In this case, the techniques of hard classification and soft classification (spectral unmixing) are researched mainly based on support vector machine (SVM) theory in the paper.
Firstly, a band selection method based on stepwise deletion of similar feature and a gauss low pass filtering method are proposed. The band selection method is constructed on the computation of feature similarity. The method is unsupervised and of low computational complexity. The proposed gauss low pass filtering method aims to weaken or eliminate the high frequency component of hyperspectral images but not change its low frequency component. The filter is designed to smooth hyperspectral, to reduce within-class distance and to enlarge between-class distance. In this case, the filtering method is helpful of following classification processing of hyperspectral images.
Secondly, SVM theory is researched systemically, including theory basis, classification principle, the generalization form linear classification to nonlinear classification, the extent from bi-class problem to multi-class problem, and the main implementation techniques. The classification performance of SVM is also tested in this paper. The studies of theory basis and classification principle benefit to understand the unique dominance of SVM, the studies of optimization algorithm and development version are helpful of improving its application efficiency, and the study of multi-class extension makes it possible for the technique to process classification problem with large number of classes conveniently. These studies provide necessary theory basis for the progress of the dissertation.
Thirdly, the classification performance of SVM is improved; including the usage of fuzzy method before classification, distance based fuzzy SVM, and secondary training in multi-class problem. In order to overcome the blindness of sample selection, fuzzy method select training samples based on fuzzy xxx, followed by SVM based classification. The weighted SVM makes use of distance measure to fuzzy weigh the punishment terms in least square SVM, and so overcomes the bad influence brought by outliers in process of training. In the idea of secondary training, all parameters in two kinds of SVM are regulated effectively. Through the secondary parameter regulation for some weak classifiers, new general classifier is formed by sub-classifiers with optimal parameters.
Finally, the feasibility and method of applying SVM to spectral unmixing (a kind of soft classification) and the selection method of class sub-set are researched. On the one hand, the principle of applying linear SVM to spectral unmixing is introduced, and then the application is intended to nonlinear SVM. The unmixing effect of the application is also tested. On the other hand, the selection of correlative class sub-set is conducted based on spatial correlation and on class-of-interest is researched, and the more accuracy spectral unmixing is implemented on the class sub-set.
Experiments show that SVM has good performance both in hard classification and in soft classification, and proper preprocessing measure, improving measure of SVM, and selection measure of class sub-set are all helpful of getting better analysis effect.
第一,研究基于相似特征逐步删除的超谱图像波段选择和高斯低通滤波预处理方法。该波段选择方法建立在特征相似性计算之上,具有无监督性并且计算复杂度很小。所提出的高斯低通滤波方法旨在减弱或消除超谱遥感图像的高频分量但不影响低频分量,使得图像平滑且平滑后的图像类内距离变小而类间距离变大,以便有利于后续分类处理。
第二,系统研究支持向量机相关理论,包括理论基础、分类原理、线性分类到非线性分类的推广、二类分类到多类分类的扩展、主要实现技术等,并且对其分类性能进行了实验测试。理论基础和主要原理的研究有利于理解支持向量机所具有的独特优势;发展类型和优化算法的研究旨在提高支持向量机的应用效率;多类实现方法的研究使得该技术能够更为方便地处理类别较多的分类问题。这部分内容的研究为后文开展奠定了必要的理论基础。
第三,研究提高支持向量机分类精度的方法,包括分类前的模糊方法的应用,训练过程中加权方法的应用,以及初次训练完成后对于部分子分类器的二次训练思想等。模糊方法在模糊聚类的基础上选择训练样本,并采用支持向量机分类算法对图像进行最终的分类,用以克服样本选择的盲目性;加权方法采用距离尺度对最小二乘支持向量机惩罚项进行加权,以克服训练过程中噪声点的不良干扰;二次训练思想对两种类型的支持向量机和全部参数均进行有效的二次调整,通过对分类效果最差的几个子分类器进行二次参数调整,最后整合利用两次获得的最优参数赋予相应的子分类器构成新的总体分类器。
第四,研究支持向量机应用于光谱分离即软分类的可行性和方法,以及光谱分离中有效的类别子集的选择方法。一方面,介绍了线性支持向量机应用于光谱分离的原理,应用的非线性扩展,并对其应用效果进行了论证;另一方面在光谱分离中分别根据空间相关性和感兴趣类别进行相关类别子集的选择,利用相关类别对混合像元进行更为精确的光谱分离。
实验结果表明,支持向量机对于超谱图像的软、硬分类有着非常良好的效果;而恰当的预处理方法、支持向量机性能提升方法和类别子集选择有助于获得更好的分析效果。
With the development of digital signal processing technology, computer technology and communication technology, remote sensing imagery processing takes increasingly important effects in the fields of military and civil applications. Compared with multispectral remote sensing, the hyperspectral remote sensing has a higher spectral resolution. The research of hyperspectral images (HSI) classification is one of the main contents of the hyperspectral remote sensing application. Hard classification which aims at simplifying the complex phenomenon is one of the significant processing methods in the interest information extraction of hyperspectral images. On the other hand, mixed pixels are widely existent in hyperspectral images for its low spatial resolution. The analysis and processing of mixed pixels are of more importance and significance. As a main technique of mixed pixel processing, spectral unmixing is to work out the mixing proportion of each class included in mixed pixel. It is a more accurate soft classification technique. At present, there are lots of hard classification methods, but their classification performances are not very perfect, or some methods themselves are to be improved. Traditional spectral unmixing methods are inefficient for the participation of unrelated classes and for the deficiency of spectral unmixing model. In this case, the techniques of hard classification and soft classification (spectral unmixing) are researched mainly based on support vector machine (SVM) theory in the paper.
Firstly, a band selection method based on stepwise deletion of similar feature and a gauss low pass filtering method are proposed. The band selection method is constructed on the computation of feature similarity. The method is unsupervised and of low computational complexity. The proposed gauss low pass filtering method aims to weaken or eliminate the high frequency component of hyperspectral images but not change its low frequency component. The filter is designed to smooth hyperspectral, to reduce within-class distance and to enlarge between-class distance. In this case, the filtering method is helpful of following classification processing of hyperspectral images.
Secondly, SVM theory is researched systemically, including theory basis, classification principle, the generalization form linear classification to nonlinear classification, the extent from bi-class problem to multi-class problem, and the main implementation techniques. The classification performance of SVM is also tested in this paper. The studies of theory basis and classification principle benefit to understand the unique dominance of SVM, the studies of optimization algorithm and development version are helpful of improving its application efficiency, and the study of multi-class extension makes it possible for the technique to process classification problem with large number of classes conveniently. These studies provide necessary theory basis for the progress of the dissertation.
