基于光谱特性的高光谱图像异常目标检测算法研究
|
摘要
高光谱图像是一种新型的具有图谱合一特性的遥感图像，与多光谱等图像相比，其对地表物质间的细微差异通过连续的光谱曲线有更好的表达，使得高光谱遥感图像在地表物质的分类、解混、目标探测和异常检测等方面得到广泛应用。在高光谱遥感图像的诸多应用中，异常目标检测是近年来的一个热点，因为其不需要先验光谱信息，仅通过高光谱遥感图像自身特性就可以把需要检测的目标从背景信息中提取出来，具有较强的实用性。许多研究者针对异常目标检测进行了深入研究，并提出了相应的异常检测算法。但是，由于高光谱图像自身存在的高数据维，严重的背景干扰，同物异谱，波段间非线性相关性和图像中含有混合像元等问题，使得现有的异常检测算法在一定程度上都存在着或多或少的不足。现实的需要要求研究者开发一些新的算法解决目前异常目标检测存在的问题。本文依据真实的高光谱遥感图像，在分析其光谱分辨率特性、波段间相关性和背景模型等特性的基础上，以高光谱遥感图像的光谱特性为主线，利用高光谱降维技术、特征提取技术和非线性核机器学习等方法，提出了三种有创新性的异常目标检测算法。论文主要的工作如下：
首先，论文对高光谱遥感图像的成像机理进行了简单介绍，详细分析了高光谱遥感图像的光谱分辨率特性、波段间相关性和背景模型等特性。并重点介绍了核函数涉及的相关内容，特别是对后续研究中用的最多的高斯径向基核函数进行了详细阐述。对这些光谱特性和核函数等问题的分析，为后文的研究工作开展打下基础。
其次，针对高光谱图像的高数据维、数据间的冗余性和背景噪声干扰问题，论文提出了利用光谱维变换和空域滤波的异常检测算法。该算法首先利用最大噪声分量变换技术对原始高光谱图像进行变换，按照变换后的各波段的信噪比，设定合适的阈值，提取一定数量的波段对应的最大噪声分量变换矩阵，构造正交子空间投影算子。将变换后的高光谱图像数据投影到这个正交子空间上，得到残差数据；再利用主成分分析方法对此残差数据进行特征提取，使异常目标的能量集中在前面几个主成分中，并设定合适的阈值，确定需选择的主成分数目；然后，把含有丰富异常目标信息的主成分分量构成的高光谱图像数据集通过空域滤波器滤波，最大可能消除数据中含有的各类噪声。最后，把滤波后的波段子集数据输入RX异常检测器进行异常目标检测。该算法很好地解决了已有算法在处理高光谱图像高数据维、数据间的冗余性和背景噪声干扰等方面的不足。
再次，针对高光谱图像波段间数据冗余性和背景信息干扰导致经典核RX算法检测性能不高等问题，提出了基于四阶累积量的波段子集非线性异常检测算法。该算法先依据高光谱图像波段具有分块相关性的特点，计算相邻波段的相关系数，将原始图像划分为维数不同的波段子空间；然后，利用主成分分析构造的正交子空间对各波段子集进行背景抑制，得到图像误差数据；在此基础上，再次利用主成分分析提取各波段子集的特征信息，使异常目标信息集中于前面几个波段；最后，利用高光谱数据含有异常目标时背景呈现奇异性不符合高斯分布的特性，提取各子集主成分中含有最大四阶累积量值的波段，构成最优波段子集，并与核RX算法结合进行异常检测。该算法充分利用了高光谱图像的光谱特性，克服了高光谱图像的高维性、波段间的冗余性和背景信息干扰对经典核RX算法的影响。
最后，针对含有混合像元情况的异常目标检测问题，提出了一种新的结合光谱解混技术的支持向量数据描述的高光谱图像异常检测算法。该算法将光谱解混技术引入到异常检测问题中，利用新的约束非负矩阵分解的解混算法实现高光谱图像复杂背景信息和目标信息的分离，使解混后的误差数据含有丰富的目标信息，抑制了背景干扰信息；然后将解混误差数据利用非线性的支持向量数据描述方法映射到高维特征空间，在充分利用高光谱图像波段间的非线性统计特性的基础上，完成异常目标的检测。该算法很好的解决了背景信息和异常目标混合问题，最大程度抑制了背景信息对异常目标的干扰，突出了异常目标，提高了高光谱图像异常目标检测的精度。
Hyperspectral image is a new class of remote sensing image with the property of imageand spectrum, it has very good expression to the slight differences in surface substance bycontinuous spectrum curve by comparing with multispectral, and make hyperspectral image tohave widely application on spectral classification, spectral unmixing, target detection andanomaly detection etc. In recent years, the anomaly target detection is a hot issue in theapplication field of hyperspectral remote sensing image because of no prior knowledge of thetarget spectral signature is utilized or assumed. That is very useful in reality because thehyperspectral remote sensing image can put the need to detection target from backgroundinformation through spectral features. The existing algorithms are boundedness due to thehigh dimensionality, background interference, nonlinear correlation between bands, andmixed pixels in hyperspectral imagery. Based on the real hyperspectral image, the thesisanalysizes spectral resolution characteristics, band correlation and the background model.Then, based on the spectral characteristics, it is proposed several innovative anomaly targetdetection algorithm by using hyperspectral dimension reduction techniques, feature extractiontechnology and nonlinear kernel machine learning method. The thesis mainly work asfollows:
Firstly, the thesis introduces the imaging mechanism of hyperspectral remote sensingimage in brief, and analysizes spectral resolution characteristics, band correlation andbackground model in detail. And the thesis mainly describes the kernel function methods,specially, it describes the gaussian RBF kernel function which is a foundation for the laterresearch work.
Secondly, a novel anomaly detection algorithm is proposed for hyperspectral images toresolve the high dimensionality, the nonlinear statistical property and background interference,which is the extended RX algorithm based on spectral dimension transformation and spatialfilter(STSF-RX). Firstly, the maximum noise fraction transform is performed on the originalhyperspectral images, and it obtains MNF transform matrices by setting a SNR threshold, thatthe SNR of their corresponding bands are larger than the threshold. Then, for suppressingbackground interferences, The orthogonal subspace projection is estabished by MNFtransform matrices, and project the hyperspectral data of MNF transform to the orthogonal subspace, and obtain the error data of hyperspectral. In order to concentrate the energy ofdetection targets a few components for the first, the method of principal components analysisis performed on the processing hyperspectral image. Finally, we obtain bands for PCAtransform based on the eigenvalue threshold, the eigenvalue of the bands are larger thanthreshold, and the bands are input to the RX detector. the proposed STSF-RX algorithm areeffectively resolved the high dimensionnality and background interferences.
Thirdly, The Kernel RX is the classical anomaly detection algorithm of hyperspectralimages, which exploits nonlinear statistical property between bands. But, the algorithm hasn’tthink about the complexity of spectral and spatial speciality. In addition, the high dimensi-onality and redundancy between bands affect the performance of the KRX algorithm.Therefore, the detection performance of Kernel RX is low. Aiming at the problem, the paperproposes the algorithm of band subsets anomaly detection of hyperspectral image based onfourth order cumulant(KBS-KRX). Firstly, the algorithm divides the original hyperspectralimage to subset of low dimensions according to the correlation coefficient between spectralbands. Then, the error image data is achieved via subset bands were suppressed backgroundinterferences for detection by using orthogonal subspace projection, which is producd by theprincipal component analysis. Based on the data, the feature Information of all band subsetswere extracted by using the principal component analysis, which make the information ofanomaly target concentration on previous bands. At last, the optimal band subsets wereachieved by fourth order cumulant in principal component. In band subsets, the anomalydetection is carried by the kernel RX. KBS-KRX algorithm makes full use of blockingcharacteristics of band correlation in hyperspectral images.
Finally, the thesis proposes a novel algorithm for spectral unmixing support vector datadescription(SU-SVDD), it resolves the mixed pixels anomaly detection problem, the proposedalgorithm introduces hyperspectral unmixing into the problem of anomaly detection toseparate target information from complicated background clutter. After spectral unmixing, theerror datum includes abundant target information, and at the same time suppressedbackground interference; then the error datum is mapped into a high dimensional featurespace by a nonlinear SVDD. By exploiting nonlinear information between the spectral bandsof hyperspectral imagery, the anomaly targets can be detected. The proposed algorithm canhighlight anomaly target and highly detect precision.