Thirdly, the classification performance of SVM is improved; including the usage of fuzzy method before classification, distance based fuzzy SVM, and secondary training in multi-class problem. In order to overcome the blindness of sample selection, fuzzy method select training samples based on fuzzy xxx, followed by SVM based classification. The weighted SVM makes use of distance measure to fuzzy weigh the punishment terms in least square SVM, and so overcomes the bad influence brought by outliers in process of training. In the idea of secondary training, all parameters in two kinds of SVM are regulated effectively. Through the secondary parameter regulation for some weak classifiers, new general classifier is formed by sub-classifiers with optimal parameters.
Finally, the feasibility and method of applying SVM to spectral unmixing (a kind of soft classification) and the selection method of class sub-set are researched. On the one hand, the principle of applying linear SVM to spectral unmixing is introduced, and then the application is intended to nonlinear SVM. The unmixing effect of the application is also tested. On the other hand, the selection of correlative class sub-set is conducted based on spatial correlation and on class-of-interest is researched, and the more accuracy spectral unmixing is implemented on the class sub-set.
Experiments show that SVM has good performance both in hard classification and in soft classification, and proper preprocessing measure, improving measure of SVM, and selection measure of class sub-set are all helpful of getting better analysis effect.
引文
[1]孙家柄.遥感原理与应用.武汉:武汉大学出版社.2003:1-2
[2]钱乐祥等编著.遥感数字影像处理与地理特征提取.北京:科学出版社.2004.7:1-3
[3]宁书年,吕松棠,杨小琴,王四龙,余才英,张景发.遥感图像处理与应用.地震出版社.1995:39-45
[4]D.A.Landgrebe,S.B.Serpico,M.M.Crawford,Vem Singhroy.Introduction to the Special Issue on Analysis of Hyperspectral Image Data.IEEE Trans.on Geoscience and Remote Sensing.2001,39(7):1343-1344
[5]Algorithms and technologies for multispectral,hyperspectral and ultraspectral imagery.http://www.spie.org/Conferences/Calls/04/or/SubmitAbstract/index .cfm?fuseaction=OR36
[6]Algorithms and technologies for multispectral,hyperspectral and ultraspectral imagery.http://www.spie.org/Conferences/Calls/05/dss/conferences/index.cf m?fuseaction=OR47
[7]孙家柄.遥感原理与应用.武汉:武汉大学出版社.2003:25-26
[8]陈述彭,章庆禧,郭华东.遥感信息机理研究.科学出版社,1998:141-142页
[9]Green Robert O,Pavri Betina E,Chrien Thomas G.On-orbit radiometric and spectral calibration characteristics of EO-1 hyperion derived with an underflight of AVIRIS and In situ measurements at Salar de Arizaro,Argentina.IEEE Transactions on Geoscience and Remote Sensing,PART Ⅰ,2003,41(6):1194-1203.
[10]Luis O.Jimenez & David A.Landgrebe.Supervised Classification in High-Dimensional Space:Geometrical,Statistical,and Asymptotical Properties of Multivariate Data.IEEE Trans.on System,Man,and Cybernetics-Part C:Applications and Reviews.1998,28(1):39-54
[11]边肇祺,张学工.模式识别.北京:清华大学出版社.2000:24-30
[12]Richards,J.A.Analysis of remotely sensed data:the formative decades and the future.Geoscience and Remote Sensing.IEEE Transactions on.2005,43(3):422-432
[13]Landgrebe,D.A.Multispectral land sensing:where from,where to?Geoscience and Remote Sensing,IEEE Transactions on.2005,43(3):414-421
[14]陈宜金,高金起,申进志,梁晓文.基于层次结构的Cito Map地理信息数据采集系统的若干特点.矿山测量,2004,4:16-18
[15]张斌,朱正中,葛成辉,吴佑寿.一种基于边缘轮廓信息的多源遥感图像子像元匹配定位方法.中国图像图形学报.2000,5(A,10):830-835
[16]顾松刚,史培军.基于混合象元分解的辽东湾海冰资源量估算.北京师范大学学报(自然科学版).2004,40(3):411-416
[17]Liang Shunlin,Fang Hongliang.An improved atmospheric correction algorithm for hyperspectral remotely sensed imagery.IEEE Geoscience and Remote Sensing Letters.2004,1(2):112-117
[18]Hardie Russell C,Eismann Michael T,Wilson Gregory L.MAP estimation for hyperspectral image resolution enhancement using an auxiliary sensor Source:IEEE Transactions on Image Processing.2004,13(9):1174-1184
[19]Gupta Neelam,Voloshinov Vitaly.Hyperspectral imager,from ultraviolet to visible,with a KDP acousto-optic tunable filter.Applied Optics.2004,43(13):2752-2759
[20]Bei Ling,Duffin Kirk L,Camahan Jon W.Inductively coupled plasma chemistry examinations with visible acousto-optic tunable filter hyperspectral imaging.Journal of Analytical Atomic Spectrometry.Winter Conference on Plasma Spectrochemistry.2004,19(9):1151-1157
[21]Raviv O,Rotman S.R.Applying ordered statistics filters for point target detection in hyperspectral data Proceedings of SPIE-The International Society for Optical Engineering.2004,5204:35-40
[22]Bachmarm,C.M.;Ainsworth,T.L.;Fusina,R.A.Exploiting manifold geometry in hyperspectral imagery.Geoscience and Remote Sensing,IEEE Transactions on.2005,43(3):441-454
[23]李金宗.模式识别导论.北京:高等教育出版社,1994.7:5-7
[24]Dundar M.Murat,Landgrebe David A.Toward an optimal supervised classifier for the analysis of hyperspectral data.Source:IEEE Transactions on Geoscience and Remote Sensing.2004,42(1):271-277
[25]Jia,Xiuping,Richards,John A.Efficient transmission and classification of hyperspectral image data.IEEE Transactions on Geoscience and Remote Sensing.2003,41(5):1129-1131
[26]钱乐祥等编著.遥感数字影像处理与地理特征提取.北京:科学出版社.2004:171-172
[27]Chang Chein-I,Chiang Shao-Shan.Anomaly detection and classification for hyperspectral imagery.IEEE Transactions on Geoscience and Remote Sensing.2002,40(6):1314-1325
[28]Rand Robert S.Spectral/spatial annealing of hyperspectral imagery initialized by a supervised classification method.Proceedings of SPIE-The International Society for Optical Engineering.2002,4725:242-253
[29]Ji Baohong,Chang Chein-I,Jensen Janet L,Jensen James O.Unsupervised constrained linear fisher's discdminant analysis for hyperspectral image classification.Proceedings of SPIE - The International Society for Optical Engineering,Imaging Spectrometry X,2004,5546:44-353
[30]Kumar S,Ghosh J,Crawford M.M.Best-bases feature extraction algorithms for classification of hyperspectral data.IEEE Transactions on Geoscience and Remote Sensing.2001,39(7):1368-1379
[31]Kuo Bor-Chen,Yang Jinn-Min.Landgrebe David A.Gaussian Mixture Classifier with Regularized Covariance Estimator for Hyperspectral Data Classification. International Geoscience and Remote Sensing Symposium (IGARSS).2003, 1:276-278
[32] Murphy Patricia K, Kolodner Marc A. Implementation of a multi-scale Bayesian classification approach for hyperspectral terrain categorization.Proceedings of SPIE - The International Society for Optical Engineering.2002,4816: 278-287
[33] Santich N.T. Reducing the parameterization of the covariance matrix for maximum likelihood classification. International Geoscience and Remote Sensing Symposium (IGARSS). 2002, 6: 3519-3521
[34] Dundar M.M, Landgrebe D.A. Toward an optimal supervised classifier for the analysis of hyperspectral data. Geoscience and Remote Sensing, IEEE Transactions on. 2004 42(1): 271 - 277
[35] Rand Robert S. Spectral/spatial annealing of hyperspectral imagery initialized by a supervised classification method. Proceedings of SPIE - The International Society for Optical Engineering. 2002, 4725: 242-253
[36] Landgrebe David, Murat Dundar M. A model-based mixture-supervised classification approach in hyperspectral data analysis. IEEE Transactions on Geoscience and Remote Sensing. 2002, 40(12): 2692-2699
[37] Chang Yang-Lang, Han Chin-Chuan. Greedy modular eigenspaces and positive Boolean function for supervised hyperspectral image classification Optical Engineering. 2003, 42(9): 2576-2587
[38] Wu Hao, Kuang Gangyao, Yu Wenxian. An Unsupervised Classification Method for Hyperspectral Image Combining PCA and Gaussian Mixture Model. Proceedings of SPIE - The International Society for Optical Engineering. 2003, 5286(2): 729-734
[39] Wang Jing, Chang Chein-I. A uniform projection-based unsupervised classification for hyperspectral imagery International Geoscience and Remote Sensing Symposium (IGARSS), 2004, 5: 3066-3068
[40] Shah Chintan A, Arora Manoj K, Varshney Pramod K. Unsupervised classification of hyperspectral data: An ICA mixture model based approach. International Journal of Remote Sensing. 2004, 25(2): 481-487
[41] Meyer Alan, Paglieroni David, Astaneh Cyrus. K-Means Re-Clustering -Algorithmic options with quantifiable performance comparisons.Proceedings of SPIE - The International Society for Optical Engineering.2003,5001:84-92
[42] 孙家柄.遥感原理与应用.武汉:武汉大学出版社. 2003:210-211
[43] Lee Sanghoon, Crawford Melba M. Hierarchical clustering approach for unsupervised image classification of hyperspectral data. International Geoscience and Remote Sensing Symposium (IGARSS). 2004, 2:941-944
[44] Jimenez Luis O, Rivera-Medina Jorge L. Integration of spatial and spectral information by means of unsupervised extraction and classification for homogenous objects applied to multispectral and hyperspectral data IEEE Transactions on Geoscience and Remote Sensing. 2005,43(4): 844-851
[45] Du Qian. Independent component analysis to hyperspectral image classification Proceedings of SPIE - The International Society for Optical Engineering. Imaging Spectrometry X, 2004, 5546:366-373
[46] Shah Chintan A, Arora Manoj K, Varshney Pramod K. Unsupervised classification of hyperspectral data: An ICA mixture model based approach International Journal of Remote Sensing. 2004, 25(2): 481-487
[47] Koltunov A, Ben-Dor E. Mixture density separation as a tool for high quality interpretation of multi-source remote sensing data and related issues.International Journal of Remote Sensing. 2004, 25(16): 3275-3299
[48] Salazar Jose S, Post Brian N. A novel distribution-free segmentation approach applied to multispectral thermal imager data. Proceedings of SPIE - The International Society for Optical Engineering. 2004, 5425:118-129
[49] Gomez-Chova Luis, Calpe Javier, et al. Robust automatic classification method for hyperspectral imagery. Proceedings of SPIE - The International Society for Optical Engineering. 2004, 5238:398-407
[50]Ji Baohong,Chang Chein-I.Unsupervised constrained linear fisher's discriminant analysis for hyperspectral image classification Proceedings of SPIE-The International Society for Optical Engineering.2004,5546:344-353
[51]Du Qian.Realtime online tmsupervised detection and classification for remotely sensed imagery.Proceedings of SPIE-The International Society for Optical Engineering.2004,5425:665-672
[52]Stein David W.J.Material Identification and Classification from Hyperspectral Imagery using the Normal Compositional Model.Proceedings of SPIE-The International Society for Optical Engineering.2003,5093:559-568
[53]Chakravarty Sumit,Du Qian,Ren Hsuan.Adaptive Gaussian Mixture Estimation and Its Application to Unsupervised Classification of Remotely Sensed Images.International Geoscience and Remote Sensing Symposium (IGARSS).2003,3:1796-1798
[54]曾志远.卫星遥感图像计算机分类与地学应用研究.北京:科学出版社.2004:6-7
[55]Jia Xiuping.Simplified maximum likelihood classification for hyperspectral data in cluster space.International Geoscience and Remote Sensing Symposium(IGARSS).2002,5:2578-2580
[56]Gomez-Chova Luis,Calpe Javier,Robust automatic classification method for hyperspectral imagery.Proceedings of SPIE-The International Society for Optical Engineering.2004,5238:398-407
[57]陈进,王润生.高斯最大似然分类在高光谱分类中的应用研究.计算机应用.2006,8:1876-1878
[58]Robila Stefan.Distributed source separation algorithms for hyperspectral image processing.Proceedings of SPIE-The International Society for Optical Engineering.2004,5425:628-635
[59]徐宏根,马洪超,李德仁.结合SOM神经网络和混合像元分解的高光谱影像分类方法研究.遥感学报.2007,6:778-786
[60]Lawrence Rick,Bunn Andrew,et al.Classification of remotely sensed imagery using stochastic gradient boosting as a refinement of classification tree analysis Remote Sensing of Environment.2004,90(3):331-336
[61]曾志远.卫星遥感图像计算机分类与地学应用研究.北京:科学出版社.2004:31-32
[62]李娇.基于神经网络的高光谱图像超分辨率算法研究.哈尔滨工业大学硕士学位论文.2004
[63]Benediktsson Jon Atli,Palmason Jon Aevar,Sveinsson Johannes R.Classification of hyperspectral data from urban areas based on extended morphological profiles.IEEE Transactions on Geoscience and Remote Sensing.2005,43(3):480-491