首先，论文对高光谱遥感图像的成像机理进行了简单介绍，详细分析了高光谱遥感图像的光谱分辨率特性、波段间相关性和背景模型等特性。并重点介绍了核函数涉及的相关内容，特别是对后续研究中用的最多的高斯径向基核函数进行了详细阐述。对这些光谱特性和核函数等问题的分析，为后文的研究工作开展打下基础。
其次，针对高光谱图像的高数据维、数据间的冗余性和背景噪声干扰问题，论文提出了利用光谱维变换和空域滤波的异常检测算法。该算法首先利用最大噪声分量变换技术对原始高光谱图像进行变换，按照变换后的各波段的信噪比，设定合适的阈值，提取一定数量的波段对应的最大噪声分量变换矩阵，构造正交子空间投影算子。将变换后的高光谱图像数据投影到这个正交子空间上，得到残差数据；再利用主成分分析方法对此残差数据进行特征提取，使异常目标的能量集中在前面几个主成分中，并设定合适的阈值，确定需选择的主成分数目；然后，把含有丰富异常目标信息的主成分分量构成的高光谱图像数据集通过空域滤波器滤波，最大可能消除数据中含有的各类噪声。最后，把滤波后的波段子集数据输入RX异常检测器进行异常目标检测。该算法很好地解决了已有算法在处理高光谱图像高数据维、数据间的冗余性和背景噪声干扰等方面的不足。
再次，针对高光谱图像波段间数据冗余性和背景信息干扰导致经典核RX算法检测性能不高等问题，提出了基于四阶累积量的波段子集非线性异常检测算法。该算法先依据高光谱图像波段具有分块相关性的特点，计算相邻波段的相关系数，将原始图像划分为维数不同的波段子空间；然后，利用主成分分析构造的正交子空间对各波段子集进行背景抑制，得到图像误差数据；在此基础上，再次利用主成分分析提取各波段子集的特征信息，使异常目标信息集中于前面几个波段；最后，利用高光谱数据含有异常目标时背景呈现奇异性不符合高斯分布的特性，提取各子集主成分中含有最大四阶累积量值的波段，构成最优波段子集，并与核RX算法结合进行异常检测。该算法充分利用了高光谱图像的光谱特性，克服了高光谱图像的高维性、波段间的冗余性和背景信息干扰对经典核RX算法的影响。
最后，针对含有混合像元情况的异常目标检测问题，提出了一种新的结合光谱解混技术的支持向量数据描述的高光谱图像异常检测算法。该算法将光谱解混技术引入到异常检测问题中，利用新的约束非负矩阵分解的解混算法实现高光谱图像复杂背景信息和目标信息的分离，使解混后的误差数据含有丰富的目标信息，抑制了背景干扰信息；然后将解混误差数据利用非线性的支持向量数据描述方法映射到高维特征空间，在充分利用高光谱图像波段间的非线性统计特性的基础上，完成异常目标的检测。该算法很好的解决了背景信息和异常目标混合问题，最大程度抑制了背景信息对异常目标的干扰，突出了异常目标，提高了高光谱图像异常目标检测的精度。
Hyperspectral image is a new class of remote sensing image with the property of imageand spectrum, it has very good expression to the slight differences in surface substance bycontinuous spectrum curve by comparing with multispectral, and make hyperspectral image tohave widely application on spectral classification, spectral unmixing, target detection andanomaly detection etc. In recent years, the anomaly target detection is a hot issue in theapplication field of hyperspectral remote sensing image because of no prior knowledge of thetarget spectral signature is utilized or assumed. That is very useful in reality because thehyperspectral remote sensing image can put the need to detection target from backgroundinformation through spectral features. The existing algorithms are boundedness due to thehigh dimensionality, background interference, nonlinear correlation between bands, andmixed pixels in hyperspectral imagery. Based on the real hyperspectral image, the thesisanalysizes spectral resolution characteristics, band correlation and the background model.Then, based on the spectral characteristics, it is proposed several innovative anomaly targetdetection algorithm by using hyperspectral dimension reduction techniques, feature extractiontechnology and nonlinear kernel machine learning method. The thesis mainly work asfollows:
Firstly, the thesis introduces the imaging mechanism of hyperspectral remote sensingimage in brief, and analysizes spectral resolution characteristics, band correlation andbackground model in detail. And the thesis mainly describes the kernel function methods,specially, it describes the gaussian RBF kernel function which is a foundation for the laterresearch work.
Secondly, a novel anomaly detection algorithm is proposed for hyperspectral images toresolve the high dimensionality, the nonlinear statistical property and background interference,which is the extended RX algorithm based on spectral dimension transformation and spatialfilter(STSF-RX). Firstly, the maximum noise fraction transform is performed on the originalhyperspectral images, and it obtains MNF transform matrices by setting a SNR threshold, thatthe SNR of their corresponding bands are larger than the threshold. Then, for suppressingbackground interferences, The orthogonal subspace projection is estabished by MNFtransform matrices, and project the hyperspectral data of MNF transform to the orthogonal subspace, and obtain the error data of hyperspectral. In order to concentrate the energy ofdetection targets a few components for the first, the method of principal components analysisis performed on the processing hyperspectral image. Finally, we obtain bands for PCAtransform based on the eigenvalue threshold, the eigenvalue of the bands are larger thanthreshold, and the bands are input to the RX detector. the proposed STSF-RX algorithm areeffectively resolved the high dimensionnality and background interferences.
Thirdly, The Kernel RX is the classical anomaly detection algorithm of hyperspectralimages, which exploits nonlinear statistical property between bands. But, the algorithm hasn’tthink about the complexity of spectral and spatial speciality. In addition, the high dimensi-onality and redundancy between bands affect the performance of the KRX algorithm.Therefore, the detection performance of Kernel RX is low. Aiming at the problem, the paperproposes the algorithm of band subsets anomaly detection of hyperspectral image based onfourth order cumulant(KBS-KRX). Firstly, the algorithm divides the original hyperspectralimage to subset of low dimensions according to the correlation coefficient between spectralbands. Then, the error image data is achieved via subset bands were suppressed backgroundinterferences for detection by using orthogonal subspace projection, which is producd by theprincipal component analysis. Based on the data, the feature Information of all band subsetswere extracted by using the principal component analysis, which make the information ofanomaly target concentration on previous bands. At last, the optimal band subsets wereachieved by fourth order cumulant in principal component. In band subsets, the anomalydetection is carried by the kernel RX. KBS-KRX algorithm makes full use of blockingcharacteristics of band correlation in hyperspectral images.
Finally, the thesis proposes a novel algorithm for spectral unmixing support vector datadescription(SU-SVDD), it resolves the mixed pixels anomaly detection problem, the proposedalgorithm introduces hyperspectral unmixing into the problem of anomaly detection toseparate target information from complicated background clutter. After spectral unmixing, theerror datum includes abundant target information, and at the same time suppressedbackground interference; then the error datum is mapped into a high dimensional featurespace by a nonlinear SVDD. By exploiting nonlinear information between the spectral bandsof hyperspectral imagery, the anomaly targets can be detected. The proposed algorithm canhighlight anomaly target and highly detect precision.
引文
[1] G.R. Hunt. Near-Infrared (1.3-2.4μm) Spectra of Alteration Minerals-Potential for Usein Remote Sensing[J].Geophysics,1979,44(12):1974-1986.
[2]谷延锋.基于核方法的高光谱图象分类和目标检测技术研究[D].哈尔滨:哈尔滨工业大学博士学位论文,2005.
[3] F. H.A. Goetz, V. Gregg, J. E. Solomon, et al. Imaging Spectrometry for Earth RemoteSensing.[J].Science,1985,228(4704):1147-1153.
[4] R.A. Schowengerdt.遥感图像处理模型与方法[M].3版.微波成像技术国家重点实验室,译.北京:电子工业出版社,2010:31-83.
[5] G. Vane, A.F.H Goetz.Terrestrial imaging spectraometry:current status, the futuretrends[J].Remote Sensing of Environment,1993,44:117-126.
[6] A.F.H. Goetz, L.C Rowan. Geological Remote Sensing[J].Science,1981,211:781-791.
[7]童庆禧,张兵,郑兰芬.高光谱遥感—原理、技术与应用[M].北京:高等教育出版社,2006:246-247.
[8]王晓飞.高光谱图像分辨率增强及在小目标检测中的应用研究[D].哈尔滨:哈尔滨工业大学博士学位论文,2011:13-17.
[9]胡秀清,刘京晶,邱康睦,等.神舟3号飞船中分辨率成像光谱仪场地替代定标新方法研究[J].光谱学与光谱分析,2009,29(5):1153-1156.
[10] L. He，Q. Pan，W. Di, et al. Anomaly detection in hyperspectral imagery based onmaximum entropy and nonparametric estimation[J].Pattern Recognition Letters,2009,29:1392-1403.
[11] I.S. Reed, X. Yu. Adaptive multiple-band cfar detection of an optical pattern withunknown spectral distribution[J].IEEE Transactions on Acoustics, Speech and SignalProcessing.,1990,38(10):1760-1770.
[12] X.L. Yu, L.E. Hoff, I.S. Reed, et al. Automatic target detection and recognition inmultiband imagery: a unified ml detection and estimation approach[J].IEEE Transact-ions on Image Processing.,1997,6(1):143-156.
[13]谷延锋,刘颖,贾友华,等.基于光谱解译的高光谱图像奇异检测算法[J].红外与毫米波学报,2006,25(6):473-477.
[14] H. Kwon, N.M. Nasrabad. Kernel RX-algorithm:a nonlinear anomaly detector forhyperspectral imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2005,43(2):388-397.
[15] A. Banerjee, P. Burlina, C. Diehl. A support vector method for anomaly detection inhyperspectral imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2006,44(8):2282-2291.
[16]李杰,赵春晖,梅锋.利用背景残差数据检测高光谱图异常[J].红外与毫米波学报,2010,29(2):150-155.
[17] M.J. Carlotto. A cluster-based approach for detecting man-made objects and changesin imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2005,43(2):374-387.
[18] B. Du, L.P. Zhang. Random-selection-based anomaly detector for hyperspectral imag-ery[J].IEEE Transactions on Geoscience and Remote Sensing,2011,49(5):1578-1589.
[19]梅锋.基于核机器学习的高光谱异常目标检测算法研究[D].哈尔滨:哈尔滨工程大学博士学位论文,2009.
[20] C.I. Chang, S.S. Chiang. Anomaly detection and classification for hyperspectralimagery[J].IEEE Transactions on Geoscience And Remote Sensing,2002,40(6):1314-1325.
[21] D.W.J. Stein, S.G. Beaven, L.E. Hoff, et al. Anomaly detection from hyperspectralimagery[J].IEEE Signal Process. Mag.,2002,19(1):58-69.
[22] D.W.J. Stein. Stochastic compositional models applied to subpixel analysis of hyper-spectral imagery[C].Proc. SPIE,2001,4480:49-56.
[23] J.E. Fowler, Q. Du. Anomaly detection and reconstruction from random projections[J].IEEE Transactions on Image Processing,2012,21(1):184-195.
[24] S. Matteoli, M. Diani, G. Corsini. Hyperspectral anomaly detection with kurtosis-driven local covariance matrix corruption mitigation[J].IEEE Geoscience and RemoteSensing Letters,2011,8(3):531-535.
[25] S. Matteoli, M. Diani, G. Corsini. Improved estimation of background covariancematrix for anomaly detection in hyperspectral images[J].Opt.Eng.,2010,49(4):046201-1-16.
[26] J.M. Molero, A. Paz, E.M. Garzón, et al. Fast anomaly detection in hyperspectralimages with RX method on heterogeneous clusters[J].J Supercomput,2011,58:411-419.
[27] H. Ren, C.W. Chen, H.T. Chen. Weighted anomaly detection for hyperspectral remo-tely sensed images[C].USA:SPIE The International Society for Optical Engineering,2005,5995:599501-599507.
[28] R.A. Riley, R.K. Newsom, A.K. Andrews. Anomaly detection in noisy hyperspectralimagery[C] USA: SPIE-Int. Soc. Opt. Eng,2004,5546:159-170.
[29] S.M. Schweizer, J.M.F. Moura. Hyperspectral imagery:clutter adaptation in anomalydetection[J].IEEE Transactions on Information Theory,2000,46(5):1855-1871.
[30] S.M. Schweizer, J.M.F. Moura. Efficient detection in hyperspectral imagery[J].IEEETransactions on Image Processing,2001,10(4):584-597.
[31]贺霖.高光谱图像自动目标检测技术研究[J].西安:西北工业大学博士学位论文,2007:29-32.
[32]张立燕,谌德荣,李世义,等.基于低概率检测的高光谱图像有损压缩方法研究[J].弹箭与制导学报,2008,28(1):307-310.
[33]王玉磊,赵春晖,王江洪.基于低概率检测的高光谱异常目标检测算法研究[J].黑龙江大学自然科学学报,2010,27(3):411-416.
[34] B. Yver, R. Marion. A theoretical framework for hyperspectral anomaly detectionusing spectral and spatial a priori information[J].IEEE Geoscience and Remote SensingLetters.,2007,4(3):436-440.
[35] H. Kwon, S.Z. Der, N.M. Nasrabadi. Adaptive anomaly detection using subspace sep-arateion for hyperspectral imagery[J].Optical Engineering.,2003,42(11):3342-3351.
[36] H. Kwon, S.Z. Der, N.M. Nasrabadi. Projection-based adaptive anomaly detection forhyperspectral imagery[C].USA:Proceedings2003International Conference on ImageProcessing(Cat. No.03CH37429),2003:1001-1004.
[37] J. Broadwater, R.Chellappa. Hybrid detectors for subpixel targets[J].IEEE Transac-tions on Pattern Analysis and Machine Intelligence.,2007,29(11):1891-1903.
[38] B. Scholkopf, A.J. Smola. Learning with kernels:support vector machines regularize-tion,optimization, and beyond[M].Cambridge:MIT Press,2001.
[39] H. Kwon, N.M. Nasrabadi. A comparative study of kernel spectral matched signaldetectors for hyperspectral target detection[C].USA:Proc. SPIE Int. Soc. Opt. Eng.,2005,5806:827-838.
[40] H. Kwon, N.M. Nasrabadi. Kernel adaptive subspace detector for hyperspectral targetdetection[C].USA:IEEE International Conference on Acoustics, Speech, and SignalProcessing(Cat. No.05CH37625),2005,4:681-684.
[41] H. Kwon, N.M Nasrabadi. Kernel-based subpixel target detection in hyperspectralimages[C].USA:IEEE International Joint Conference on Neural Networks(Cat.No.04CH37541),2004:717-721.
[42]赵春晖,李杰,梅锋.核加权RX高光谱图像异常检测算法[J].红外与毫米波学报，2011,29(5):378-382.
[43]赵春晖,胡春梅,包玉刚.一种背景误差累积的高光谱图像异常检测算法[J].光子学报,2010,39(10):1830-1835.
[44]赵春晖,胡春梅.基于目标正交子空间投影加权的高光谱图像异常检测算法[J].吉林大学学报:工学版,2011,41(5):1468-1474.
[45]梅锋,赵春晖.基于空域滤波的核RX高光谱图像异常检测算法[J].哈尔滨工程大学学报,2009,30(6):697-702.
[46] D.M.J. Tax, A. Ypma, R.P.W. Duin. Support vector data description applied tomachine vibration analysis[C].Heijen:Prec5th Anna Conf Adv School Compu Imag.,1999:398-405．
[47]谌德荣,宫久路,何光林,等.高光谱图像全局异常检测RFS-SVDD算法[J].宇航学报,2010,31(1):228-232.
[48] S. Khazai, S. Homayouni, A. Safari. Anomaly detection in hyperspectral images basedon an adaptive support vector method[J].IEEE geoscience and remote sensing letters,2011,8(4):646-650.
[49]谌德荣,张文燕,陶鹏,等.结合空间邻域聚类分割的高光谱图像异常检测支持向量数据描述方法[J].宇航学报,2007,28(3):767-771．
[50]梅锋,赵春晖,王立国,等.基于支持向量描述的自适应高光谱异常检测算法[J].光子学报,2009,38(11):2820-2825.
[51] P. Gurram, H. Kwon, T. Han. Sparse kernel-based hyperspectral anomaly detection[J].IEEE Geoscience and Remote Sensing Letters,2012,9(5):943-948.
[52] S. Khazai, A. Safari, B. Mojaradi. A fast-adaptive support vector method for full-pixelanomaly detection in hyperspectral images[C].Canada: IEEE International Geoscienceand Remote Sensing Symposium,2011:1763-1767.
[53]谌德荣,宫久路,陈乾,等.基于样本分割的快速高光谱图像异常检测支持向量数据描述方法[J].兵工学报,2008,29(9):1049-1053．
[54] H. Goldberg, H. Kwon, N.M. Nasrabadi. Kernel eigenspace separation transform forsubspace anomaly detection in hyperspectral imagery[J].IEEE Geoscience and RemoteSensing Letters,2007,4(4):581-585.
[55]李智勇,匡纲要,郁文贤,等.基于高光谱图像主成分分量的小目标检测算法研究[J].红外与毫米波学报,2004,23(4):286-290.
[56]李智勇,郁文贤,匡纲要.基于高维几何特性的高光谱异常检测算法研究[J].遥感技术与应用,2003,18(6):379-383.
[57]孙显,付琨,王宏琦.高分辨率图像理解[M].北京:科学出版社,2011:2-3.
[58] J.R. Schott. Remote sensing:the image chain approach[M].New York:Oxford Univers-ity Press,1996:74-75.
[59]李智勇.高光谱图像异常检测方法研究[D].长沙:国防科学技术大学博士学位论文,2004.
[60] G. Swayze. The hydrothermal and structural history of the cuprite mining district,Southwestern Nevada:an integrated geological and geophysical approach[D].USA:Ph.D. dissertation, Univ. Colorado,Boulder, CO,1997.
[61] R.N. Clark, G.A. Swayze. Evolution in imaging spectroscopy analysis and sensorsignal-to-noise: an e-amination of how far we have come[C].in Proc.6th Annu. JPLAirborne Earth Sci. Workshop,1996:49-53.
[62] G. Swayze, R. Clark, S. Sutley. Ground-truthing AVIRIS mineral mapping at Cuprite,Nevada[C].in Proc. Summ.3rd Annu. JPL Airborne Geosci. Workshop,1992:47-49.
[63] C.I. Chang, X.Li. Jiao C.C. Wu, et al. Component analysis-based unsupervised linearspectral mixture analysis for hyperspectral imagery[J].IEEE Trans. Geosci. RemoteSens.,2011,49(11):4123-4137.
[64] D. Landgrebe. Information extraction principles and methods for multispectral andhyperspectral image data:chapter1of information proeessing for remote sensing.[M].USA:World Scientific Publishing,2000:1-30.
[65] D.W. J. Stein, S.G. Beaven, L.E. Hoff. Anomaly detection for hyperspectral imagery [J].IEEE signal Processing Magazine,2002(1):58-69.
[66] N. Henze，T. Wagner. A new approach to the BHEP tests for multivariate normality[J].J.Multivariate Analysis,1997,62:1-23.
[67] P. Stoica, Y. Selen. Model-order selection:a review of information criterion rules[J].IEEE Signal Processing Magazine,2004,21(4):36-47.
[68]李红英.支持向量分类机的核函数研究[D].重庆:重庆大学硕士学位论文,2009.
[69] J. Shawe-Taylor, N. Cristianini. Kernel methods for pattern analysis[M].England:Cambridge University Press,2004:34-76.
[70]朱孝开.基于核方法的图像目标识别技术研究[D].长沙:国防科学技术大学博士学位论文,2009.
[71] D.M.J. Tax, R.P.W. Duin. Support vector data description[J].Mach.Learn.,2004,54(1):45-66.
[72] P.F. Evangelista, M.J. Embrechts, B.K. Szymanski. Some properties of the gaussiankernel for one class learning[C].in Proc.17th ICANN:Lecture Notes in ComputerScience,2007,4668:269-278.
[73] F. Mei, C.H. Zhao, H. Huo. An adaptive kernel method for anomaly detection in hyper-spectral imagery[C].in Proc.2nd Int. Symp.Intell. Inf. Technol. Appl.,2008:874-878.