[64]Goel P.K,Prasher S.O,et al.Classification of hyperspectral data by decision trees and artificial neural networks to identify weed stress and nitrogen status of corn.Computers and Electronics in Agriculture.2003,39(2):67-93
[65]Fernandez-Redondo Mercedes,Hernandez-Espinosa Carlos,Torres-Sospedra Joaquin.Hyperspectral image classification by ensembles of multilayer feedforward networks.IEEE International Conference on Neural Networks-Conference Proceedings.2004,2:1145-1149
[66]李海涛,顾海燕,张兵,高连如.基于MNF和SVM的高光谱遥感影像分类研究.遥感信息.2007,5:12-17
[67]Rand Robert S,Bosch Edward H.The effect of wavelet-based dimension reduction on neural network classification and subpixel targeting algorithms.Proceedings of SPIE-The International Society for Optical Engineering.2004,5425:653-664
[68]Plaza Antonio,Martinez Pablo,et al.A new approach to mixed pixel classification of hyperspectral imagery based on extended morphological profiles.Pattern Recognition.2004,37(6):1097-1116
[69]Pal Mahesh,Mather Paul M.An assessment of the effectiveness of decision tree methods for land cover classification.Remote Sensing of Environment.2003,86(4):554-565
[70]陈万海,赵春晖,刘春红.超谱遥感图像的模糊最大似然分类研究.哈尔滨工程大学学报.2006,27(5):772-776
[71]Rosario Dalton.A semiparametric approach using the discriminant metric SAM(spectral angle mapper).Proceedings of SPIE-The International Society for Optical Engineering.2004,5426:58-66
[72]Goetz Alexander F.H,Vane Gregg,et al.IMAGING SPECTROMETRY FOR EARTH REMOTE SENSING.Science.1985,228(4704):1147-1153
[73]Schmidt K.S,Skidmore A.K,et al.Mapping coastal vegetation using an expert system and hyperspectral imagery.Photogrammetric Engineering and Remote Sensing.2004,70(6):703-715
[74]G.Vane,R.Green,T.Chrien,H.Enmark,E.Hansen,and W.Porter.The Airborne Visible /Infrared Imaging Spectrometer(AVIRIS).Remote Sensing of Environment.1993,44:127-143
[75]P.H.Swain and S.M.Davis.遥感定量方法.朱振福,童寿彬,张晋,舒守荣等译.科学出版社.1984:3-4
[76]N.Keshava,J.F.Mustard.Spectral unmixing.IEEE Trans.on Signal Processing Magazine.2002,19(1):44-57
[77]J.C.Harsanyi,Chein-I Chang.Hyperspectral Image Classification and Dimensionality Reduction:An Orthogonal Subspace Projection Approach.IEEE Trans.on Geoscience and Remote Sensing.1994,32(4):779-785
[78]B.Solaiman and M.C.Mouchot.A Comparative Study of Conventional and Neural Network Classification of Multispectral Data.Proceedings of the 1994 International Geoscience and Remote Sensing Symposium.USA.1994:1413-1415
[79]Chein-I Chang.Further Results on Relationship Between Spectral Unmixing and Subspace Projection.IEEE Trans.on Geoscience and Remote Sensing.1998,36(3):1030-1032
[80]Chein-I Chang,Xiao-Li Zhao,Mark L.G.Althouse and Jeng Jong Pan.Least Squares Subspace Projection Approach to Mixed Pixel Classification for Hyperspectral Images.IEEE Trans.on Geoscience and Remote Sensing.1998,36(3):898-912
[81]Agustin Ifarraguerri and Chein-I Chang.Projection Pursuit Analysis of Hyperspectral Scenes.SPIE.1998,3372:51-59
[82]Agustin Ifarraguerri and Chein-I Chang.Multispectral and Hyperspectral Image Analysis with Convex Cones.IEEE Trans.on Geoscience and Remote Sensing.1999,37(2):756-770
[83]J.B.Adams.Visible and Near Infrared Diffuse Reflectance:Spectra of Pyroxenes As Applied to Remote Sensing of Solid Objects in The Solar Systems.J.Geophys.Res.1974,79:4829-4836
[84]F.J.Garcia-Haro,M.A.Gilabert,and J.Melia.Linear spectral mixture modeling to estimate vegetation amount from optical spectral data.Int.J.Remote Sensing.1996,17:3373-3400
[85]P.M.Atkinson,M.E.J.Cutler,and H.Lewis.Mapping subpixel proportional land cover with AVHRR imagery.Int.J.Remote Sensing.1997,18:917-935
[86]R.A.Schowengerdt.Remote Sensing:Models and Methods for Image Processing.San Diego,CA:Academic,1997
[87]杨竹青,李勇,胡德文.独立成分分析方法综述.自动化学报.2002,5:762-772
[88]M.Lennon,G.Mercier,M.C.Mouchot and L.Hubert-Moy.Spectral unmixing of hyperspectral images with the independent component analysis and wavelet packets.International Geoscience and Remote Sensing Symposium(IGARSS).2001,6:2896-2898
[89]B.Martin,G.L.Hugh and R.G.Steve.Linear Spectral Mixture Models and Support Vector Machines for Remote Sensing.IEEE Trans.On Geoscience and Remote Sensing.2000,38(5):2346-2360
[90]Hassan Emami.Introducing correctness coefficient as an accuracy measure for sub pixel classification results,http://www.ncc.org.ir/articles/poster83/H.Emami.pdf
[91]V.N.Vapnik The Nature of Statistical Learning Theory.New York:Springer Press,NY.1995.
[92]V N.Vapnik.统计学习理论的本质.张学工译.清华大学出版社,2000
[93]Nello Cristianini and John Shawe-Taylor.支持向量机导论,李国正,王猛,曾华军译.电子工业出版社,国外计算机科学教材系列,2004
[94]Karpinski M and Werther T.1989.VC dimension and uniform learnability of sparse polynomials and rational functions.SIAM J.Computing.Preprint 8537-CS,Bonn University,1989
[95]朱启兵,刘杰,李允公.闻邦椿.基于结构风险最小化原则的奇异值分解降噪研究.振动工程学报.2005,18(2):204-207
[96]刘雪燕,李明,张亚芬.基于PCA和多约简SVM的多级说话人辨识.计算机应用.2008,1:127-130
[97]Song Jie,Tang Huan-Wen.v-Support vector machine classifier based on linear programming.Dalian Ligong Daxue Xuebao/Journal of Dalian University of Technology.2005,45(2):303-307
[98]J.A.K.Suykens,J.D.Brabanter,L.Lukas and J.Vandewalle.Weighted Least Squares Support Vector Machines:Robustness and Sparse Approximation.Neurocomputing.2002,48(1-4):85-105
[99]吴青,刘三阳,张乐友.最小二乘支持向量机的预优共轭梯度法.系统工程与电子技术.2007,10:1746-1748
[100]Qing Song,Wenjie Hu and Wenfang Xie.Robust Support Vector Machine with Bullet Hole Image Classification.IEEE Trans.on Systems,Man and Cybernetics,Part C.2002,32(4):440-448
[101]张浩然,汪晓东,张长江.一种鲁棒回归支持向量机及其学习算法.南京理工大学学报(自然科学版).2006,3:311-314
[102]范昕炜.支持向量机算法的研究及其应用.浙江大学.博士论文.2003:1-24
[103]T.Joachims.Making Large Scale SVM Learning Practical.Advances in Kernel Methods-Support Vector Learning.MIT Press,1999
[104]S.S.Keerthi,S.K.Shevade,C.Bhattacharyya,and K.R.K.Murthy.A Fast Iterative Nearest Point Algorithm for Support Vector Machine Classifier Design.IEEE Trans.on Neural Networks.2000,11(1):124-136.
[105]骆世广,杨晓伟,吴广潮,张新华.一种改进的序贯最小优化算法.计算机科学.2006,11:146-148
[106]Klaus-Robert M.,Sebastian Mika,Gunnar R(a丨¨)tsch,Koji Tsuda,and Bernhard Sch(o丨¨)lkopf,An Introduction to Kernel-Based Learning Algorithms.IEEE Trans.on Neural Networks.2001,12(2):181-201
[107]Alberto Ruiz and Pedro E.L6pez-de-Teruel.Nonlinear Kernel-Based Statistical Pattern Analysis.IEEE Trans.on Neural Networks.2001,12(1):16-32
[108]A.Smola.Learning with kernels.Thesis.1998
[109]屈颖歌.支持向量机在图像处理应用中若干问题研究.南京理工大学.硕士论文.2004:7-21
[110]沈培华.支持矢量机的算法研究和应用.南京理工大学.博士论文2002:1-24
[111]欣栋.支持向量机算法的研究及在说话人识别上的应用.浙江大学..硕士论文.2002:4-21
[112]姬水旺.强噪声和类间重叠数据下支持向量机学习的研究.武汉科技大学.硕士论文.2002:5-21
[113]董云杰.支持向量即及其在模式识别应用中的研究.兰州理工大学.硕士论文.2003:1-7
[114]夏建涛.基于机器学习的高维多光谱数据分类.西北工业大学.博士学位论文.2002:1-8
[115]Adelmann Holger G..Frequency-domain Gaussian filter module for quantitative and reproducible high-pass,low-pass,and bandpass filtering of images.American Laboratory.1997,29(6):6
[116]Rosario Dalton.A semiparametric approach using the discriminant metric SAM(spectral angle mapper).Proceedings of SPIE - The International Society for Optical Engineering.2004,5426:58-66
[117]郭春燕,基于支持向量机的高光谱图像分类,哈尔滨工程大学硕士学位论文,2007
[118]刘春红,赵春晖,张凌雁.一种新的超谱遥感图像降维方法.中国图像图形学报,2005,Vol.10,No.3:218-222页.
[119]R.Fletcher.Practical Methods of Optimization.Chichester.U.K.:Wiley,1987.
[120]Qian Du and Chang Chein-I.Linear Mixture Analysis-Based Compression for Hyperspectal Image Analysis.IEEE transactions on geoscience and remote sensing.2004,42(4):875-891
[121]M.E.Winter,P.G.Lucey and D.Steuter.Examining Hyperspectral Unmixing Error Reduction Due to Stepwise Unmixing.Proceedings of SPIE-The International Society for Optical Engineering.2003,5093:380-389
[122]He Qing and Xiong Zhen.Neighbor Field-based Mixed Pixel Interpretation.Journal of Northern Jiaotong University.1999,23(4):118-121
[123] L. Junwu, L. K. Roger and Y. Nicolas. An Unmixing Algorithm Based on Vicinal Information. Geoscience and Remote Sensing Symposium. 2002,3:1453-1455
[124] M. Brown, Gunn S R, and Lewis H G Support Vector Machines for Optimal Classification and Spectral Unmixing. Ecol. Modeling. 1999,120:167-179
[125] Hassan Emami. Introducing correctness coefficient as an accuracy measure for sub pixel classification results. http://www.ncc.org.ir/articles/poster83/H.Emami.pdf
[2]钱乐祥等编著.遥感数字影像处理与地理特征提取.北京:科学出版社.2004.7:1-3
[3]宁书年,吕松棠,杨小琴,王四龙,余才英,张景发.遥感图像处理与应用.地震出版社.1995:39-45
[4]D.A.Landgrebe,S.B.Serpico,M.M.Crawford,Vem Singhroy.Introduction to the Special Issue on Analysis of Hyperspectral Image Data.IEEE Trans.on Geoscience and Remote Sensing.2001,39(7):1343-1344
[5]Algorithms and technologies for multispectral,hyperspectral and ultraspectral imagery.http://www.spie.org/Conferences/Calls/04/or/SubmitAbstract/index .cfm?fuseaction=OR36
[6]Algorithms and technologies for multispectral,hyperspectral and ultraspectral imagery.http://www.spie.org/Conferences/Calls/05/dss/conferences/index.cf m?fuseaction=OR47
[7]孙家柄.遥感原理与应用.武汉:武汉大学出版社.2003:25-26
[8]陈述彭,章庆禧,郭华东.遥感信息机理研究.科学出版社,1998:141-142页
[9]Green Robert O,Pavri Betina E,Chrien Thomas G.On-orbit radiometric and spectral calibration characteristics of EO-1 hyperion derived with an underflight of AVIRIS and In situ measurements at Salar de Arizaro,Argentina.IEEE Transactions on Geoscience and Remote Sensing,PART Ⅰ,2003,41(6):1194-1203.