[74]季亚新.高光谱图像异常检测算法研究[D].哈尔滨:哈尔滨工程大学硕士学位论文,2008.
[75] A. Green, M. Berman, P. Switzer, et al. A transformation for ordering multispectraldata in terms of image quality with implications for noise removal[J].IEEE Trans.Geosci. Remote Sens.,1988,26:65-74.
[76] J.C. Harsanyi, C.I. Chang. Hyperspectral image classification and dimensionality redu-ction:an orthogonal subspace projection[J].IEEE Trans. Geosci. Remote Sensing,1994,32(4):779-785.
[77] L.M. Bruce. Dimensionality reduction of hyperspectral data using discrete wavelettransform feature extraction[J].IEEE Transactions on Geoscience and Remote Sensing,2002,40(10):2331-2338.
[78] J. Herault, C. Jutten. Space or time adaptive signal prcessing by neural network models[C].USA:AIP Conference Proceedings,1986,151:206-211.
[79] X.P. Jia，J.A. Richards. Segemted Pricipal Comonpents Transformation for EfficientHyperspectral Remote Sensing Image Display and Classification[J].IEEE Trans. on Ge-oscience and Remote Sensing,1999,37(1):538-542．
[80] B. Sch kopf, A. J. Smola, K.R. Mülle. Kernel principal component analysis[J].NeuralComput.,1999,10:1299-1319.
[81] A. Ruiz, E.L. Teruel. Nonlinear kernel-based statistical pattern analysis[J].IEEE Trans.Neural Networks,2001,12(1):16-32.
[82] F.R. Bach, M.I. Jordan. Kernel Independent Component Analysis[J].Journal of Mac-hine Learning Research,2002(3):1-48.
[83] S. Jia, Z. Ji, Y.T. Qian. Band selection for hyperspectral imagery using affinity propag-ation[C].Canberra:Proc. Dicta,2008:137-141.
[84] C. Ozkan, F.S.Erbek. Comparing Feature Extraction Techniques for Urban Land-useClassification[J].International Journal of Remote Sensing,2005,26(4):747-757.
[85]张连蓬,储美华,刘国林,等.高光谱遥感波段的非线性投影寻踪方法[J].徐州师范大学学报:自然科学版,2004,22(4):49-53.
[86] S.D. Backer, P. Kempeneers, W. Debruyn, et al. A band selection technique for spe-ctral classification[J].IEEE Geoscience and Remote Sensing Letters,2005,2(3):319-323.
[87] C.I. Chang. Hyperspectral imaging: techniques for spectral detection and classification[M].New York: Kluwer,2003:15-35.
[88] H. Yang, Q. Du, H.J. Su et al. An efficient method for supervised hyperspectral bandselection[J]. IEEE Geoscience and Remote Sensing Letters,2011,8(1):138-142.
[89] R. Huang, M. He. Band selection based on feature weighting for classification of hype-rspectral imagery[J].IEEE Geoscience and Remote Sensing Letters,2005,2(2):156-159.
[90] S. Chiang, C.I. Chang, I. W. Ginsberg. Unsupervised hyperspectral image analysisusing independent component analysis[C].Honolulu:in Proc.IGARSS,2000:3136-3138.
[91]刘翔.基于光谱维变换的高光谱图像目标探测研究[D].北京:中科院研究生院博士学位论文,2008.
[92]史习智.盲信号处理─理论与实践[M].上海:上海交通大学出版社,2008:66-67.
[93]齐滨.高光谱图像分类及端元提取算法研究[D].哈尔滨:哈尔滨工程大学博士学位论文,2012.
[94] J. Lee, A. Woodyatt, M. Berman. Enhancement of high spectral resolution remotesensing data by a noise-adjusted principal components transform[J]. IEEE Trans.Geosci. Remote Sens.,1990,28(3):295-304.
[95] R.E. Roger. A fast way to compute the noise-adjusted principal components transformmatrix[J].IEEE Trans. Geosci. Remote Sensing,1994,32(11):1194-1196.
[96] C.I. Chang, Q. Du. Interference and noise-adjusted principal components analysis[J].IEEE Transactions on Geoscience and Remote Sensing,1999,37(5):2387-2396.
[97] C.I. Chang, Q. Du. A joint band prioritization and band decorrelation approach to bandselection[J].IEEE Trans. Geosci. Remote Sensing,1999,37(6):2631-2641.
[98] J.A. Richards, X.P. Jia.遥感数字图像分析[M].张烨,等译.4版.北京:电子工业出版社,2009:118-120.
[99] H. Ren, C.I. Chang. A generalized orthogonal subspace projection approach tounsupervised multispectral image classification[J].IEEE Transactions on Geoscienceand Remote Sensing,2000,38(6):2515-2528.
[100] C.I. Chang. Orthogonal subspace projection(osp)revisited: a comprehensive study andanalysis[J].IEEE Transactions on Geoscience and Remote Sensing,2005,43(3):502-518.
[101] S. Matteoli, M. Diani, G. Corsini. A tutorial overview of anomaly detection in hyper-spectral images[J]. IEEE A&E Systems Magazine,2010,25(7):5-28.
[102]寻丽娜,方勇华,李新.高光谱图像中基于端元提取的小目标检测算法[J].光学学报,2007,27(7):1178-1182.
[103] G. Camps-Valls, J. Mooij, B. Sch lkopf. Remote sensing feature selection by kerneldependence measures[J].IEEE Geoscience and Remote Sensing Letters,2010,7(3):587-591.
[104] G. Gao. A parzen-window-kernel-based cfar algorithm for ship detection in sar images[J].IEEE Geoscience and Remote Sensing Letters,2011,8(3):557-561.
[105] T. Blaschke. CuBICA:independment component analysis by simultaneous third andfourth order cumulant diagonalization[J].IEEE Trans. Signal Processing,2004,52(5):1250-1256.
[106]杨福生,洪波.独立分量分析的原理与应用[M].北京:清华大学出版社,2006:22-38.
[107] K. Safa, H. Saeid, S. Abdolreza. Anomaly detection in hyperspectral images based onan adaptive support vector method[J].IEEE Geoscience and Remote Sensing Letters,2011,8(4):646-650.
[108] X. Lu, L.E. Hoff, I.S. Reed, et al. Automatic target detection and recognition inmultiba-nd imagery:a unified ML detection and estimation approach[J].IEEETransactions Image Process,1997,6(1):143-156.
[109] Y. Zhang, J.P. Zhang, M. Jin. Adaptive subspace decomposition and classification forhyperspectral images[J].Chinese Journal of Electronics,2000,9(1):82-88.
[110]谷延锋,张晔.基于自动子空间划分的高光谱数据特征提取[J].遥感技术与应用,2003,18(6):384-387.
[111]王立国,谷延锋,张晔.基于支持向量机和子空间划分的波段选择方法[J].系统工程与电子技术,2005,27(6):974-977.
[112] C.H. Zhao, Y.L. Wang, F. Wang. Kernel ICA feature extraction for anomaly detectionin hyperspectral imagery[J].Chinese Journal of Electronics,2012,21(2):265-269.
[113]寻丽娜,方勇华,李新.高光谱图像中基于端元提取的小目标检测算法[J].光学学报,2007,27(7):1178-1182.
[114] S. Matteoli, M. Diani, G. Corsini. Hyperspectral anomaly detection with kurtosisdriven local covariance matrix corruption mitigation[J].IEEE Geoscience and RemoteSensing Letters,2011,8(3):531-535.
[115]梅锋,赵春晖,孙岩,等.基于新型光谱相似度量核的高光谱异常检测算法[J].光子学报,2009,38(12):3165-3170.
[116] W. Sakla, A. Chan, J. Ji, et al. An SVDD-based algorithm for target detection in hype-rspectral imagery[J].IEEE Geoscience and Remote Sensing Letters,2011,8(2):384-388.
[117] S. Khazai, A. Safari, B.Mojaradi, et al. A fast adaptive support vector method for full-pixel anomaly detection in hyperspectral images[C].Canada:IEEE Geoscience and Re-mote Sensing Society,2011:1763-1766.
[118] P. Gurram, H. Kwon. Support vector based hyperspectral anomaly detection usingoptimized kernel parameters[J].IEEE Geoscience and Remote Sensing Letters,2011,8(6):1060-1064.
[119]谌德荣,宫久路,何光林,等.高光谱图像全局异常检测RFS-SVDD算法[J].宇航学报，2010,31(1):228-232.
[120] N. Keshava. A survey of spectral unmixing algorithms[J].Lincoln Lab. J.,2003,14(1):55-78.
[121] S. Jia, Y.T. Qian. Constrained nonnegative matrix factorization for hyperspectralunmixing[J].IEEE Transactions On Geoscience And Remote Sensing,2009,47(1):161-173.
[122] T.H. Chan, C.Y. Chi, Y.M. Huang. A convex analysis-based minimum-volume enclos-eing simplex algorithm for hyperspectral unmixing[J]. IEEE Transactions On SignalProcessing,2009,57(11):4418-4432.
[123] A. Plaza, P. Martinez, R. Perez, et al. Spatial/spectral endmember extraction by multid-imensional morphological operations[J].IEEE Trans. Geosci. Remote Sens.,2002,40(9):2025-2041.
[124] M. Zortea, A. Plaza. Spatial preprocessing for endmember extraction[J].IEEE Transa-Ctions on Geoscience and Remote Sensing,2009,47(8):2679-2693.
[125]罗文斐,钟亮,张兵.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):307-331.
[126] J.W. Boardman, F.A. Kruse, R.O. Green. Mapping target signatures via partialunmixing of AVIRIS data[C].USA:in Summaries of the VI JPL Airborne Earth ScienceWorkshop, Pasadena, CA,1995:23-26.