[10]Luis O.Jimenez & David A.Landgrebe.Supervised Classification in High-Dimensional Space:Geometrical,Statistical,and Asymptotical Properties of Multivariate Data.IEEE Trans.on System,Man,and Cybernetics-Part C:Applications and Reviews.1998,28(1):39-54
[11]边肇祺,张学工.模式识别.北京:清华大学出版社.2000:24-30
[12]Richards,J.A.Analysis of remotely sensed data:the formative decades and the future.Geoscience and Remote Sensing.IEEE Transactions on.2005,43(3):422-432
[13]Landgrebe,D.A.Multispectral land sensing:where from,where to?Geoscience and Remote Sensing,IEEE Transactions on.2005,43(3):414-421
[14]陈宜金,高金起,申进志,梁晓文.基于层次结构的Cito Map地理信息数据采集系统的若干特点.矿山测量,2004,4:16-18
[15]张斌,朱正中,葛成辉,吴佑寿.一种基于边缘轮廓信息的多源遥感图像子像元匹配定位方法.中国图像图形学报.2000,5(A,10):830-835
[16]顾松刚,史培军.基于混合象元分解的辽东湾海冰资源量估算.北京师范大学学报(自然科学版).2004,40(3):411-416
[17]Liang Shunlin,Fang Hongliang.An improved atmospheric correction algorithm for hyperspectral remotely sensed imagery.IEEE Geoscience and Remote Sensing Letters.2004,1(2):112-117
[18]Hardie Russell C,Eismann Michael T,Wilson Gregory L.MAP estimation for hyperspectral image resolution enhancement using an auxiliary sensor Source:IEEE Transactions on Image Processing.2004,13(9):1174-1184
[19]Gupta Neelam,Voloshinov Vitaly.Hyperspectral imager,from ultraviolet to visible,with a KDP acousto-optic tunable filter.Applied Optics.2004,43(13):2752-2759
[20]Bei Ling,Duffin Kirk L,Camahan Jon W.Inductively coupled plasma chemistry examinations with visible acousto-optic tunable filter hyperspectral imaging.Journal of Analytical Atomic Spectrometry.Winter Conference on Plasma Spectrochemistry.2004,19(9):1151-1157
[21]Raviv O,Rotman S.R.Applying ordered statistics filters for point target detection in hyperspectral data Proceedings of SPIE-The International Society for Optical Engineering.2004,5204:35-40
[22]Bachmarm,C.M.;Ainsworth,T.L.;Fusina,R.A.Exploiting manifold geometry in hyperspectral imagery.Geoscience and Remote Sensing,IEEE Transactions on.2005,43(3):441-454
[23]李金宗.模式识别导论.北京:高等教育出版社,1994.7:5-7
[24]Dundar M.Murat,Landgrebe David A.Toward an optimal supervised classifier for the analysis of hyperspectral data.Source:IEEE Transactions on Geoscience and Remote Sensing.2004,42(1):271-277
[25]Jia,Xiuping,Richards,John A.Efficient transmission and classification of hyperspectral image data.IEEE Transactions on Geoscience and Remote Sensing.2003,41(5):1129-1131
[26]钱乐祥等编著.遥感数字影像处理与地理特征提取.北京:科学出版社.2004:171-172
[27]Chang Chein-I,Chiang Shao-Shan.Anomaly detection and classification for hyperspectral imagery.IEEE Transactions on Geoscience and Remote Sensing.2002,40(6):1314-1325
[28]Rand Robert S.Spectral/spatial annealing of hyperspectral imagery initialized by a supervised classification method.Proceedings of SPIE-The International Society for Optical Engineering.2002,4725:242-253
[29]Ji Baohong,Chang Chein-I,Jensen Janet L,Jensen James O.Unsupervised constrained linear fisher's discdminant analysis for hyperspectral image classification.Proceedings of SPIE - The International Society for Optical Engineering,Imaging Spectrometry X,2004,5546:44-353
[30]Kumar S,Ghosh J,Crawford M.M.Best-bases feature extraction algorithms for classification of hyperspectral data.IEEE Transactions on Geoscience and Remote Sensing.2001,39(7):1368-1379
[31]Kuo Bor-Chen,Yang Jinn-Min.Landgrebe David A.Gaussian Mixture Classifier with Regularized Covariance Estimator for Hyperspectral Data Classification. International Geoscience and Remote Sensing Symposium (IGARSS).2003, 1:276-278
[32] Murphy Patricia K, Kolodner Marc A. Implementation of a multi-scale Bayesian classification approach for hyperspectral terrain categorization.Proceedings of SPIE - The International Society for Optical Engineering.2002,4816: 278-287
[33] Santich N.T. Reducing the parameterization of the covariance matrix for maximum likelihood classification. International Geoscience and Remote Sensing Symposium (IGARSS). 2002, 6: 3519-3521
[34] Dundar M.M, Landgrebe D.A. Toward an optimal supervised classifier for the analysis of hyperspectral data. Geoscience and Remote Sensing, IEEE Transactions on. 2004 42(1): 271 - 277
[35] Rand Robert S. Spectral/spatial annealing of hyperspectral imagery initialized by a supervised classification method. Proceedings of SPIE - The International Society for Optical Engineering. 2002, 4725: 242-253
[36] Landgrebe David, Murat Dundar M. A model-based mixture-supervised classification approach in hyperspectral data analysis. IEEE Transactions on Geoscience and Remote Sensing. 2002, 40(12): 2692-2699
[37] Chang Yang-Lang, Han Chin-Chuan. Greedy modular eigenspaces and positive Boolean function for supervised hyperspectral image classification Optical Engineering. 2003, 42(9): 2576-2587
[38] Wu Hao, Kuang Gangyao, Yu Wenxian. An Unsupervised Classification Method for Hyperspectral Image Combining PCA and Gaussian Mixture Model. Proceedings of SPIE - The International Society for Optical Engineering. 2003, 5286(2): 729-734
[39] Wang Jing, Chang Chein-I. A uniform projection-based unsupervised classification for hyperspectral imagery International Geoscience and Remote Sensing Symposium (IGARSS), 2004, 5: 3066-3068
[40] Shah Chintan A, Arora Manoj K, Varshney Pramod K. Unsupervised classification of hyperspectral data: An ICA mixture model based approach. International Journal of Remote Sensing. 2004, 25(2): 481-487
[41] Meyer Alan, Paglieroni David, Astaneh Cyrus. K-Means Re-Clustering -Algorithmic options with quantifiable performance comparisons.Proceedings of SPIE - The International Society for Optical Engineering.2003,5001:84-92
[42] 孙家柄.遥感原理与应用.武汉:武汉大学出版社. 2003:210-211
[43] Lee Sanghoon, Crawford Melba M. Hierarchical clustering approach for unsupervised image classification of hyperspectral data. International Geoscience and Remote Sensing Symposium (IGARSS). 2004, 2:941-944
[44] Jimenez Luis O, Rivera-Medina Jorge L. Integration of spatial and spectral information by means of unsupervised extraction and classification for homogenous objects applied to multispectral and hyperspectral data IEEE Transactions on Geoscience and Remote Sensing. 2005,43(4): 844-851
[45] Du Qian. Independent component analysis to hyperspectral image classification Proceedings of SPIE - The International Society for Optical Engineering. Imaging Spectrometry X, 2004, 5546:366-373
[46] Shah Chintan A, Arora Manoj K, Varshney Pramod K. Unsupervised classification of hyperspectral data: An ICA mixture model based approach International Journal of Remote Sensing. 2004, 25(2): 481-487
[47] Koltunov A, Ben-Dor E. Mixture density separation as a tool for high quality interpretation of multi-source remote sensing data and related issues.International Journal of Remote Sensing. 2004, 25(16): 3275-3299