[127] M.E. Winter. N-finder: an algorithm for fast autonomous spectral endmember determ-ination in hyperspectral data[C].Image Spectrometry V, Proc. SPIE3753,1999:266-277.
[128] J.M.P. Nascimento, J.M.B. Dias. Vertex component analysis:a fast algorithm to unmixhyperspectral data[J].IEEE Transactions On Geoscience and Remote Sensing,2005,43(4):898-910.
[129] L.D. Miao, H.R. Qi. Endmember extraction from highly mixed data using minimumvolume constrained nonnegative matrix factorization[J].IEEE Geoscience and RemoteSensing Letters,2007,45(3):765-777.
[130] B. Zhang, X. Sun, L. Gao, et al. Endmember extraction of hyperspectral remotesensing images based on the ant colony optimization(ACO) algorithm[J]. IEEETransactions on Geoscience and Remote Sensing,2011,49(7):2635-2646.
[131] R.A. Neville, K. Staenz, T. Szeredi, et al. Automatie endmember extraetion from hyp-erspectral data for mineral exploration[C].Canadian:In21st Canadian Symposium onRemote Sensing,1999:21-24.
[132]王立国,赵春晖,毕晓君.端元选择算法在波段选择中的应用[J].吉林大学学报:工学版,2007,37(4):915-919.
[133] Y.T. Qian, S. Jia, J. Zhou, et al. Hyperspectral unmixing viaL1/2sparsity-constrainednonnegative matrix factorization[J]. IEEE Transactions on Geoscience and RemoteSensing,2011,49(11):4282-4297.
[134] A. Huck, M. Guillaume, J. Blanc-Talon. Minimum dispersion constrained nonnegativematrix factorization to unmix hyperspectral data[J].IEEE Transactions On Geoscienceand Remote Sensing,2010,48(6):2590-2602.
[135]贾森.非监督的高光谱图像解混技术研究[D].杭州:浙江大学博士学位论文,2007:7-18.
[136] J. Nascimento, J. Bioucas-Dias. Hyerspectral unmixing algorithm via dependent com-ponent analysis[C].IEEE Internationla Geoscience and Remote sensing Symposium,2007:4033-4036.
[137] D.C. Heinz, C.I. Chang. Fully constrained least squares linear spectral mixture analysismethod for material quantification in hyperspectral imagery[J].IEEE Transactions OnGeoscience and Remote Sensing,2001,39(3):529-545.
[138] C. Jutten, J. Herault. Blind separation of sources I. an adaptive algorithm based onneuromimetic architecture[J].Signal Processing,1991,24(1):1-10.
[139] P. Comon, C. Jutten, J. Herault. Blind separation of sources II. problems statement[J].Signal Processing.,1991,24(1):11-20.
[140] M. Lennon, M. Mouchot, G. Mercier, et al. Spectral unmixing of hyperspectral imageswith the independent component analysis and wavelet packets[C].Sydney:in Proc.IGARSS,2001:2896-2898.
[141] J. M. P. Nascimento, J. M. Bioucas Dias. Does independent component analysis play arole in unmixing hyperspectral data[J].IEEE Transactions on Geoscience and RemoteSensing,2005,43(1):175-187.
[142] W. Xia, X.S. Liu, B. Wang. Independent component analysis for blind unmixing ofhyperspectral imagery with additional constraints[J].IEEE Transactions on Geoscienceand Remote Sensing,2011,49(6):2165-2179.
[143] S.H. Mei, M.Y. He, Z.Y. Wang. Spatial purity based endmember extraction for spec-tral mixture analysis[J].IEEE Transactions on Geoscience and Remote Sensing,2010,48(9):3434-3445.
[144]贾森,钱沄涛,纪震,等.基于光谱和空间特性的高光谱解混方法[J].深圳理工大学学报理工版,2009,26(3):262-267.
[145] J.H. Friedman, J.W. Tukey. A projection pursuit algorithm for exploratory dataanalysis[J].IEEE Transactions on Computers,1974,23:881-890.
[146] J. Bowles, P. Palmadesso, J. Antoniades. Use of filter vectors in hyperspectral dataanalysis[C].San Diego:Proceedings of the Meeting of Infrared Spaceborne RemoteSensing III,1995:148-157.
[147] C.I. Chang. Further results on relationship between spectral unmixing and subspaceprojection[J].IEEE Transactions on Geoscience and Remote Sensing,1998,36(3):1030-1032.
[148]刘力帆,王斌,张立明.基于自组织映射和模糊隶属度的混合像元分解[J].计算机辅助设计与图形学学报,2008,20(10):1307-1317.
[149] D.D. Lee, H.S. Seung. Learning the parts of objects by of objects by nonneative matrixfactorization[J].Nature,1999,401(6755):788-791.
[150] C.J. Lin. Projected gradient methods for nonnegative matrix factorization[J].NeuralComputation,2007,19(10):2756-2779.
[151] A. Huck, M. Guillaume, B.T. Jacques. Minimum dispersion constrained nonnegativematrix factorization to unmix hyperspectral data[J].IEEE Trans. Geosci. Remote Sens.,2008,48(6):2590-2602.
[152] X.S. Liu, W. Xia, B. Wang, et al. An approach based on constrained nonnegativematrix factorization to unmix hyperspectral data[J].IEEE Trans. Geosci. RemoteSens.,2011,49(2):757-772.
[153] R.A. Johnson, D.W. Wiechern. Applied Multivariate Statistical Analysis[M].6thed.Englewood Cliffs,NJ: Prentice-Hall,2007.
[154] H. Yang, Q. Du, H.J. Su,et al. An efficient method for supervised hyperspectral bandselection[J].IEEE Trans. Geosci. Remote Sens.Lett,2011,8(1):138-142.
[155]吴波,张良培,李平湘.高光谱端元自动提取的迭代分解方法[J].遥感学报,2005,9(3):287-292.
[156]吴波,赵银娣,周小成.端元约束下的高光谱混合像元非负矩阵分解[J].计算机工程,2008,34(22):229-230.
[157] Y. Yue, G. Shan, W.D. SUN. Minimum distance constrained nonnegative matrix fac-torizeation for the endmember extraction of hyperspectral images[J].in Proc. of theSPIE,2007,6790:6790151-9.
[158] A. Morten, N. Mikkel, S.J. Larsen. Unmixing of hyperspectral images using bayesiannonnegative matrix factorization with volume prior[C]. MLSP2009,1-18.
[159] D.C. Heinz, C.I. Chang. Fully constrained least squares linear spectral mixture analysismethod for material quantification in Hyperspectral imagery[J].IEEE Trans. Geosci.Remote Sens.,2001,39(3):529-545.
[160] N. Keshava, J.F. Mustard. Spectral unmixing[J].IEEE Signal Process. Mag.,2002,19(1):44-57.
[161] A. Plaza, P. Martinez, R. Perez, et al. A quantitative and comparative analysis ofendmember extraction algorithms from hyperspectral data[J].IEEE Trans. Geosci.Remote Sens.,2004,42(3):650-663.
[162] R. N. Clark, G. A. Swayze, R. Wise, et al. USGS Digital Spectral Library splib05a[C].USGS Open File Report03-395,2003.
[163] J.M. Bioucas-Dias, J.M.P. Nascimento. Hyperspectral subspace identification[J].IEEETrans. Geosci. Remote Sens.,2008,46(8):2435-2445.
[164] M.J. Tax David, P.W Duin Robert. Support Vector Data Description[J]. MachineLearning,2004,54(1):45-66.
[165] X.M. Wang, F.L. Chung, S.T. Wang. Theoretical analysis for solution of support vect-or data description[J].Neural Networks,2011,24:360-369.
[166] B. Qi, C.H. Zhao, E. Youn, et al. Use of weighting algorithms to improve traditionalsupport vector machine based classifications of reflectance data[J].Optics express,2011,19(27):26816-26826.
[2]谷延锋.基于核方法的高光谱图象分类和目标检测技术研究[D].哈尔滨:哈尔滨工业大学博士学位论文,2005.
[3] F. H.A. Goetz, V. Gregg, J. E. Solomon, et al. Imaging Spectrometry for Earth RemoteSensing.[J].Science,1985,228(4704):1147-1153.
[4] R.A. Schowengerdt.遥感图像处理模型与方法[M].3版.微波成像技术国家重点实验室,译.北京:电子工业出版社,2010:31-83.
[5] G. Vane, A.F.H Goetz.Terrestrial imaging spectraometry:current status, the futuretrends[J].Remote Sensing of Environment,1993,44:117-126.
[6] A.F.H. Goetz, L.C Rowan. Geological Remote Sensing[J].Science,1981,211:781-791.
[7]童庆禧,张兵,郑兰芬.高光谱遥感—原理、技术与应用[M].北京:高等教育出版社,2006:246-247.
[8]王晓飞.高光谱图像分辨率增强及在小目标检测中的应用研究[D].哈尔滨:哈尔滨工业大学博士学位论文,2011:13-17.
[9]胡秀清,刘京晶,邱康睦,等.神舟3号飞船中分辨率成像光谱仪场地替代定标新方法研究[J].光谱学与光谱分析,2009,29(5):1153-1156.
[10] L. He，Q. Pan，W. Di, et al. Anomaly detection in hyperspectral imagery based onmaximum entropy and nonparametric estimation[J].Pattern Recognition Letters,2009,29:1392-1403.
[11] I.S. Reed, X. Yu. Adaptive multiple-band cfar detection of an optical pattern withunknown spectral distribution[J].IEEE Transactions on Acoustics, Speech and SignalProcessing.,1990,38(10):1760-1770.
[12] X.L. Yu, L.E. Hoff, I.S. Reed, et al. Automatic target detection and recognition inmultiband imagery: a unified ml detection and estimation approach[J].IEEE Transact-ions on Image Processing.,1997,6(1):143-156.
[13]谷延锋,刘颖,贾友华,等.基于光谱解译的高光谱图像奇异检测算法[J].红外与毫米波学报,2006,25(6):473-477.
[14] H. Kwon, N.M. Nasrabad. Kernel RX-algorithm:a nonlinear anomaly detector forhyperspectral imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2005,43(2):388-397.
[15] A. Banerjee, P. Burlina, C. Diehl. A support vector method for anomaly detection inhyperspectral imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2006,44(8):2282-2291.
[16]李杰,赵春晖,梅锋.利用背景残差数据检测高光谱图异常[J].红外与毫米波学报,2010,29(2):150-155.
[17] M.J. Carlotto. A cluster-based approach for detecting man-made objects and changesin imagery[J].IEEE Transactions on Geoscience and Remote Sensing,2005,43(2):374-387.
[18] B. Du, L.P. Zhang. Random-selection-based anomaly detector for hyperspectral imag-ery[J].IEEE Transactions on Geoscience and Remote Sensing,2011,49(5):1578-1589.
[19]梅锋.基于核机器学习的高光谱异常目标检测算法研究[D].哈尔滨:哈尔滨工程大学博士学位论文,2009.
[20] C.I. Chang, S.S. Chiang. Anomaly detection and classification for hyperspectralimagery[J].IEEE Transactions on Geoscience And Remote Sensing,2002,40(6):1314-1325.
[21] D.W.J. Stein, S.G. Beaven, L.E. Hoff, et al. Anomaly detection from hyperspectralimagery[J].IEEE Signal Process. Mag.,2002,19(1):58-69.
[22] D.W.J. Stein. Stochastic compositional models applied to subpixel analysis of hyper-spectral imagery[C].Proc. SPIE,2001,4480:49-56.
[23] J.E. Fowler, Q. Du. Anomaly detection and reconstruction from random projections[J].IEEE Transactions on Image Processing,2012,21(1):184-195.
[24] S. Matteoli, M. Diani, G. Corsini. Hyperspectral anomaly detection with kurtosis-driven local covariance matrix corruption mitigation[J].IEEE Geoscience and RemoteSensing Letters,2011,8(3):531-535.
[25] S. Matteoli, M. Diani, G. Corsini. Improved estimation of background covariancematrix for anomaly detection in hyperspectral images[J].Opt.Eng.,2010,49(4):046201-1-16.
[26] J.M. Molero, A. Paz, E.M. Garzón, et al. Fast anomaly detection in hyperspectralimages with RX method on heterogeneous clusters[J].J Supercomput,2011,58:411-419.
[27] H. Ren, C.W. Chen, H.T. Chen. Weighted anomaly detection for hyperspectral remo-tely sensed images[C].USA:SPIE The International Society for Optical Engineering,2005,5995:599501-599507.
[28] R.A. Riley, R.K. Newsom, A.K. Andrews. Anomaly detection in noisy hyperspectralimagery[C] USA: SPIE-Int. Soc. Opt. Eng,2004,5546:159-170.
[29] S.M. Schweizer, J.M.F. Moura. Hyperspectral imagery:clutter adaptation in anomalydetection[J].IEEE Transactions on Information Theory,2000,46(5):1855-1871.
[30] S.M. Schweizer, J.M.F. Moura. Efficient detection in hyperspectral imagery[J].IEEETransactions on Image Processing,2001,10(4):584-597.
[31]贺霖.高光谱图像自动目标检测技术研究[J].西安:西北工业大学博士学位论文,2007:29-32.
[32]张立燕,谌德荣,李世义,等.基于低概率检测的高光谱图像有损压缩方法研究[J].弹箭与制导学报,2008,28(1):307-310.
[33]王玉磊,赵春晖,王江洪.基于低概率检测的高光谱异常目标检测算法研究[J].黑龙江大学自然科学学报,2010,27(3):411-416.
[34] B. Yver, R. Marion. A theoretical framework for hyperspectral anomaly detectionusing spectral and spatial a priori information[J].IEEE Geoscience and Remote SensingLetters.,2007,4(3):436-440.
[35] H. Kwon, S.Z. Der, N.M. Nasrabadi. Adaptive anomaly detection using subspace sep-arateion for hyperspectral imagery[J].Optical Engineering.,2003,42(11):3342-3351.
[36] H. Kwon, S.Z. Der, N.M. Nasrabadi. Projection-based adaptive anomaly detection forhyperspectral imagery[C].USA:Proceedings2003International Conference on ImageProcessing(Cat. No.03CH37429),2003:1001-1004.
[37] J. Broadwater, R.Chellappa. Hybrid detectors for subpixel targets[J].IEEE Transac-tions on Pattern Analysis and Machine Intelligence.,2007,29(11):1891-1903.
[38] B. Scholkopf, A.J. Smola. Learning with kernels:support vector machines regularize-tion,optimization, and beyond[M].Cambridge:MIT Press,2001.
[39] H. Kwon, N.M. Nasrabadi. A comparative study of kernel spectral matched signaldetectors for hyperspectral target detection[C].USA:Proc. SPIE Int. Soc. Opt. Eng.,2005,5806:827-838.
[40] H. Kwon, N.M. Nasrabadi. Kernel adaptive subspace detector for hyperspectral targetdetection[C].USA:IEEE International Conference on Acoustics, Speech, and SignalProcessing(Cat. No.05CH37625),2005,4:681-684.
[41] H. Kwon, N.M Nasrabadi. Kernel-based subpixel target detection in hyperspectralimages[C].USA:IEEE International Joint Conference on Neural Networks(Cat.No.04CH37541),2004:717-721.
[42]赵春晖,李杰,梅锋.核加权RX高光谱图像异常检测算法[J].红外与毫米波学报，2011,29(5):378-382.
[43]赵春晖,胡春梅,包玉刚.一种背景误差累积的高光谱图像异常检测算法[J].光子学报,2010,39(10):1830-1835.
[44]赵春晖,胡春梅.基于目标正交子空间投影加权的高光谱图像异常检测算法[J].吉林大学学报:工学版,2011,41(5):1468-1474.
[45]梅锋,赵春晖.基于空域滤波的核RX高光谱图像异常检测算法[J].哈尔滨工程大学学报,2009,30(6):697-702.
[46] D.M.J. Tax, A. Ypma, R.P.W. Duin. Support vector data description applied tomachine vibration analysis[C].Heijen:Prec5th Anna Conf Adv School Compu Imag.,1999:398-405．
[47]谌德荣,宫久路,何光林,等.高光谱图像全局异常检测RFS-SVDD算法[J].宇航学报,2010,31(1):228-232.
[48] S. Khazai, S. Homayouni, A. Safari. Anomaly detection in hyperspectral images basedon an adaptive support vector method[J].IEEE geoscience and remote sensing letters,2011,8(4):646-650.
[49]谌德荣,张文燕,陶鹏,等.结合空间邻域聚类分割的高光谱图像异常检测支持向量数据描述方法[J].宇航学报,2007,28(3):767-771．
[50]梅锋,赵春晖,王立国,等.基于支持向量描述的自适应高光谱异常检测算法[J].光子学报,2009,38(11):2820-2825.
[51] P. Gurram, H. Kwon, T. Han. Sparse kernel-based hyperspectral anomaly detection[J].IEEE Geoscience and Remote Sensing Letters,2012,9(5):943-948.
[52] S. Khazai, A. Safari, B. Mojaradi. A fast-adaptive support vector method for full-pixelanomaly detection in hyperspectral images[C].Canada: IEEE International Geoscienceand Remote Sensing Symposium,2011:1763-1767.
[53]谌德荣,宫久路,陈乾,等.基于样本分割的快速高光谱图像异常检测支持向量数据描述方法[J].兵工学报,2008,29(9):1049-1053．
[54] H. Goldberg, H. Kwon, N.M. Nasrabadi. Kernel eigenspace separation transform forsubspace anomaly detection in hyperspectral imagery[J].IEEE Geoscience and RemoteSensing Letters,2007,4(4):581-585.
[55]李智勇,匡纲要,郁文贤,等.基于高光谱图像主成分分量的小目标检测算法研究[J].红外与毫米波学报,2004,23(4):286-290.
[56]李智勇,郁文贤,匡纲要.基于高维几何特性的高光谱异常检测算法研究[J].遥感技术与应用,2003,18(6):379-383.
[57]孙显,付琨,王宏琦.高分辨率图像理解[M].北京:科学出版社,2011:2-3.
[58] J.R. Schott. Remote sensing:the image chain approach[M].New York:Oxford Univers-ity Press,1996:74-75.
[59]李智勇.高光谱图像异常检测方法研究[D].长沙:国防科学技术大学博士学位论文,2004.
[60] G. Swayze. The hydrothermal and structural history of the cuprite mining district,Southwestern Nevada:an integrated geological and geophysical approach[D].USA:Ph.D. dissertation, Univ. Colorado,Boulder, CO,1997.
[61] R.N. Clark, G.A. Swayze. Evolution in imaging spectroscopy analysis and sensorsignal-to-noise: an e-amination of how far we have come[C].in Proc.6th Annu. JPLAirborne Earth Sci. Workshop,1996:49-53.
[62] G. Swayze, R. Clark, S. Sutley. Ground-truthing AVIRIS mineral mapping at Cuprite,Nevada[C].in Proc. Summ.3rd Annu. JPL Airborne Geosci. Workshop,1992:47-49.
[63] C.I. Chang, X.Li. Jiao C.C. Wu, et al. Component analysis-based unsupervised linearspectral mixture analysis for hyperspectral imagery[J].IEEE Trans. Geosci. RemoteSens.,2011,49(11):4123-4137.