[48] Salazar Jose S, Post Brian N. A novel distribution-free segmentation approach applied to multispectral thermal imager data. Proceedings of SPIE - The International Society for Optical Engineering. 2004, 5425:118-129
[49] Gomez-Chova Luis, Calpe Javier, et al. Robust automatic classification method for hyperspectral imagery. Proceedings of SPIE - The International Society for Optical Engineering. 2004, 5238:398-407
[50]Ji Baohong,Chang Chein-I.Unsupervised constrained linear fisher's discriminant analysis for hyperspectral image classification Proceedings of SPIE-The International Society for Optical Engineering.2004,5546:344-353
[51]Du Qian.Realtime online tmsupervised detection and classification for remotely sensed imagery.Proceedings of SPIE-The International Society for Optical Engineering.2004,5425:665-672
[52]Stein David W.J.Material Identification and Classification from Hyperspectral Imagery using the Normal Compositional Model.Proceedings of SPIE-The International Society for Optical Engineering.2003,5093:559-568
[53]Chakravarty Sumit,Du Qian,Ren Hsuan.Adaptive Gaussian Mixture Estimation and Its Application to Unsupervised Classification of Remotely Sensed Images.International Geoscience and Remote Sensing Symposium (IGARSS).2003,3:1796-1798
[54]曾志远.卫星遥感图像计算机分类与地学应用研究.北京:科学出版社.2004:6-7
[55]Jia Xiuping.Simplified maximum likelihood classification for hyperspectral data in cluster space.International Geoscience and Remote Sensing Symposium(IGARSS).2002,5:2578-2580
[56]Gomez-Chova Luis,Calpe Javier,Robust automatic classification method for hyperspectral imagery.Proceedings of SPIE-The International Society for Optical Engineering.2004,5238:398-407
[57]陈进,王润生.高斯最大似然分类在高光谱分类中的应用研究.计算机应用.2006,8:1876-1878
[58]Robila Stefan.Distributed source separation algorithms for hyperspectral image processing.Proceedings of SPIE-The International Society for Optical Engineering.2004,5425:628-635
[59]徐宏根,马洪超,李德仁.结合SOM神经网络和混合像元分解的高光谱影像分类方法研究.遥感学报.2007,6:778-786
[60]Lawrence Rick,Bunn Andrew,et al.Classification of remotely sensed imagery using stochastic gradient boosting as a refinement of classification tree analysis Remote Sensing of Environment.2004,90(3):331-336
[61]曾志远.卫星遥感图像计算机分类与地学应用研究.北京:科学出版社.2004:31-32
[62]李娇.基于神经网络的高光谱图像超分辨率算法研究.哈尔滨工业大学硕士学位论文.2004
[63]Benediktsson Jon Atli,Palmason Jon Aevar,Sveinsson Johannes R.Classification of hyperspectral data from urban areas based on extended morphological profiles.IEEE Transactions on Geoscience and Remote Sensing.2005,43(3):480-491
[64]Goel P.K,Prasher S.O,et al.Classification of hyperspectral data by decision trees and artificial neural networks to identify weed stress and nitrogen status of corn.Computers and Electronics in Agriculture.2003,39(2):67-93
[65]Fernandez-Redondo Mercedes,Hernandez-Espinosa Carlos,Torres-Sospedra Joaquin.Hyperspectral image classification by ensembles of multilayer feedforward networks.IEEE International Conference on Neural Networks-Conference Proceedings.2004,2:1145-1149
[66]李海涛,顾海燕,张兵,高连如.基于MNF和SVM的高光谱遥感影像分类研究.遥感信息.2007,5:12-17
[67]Rand Robert S,Bosch Edward H.The effect of wavelet-based dimension reduction on neural network classification and subpixel targeting algorithms.Proceedings of SPIE-The International Society for Optical Engineering.2004,5425:653-664
[68]Plaza Antonio,Martinez Pablo,et al.A new approach to mixed pixel classification of hyperspectral imagery based on extended morphological profiles.Pattern Recognition.2004,37(6):1097-1116
[69]Pal Mahesh,Mather Paul M.An assessment of the effectiveness of decision tree methods for land cover classification.Remote Sensing of Environment.2003,86(4):554-565
[70]陈万海,赵春晖,刘春红.超谱遥感图像的模糊最大似然分类研究.哈尔滨工程大学学报.2006,27(5):772-776
[71]Rosario Dalton.A semiparametric approach using the discriminant metric SAM(spectral angle mapper).Proceedings of SPIE-The International Society for Optical Engineering.2004,5426:58-66
[72]Goetz Alexander F.H,Vane Gregg,et al.IMAGING SPECTROMETRY FOR EARTH REMOTE SENSING.Science.1985,228(4704):1147-1153
[73]Schmidt K.S,Skidmore A.K,et al.Mapping coastal vegetation using an expert system and hyperspectral imagery.Photogrammetric Engineering and Remote Sensing.2004,70(6):703-715
[74]G.Vane,R.Green,T.Chrien,H.Enmark,E.Hansen,and W.Porter.The Airborne Visible /Infrared Imaging Spectrometer(AVIRIS).Remote Sensing of Environment.1993,44:127-143
[75]P.H.Swain and S.M.Davis.遥感定量方法.朱振福,童寿彬,张晋,舒守荣等译.科学出版社.1984:3-4
[76]N.Keshava,J.F.Mustard.Spectral unmixing.IEEE Trans.on Signal Processing Magazine.2002,19(1):44-57
[77]J.C.Harsanyi,Chein-I Chang.Hyperspectral Image Classification and Dimensionality Reduction:An Orthogonal Subspace Projection Approach.IEEE Trans.on Geoscience and Remote Sensing.1994,32(4):779-785
[78]B.Solaiman and M.C.Mouchot.A Comparative Study of Conventional and Neural Network Classification of Multispectral Data.Proceedings of the 1994 International Geoscience and Remote Sensing Symposium.USA.1994:1413-1415
[79]Chein-I Chang.Further Results on Relationship Between Spectral Unmixing and Subspace Projection.IEEE Trans.on Geoscience and Remote Sensing.1998,36(3):1030-1032
[80]Chein-I Chang,Xiao-Li Zhao,Mark L.G.Althouse and Jeng Jong Pan.Least Squares Subspace Projection Approach to Mixed Pixel Classification for Hyperspectral Images.IEEE Trans.on Geoscience and Remote Sensing.1998,36(3):898-912
[81]Agustin Ifarraguerri and Chein-I Chang.Projection Pursuit Analysis of Hyperspectral Scenes.SPIE.1998,3372:51-59
[82]Agustin Ifarraguerri and Chein-I Chang.Multispectral and Hyperspectral Image Analysis with Convex Cones.IEEE Trans.on Geoscience and Remote Sensing.1999,37(2):756-770
[83]J.B.Adams.Visible and Near Infrared Diffuse Reflectance:Spectra of Pyroxenes As Applied to Remote Sensing of Solid Objects in The Solar Systems.J.Geophys.Res.1974,79:4829-4836
[84]F.J.Garcia-Haro,M.A.Gilabert,and J.Melia.Linear spectral mixture modeling to estimate vegetation amount from optical spectral data.Int.J.Remote Sensing.1996,17:3373-3400
[85]P.M.Atkinson,M.E.J.Cutler,and H.Lewis.Mapping subpixel proportional land cover with AVHRR imagery.Int.J.Remote Sensing.1997,18:917-935
[86]R.A.Schowengerdt.Remote Sensing:Models and Methods for Image Processing.San Diego,CA:Academic,1997
[87]杨竹青,李勇,胡德文.独立成分分析方法综述.自动化学报.2002,5:762-772
[88]M.Lennon,G.Mercier,M.C.Mouchot and L.Hubert-Moy.Spectral unmixing of hyperspectral images with the independent component analysis and wavelet packets.International Geoscience and Remote Sensing Symposium(IGARSS).2001,6:2896-2898
[89]B.Martin,G.L.Hugh and R.G.Steve.Linear Spectral Mixture Models and Support Vector Machines for Remote Sensing.IEEE Trans.On Geoscience and Remote Sensing.2000,38(5):2346-2360
[90]Hassan Emami.Introducing correctness coefficient as an accuracy measure for sub pixel classification results,http://www.ncc.org.ir/articles/poster83/H.Emami.pdf
[91]V.N.Vapnik The Nature of Statistical Learning Theory.New York:Springer Press,NY.1995.