[64] D. Landgrebe. Information extraction principles and methods for multispectral andhyperspectral image data:chapter1of information proeessing for remote sensing.[M].USA:World Scientific Publishing,2000:1-30.
[65] D.W. J. Stein, S.G. Beaven, L.E. Hoff. Anomaly detection for hyperspectral imagery [J].IEEE signal Processing Magazine,2002(1):58-69.
[66] N. Henze，T. Wagner. A new approach to the BHEP tests for multivariate normality[J].J.Multivariate Analysis,1997,62:1-23.
[67] P. Stoica, Y. Selen. Model-order selection:a review of information criterion rules[J].IEEE Signal Processing Magazine,2004,21(4):36-47.
[68]李红英.支持向量分类机的核函数研究[D].重庆:重庆大学硕士学位论文,2009.
[69] J. Shawe-Taylor, N. Cristianini. Kernel methods for pattern analysis[M].England:Cambridge University Press,2004:34-76.
[70]朱孝开.基于核方法的图像目标识别技术研究[D].长沙:国防科学技术大学博士学位论文,2009.
[71] D.M.J. Tax, R.P.W. Duin. Support vector data description[J].Mach.Learn.,2004,54(1):45-66.
[72] P.F. Evangelista, M.J. Embrechts, B.K. Szymanski. Some properties of the gaussiankernel for one class learning[C].in Proc.17th ICANN:Lecture Notes in ComputerScience,2007,4668:269-278.
[73] F. Mei, C.H. Zhao, H. Huo. An adaptive kernel method for anomaly detection in hyper-spectral imagery[C].in Proc.2nd Int. Symp.Intell. Inf. Technol. Appl.,2008:874-878.
[74]季亚新.高光谱图像异常检测算法研究[D].哈尔滨:哈尔滨工程大学硕士学位论文,2008.
[75] A. Green, M. Berman, P. Switzer, et al. A transformation for ordering multispectraldata in terms of image quality with implications for noise removal[J].IEEE Trans.Geosci. Remote Sens.,1988,26:65-74.
[76] J.C. Harsanyi, C.I. Chang. Hyperspectral image classification and dimensionality redu-ction:an orthogonal subspace projection[J].IEEE Trans. Geosci. Remote Sensing,1994,32(4):779-785.
[77] L.M. Bruce. Dimensionality reduction of hyperspectral data using discrete wavelettransform feature extraction[J].IEEE Transactions on Geoscience and Remote Sensing,2002,40(10):2331-2338.
[78] J. Herault, C. Jutten. Space or time adaptive signal prcessing by neural network models[C].USA:AIP Conference Proceedings,1986,151:206-211.
[79] X.P. Jia，J.A. Richards. Segemted Pricipal Comonpents Transformation for EfficientHyperspectral Remote Sensing Image Display and Classification[J].IEEE Trans. on Ge-oscience and Remote Sensing,1999,37(1):538-542．
[80] B. Sch kopf, A. J. Smola, K.R. Mülle. Kernel principal component analysis[J].NeuralComput.,1999,10:1299-1319.
[81] A. Ruiz, E.L. Teruel. Nonlinear kernel-based statistical pattern analysis[J].IEEE Trans.Neural Networks,2001,12(1):16-32.
[82] F.R. Bach, M.I. Jordan. Kernel Independent Component Analysis[J].Journal of Mac-hine Learning Research,2002(3):1-48.
[83] S. Jia, Z. Ji, Y.T. Qian. Band selection for hyperspectral imagery using affinity propag-ation[C].Canberra:Proc. Dicta,2008:137-141.
[84] C. Ozkan, F.S.Erbek. Comparing Feature Extraction Techniques for Urban Land-useClassification[J].International Journal of Remote Sensing,2005,26(4):747-757.
[85]张连蓬,储美华,刘国林,等.高光谱遥感波段的非线性投影寻踪方法[J].徐州师范大学学报:自然科学版,2004,22(4):49-53.
[86] S.D. Backer, P. Kempeneers, W. Debruyn, et al. A band selection technique for spe-ctral classification[J].IEEE Geoscience and Remote Sensing Letters,2005,2(3):319-323.
[87] C.I. Chang. Hyperspectral imaging: techniques for spectral detection and classification[M].New York: Kluwer,2003:15-35.
[88] H. Yang, Q. Du, H.J. Su et al. An efficient method for supervised hyperspectral bandselection[J]. IEEE Geoscience and Remote Sensing Letters,2011,8(1):138-142.
[89] R. Huang, M. He. Band selection based on feature weighting for classification of hype-rspectral imagery[J].IEEE Geoscience and Remote Sensing Letters,2005,2(2):156-159.
[90] S. Chiang, C.I. Chang, I. W. Ginsberg. Unsupervised hyperspectral image analysisusing independent component analysis[C].Honolulu:in Proc.IGARSS,2000:3136-3138.
[91]刘翔.基于光谱维变换的高光谱图像目标探测研究[D].北京:中科院研究生院博士学位论文,2008.
[92]史习智.盲信号处理─理论与实践[M].上海:上海交通大学出版社,2008:66-67.
[93]齐滨.高光谱图像分类及端元提取算法研究[D].哈尔滨:哈尔滨工程大学博士学位论文,2012.
[94] J. Lee, A. Woodyatt, M. Berman. Enhancement of high spectral resolution remotesensing data by a noise-adjusted principal components transform[J]. IEEE Trans.Geosci. Remote Sens.,1990,28(3):295-304.
[95] R.E. Roger. A fast way to compute the noise-adjusted principal components transformmatrix[J].IEEE Trans. Geosci. Remote Sensing,1994,32(11):1194-1196.
[96] C.I. Chang, Q. Du. Interference and noise-adjusted principal components analysis[J].IEEE Transactions on Geoscience and Remote Sensing,1999,37(5):2387-2396.
[97] C.I. Chang, Q. Du. A joint band prioritization and band decorrelation approach to bandselection[J].IEEE Trans. Geosci. Remote Sensing,1999,37(6):2631-2641.
[98] J.A. Richards, X.P. Jia.遥感数字图像分析[M].张烨,等译.4版.北京:电子工业出版社,2009:118-120.
[99] H. Ren, C.I. Chang. A generalized orthogonal subspace projection approach tounsupervised multispectral image classification[J].IEEE Transactions on Geoscienceand Remote Sensing,2000,38(6):2515-2528.
[100] C.I. Chang. Orthogonal subspace projection(osp)revisited: a comprehensive study andanalysis[J].IEEE Transactions on Geoscience and Remote Sensing,2005,43(3):502-518.
[101] S. Matteoli, M. Diani, G. Corsini. A tutorial overview of anomaly detection in hyper-spectral images[J]. IEEE A&E Systems Magazine,2010,25(7):5-28.
[102]寻丽娜,方勇华,李新.高光谱图像中基于端元提取的小目标检测算法[J].光学学报,2007,27(7):1178-1182.
[103] G. Camps-Valls, J. Mooij, B. Sch lkopf. Remote sensing feature selection by kerneldependence measures[J].IEEE Geoscience and Remote Sensing Letters,2010,7(3):587-591.
[104] G. Gao. A parzen-window-kernel-based cfar algorithm for ship detection in sar images[J].IEEE Geoscience and Remote Sensing Letters,2011,8(3):557-561.
[105] T. Blaschke. CuBICA:independment component analysis by simultaneous third andfourth order cumulant diagonalization[J].IEEE Trans. Signal Processing,2004,52(5):1250-1256.
[106]杨福生,洪波.独立分量分析的原理与应用[M].北京:清华大学出版社,2006:22-38.
[107] K. Safa, H. Saeid, S. Abdolreza. Anomaly detection in hyperspectral images based onan adaptive support vector method[J].IEEE Geoscience and Remote Sensing Letters,2011,8(4):646-650.
[108] X. Lu, L.E. Hoff, I.S. Reed, et al. Automatic target detection and recognition inmultiba-nd imagery:a unified ML detection and estimation approach[J].IEEETransactions Image Process,1997,6(1):143-156.
[109] Y. Zhang, J.P. Zhang, M. Jin. Adaptive subspace decomposition and classification forhyperspectral images[J].Chinese Journal of Electronics,2000,9(1):82-88.
[110]谷延锋,张晔.基于自动子空间划分的高光谱数据特征提取[J].遥感技术与应用,2003,18(6):384-387.
[111]王立国,谷延锋,张晔.基于支持向量机和子空间划分的波段选择方法[J].系统工程与电子技术,2005,27(6):974-977.
[112] C.H. Zhao, Y.L. Wang, F. Wang. Kernel ICA feature extraction for anomaly detectionin hyperspectral imagery[J].Chinese Journal of Electronics,2012,21(2):265-269.
[113]寻丽娜,方勇华,李新.高光谱图像中基于端元提取的小目标检测算法[J].光学学报,2007,27(7):1178-1182.
[114] S. Matteoli, M. Diani, G. Corsini. Hyperspectral anomaly detection with kurtosisdriven local covariance matrix corruption mitigation[J].IEEE Geoscience and RemoteSensing Letters,2011,8(3):531-535.
[115]梅锋,赵春晖,孙岩,等.基于新型光谱相似度量核的高光谱异常检测算法[J].光子学报,2009,38(12):3165-3170.
[116] W. Sakla, A. Chan, J. Ji, et al. An SVDD-based algorithm for target detection in hype-rspectral imagery[J].IEEE Geoscience and Remote Sensing Letters,2011,8(2):384-388.
[117] S. Khazai, A. Safari, B.Mojaradi, et al. A fast adaptive support vector method for full-pixel anomaly detection in hyperspectral images[C].Canada:IEEE Geoscience and Re-mote Sensing Society,2011:1763-1766.
[118] P. Gurram, H. Kwon. Support vector based hyperspectral anomaly detection usingoptimized kernel parameters[J].IEEE Geoscience and Remote Sensing Letters,2011,8(6):1060-1064.
[119]谌德荣,宫久路,何光林,等.高光谱图像全局异常检测RFS-SVDD算法[J].宇航学报，2010,31(1):228-232.
[120] N. Keshava. A survey of spectral unmixing algorithms[J].Lincoln Lab. J.,2003,14(1):55-78.
[121] S. Jia, Y.T. Qian. Constrained nonnegative matrix factorization for hyperspectralunmixing[J].IEEE Transactions On Geoscience And Remote Sensing,2009,47(1):161-173.
[122] T.H. Chan, C.Y. Chi, Y.M. Huang. A convex analysis-based minimum-volume enclos-eing simplex algorithm for hyperspectral unmixing[J]. IEEE Transactions On SignalProcessing,2009,57(11):4418-4432.
[123] A. Plaza, P. Martinez, R. Perez, et al. Spatial/spectral endmember extraction by multid-imensional morphological operations[J].IEEE Trans. Geosci. Remote Sens.,2002,40(9):2025-2041.
[124] M. Zortea, A. Plaza. Spatial preprocessing for endmember extraction[J].IEEE Transa-Ctions on Geoscience and Remote Sensing,2009,47(8):2679-2693.
[125]罗文斐,钟亮,张兵.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):307-331.
[126] J.W. Boardman, F.A. Kruse, R.O. Green. Mapping target signatures via partialunmixing of AVIRIS data[C].USA:in Summaries of the VI JPL Airborne Earth ScienceWorkshop, Pasadena, CA,1995:23-26.
[127] M.E. Winter. N-finder: an algorithm for fast autonomous spectral endmember determ-ination in hyperspectral data[C].Image Spectrometry V, Proc. SPIE3753,1999:266-277.
[128] J.M.P. Nascimento, J.M.B. Dias. Vertex component analysis:a fast algorithm to unmixhyperspectral data[J].IEEE Transactions On Geoscience and Remote Sensing,2005,43(4):898-910.
[129] L.D. Miao, H.R. Qi. Endmember extraction from highly mixed data using minimumvolume constrained nonnegative matrix factorization[J].IEEE Geoscience and RemoteSensing Letters,2007,45(3):765-777.
[130] B. Zhang, X. Sun, L. Gao, et al. Endmember extraction of hyperspectral remotesensing images based on the ant colony optimization(ACO) algorithm[J]. IEEETransactions on Geoscience and Remote Sensing,2011,49(7):2635-2646.
[131] R.A. Neville, K. Staenz, T. Szeredi, et al. Automatie endmember extraetion from hyp-erspectral data for mineral exploration[C].Canadian:In21st Canadian Symposium onRemote Sensing,1999:21-24.
[132]王立国,赵春晖,毕晓君.端元选择算法在波段选择中的应用[J].吉林大学学报:工学版,2007,37(4):915-919.
[133] Y.T. Qian, S. Jia, J. Zhou, et al. Hyperspectral unmixing viaL1/2sparsity-constrainednonnegative matrix factorization[J]. IEEE Transactions on Geoscience and RemoteSensing,2011,49(11):4282-4297.
[134] A. Huck, M. Guillaume, J. Blanc-Talon. Minimum dispersion constrained nonnegativematrix factorization to unmix hyperspectral data[J].IEEE Transactions On Geoscienceand Remote Sensing,2010,48(6):2590-2602.
[135]贾森.非监督的高光谱图像解混技术研究[D].杭州:浙江大学博士学位论文,2007:7-18.
[136] J. Nascimento, J. Bioucas-Dias. Hyerspectral unmixing algorithm via dependent com-ponent analysis[C].IEEE Internationla Geoscience and Remote sensing Symposium,2007:4033-4036.
[137] D.C. Heinz, C.I. Chang. Fully constrained least squares linear spectral mixture analysismethod for material quantification in hyperspectral imagery[J].IEEE Transactions OnGeoscience and Remote Sensing,2001,39(3):529-545.
[138] C. Jutten, J. Herault. Blind separation of sources I. an adaptive algorithm based onneuromimetic architecture[J].Signal Processing,1991,24(1):1-10.
[139] P. Comon, C. Jutten, J. Herault. Blind separation of sources II. problems statement[J].Signal Processing.,1991,24(1):11-20.
[140] M. Lennon, M. Mouchot, G. Mercier, et al. Spectral unmixing of hyperspectral imageswith the independent component analysis and wavelet packets[C].Sydney:in Proc.IGARSS,2001:2896-2898.
[141] J. M. P. Nascimento, J. M. Bioucas Dias. Does independent component analysis play arole in unmixing hyperspectral data[J].IEEE Transactions on Geoscience and RemoteSensing,2005,43(1):175-187.
[142] W. Xia, X.S. Liu, B. Wang. Independent component analysis for blind unmixing ofhyperspectral imagery with additional constraints[J].IEEE Transactions on Geoscienceand Remote Sensing,2011,49(6):2165-2179.
[143] S.H. Mei, M.Y. He, Z.Y. Wang. Spatial purity based endmember extraction for spec-tral mixture analysis[J].IEEE Transactions on Geoscience and Remote Sensing,2010,48(9):3434-3445.
[144]贾森,钱沄涛,纪震,等.基于光谱和空间特性的高光谱解混方法[J].深圳理工大学学报理工版,2009,26(3):262-267.
[145] J.H. Friedman, J.W. Tukey. A projection pursuit algorithm for exploratory dataanalysis[J].IEEE Transactions on Computers,1974,23:881-890.
[146] J. Bowles, P. Palmadesso, J. Antoniades. Use of filter vectors in hyperspectral dataanalysis[C].San Diego:Proceedings of the Meeting of Infrared Spaceborne RemoteSensing III,1995:148-157.
[147] C.I. Chang. Further results on relationship between spectral unmixing and subspaceprojection[J].IEEE Transactions on Geoscience and Remote Sensing,1998,36(3):1030-1032.
[148]刘力帆,王斌,张立明.基于自组织映射和模糊隶属度的混合像元分解[J].计算机辅助设计与图形学学报,2008,20(10):1307-1317.
[149] D.D. Lee, H.S. Seung. Learning the parts of objects by of objects by nonneative matrixfactorization[J].Nature,1999,401(6755):788-791.
[150] C.J. Lin. Projected gradient methods for nonnegative matrix factorization[J].NeuralComputation,2007,19(10):2756-2779.
[151] A. Huck, M. Guillaume, B.T. Jacques. Minimum dispersion constrained nonnegativematrix factorization to unmix hyperspectral data[J].IEEE Trans. Geosci. Remote Sens.,2008,48(6):2590-2602.
[152] X.S. Liu, W. Xia, B. Wang, et al. An approach based on constrained nonnegativematrix factorization to unmix hyperspectral data[J].IEEE Trans. Geosci. RemoteSens.,2011,49(2):757-772.
[153] R.A. Johnson, D.W. Wiechern. Applied Multivariate Statistical Analysis[M].6thed.Englewood Cliffs,NJ: Prentice-Hall,2007.
[154] H. Yang, Q. Du, H.J. Su,et al. An efficient method for supervised hyperspectral bandselection[J].IEEE Trans. Geosci. Remote Sens.Lett,2011,8(1):138-142.
[155]吴波,张良培,李平湘.高光谱端元自动提取的迭代分解方法[J].遥感学报,2005,9(3):287-292.
[156]吴波,赵银娣,周小成.端元约束下的高光谱混合像元非负矩阵分解[J].计算机工程,2008,34(22):229-230.
[157] Y. Yue, G. Shan, W.D. SUN. Minimum distance constrained nonnegative matrix fac-torizeation for the endmember extraction of hyperspectral images[J].in Proc. of theSPIE,2007,6790:6790151-9.
[158] A. Morten, N. Mikkel, S.J. Larsen. Unmixing of hyperspectral images using bayesiannonnegative matrix factorization with volume prior[C]. MLSP2009,1-18.
[159] D.C. Heinz, C.I. Chang. Fully constrained least squares linear spectral mixture analysismethod for material quantification in Hyperspectral imagery[J].IEEE Trans. Geosci.Remote Sens.,2001,39(3):529-545.
[160] N. Keshava, J.F. Mustard. Spectral unmixing[J].IEEE Signal Process. Mag.,2002,19(1):44-57.
[161] A. Plaza, P. Martinez, R. Perez, et al. A quantitative and comparative analysis ofendmember extraction algorithms from hyperspectral data[J].IEEE Trans. Geosci.Remote Sens.,2004,42(3):650-663.
[162] R. N. Clark, G. A. Swayze, R. Wise, et al. USGS Digital Spectral Library splib05a[C].USGS Open File Report03-395,2003.
[163] J.M. Bioucas-Dias, J.M.P. Nascimento. Hyperspectral subspace identification[J].IEEETrans. Geosci. Remote Sens.,2008,46(8):2435-2445.
[164] M.J. Tax David, P.W Duin Robert. Support Vector Data Description[J]. MachineLearning,2004,54(1):45-66.
[165] X.M. Wang, F.L. Chung, S.T. Wang. Theoretical analysis for solution of support vect-or data description[J].Neural Networks,2011,24:360-369.
[166] B. Qi, C.H. Zhao, E. Youn, et al. Use of weighting algorithms to improve traditionalsupport vector machine based classifications of reflectance data[J].Optics express,2011,19(27):26816-26826.