[92]V N.Vapnik.统计学习理论的本质.张学工译.清华大学出版社,2000
[93]Nello Cristianini and John Shawe-Taylor.支持向量机导论,李国正,王猛,曾华军译.电子工业出版社,国外计算机科学教材系列,2004
[94]Karpinski M and Werther T.1989.VC dimension and uniform learnability of sparse polynomials and rational functions.SIAM J.Computing.Preprint 8537-CS,Bonn University,1989
[95]朱启兵,刘杰,李允公.闻邦椿.基于结构风险最小化原则的奇异值分解降噪研究.振动工程学报.2005,18(2):204-207
[96]刘雪燕,李明,张亚芬.基于PCA和多约简SVM的多级说话人辨识.计算机应用.2008,1:127-130
[97]Song Jie,Tang Huan-Wen.v-Support vector machine classifier based on linear programming.Dalian Ligong Daxue Xuebao/Journal of Dalian University of Technology.2005,45(2):303-307
[98]J.A.K.Suykens,J.D.Brabanter,L.Lukas and J.Vandewalle.Weighted Least Squares Support Vector Machines:Robustness and Sparse Approximation.Neurocomputing.2002,48(1-4):85-105
[99]吴青,刘三阳,张乐友.最小二乘支持向量机的预优共轭梯度法.系统工程与电子技术.2007,10:1746-1748
[100]Qing Song,Wenjie Hu and Wenfang Xie.Robust Support Vector Machine with Bullet Hole Image Classification.IEEE Trans.on Systems,Man and Cybernetics,Part C.2002,32(4):440-448
[101]张浩然,汪晓东,张长江.一种鲁棒回归支持向量机及其学习算法.南京理工大学学报(自然科学版).2006,3:311-314
[102]范昕炜.支持向量机算法的研究及其应用.浙江大学.博士论文.2003:1-24
[103]T.Joachims.Making Large Scale SVM Learning Practical.Advances in Kernel Methods-Support Vector Learning.MIT Press,1999
[104]S.S.Keerthi,S.K.Shevade,C.Bhattacharyya,and K.R.K.Murthy.A Fast Iterative Nearest Point Algorithm for Support Vector Machine Classifier Design.IEEE Trans.on Neural Networks.2000,11(1):124-136.
[105]骆世广,杨晓伟,吴广潮,张新华.一种改进的序贯最小优化算法.计算机科学.2006,11:146-148
[106]Klaus-Robert M.,Sebastian Mika,Gunnar R(a丨¨)tsch,Koji Tsuda,and Bernhard Sch(o丨¨)lkopf,An Introduction to Kernel-Based Learning Algorithms.IEEE Trans.on Neural Networks.2001,12(2):181-201
[107]Alberto Ruiz and Pedro E.L6pez-de-Teruel.Nonlinear Kernel-Based Statistical Pattern Analysis.IEEE Trans.on Neural Networks.2001,12(1):16-32
[108]A.Smola.Learning with kernels.Thesis.1998
[109]屈颖歌.支持向量机在图像处理应用中若干问题研究.南京理工大学.硕士论文.2004:7-21
[110]沈培华.支持矢量机的算法研究和应用.南京理工大学.博士论文2002:1-24
[111]欣栋.支持向量机算法的研究及在说话人识别上的应用.浙江大学..硕士论文.2002:4-21
[112]姬水旺.强噪声和类间重叠数据下支持向量机学习的研究.武汉科技大学.硕士论文.2002:5-21
[113]董云杰.支持向量即及其在模式识别应用中的研究.兰州理工大学.硕士论文.2003:1-7
[114]夏建涛.基于机器学习的高维多光谱数据分类.西北工业大学.博士学位论文.2002:1-8
[115]Adelmann Holger G..Frequency-domain Gaussian filter module for quantitative and reproducible high-pass,low-pass,and bandpass filtering of images.American Laboratory.1997,29(6):6
[116]Rosario Dalton.A semiparametric approach using the discriminant metric SAM(spectral angle mapper).Proceedings of SPIE - The International Society for Optical Engineering.2004,5426:58-66
[117]郭春燕,基于支持向量机的高光谱图像分类,哈尔滨工程大学硕士学位论文,2007
[118]刘春红,赵春晖,张凌雁.一种新的超谱遥感图像降维方法.中国图像图形学报,2005,Vol.10,No.3:218-222页.
[119]R.Fletcher.Practical Methods of Optimization.Chichester.U.K.:Wiley,1987.
[120]Qian Du and Chang Chein-I.Linear Mixture Analysis-Based Compression for Hyperspectal Image Analysis.IEEE transactions on geoscience and remote sensing.2004,42(4):875-891
[121]M.E.Winter,P.G.Lucey and D.Steuter.Examining Hyperspectral Unmixing Error Reduction Due to Stepwise Unmixing.Proceedings of SPIE-The International Society for Optical Engineering.2003,5093:380-389
[122]He Qing and Xiong Zhen.Neighbor Field-based Mixed Pixel Interpretation.Journal of Northern Jiaotong University.1999,23(4):118-121
[123] L. Junwu, L. K. Roger and Y. Nicolas. An Unmixing Algorithm Based on Vicinal Information. Geoscience and Remote Sensing Symposium. 2002,3:1453-1455
[124] M. Brown, Gunn S R, and Lewis H G Support Vector Machines for Optimal Classification and Spectral Unmixing. Ecol. Modeling. 1999,120:167-179
[125] Hassan Emami. Introducing correctness coefficient as an accuracy measure for sub pixel classification results. http://www.ncc.org.ir/articles/poster83/H.Emami.pdf
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |