独立分量分析在遥感图像土地覆盖信息提取中的应用
|
摘要
近年来，在城市化过程中，城市及其周边地区土地覆盖状况频繁变化，从城市土地利用以及预防各类灾害的角度出发，如何对这些变化情况进行有效的监测，一直是科技工作者们的重点研究方向。另外，随着遥感传感器技术的进步，遥感技术已经能够大量地获取地表土地覆盖信息，但是如何能够从这些遥感数据中精确地提取出地表土地覆盖信息则成为土地覆盖变化监测的热点和难点。
独立分量分析(independent component analysis, ICA)作为一种盲源分离技术，能够有效地从观测混合信号中分离出源信号。支持向量机(support vectormachine, SVM)能够将低维空间中难以进行线性划分的数据信息非线性映射到高维特征空间中，并通过结构风险最小化原则实现地物信息的非线性分类提取。两者在遥感图像土地覆盖信息提取中都具有巨大的应用潜力。本文对ICA和SVM方法及其在遥感图像土地覆盖信息提取中的应用进行了深入的研究，主要体现在以下几个方面：
(1)针对传统ICA模型在遥感图像土地覆盖信息提取中的现状，提出了变分贝叶斯ICA(variational Bayesian ICA)方法。通过将贝叶斯网络引入到ICA模型中，根据贝叶斯推论来计算遥感图像中不同地物成分的后验概率分布，并利用变分近似算法进行简化，使分离出的地物成分信息尽可能接近地表真实分布情况。遥感图像分析结果表明，变分贝叶斯ICA方法稳定性好，分离程度较高，且分离出的各地物成分信息目视效果较好。
(2)在综合考虑变分贝叶斯ICA和SVM算法以及遥感图像特点的基础上，提出了变分贝叶斯ICA和SVM相结合的遥感图像土地覆盖信息提取方法。遥感图像土地覆盖信息提取结果表明，变分贝叶斯ICA和SVM相结合方法具有较强的抗噪性和普适性，且提取精度高，目视效果好。
(3)将变分贝叶斯ICA和SVM相结合方法应用到重庆都市核心区遥感图像土地覆盖信息提取研究中，分别提取出1988年和2007年的各类型土地覆盖信息，并对其时空变化进行了分析。结果表明，城市建设用地主要向东北方向扩展。在土地覆盖信息提取应用中所采用的提取原理和技术流程对其它山区城市的土地覆盖信息提取和变化研究具有重要的借鉴意义。
In recent years, the land cover information of the cities and their surroundingareas keeps changing frequently in the rapid urbanizing process. So from theperspective of the urban land use and the prevention of disasters, how to effectivelymonitor these changes has always been the key researching direction for scientificand technical workers. Besides, with the development of remote sensor technology,remote sensing (RS) has been able to acquire a good deal of land cover information;however, how to extract the precise land cover information out of these RS databecomes a hot and difficult issue in the monitoring of land cover changes.
As a kind of blind source separation (BSS) technology, independent componentanalysis (ICA) is able to separate the source signals from the observing mixedsignals. Support vector machine (SVM) can nonlinear map the sample data which ishard to be linear separated in low dimensional space to high dimensional featurespace, and finally fulfill the nonlinear classification and extraction of the sample dataaccording to the structural risk minimization principle (SRM). They both havetremendous applicable potentials in RS image land cover information extraction.This paper has delved into ICA, SVM and their application in RS image land coverinformation extraction, which are mainly embodied in the following aspects:
(1) Aiming at the actuality of ICA model in the extraction of RS image landcover information, this study puts forward the method of variational Bayesian ICA,whose working principle is that through the introduction of Bayesian network intoICA model, work out the posterior probability distribution of different types ofground objects with Bayesian inferences and get the simplification with the aid ofvariational approximate algorithm, so as to make the independent componentsseparated from ground objects approach the earth surface real distribution as muchas possible. RS image analyzing results indicate that variational Bayesian ICA hasthe advantages of good stability, high separation degree, and good visual effect.
(2) On the basis of a comprehensive consideration of variational Bayesian ICA,SVM algorithm and RS image features, this study puts forward a RS image landcover information extraction method with the combination of variational BayesianICA and SVM. The extraction result shows that the combined method is equippedwith a high noise immunity, universality, extraction precision and visual effect.
(3) This paper tries to apply the combination of variational Bayesian ICA andSVM into the study of the RS image land cover information extraction of Chongqingurban core areas, and has extracted each type of the land cover information in1988and2007respectively, and has given an analysis of their temporal&spatial variation.It turns out that the urban construction land is mainly expanding toward the northeast.The extraction principle and technique process in the application of RS image landcover information extraction has great referential significance for the land coverinformation extraction and the study of the changes in other hilly cities.
独立分量分析(independent component analysis, ICA)作为一种盲源分离技术，能够有效地从观测混合信号中分离出源信号。支持向量机(support vectormachine, SVM)能够将低维空间中难以进行线性划分的数据信息非线性映射到高维特征空间中，并通过结构风险最小化原则实现地物信息的非线性分类提取。两者在遥感图像土地覆盖信息提取中都具有巨大的应用潜力。本文对ICA和SVM方法及其在遥感图像土地覆盖信息提取中的应用进行了深入的研究，主要体现在以下几个方面：
(1)针对传统ICA模型在遥感图像土地覆盖信息提取中的现状，提出了变分贝叶斯ICA(variational Bayesian ICA)方法。通过将贝叶斯网络引入到ICA模型中，根据贝叶斯推论来计算遥感图像中不同地物成分的后验概率分布，并利用变分近似算法进行简化，使分离出的地物成分信息尽可能接近地表真实分布情况。遥感图像分析结果表明，变分贝叶斯ICA方法稳定性好，分离程度较高，且分离出的各地物成分信息目视效果较好。
(2)在综合考虑变分贝叶斯ICA和SVM算法以及遥感图像特点的基础上，提出了变分贝叶斯ICA和SVM相结合的遥感图像土地覆盖信息提取方法。遥感图像土地覆盖信息提取结果表明，变分贝叶斯ICA和SVM相结合方法具有较强的抗噪性和普适性，且提取精度高，目视效果好。
(3)将变分贝叶斯ICA和SVM相结合方法应用到重庆都市核心区遥感图像土地覆盖信息提取研究中，分别提取出1988年和2007年的各类型土地覆盖信息，并对其时空变化进行了分析。结果表明，城市建设用地主要向东北方向扩展。在土地覆盖信息提取应用中所采用的提取原理和技术流程对其它山区城市的土地覆盖信息提取和变化研究具有重要的借鉴意义。
In recent years, the land cover information of the cities and their surroundingareas keeps changing frequently in the rapid urbanizing process. So from theperspective of the urban land use and the prevention of disasters, how to effectivelymonitor these changes has always been the key researching direction for scientificand technical workers. Besides, with the development of remote sensor technology,remote sensing (RS) has been able to acquire a good deal of land cover information;however, how to extract the precise land cover information out of these RS databecomes a hot and difficult issue in the monitoring of land cover changes.
As a kind of blind source separation (BSS) technology, independent componentanalysis (ICA) is able to separate the source signals from the observing mixedsignals. Support vector machine (SVM) can nonlinear map the sample data which ishard to be linear separated in low dimensional space to high dimensional featurespace, and finally fulfill the nonlinear classification and extraction of the sample dataaccording to the structural risk minimization principle (SRM). They both havetremendous applicable potentials in RS image land cover information extraction.This paper has delved into ICA, SVM and their application in RS image land coverinformation extraction, which are mainly embodied in the following aspects:
(1) Aiming at the actuality of ICA model in the extraction of RS image landcover information, this study puts forward the method of variational Bayesian ICA,whose working principle is that through the introduction of Bayesian network intoICA model, work out the posterior probability distribution of different types ofground objects with Bayesian inferences and get the simplification with the aid ofvariational approximate algorithm, so as to make the independent componentsseparated from ground objects approach the earth surface real distribution as muchas possible. RS image analyzing results indicate that variational Bayesian ICA hasthe advantages of good stability, high separation degree, and good visual effect.
(2) On the basis of a comprehensive consideration of variational Bayesian ICA,SVM algorithm and RS image features, this study puts forward a RS image landcover information extraction method with the combination of variational BayesianICA and SVM. The extraction result shows that the combined method is equippedwith a high noise immunity, universality, extraction precision and visual effect.
(3) This paper tries to apply the combination of variational Bayesian ICA andSVM into the study of the RS image land cover information extraction of Chongqingurban core areas, and has extracted each type of the land cover information in1988and2007respectively, and has given an analysis of their temporal&spatial variation.It turns out that the urban construction land is mainly expanding toward the northeast.The extraction principle and technique process in the application of RS image landcover information extraction has great referential significance for the land coverinformation extraction and the study of the changes in other hilly cities.
引文
【1】. Herault, J., Jutten, C. Space or time adapetive processing by neural network models[C].In Denker J.S.(ed), editor, Neural networks for computing: AIP conferenceproceddings151, New York,1986.
【2】. Hyvarinen A., Karhunen J., Oja E. Independent Component Analysis[M]. New York,John Wiley＆Sons,2001.
【3】.史振威.独立分量分析的若干算法及其应用研究[D].大连理工大学博士学位论文,2005.
【4】. Comon P., Jutten C., Herault J. Blind separation of sources, Part Ⅱ: problemsstatement[J]. SignalProcessing,1991,(24):11-20.
【5】. Comon P. Independent component analysis-a new concept?[J]. Signal Processing,1994,(36):387-314.
【6】. Bell A., Sejnowski T. An information-maximization approach to blind separation andblind deconvolution[J]. Neural Computation,1995,7(6):1129-1159.
【7】. Amari S.I., Cichocki A., Yang H.H. A new learning algorithm for blind sourceseparation[J]. Advances in Neural Information Processing System,1996,(8):757-763.
【8】. Hyvarinen A., Oja E. A fastfixed-point algorithm for independent componentanalysis[J]. Neural Computation,1997,9(7):1483-1492.
【9】. Hyvarinen A. Fast and robust fixed-point algorithm for independent componentanalysis[J]. IEEE Transaction on Neural Networks,1999,10(3):626-634.
【10】. Hyvarinen A., Oja E. Independent component analysis: algorithms and applications[J].Neural Networks,2000,(13):411-430.
【11】. Roberts S.J., Everson R. Independent component analysis: principles and practice[M].London, Cambridge University Press,2001.
【12】.王明祥,莫玉龙.一种基于FastICA的运动目标检测新方法[J].计算机工程,2004,30(3):58-60.
【13】. Cardoso J.F., Laheld B.H. Equivariant adative source separation[J]. IEEE Transactionson Signal Processing,1996,44(12):3017-3030.
【14】.曾生根,王小敏,范瑞斌,夏德深.基于独立分量分析的遥感图像分类技术[J].遥感学报,2004,8(2):150-157.
【15】.彭迪,王毅.一种改进的基于ICA特征空间的高空间分辨率影像的目标识别[J].计算机应用技术,2010,(22):100-103.
【16】. Girolami M. An alternative perspective on adapetive independent component analysisalgorithms[J]. Neural Computation,1998,10(10):2103-2114.
【17】. Girolami M. Self-organising neural networks: independent component analysis andblind source separation[M]. London, Springer Verlag,1999.
【18】. Lee T.W., Girolami M., Sejnowski T. Independent component analysis using anextended infomax algorithm for mixed subgaussian and supergaussian sources[J].Neural Computation,1999,11(2):417-441.
【19】. Hyvarinen A. Independent component analysis in the presence of Gaussian noise bymaximizing joint likeihood[J]. Neurocomputing,1998,22(1-3):49-67.
【20】. Hyvarinen A. Independent component analysis for time-dependent stochasticprocess[C]. Inproceedings of the International Conference on Artificial NeuralNetworks, Skovde, Sweden,1998:135-140.
【21】. Zhang M.J., Tang H.W., Wang H.L., Tang Y.Y. An EM algorithm for independentcomponent analysis in the presence of Gaussian noise[J]. Neural InforamtionProcessing:letters and Reviews,2004,2(1):11-17.
【22】. Hyvarinen A. Complexity pursuit: separating interesting components fromtime-series[J]. Neural Computation,2001,13(4):883-898.
【23】. Douglas S.C., Gupta M., Sawada H., Makino S. Spatio-temporal FastICA algorithmsfor the blind separation of convolutive mixtures[J]. IEEE Transaction on Audio,Speech, and Language Processing,2007,15(5):1511-1520.
【24】. Harmeling S., Ziehe A., Kawanabe M., Muller K.R. Kernel-based nonlinear blindsource separation[J]. Neural Computation,2003,(15):1089-1124.
【25】. Hyvarinen A., Pajunen P. Nonlinear independent component analysis: exiatence anduniqueness[J]. Neural Networks,1999,(12):429-439.
【26】. Lappalainen H., Honlela A. Bayesian nonlinear independent component analysis bymulti-layer perceptrons[C]. Girolami, M(ed), Advances in Independent ComponentAnalysis, Springer,2000:93-121.
【27】. Pham D.T., Cardoso J.F. Blind separation of instantaneous mixtures of nonstationarysources[J]. IEEE Transactions on Signal Processing,2001,49(9):1837-1848.
【28】. Sanchez A.V.D. Frontiers of research in BSS/ICA[J]. Neurocomputing,2002,(49):7-23.
【29】. Jutten C., Herault J. Blind separation of sources, PartⅠ: an adaptive algorithm basedon neuromimetic architecture[J]. Signal Processing,1991,(24):1-10.
【30】. Sorouchyari E. Blind separation of sources, Part Ⅲ: stability analysis[J]. SignalProcessing,1991,(24):21-29.
【31】. Nascimento J.M.P., Dias J.M.B. Does independent component analysis play a role inunmixing hyperspectral data?[J]. IEEE Transactions on Geoscience and RemoteSensing,2005,43(1):175-187.
【32】.周宗潭,董国华,徐昕,胡德文等译.独立成分分析[M].北京:电子工业出版社,2007.
【33】.梁亮,杨敏华,李英芳.基于ICA与SVM算法的高光谱遥感影像分类[J].光谱学与光谱分析,2010,30(10):2724-2728.
【34】. Chang C.I., Chiang S.S., Smith J.A., Ginsberg I.W. Linear spectral random mixtureanalysis for hyperspectral imagery[J]. IEEE Transactions on Geoscience and RemoteSensing,2002,40(2):375-392.
【35】. Nascimento J.M.P., Dias J.M.B. Independent component analysis applied to unnixinghyperspectral data[A], In: Proceedings of SPIE Image and Signal Processing forRemote Sensing Ⅸ[C], Bellingham, WA,2004,(5238):306-315.
【36】. Wang J., Chein C. Independent component analysis-based dimensionality reductionwith applications in hyperspectral image analysis[J]. IEEE Transactions on Geoscienceand Remote Sensing,2006,44(6):1586-1600.
【37】.罗文斐,钟亮,张兵,高连如.高光谱遥感图像光谱解混的独立成分分析技术[J].光谱学与光谱分析,2010,30(6):1628-1633.
【38】.胡文婷,董海燕,戚玉玺,田涛.一种用于多光谱纹理分类的ICA多尺度算子[J].青岛理工大学学报,2011,32(1):87-92.
【39】. Chen C.H., Zhang X.H. Independent component analysis for remote sensing study[C].Part of the EUROPTO Conference on Image and Signal Processing for RemoteSensing Ⅴ. SPIE,1999,(3871):150-155.
【40】.易尧华,余长慧,秦前清,龚健雅.基于独立分量分析的遥感影像非监督分类[J].武汉大学学报(信息科学版),2005,30(1):19-22.
【41】.张飞,塔西普拉提·特依拜,丁建丽,买买提·沙吾提,田源. ICA结合纹理特征的SVM盐渍化信息提取研究[J].计算机工程与应用,2010,46(9):193-197.
【42】.宋江琦,黄昕.结合独立分量分析和支持向量机的遥感影像土地覆盖分类[J].广东土地科学,2008,7(4):26-32.
【43】. Vapnik V.N. Statistical Learning Theory[M]. Wiley, New York,1998.
【44】.钱茹茹.遥感图像分类方法比较研究[D].长安大学硕士学位论文,2007.
【45】.王小敏.独立分量分析及其在遥感动态监测中的应用研究[D].南京理工大学博士学位论文,2005.
【46】.刘顺喜.高光谱遥感土地利用信息提取技术研究-以江苏宜兴实验区为例[D].北京林业大学博士学位论文,2005.
【47】. Compoton J.T, John R.G., Thomas E.G. African land cover classification usingsatellite data[J]. Science,1985,227(4685):369-375.
【48】. Maxwell S.K., Hoffer, P.L., Chapman. AVHRR composite period selection for landcover classification[J]. International Journal of Remote Sensing,2002,23(23):5043-5059.
【49】.陈述彭,赵英时.遥感地学分析[M].北京:测绘出版社,1990.
【50】.陈述彭.遥感地学分析的时空维[J].遥感学报,1997,1(3):161-171.
【51】.杨桄,刘湘楠.遥感影像解译的研究现状和发展趋势[J].国土资源遥感,2004,(2):7-10.
【52】.濮静娟.遥感图像目视解译原理与方法[M].北京:科学技术出版社,1992.
【53】.李建利.人机交互式多波段数字图像解译技术方法研究[J].测绘标准,1999,15(2):13-15.
【54】.王涛,阎守邕,王世新.遥感图像人机交互判读系统的关键技术[J].中国科学院研究生院学报,1999,16(2):161-168.
【55】.陈宁强,戴锦芳.人机交互式土地资源遥感解译方法研究[J].遥感技术与应用,1998,13(2):15-20.
【56】.术洪磊,毛赞猷. GIS辅助下的基于知识的遥感影像分类方法研究——以土地覆盖/土地利用类型为例[J].测绘学报,1997,26(4):328-336.
【57】.张若琳,万力,张发旺,石迎春.土地利用遥感分类方法研究进展[J].南水北调与水利科技,2006,4(2):39-42.
【58】.傅肃性.遥感专题分析与地学图谱[M].北京:科学出版社,2002.
【59】.孙家抦.遥感原理与应用[M].武汉:武汉大学出版社,2002.
【60】.李石华,王金亮,毕艳,陈姚,朱妙园,杨帅,朱佳.遥感图像分类方法研究综述[J].国土资源遥感,2005,(2):1-6.
【61】.王一达,沈熙玲,谢炯.遥感图像分类方法综述[J].遥感信息,2006,(5):67-71.
【62】. SanRen H., CheinI C.I. A generalized orthogonalal subspace projection approach tounsupervised multi-spectral image classification[J]. IEEE TransactionS on Geoscienceand Remote Sensing,2000,38(6):2515-2528.
【63】.闫琰,董秀兰,李燕.基于ENVI的遥感图像监督分类方法比较研究[J].北京测绘,2011,(3):14-16.
【64】.高恒振,万建伟,许可,钱林杰.基于聚类核函数的最小二乘支持向量机高光谱图像半监督分类[J].信号处理,2011,27(2):276-280.
【65】.熊彪,江万寿,李乐林.基于高斯混合模型的遥感影像半监督分类[J].武汉大学学报(信息科学版),2011,36(1):108-112.
【66】. Ediriwickrema J., Khorram S. Hierarchical Maximum-Likelihood Classification forImproved Accuracies[J]. IEEE Transactions on Geoscience and Remote Sensing,1997,35(4):810-816.
【67】. Yamazaki T., Gingras D. Image Classification Using Spectral and Information Basedon MAR Models[J]. IEEE Transaction on Image Processing,1995,14(9):1333-1339.
【68】. Mclachlang J., Basford K.E. The EM Algorithm and Extensions[M]. New York:JohnWiley,1997.
【69】. Salu Y., Tilton J. Classification of multispectral image data by the binary diamondneural network and by nonparametric, pixel-by-pixel methods[J]. IEEE TransactionsOn Geoscience and Remote Sensing,1993,31(3):606-617.
【70】. Duda T., Canty M. Unsupervised classification of satellite imagery: choosing a goodalgorithm[J]. International Journal of Remote Sensing,2002,23(11):2193-2212.
【71】. Chamundeeswari V.V., Singh D., Singh K. An analysis of texture measures inPCA-based unsupervised classification of SAR images[J]. IEEE Transaction andRemote Sensing Letters,2009,6(2):214-218.
【72】. Ifarraguerri Agustin, Chein Ichang. Unsupervised hyperspectral image analysis withprojection on pursuit[J]. IEEE Transactions onGeoscience and Remote Sensing,2000,38(6):2529-2538.
【73】.王圆圆,李京.遥感影像土地利用/土地覆盖分类方法研究综述[J].遥感信息,2004,(1):53-59.
【74】. Flygare A.M. A comparison of contextural classification methods using landsat TM[J].International Journal of Remote Sensing,1997,18(18):3885-3842.
【75】. Franklin S.E., Peddle D.R. Spectrumtexture for improved class discrimanation incomplex terrain[J]. International Journal of Remote Sensing.1989,10(8):1437-1443.
【76】.朱长青,杨启和,朱文忠.基于小波变化特征的遥感地貌影像纹理分析和分类[J].测绘学报,1996,25(4):252-255.
【77】.李厚强,刘政凯,林峰.基于分形理论的航空图像分类方法[J].遥感学报,2001,5(5):353-357.
【78】.张宝光.数学形态学在遥感数字图像分类处理中的应用[J].测绘信息与工程,2000,(2):1-5.
【79】. Hellwich O., Wiedemann C. Object extraction from high-resolution multisensor imagedata[C]. In:3rd International Conference on Fusion of Earth Data, Sophia Antipolis,France,26-28January2000, SEE GreCA, Nice:105-115.
【80】. Ehrlich D., Lambin, E.F. Broad scale land-cover classification and internal climaticvariability[J]. International Journal of Remote Sensing,1996,17(5):845-862.
【81】. Defries R.S., Townshend, J.R.G. NDVI-derived land cover classification at a globalscale[J]. International Journal of Remote Sensing,1994,15(17):3567-3586.
【82】.龙飞,赵英时. NOAA卫星角度信息在分类中的有效性研究[J].中国科学院研究生院学报,2002,19(1):69-74.
【83】.贾永红.人工神经网络在多源遥感影响分类中的应用[J].测绘通报,2000,(7):7-8.
【84】.李朝峰,王桂梁.模糊控制BP网络的遥感图像分类方法研究[J].中国矿业大学学报(自然科学版),2001,30(3):311-314.
【85】. Rumelhart D.E., McClelland J.L., PDP Research Group. Parallel distributed processing:explorations in the microstructure of cognition, Volume1: Foundations[M], MIT Press,Cambridge, MA,1986.
【86】. Mural H., Omatu S. Remote sensing image analysis using a neural network andknowledge-based processing[J]. Remote sensing,1997,18(4):811-828.
【87】.蔡煜东,李伟,许伟杰.遥感土地覆盖类型识别的自组织人工神经网络模型[J].国土资源遥感,1994,(4):63-66.
【88】.孙丹峰,汲长远,林培.自组织网络在遥感土地覆盖分类中应用研究[J].遥感学报,1999,3(2):139-143.
【89】.任军号,吉沛琦,耿跃. SOM神经网络改进及在遥感图像分类中的应用[J].计算机应用研究,2011,28(3):1170-1182.
【90】.骆剑承,周成虎,杨艳.基于径向基函数(RBF)映射理论的遥感影像分类模型研究[J].中国图象图形学报,2000,5(2):94-99.
【91】.巫兆聪.基于粗糙理论的RBF网络及其遥感影像分类应用[J].测绘学报,2003,32(1):53-57.
【92】. Gopal S., Woodcock C.E., Strahler A.H. Fuzzy neural network classification of globalland cover from a10AVHRR data set[J]. Remote Sensing of Environment,1999,(67):230-247.
【93】.刘正军,王长耀,延昊,牛铮，王雷.基于FuzzyARTMAP神经网络的高分辨率图象土地覆盖分类及其评价[J].中国图象图形学报,2003,8(2):151-154.
【94】.林剑,鲍光淑,敬荣中,黄继先. FasART模糊神经网络用于遥感图象监督分类的研究[J].中国图象图形学报,2002,7(2):1263-1268.
【95】.谭琨,杜培军.基于径向基函数神经网络的高光谱遥感图像分类[J].光谱学与光谱分析,2008,28(9):2009-2013.
【96】.杨希,王鹏.基于BP神经网络的高分辨率遥感影像分类[J].测绘,2011,34(3):115-118.
【97】.裴亮,谭阳,李文杰.基于变差函数和神经网络的遥感影像分类[J].遥感信息,2009,(1):60-65.
【98】.骆剑承,周成虎,杨艳.具有部分监督的遥感影像模糊聚类方法研究及应用[J].遥感技术与应用,1999,14(4):37-43.
【99】. Zhang J., Foody G.M. A fuzzy classification of sub-urban land cover from remotelysensed imagery[J]. International Journal of Remote Sensing,1998,19(14):2721-2738.
【100】.毛建旭,王耀南,孙炜.基于模糊小脑模型神经网络的遥感图像分类算法[J].测绘学报,2002,31(4):327-332.
【101】.张宝光.论遥感数字图像的模糊分类处理[J].天津师范大学学报(自然科学版),2005,25(2):69-72.
【102】.黎夏,叶嘉安,廖其芳.利用案例推理(CBR)方法对雷达图像进行土地利用分类[J].遥感学报,2004,8(3):246-253.
【103】.黎夏,刘凯,王树功.珠江口红树林湿地演变的遥感分析[J].地理学报,2006,61(1):26-34.
【104】.霍宏涛,王任华,游先祥.三维及相关辅助信息在提高图像分类精度中的研究[J].北京林业大学学报,2001,23(2):29-31.
【105】. Huang C., Davis L.S., Townshend J.R.G. An assessment of support vector machine forland cover classification[J]. International Journal of Remote Sensing,2002,23(4):725-749.
【106】.骆剑承,周成虎,梁怡,马江洪.支持向量机及其遥感影像空间特征提取和分类的应用研究[J].遥感学报,2002,6(1):50-55.
【107】. Defries R.S., Hansen M., Townshend J.R.G., Sohiberg R. Global land coverclassification at8km spatial resolution: the use of training data derived from landsatimagery in decision tree classification[J]. International Journal of Remote Sensing,1998,19(16):3141-3168.
【108】.李敏,赵庚星,李百红.基于遥感的乡镇级棉花面积提取与长势监测研究[J].山东农业大学学报(自然科学版),2011,42(4):533-538.
【109】.郭伟,赵春江,顾晓鹤,黄文江,马智宏,王慧芳,王大成.乡镇尺度的玉米种植面积遥感监测[J].农业工程学报,2011,27(9):69-74.
【110】.于文颍,冯锐,纪瑞鹏,张玉书,陈鹏狮,赵先丽,武晋雯.基于MODIS数据的水稻种植面积提取研究进展[J].气象与环境学报,2011,27(2):56-61.
【111】.苗翠翠,江南,彭世揆,吕恒,李杨,张瑜,王妮,李军.基于NDVI时序数据的水稻种植面积遥感监测分析[J].地球信息科学学报,2011,13(2):273-280.
【112】. Weiss E., Pfirman E.S., Marsh S.E. Application of NOAA-AVHRR NDVI time-serialdata to assess changes in Saudi Arabia’s rangelands[J]. International Journal of RemoteSensing,2001,22(6):1005-1027.
【113】.李爽,张二勋.基于决策树的遥感影像分类方法研究[J].地域研究与开发,2003,22(1):17-21.
【114】. Tucker C.J., Newcomb W.W., Dregne H.E. AVHRR data sets for determination ofdesert spatial extent[J]. International Journal of Remote Sensing,1994,15(17):3547-3565.
【115】. Yu F., Price K.P., Ellis J., Feddema J.J., Shi P. International variations of the grasslandboundaries bording the eastern edges of the Godi Desert in central Asia[J].International Journal of Remote Sensing,2004,25(2):327-345.
【116】. Http://www. agit. at/papers/2000/baatz-FP-12.pdf
【117】. Mauro C., Eufemia T. Accuracy assessment of per-field classification integrating veryfina spatial resolution satellite imagery with topographic data[J]. Journal of GeospatialEngineering,2001,3(2):127-134.
【118】. Benz U.C., Hofmann P., Willhauck G., Lingenfelder I., Heynen M. Multi-resolutionobject-oriented fuzzy analysis of remote sensing data for GIS-ready information[J].ISPRS Journal of Photogrammetry＆Remote Sensing,2004,(58):239-258.
【119】.曹雪,柯长青.基于对象级的高分辨率遥感影像分类研究[J].遥感信息,2006,(5):27-30.
【120】.张宝雷,周万村,马泽忠.三峡地区主要地类的自动提取方法研究[J].长江流域资源与环境,2005,14(4):446-449.
【121】.黄慧萍,吴炳方,李苗苗,周为峰,王忠武.高分辨率影像城市绿地快速提取技术与应用[J].遥感学报,2004,8(1):68-74.
【122】.曾涛,杨武年,黎小东,刘汉湖,彭立,简季.面向对象的高空间分辨率遥感影像信息提取——汶川地震城市震害房屋案例研究[J].自然灾害学报,2010,19(5):81-87.
【123】.龚健雅,姚璜,沈欣.利用AdaBoost算法进行高分辨率影像的面向对象分类[J].武汉大学学报(信息科学版),2010,35(12):1440-1448.
【124】.范磊,程永政,王来刚,刘婷,胡峰,冯晓.基于多尺度分割的面向对象分类方法提取冬小麦种植面积[J].中国农业资源与区划,2010,31(6):44-51.
【125】.陈燕丽,莫伟华,莫建飞,王君华,钟仕全.基于面向对象分类的南方水稻种植面积提取方法[J].遥感技术与应用,2011,26(2):163-168.
【126】.安如,陈志霞,陆玲,杨仁敏,李晓雪,吴红,龚天宇,曲春梅.面向对象的黄河源典型区湿地信息提取[J].河海大学学报(自然科学版),2011,39(4):355-360.
【127】.莫源富,周立新.分区分类法针对山区遥感图像的一种有效的分类方法[J].中国岩溶,2000,19(4):360-365.
【128】.段四波,阎广建,穆西晗,沈斌,李小文.基于DEM的山区遥感图像地形校正方法[J].地理与地理信息科学,2007,23(6):18-22.
【129】.王瑞燕,于振文,赵庚星,周伟.耕地地力调查中北方平原-山地复合区耕地资源遥感提取方法[J].农业工程学报,2011,27(7):306-311.
【130】.刘咏梅,李锐,杨勤科.基于影像融合的陕北黄土丘陵沟壑区土地利用自动分类[J].中国水土保持科学,2004,2(4):6-10.
【131】.王增柱,刘同怀,黄鲁.基于光谱分类的超光谱数据压缩方法[J].遥感技术与应用,2001,16(3):148-152.
【132】. Vermote E.F., Tanre D., Deuze J.L., Herman M., Morcette J.J. Second simulation of thesatellite signal in the solar spectrum,6S: an overview[J]. IEEE Transactions onGeoscience and Remote Sensing,1997,35,(3):675-686.
【133】.阎福礼,王世新,周艺,肖青,祝令亚,王丽涛,焦云清.利用Hypersion星载高光谱传感器监测太湖水质的研究[J].红外与毫米波学报,2006,25(6):460-464.
【134】. Richanl B. EO-1user guide v.2.2.[R]. University of Cincinnati. July15,2003.available at: http://EOS.usgs.gov.
【135】.田庆久,张良培,郑兰芬,童庆禧.成像光谱遥感定标模型的分析与评价[J].遥感技术与应用,1996,11(3):16-21.
【136】. Stanz K., Szeredi T., Schwarz J. ISDAS-a system for proceeding/analyzinghyperspectral data[J]. Candian Journal of Remote Sensing,1998,(24):99-113.
【137】. Winter M.E. N-FINDER: An algorithm for fast autonomous spectral endmemberdetermination in hyperspectral data[A]. Proceedings of SPIE Conference ImagingSpectrometryⅤ[C],1999,(3753):266-275.
【138】. Bateson C.A., Curtiss B. A tool for manual endmember selection ans spectralunmixing[R]. in Summaries of the Ⅴ JPL Airborne Earth Science Worshop, Pasadena,CA,1993.
【139】. Boardmen J.W., Kruse F.A., Green R.O. Mapping target signatures vis partialunmixing of AVIRIS data in Summaries[J]. Fifth JPL Airborne Earth ScienceWorkshop,1995,(1):23-26.
【140】. Bowles J.H., Palmadesso P.J., Antoniades J.A., Baumback M.M., Richard L.J. Use offilter vectors in hyperspectral data analysis[A]. Scholl M.S., Andreson B.F., Editors,Infrared Spaceborne Remote Sensing Ⅲ, Proc. SPIE1995, Vol.2553,148-157.
【141】. Craig M.D. Minimum volum transforms for remotely sensed data[J]. IEEETransactions on Geoscience and Remote Sensing,1994,32(3):542-552.
【142】. Nascimento J.M.P., Dias J.M.B. Vertex component analysis: a fast algorithm to unmixhyperspectral data[J]. IEEE Transactions on Geoscience and Remote Sensing,2005,43(4):898-910.
【143】.夏学齐,田庆久,杜凤兰.高光谱遥感图像的单形体分析方法[J].中国图象图形学报,2004,9(12):1486-1491.
【144】.李二森,徐波,李娜,周小明.最小体积约束的线性光谱解混算法[J].武汉大学学报(信息科学版),20111,36(6):683-686.
【145】.王立国,张晶,刘丹凤,王群明.从端元选择到光谱解混的距离测算方法[J].红外与毫米波学报,2010,29(6):471-475.
【146】.方勇,王明祥.基于自组织映射的后非线性独立分量分析的初始化方法[J].电子学报,2005,(5):889-892.
【147】.赵立权,贾雁飞.改进的快速独立分量分析方法研究[J].计算机工程与应用,2010,46(27):128-130.
【148】. Habib T., Inglada J., Mercier G., Chanussot J. Support vector reduction in svmalgorithm for abrupt change detection in remote sensing[J]. IEEE Geoscience andRemote Sensing Letters,2009,6(3):606-610.
【149】. Mountrakis G., Irn J., Ogole C. Support vector machines in remote sensing: a review[J].ISPRS Journal of Photogremmetry and Remote Sensing,2011,66(3):247-259.
【150】.朱海洲,贾银山.基于支持向量机的遥感图像分类研究[J].科学技术与工程,2010,10(15):3659-3663.
【151】.谢亮.基于独立分量分析特征提取方法的研究及其应用[D],浙江师范大学硕士学位论文,2006.
【152】. Cichocki A., Unbehauen R. Robust neural networks with on-line learning for blindidentification and blind separation of sources[J]. IEEE Transactions on Circuits andsystems,1996,43(11):894-906.
【153】. Oja E. Neural networks, principal components, and subspace[J]. International Journalon Neural Syatem,1989,(1):61-68.
【154】.曾生根.快速独立分量分析方法及其在图像分析中的若干应用研究[D].南京理工大学博士学位论文,2004.
【155】.罗江华.贝叶斯网络在机械故障诊断中的应用研究[D].重庆大学博士学位论文,2006.
【156】.刘凯.贝叶斯网络维修决策系统的开发与应用研究[D].国防科学技术大学博士学位论文,2004.
【157】.范涛.基于变分贝叶斯独立分量分析的机械故障诊断方法研究[D].郑州大学硕士学位论文,2009.
【158】. Http://baike.baidu.com/view/943316.htm.
【159】.黄青华.基于原信号模型的盲分离技术研究及应用[D].上海交通大学博士学位论文,2007.
【160】. Finneti B.D. Theory of Probability:A Critical Introductory Treatment[M]. New York:John Wiley＆Sons,1970.
【161】. Gelman A., Carlin J., Stern H. Rubin D. Bayesian data analysis[M]. Boca Raton:Chapman&Hall/CRC Press,1995.
【162】. Miskin J.W. Ensemble Learning for Independent Component Analysis[D]. Ph.D.Thesis, University of Cambridge,2000.
【163】.温奇,马建文.基于贝叶斯网络的遥感数据处理软件[J].2008,34(24):10-12.
【164】.陈雪,马建文,戴芹.基于贝叶斯网络分类的遥感影像变化监测[J].遥感学报,2005,9(6):667-672.
【165】.戴芹,马建文,李启青,陈雪,冯春.遥感数据的贝叶斯网络分类研究[J].电子与信息学报,2005,27(11):1782-1785.
【166】. Cardoso J.F. Blind beam forming for non-Gaussian signals[J]. Radar and SignalProcessing, IEEE Proceedings F,1993,140(6):362-370.
【167】.曾生根,王小敏,范瑞斌,夏德深.基于独立分量分析的遥感图像分类计数[J].遥感学报,2004,8(2):150-157.
【168】. Hyvarinen A. Survey on Independent Component Analysis [J]. Neural ComputingSurveys,1999,(2):94-128.
【169】.王小敏,曾生根,夏德深.基于松弛因子改进FastICA算法的遥感图像分类方法[J].计算机研究与发展,2006,43(4):708-715.
【170】.李国正,王猛,曾华军译,支持向量机导论[M].北京:电子工业出版社,2004.
【171】.曾志华,张银奎等译.机器学习[M].北京:机械工业出版社,2003.
【172】.梁力文.基于支持向量机的小波滤噪短波近红外光谱在药品定量分析中的研究
[D].吉林大学博士学位论文,2009.
【173】. Vapnik V.N. The nature of statistical learning theory[M]. New York: Spring VerlagPress,1995.
【174】.杨强.支持向量机的模型及其在图像分割中的应用[D].重庆大学博士学位论文,2004.
【175】.刘勇.基于空间信息技术的土地生态风险评价研究[D].上海大学博士学位论文,2008.
【176】.张学工.关于统计学习理论与支持向量机[J].自动化学报,2002,16(1):32-42.
【177】.柳回春,马树元.支持向量机的研究现状[J].中国图象图像学报,2002,7(6):618-623.
【178】. Vapnik V.N., Chervonenkis A. Necessary and sufficient sinditions for the uniformconverhence of means to their experctations[J]. Theory of Probability and itsApplications,1981,26(30):532-553.
【179】. Vapnik V.N., Chervonenkis A. The necessary and sufficient conditions for consistencyin the empirical risk minimization method[J]. Pattern Recognition and Image Analysis,1991,1(3):283-305.
【180】. Bishop C.M., Lawrence N.D. Variational Bayesian independent componentanalysis[D]. Ph.D. Thesis, University of Cambridge,2000.
【181】. Choudrey R.A. Variational Methods for Bayesian Independent ComponentAnalysis[D]. Ph.D. Thesis, University of Oxford,2002.
【182】.曲炜.信息论基础与应用[M].北京:清华大学出版社,2005.
【183】.徐尚志.盲信号分离算法的研究[D].中国科学技术大学博士学位论文,2005.
【184】. Choudrey R.A. Flexible Bayesian independent component analysis for blind sourceseparation[C]. Proceeding of ICA-2001, San Diego, USA, December2001.
【185】.许雯,董林,田家斌.一种改进的高斯混合模型算法[J].信息工程大学学报,2005,(2):12-16.
【186】. Jordan M. An introduction to variational methods in graphical models[J]. Mechanicallearning,1999,37(2):183-233.
【187】. Jordan M. Bayesian parameter estimation via variational methods[J]. Statistics andComputing,2000,(10):25-37.
【188】. Http://wenku.baidu.com/view/0690dd0e844769eae009ed43.html.
【189】. Munoz-Mari. J., Bovolo F., Gomez-Chova L., Bruzzone L., Camp-Valls G.Semisupervised one-class support vector machines foe classification of remote sensingdata[J]. IEEE Transactions on Geoscience and Remote Sensing,2010,48(8):3188-3197.
【190】.徐芳,燕琴.基于支持向量机的航空影像纹理特征分类研究[J].武汉大学学报(信息科学版),2003,28(5):517-520.
【191】.夏建涛.基于机器学习的高维多光谱数据分类[D].西北工业大学博士学位论文,2002.
【192】.王双亭,艾泽天,都伟兵,康敏.基于SVM不同核函数的多源遥感影像分类研究[J].河南理工大学学报(自然科学版),2011,30(3):304-310.
【193】. Http://www.docin.com/p-116603825.html#documentinfo.
【194】.张力,周廷刚,李成范,吴忠芳.特大型山地城市动态扩展的遥感研究[J].遥感技术与应用,2009,24(1):77-81.
【195】.周成虎,骆剑承,杨晓梅,杨存建,刘庆生.遥感影像地学理解与分析[M].北京:科学出版社,2001.
【196】.赵英时.遥感应用分析原理与方法[M].北京:科学出版社,2003.
【197】.王均,祝武功.清末明初使其北京市城市社会空间的初步研究[J].地理学报,1999,54(1):69-73.
【198】.赵涛.中国城市用地扩展及其驱动机制[D].中科院研究生院博士学位论文,2005.
【199】. Li L., Sato Y., Zhu H.H. Simulating spatial urban expansion based on a physicalprocess [J]. Landscape and Urban Planning,2003,(64):67-76.
【200】.张有全,宫辉力,赵文吉,李小娟.北京市1990年～2000年土地利用变化机制分析[J].资源科学,2007,29(3):206-213.
【201】. Paclone M. The internal structure of cities in the Third World[J]. Geography,2001,86(3):189-209.
【2】. Hyvarinen A., Karhunen J., Oja E. Independent Component Analysis[M]. New York,John Wiley＆Sons,2001.
【3】.史振威.独立分量分析的若干算法及其应用研究[D].大连理工大学博士学位论文,2005.
【4】. Comon P., Jutten C., Herault J. Blind separation of sources, Part Ⅱ: problemsstatement[J]. SignalProcessing,1991,(24):11-20.
【5】. Comon P. Independent component analysis-a new concept?[J]. Signal Processing,1994,(36):387-314.
【6】. Bell A., Sejnowski T. An information-maximization approach to blind separation andblind deconvolution[J]. Neural Computation,1995,7(6):1129-1159.
【7】. Amari S.I., Cichocki A., Yang H.H. A new learning algorithm for blind sourceseparation[J]. Advances in Neural Information Processing System,1996,(8):757-763.
【8】. Hyvarinen A., Oja E. A fastfixed-point algorithm for independent componentanalysis[J]. Neural Computation,1997,9(7):1483-1492.
【9】. Hyvarinen A. Fast and robust fixed-point algorithm for independent componentanalysis[J]. IEEE Transaction on Neural Networks,1999,10(3):626-634.
【10】. Hyvarinen A., Oja E. Independent component analysis: algorithms and applications[J].Neural Networks,2000,(13):411-430.
【11】. Roberts S.J., Everson R. Independent component analysis: principles and practice[M].London, Cambridge University Press,2001.
【12】.王明祥,莫玉龙.一种基于FastICA的运动目标检测新方法[J].计算机工程,2004,30(3):58-60.
【13】. Cardoso J.F., Laheld B.H. Equivariant adative source separation[J]. IEEE Transactionson Signal Processing,1996,44(12):3017-3030.
【14】.曾生根,王小敏,范瑞斌,夏德深.基于独立分量分析的遥感图像分类技术[J].遥感学报,2004,8(2):150-157.
【15】.彭迪,王毅.一种改进的基于ICA特征空间的高空间分辨率影像的目标识别[J].计算机应用技术,2010,(22):100-103.
【16】. Girolami M. An alternative perspective on adapetive independent component analysisalgorithms[J]. Neural Computation,1998,10(10):2103-2114.
【17】. Girolami M. Self-organising neural networks: independent component analysis andblind source separation[M]. London, Springer Verlag,1999.
【18】. Lee T.W., Girolami M., Sejnowski T. Independent component analysis using anextended infomax algorithm for mixed subgaussian and supergaussian sources[J].Neural Computation,1999,11(2):417-441.
【19】. Hyvarinen A. Independent component analysis in the presence of Gaussian noise bymaximizing joint likeihood[J]. Neurocomputing,1998,22(1-3):49-67.
【20】. Hyvarinen A. Independent component analysis for time-dependent stochasticprocess[C]. Inproceedings of the International Conference on Artificial NeuralNetworks, Skovde, Sweden,1998:135-140.
【21】. Zhang M.J., Tang H.W., Wang H.L., Tang Y.Y. An EM algorithm for independentcomponent analysis in the presence of Gaussian noise[J]. Neural InforamtionProcessing:letters and Reviews,2004,2(1):11-17.
【22】. Hyvarinen A. Complexity pursuit: separating interesting components fromtime-series[J]. Neural Computation,2001,13(4):883-898.
【23】. Douglas S.C., Gupta M., Sawada H., Makino S. Spatio-temporal FastICA algorithmsfor the blind separation of convolutive mixtures[J]. IEEE Transaction on Audio,Speech, and Language Processing,2007,15(5):1511-1520.
【24】. Harmeling S., Ziehe A., Kawanabe M., Muller K.R. Kernel-based nonlinear blindsource separation[J]. Neural Computation,2003,(15):1089-1124.
【25】. Hyvarinen A., Pajunen P. Nonlinear independent component analysis: exiatence anduniqueness[J]. Neural Networks,1999,(12):429-439.
【26】. Lappalainen H., Honlela A. Bayesian nonlinear independent component analysis bymulti-layer perceptrons[C]. Girolami, M(ed), Advances in Independent ComponentAnalysis, Springer,2000:93-121.
【27】. Pham D.T., Cardoso J.F. Blind separation of instantaneous mixtures of nonstationarysources[J]. IEEE Transactions on Signal Processing,2001,49(9):1837-1848.
【28】. Sanchez A.V.D. Frontiers of research in BSS/ICA[J]. Neurocomputing,2002,(49):7-23.
【29】. Jutten C., Herault J. Blind separation of sources, PartⅠ: an adaptive algorithm basedon neuromimetic architecture[J]. Signal Processing,1991,(24):1-10.
【30】. Sorouchyari E. Blind separation of sources, Part Ⅲ: stability analysis[J]. SignalProcessing,1991,(24):21-29.
【31】. Nascimento J.M.P., Dias J.M.B. Does independent component analysis play a role inunmixing hyperspectral data?[J]. IEEE Transactions on Geoscience and RemoteSensing,2005,43(1):175-187.
【32】.周宗潭,董国华,徐昕,胡德文等译.独立成分分析[M].北京:电子工业出版社,2007.
【33】.梁亮,杨敏华,李英芳.基于ICA与SVM算法的高光谱遥感影像分类[J].光谱学与光谱分析,2010,30(10):2724-2728.
【34】. Chang C.I., Chiang S.S., Smith J.A., Ginsberg I.W. Linear spectral random mixtureanalysis for hyperspectral imagery[J]. IEEE Transactions on Geoscience and RemoteSensing,2002,40(2):375-392.
【35】. Nascimento J.M.P., Dias J.M.B. Independent component analysis applied to unnixinghyperspectral data[A], In: Proceedings of SPIE Image and Signal Processing forRemote Sensing Ⅸ[C], Bellingham, WA,2004,(5238):306-315.
【36】. Wang J., Chein C. Independent component analysis-based dimensionality reductionwith applications in hyperspectral image analysis[J]. IEEE Transactions on Geoscienceand Remote Sensing,2006,44(6):1586-1600.
【37】.罗文斐,钟亮,张兵,高连如.高光谱遥感图像光谱解混的独立成分分析技术[J].光谱学与光谱分析,2010,30(6):1628-1633.
【38】.胡文婷,董海燕,戚玉玺,田涛.一种用于多光谱纹理分类的ICA多尺度算子[J].青岛理工大学学报,2011,32(1):87-92.
【39】. Chen C.H., Zhang X.H. Independent component analysis for remote sensing study[C].Part of the EUROPTO Conference on Image and Signal Processing for RemoteSensing Ⅴ. SPIE,1999,(3871):150-155.
【40】.易尧华,余长慧,秦前清,龚健雅.基于独立分量分析的遥感影像非监督分类[J].武汉大学学报(信息科学版),2005,30(1):19-22.
【41】.张飞,塔西普拉提·特依拜,丁建丽,买买提·沙吾提,田源. ICA结合纹理特征的SVM盐渍化信息提取研究[J].计算机工程与应用,2010,46(9):193-197.
【42】.宋江琦,黄昕.结合独立分量分析和支持向量机的遥感影像土地覆盖分类[J].广东土地科学,2008,7(4):26-32.
【43】. Vapnik V.N. Statistical Learning Theory[M]. Wiley, New York,1998.
【44】.钱茹茹.遥感图像分类方法比较研究[D].长安大学硕士学位论文,2007.
【45】.王小敏.独立分量分析及其在遥感动态监测中的应用研究[D].南京理工大学博士学位论文,2005.
【46】.刘顺喜.高光谱遥感土地利用信息提取技术研究-以江苏宜兴实验区为例[D].北京林业大学博士学位论文,2005.
【47】. Compoton J.T, John R.G., Thomas E.G. African land cover classification usingsatellite data[J]. Science,1985,227(4685):369-375.
【48】. Maxwell S.K., Hoffer, P.L., Chapman. AVHRR composite period selection for landcover classification[J]. International Journal of Remote Sensing,2002,23(23):5043-5059.
【49】.陈述彭,赵英时.遥感地学分析[M].北京:测绘出版社,1990.
【50】.陈述彭.遥感地学分析的时空维[J].遥感学报,1997,1(3):161-171.
【51】.杨桄,刘湘楠.遥感影像解译的研究现状和发展趋势[J].国土资源遥感,2004,(2):7-10.
【52】.濮静娟.遥感图像目视解译原理与方法[M].北京:科学技术出版社,1992.
【53】.李建利.人机交互式多波段数字图像解译技术方法研究[J].测绘标准,1999,15(2):13-15.
【54】.王涛,阎守邕,王世新.遥感图像人机交互判读系统的关键技术[J].中国科学院研究生院学报,1999,16(2):161-168.
【55】.陈宁强,戴锦芳.人机交互式土地资源遥感解译方法研究[J].遥感技术与应用,1998,13(2):15-20.
【56】.术洪磊,毛赞猷. GIS辅助下的基于知识的遥感影像分类方法研究——以土地覆盖/土地利用类型为例[J].测绘学报,1997,26(4):328-336.
【57】.张若琳,万力,张发旺,石迎春.土地利用遥感分类方法研究进展[J].南水北调与水利科技,2006,4(2):39-42.
【58】.傅肃性.遥感专题分析与地学图谱[M].北京:科学出版社,2002.
【59】.孙家抦.遥感原理与应用[M].武汉:武汉大学出版社,2002.
【60】.李石华,王金亮,毕艳,陈姚,朱妙园,杨帅,朱佳.遥感图像分类方法研究综述[J].国土资源遥感,2005,(2):1-6.
【61】.王一达,沈熙玲,谢炯.遥感图像分类方法综述[J].遥感信息,2006,(5):67-71.
【62】. SanRen H., CheinI C.I. A generalized orthogonalal subspace projection approach tounsupervised multi-spectral image classification[J]. IEEE TransactionS on Geoscienceand Remote Sensing,2000,38(6):2515-2528.
【63】.闫琰,董秀兰,李燕.基于ENVI的遥感图像监督分类方法比较研究[J].北京测绘,2011,(3):14-16.
【64】.高恒振,万建伟,许可,钱林杰.基于聚类核函数的最小二乘支持向量机高光谱图像半监督分类[J].信号处理,2011,27(2):276-280.
【65】.熊彪,江万寿,李乐林.基于高斯混合模型的遥感影像半监督分类[J].武汉大学学报(信息科学版),2011,36(1):108-112.
【66】. Ediriwickrema J., Khorram S. Hierarchical Maximum-Likelihood Classification forImproved Accuracies[J]. IEEE Transactions on Geoscience and Remote Sensing,1997,35(4):810-816.
【67】. Yamazaki T., Gingras D. Image Classification Using Spectral and Information Basedon MAR Models[J]. IEEE Transaction on Image Processing,1995,14(9):1333-1339.
【68】. Mclachlang J., Basford K.E. The EM Algorithm and Extensions[M]. New York:JohnWiley,1997.
【69】. Salu Y., Tilton J. Classification of multispectral image data by the binary diamondneural network and by nonparametric, pixel-by-pixel methods[J]. IEEE TransactionsOn Geoscience and Remote Sensing,1993,31(3):606-617.
【70】. Duda T., Canty M. Unsupervised classification of satellite imagery: choosing a goodalgorithm[J]. International Journal of Remote Sensing,2002,23(11):2193-2212.
【71】. Chamundeeswari V.V., Singh D., Singh K. An analysis of texture measures inPCA-based unsupervised classification of SAR images[J]. IEEE Transaction andRemote Sensing Letters,2009,6(2):214-218.
【72】. Ifarraguerri Agustin, Chein Ichang. Unsupervised hyperspectral image analysis withprojection on pursuit[J]. IEEE Transactions onGeoscience and Remote Sensing,2000,38(6):2529-2538.
【73】.王圆圆,李京.遥感影像土地利用/土地覆盖分类方法研究综述[J].遥感信息,2004,(1):53-59.
【74】. Flygare A.M. A comparison of contextural classification methods using landsat TM[J].International Journal of Remote Sensing,1997,18(18):3885-3842.
【75】. Franklin S.E., Peddle D.R. Spectrumtexture for improved class discrimanation incomplex terrain[J]. International Journal of Remote Sensing.1989,10(8):1437-1443.
【76】.朱长青,杨启和,朱文忠.基于小波变化特征的遥感地貌影像纹理分析和分类[J].测绘学报,1996,25(4):252-255.
【77】.李厚强,刘政凯,林峰.基于分形理论的航空图像分类方法[J].遥感学报,2001,5(5):353-357.
【78】.张宝光.数学形态学在遥感数字图像分类处理中的应用[J].测绘信息与工程,2000,(2):1-5.
【79】. Hellwich O., Wiedemann C. Object extraction from high-resolution multisensor imagedata[C]. In:3rd International Conference on Fusion of Earth Data, Sophia Antipolis,France,26-28January2000, SEE GreCA, Nice:105-115.
【80】. Ehrlich D., Lambin, E.F. Broad scale land-cover classification and internal climaticvariability[J]. International Journal of Remote Sensing,1996,17(5):845-862.
【81】. Defries R.S., Townshend, J.R.G. NDVI-derived land cover classification at a globalscale[J]. International Journal of Remote Sensing,1994,15(17):3567-3586.
【82】.龙飞,赵英时. NOAA卫星角度信息在分类中的有效性研究[J].中国科学院研究生院学报,2002,19(1):69-74.
【83】.贾永红.人工神经网络在多源遥感影响分类中的应用[J].测绘通报,2000,(7):7-8.
【84】.李朝峰,王桂梁.模糊控制BP网络的遥感图像分类方法研究[J].中国矿业大学学报(自然科学版),2001,30(3):311-314.
【85】. Rumelhart D.E., McClelland J.L., PDP Research Group. Parallel distributed processing:explorations in the microstructure of cognition, Volume1: Foundations[M], MIT Press,Cambridge, MA,1986.
【86】. Mural H., Omatu S. Remote sensing image analysis using a neural network andknowledge-based processing[J]. Remote sensing,1997,18(4):811-828.
【87】.蔡煜东,李伟,许伟杰.遥感土地覆盖类型识别的自组织人工神经网络模型[J].国土资源遥感,1994,(4):63-66.
【88】.孙丹峰,汲长远,林培.自组织网络在遥感土地覆盖分类中应用研究[J].遥感学报,1999,3(2):139-143.
【89】.任军号,吉沛琦,耿跃. SOM神经网络改进及在遥感图像分类中的应用[J].计算机应用研究,2011,28(3):1170-1182.
【90】.骆剑承,周成虎,杨艳.基于径向基函数(RBF)映射理论的遥感影像分类模型研究[J].中国图象图形学报,2000,5(2):94-99.
【91】.巫兆聪.基于粗糙理论的RBF网络及其遥感影像分类应用[J].测绘学报,2003,32(1):53-57.
【92】. Gopal S., Woodcock C.E., Strahler A.H. Fuzzy neural network classification of globalland cover from a10AVHRR data set[J]. Remote Sensing of Environment,1999,(67):230-247.
【93】.刘正军,王长耀,延昊,牛铮，王雷.基于FuzzyARTMAP神经网络的高分辨率图象土地覆盖分类及其评价[J].中国图象图形学报,2003,8(2):151-154.
【94】.林剑,鲍光淑,敬荣中,黄继先. FasART模糊神经网络用于遥感图象监督分类的研究[J].中国图象图形学报,2002,7(2):1263-1268.
【95】.谭琨,杜培军.基于径向基函数神经网络的高光谱遥感图像分类[J].光谱学与光谱分析,2008,28(9):2009-2013.
【96】.杨希,王鹏.基于BP神经网络的高分辨率遥感影像分类[J].测绘,2011,34(3):115-118.
【97】.裴亮,谭阳,李文杰.基于变差函数和神经网络的遥感影像分类[J].遥感信息,2009,(1):60-65.
【98】.骆剑承,周成虎,杨艳.具有部分监督的遥感影像模糊聚类方法研究及应用[J].遥感技术与应用,1999,14(4):37-43.
【99】. Zhang J., Foody G.M. A fuzzy classification of sub-urban land cover from remotelysensed imagery[J]. International Journal of Remote Sensing,1998,19(14):2721-2738.
【100】.毛建旭,王耀南,孙炜.基于模糊小脑模型神经网络的遥感图像分类算法[J].测绘学报,2002,31(4):327-332.
【101】.张宝光.论遥感数字图像的模糊分类处理[J].天津师范大学学报(自然科学版),2005,25(2):69-72.
【102】.黎夏,叶嘉安,廖其芳.利用案例推理(CBR)方法对雷达图像进行土地利用分类[J].遥感学报,2004,8(3):246-253.
【103】.黎夏,刘凯,王树功.珠江口红树林湿地演变的遥感分析[J].地理学报,2006,61(1):26-34.
【104】.霍宏涛,王任华,游先祥.三维及相关辅助信息在提高图像分类精度中的研究[J].北京林业大学学报,2001,23(2):29-31.
【105】. Huang C., Davis L.S., Townshend J.R.G. An assessment of support vector machine forland cover classification[J]. International Journal of Remote Sensing,2002,23(4):725-749.
【106】.骆剑承,周成虎,梁怡,马江洪.支持向量机及其遥感影像空间特征提取和分类的应用研究[J].遥感学报,2002,6(1):50-55.
【107】. Defries R.S., Hansen M., Townshend J.R.G., Sohiberg R. Global land coverclassification at8km spatial resolution: the use of training data derived from landsatimagery in decision tree classification[J]. International Journal of Remote Sensing,1998,19(16):3141-3168.
【108】.李敏,赵庚星,李百红.基于遥感的乡镇级棉花面积提取与长势监测研究[J].山东农业大学学报(自然科学版),2011,42(4):533-538.
【109】.郭伟,赵春江,顾晓鹤,黄文江,马智宏,王慧芳,王大成.乡镇尺度的玉米种植面积遥感监测[J].农业工程学报,2011,27(9):69-74.
【110】.于文颍,冯锐,纪瑞鹏,张玉书,陈鹏狮,赵先丽,武晋雯.基于MODIS数据的水稻种植面积提取研究进展[J].气象与环境学报,2011,27(2):56-61.
【111】.苗翠翠,江南,彭世揆,吕恒,李杨,张瑜,王妮,李军.基于NDVI时序数据的水稻种植面积遥感监测分析[J].地球信息科学学报,2011,13(2):273-280.
【112】. Weiss E., Pfirman E.S., Marsh S.E. Application of NOAA-AVHRR NDVI time-serialdata to assess changes in Saudi Arabia’s rangelands[J]. International Journal of RemoteSensing,2001,22(6):1005-1027.
【113】.李爽,张二勋.基于决策树的遥感影像分类方法研究[J].地域研究与开发,2003,22(1):17-21.
【114】. Tucker C.J., Newcomb W.W., Dregne H.E. AVHRR data sets for determination ofdesert spatial extent[J]. International Journal of Remote Sensing,1994,15(17):3547-3565.
【115】. Yu F., Price K.P., Ellis J., Feddema J.J., Shi P. International variations of the grasslandboundaries bording the eastern edges of the Godi Desert in central Asia[J].International Journal of Remote Sensing,2004,25(2):327-345.
【116】. Http://www. agit. at/papers/2000/baatz-FP-12.pdf
【117】. Mauro C., Eufemia T. Accuracy assessment of per-field classification integrating veryfina spatial resolution satellite imagery with topographic data[J]. Journal of GeospatialEngineering,2001,3(2):127-134.
【118】. Benz U.C., Hofmann P., Willhauck G., Lingenfelder I., Heynen M. Multi-resolutionobject-oriented fuzzy analysis of remote sensing data for GIS-ready information[J].ISPRS Journal of Photogrammetry＆Remote Sensing,2004,(58):239-258.
【119】.曹雪,柯长青.基于对象级的高分辨率遥感影像分类研究[J].遥感信息,2006,(5):27-30.
【120】.张宝雷,周万村,马泽忠.三峡地区主要地类的自动提取方法研究[J].长江流域资源与环境,2005,14(4):446-449.
【121】.黄慧萍,吴炳方,李苗苗,周为峰,王忠武.高分辨率影像城市绿地快速提取技术与应用[J].遥感学报,2004,8(1):68-74.
【122】.曾涛,杨武年,黎小东,刘汉湖,彭立,简季.面向对象的高空间分辨率遥感影像信息提取——汶川地震城市震害房屋案例研究[J].自然灾害学报,2010,19(5):81-87.
【123】.龚健雅,姚璜,沈欣.利用AdaBoost算法进行高分辨率影像的面向对象分类[J].武汉大学学报(信息科学版),2010,35(12):1440-1448.
【124】.范磊,程永政,王来刚,刘婷,胡峰,冯晓.基于多尺度分割的面向对象分类方法提取冬小麦种植面积[J].中国农业资源与区划,2010,31(6):44-51.
【125】.陈燕丽,莫伟华,莫建飞,王君华,钟仕全.基于面向对象分类的南方水稻种植面积提取方法[J].遥感技术与应用,2011,26(2):163-168.
【126】.安如,陈志霞,陆玲,杨仁敏,李晓雪,吴红,龚天宇,曲春梅.面向对象的黄河源典型区湿地信息提取[J].河海大学学报(自然科学版),2011,39(4):355-360.
【127】.莫源富,周立新.分区分类法针对山区遥感图像的一种有效的分类方法[J].中国岩溶,2000,19(4):360-365.
【128】.段四波,阎广建,穆西晗,沈斌,李小文.基于DEM的山区遥感图像地形校正方法[J].地理与地理信息科学,2007,23(6):18-22.
【129】.王瑞燕,于振文,赵庚星,周伟.耕地地力调查中北方平原-山地复合区耕地资源遥感提取方法[J].农业工程学报,2011,27(7):306-311.
【130】.刘咏梅,李锐,杨勤科.基于影像融合的陕北黄土丘陵沟壑区土地利用自动分类[J].中国水土保持科学,2004,2(4):6-10.
【131】.王增柱,刘同怀,黄鲁.基于光谱分类的超光谱数据压缩方法[J].遥感技术与应用,2001,16(3):148-152.
【132】. Vermote E.F., Tanre D., Deuze J.L., Herman M., Morcette J.J. Second simulation of thesatellite signal in the solar spectrum,6S: an overview[J]. IEEE Transactions onGeoscience and Remote Sensing,1997,35,(3):675-686.
【133】.阎福礼,王世新,周艺,肖青,祝令亚,王丽涛,焦云清.利用Hypersion星载高光谱传感器监测太湖水质的研究[J].红外与毫米波学报,2006,25(6):460-464.
【134】. Richanl B. EO-1user guide v.2.2.[R]. University of Cincinnati. July15,2003.available at: http://EOS.usgs.gov.
【135】.田庆久,张良培,郑兰芬,童庆禧.成像光谱遥感定标模型的分析与评价[J].遥感技术与应用,1996,11(3):16-21.
【136】. Stanz K., Szeredi T., Schwarz J. ISDAS-a system for proceeding/analyzinghyperspectral data[J]. Candian Journal of Remote Sensing,1998,(24):99-113.
【137】. Winter M.E. N-FINDER: An algorithm for fast autonomous spectral endmemberdetermination in hyperspectral data[A]. Proceedings of SPIE Conference ImagingSpectrometryⅤ[C],1999,(3753):266-275.
【138】. Bateson C.A., Curtiss B. A tool for manual endmember selection ans spectralunmixing[R]. in Summaries of the Ⅴ JPL Airborne Earth Science Worshop, Pasadena,CA,1993.
【139】. Boardmen J.W., Kruse F.A., Green R.O. Mapping target signatures vis partialunmixing of AVIRIS data in Summaries[J]. Fifth JPL Airborne Earth ScienceWorkshop,1995,(1):23-26.
【140】. Bowles J.H., Palmadesso P.J., Antoniades J.A., Baumback M.M., Richard L.J. Use offilter vectors in hyperspectral data analysis[A]. Scholl M.S., Andreson B.F., Editors,Infrared Spaceborne Remote Sensing Ⅲ, Proc. SPIE1995, Vol.2553,148-157.
【141】. Craig M.D. Minimum volum transforms for remotely sensed data[J]. IEEETransactions on Geoscience and Remote Sensing,1994,32(3):542-552.
【142】. Nascimento J.M.P., Dias J.M.B. Vertex component analysis: a fast algorithm to unmixhyperspectral data[J]. IEEE Transactions on Geoscience and Remote Sensing,2005,43(4):898-910.
【143】.夏学齐,田庆久,杜凤兰.高光谱遥感图像的单形体分析方法[J].中国图象图形学报,2004,9(12):1486-1491.
【144】.李二森,徐波,李娜,周小明.最小体积约束的线性光谱解混算法[J].武汉大学学报(信息科学版),20111,36(6):683-686.
【145】.王立国,张晶,刘丹凤,王群明.从端元选择到光谱解混的距离测算方法[J].红外与毫米波学报,2010,29(6):471-475.
【146】.方勇,王明祥.基于自组织映射的后非线性独立分量分析的初始化方法[J].电子学报,2005,(5):889-892.
【147】.赵立权,贾雁飞.改进的快速独立分量分析方法研究[J].计算机工程与应用,2010,46(27):128-130.
【148】. Habib T., Inglada J., Mercier G., Chanussot J. Support vector reduction in svmalgorithm for abrupt change detection in remote sensing[J]. IEEE Geoscience andRemote Sensing Letters,2009,6(3):606-610.
【149】. Mountrakis G., Irn J., Ogole C. Support vector machines in remote sensing: a review[J].ISPRS Journal of Photogremmetry and Remote Sensing,2011,66(3):247-259.
【150】.朱海洲,贾银山.基于支持向量机的遥感图像分类研究[J].科学技术与工程,2010,10(15):3659-3663.
【151】.谢亮.基于独立分量分析特征提取方法的研究及其应用[D],浙江师范大学硕士学位论文,2006.
【152】. Cichocki A., Unbehauen R. Robust neural networks with on-line learning for blindidentification and blind separation of sources[J]. IEEE Transactions on Circuits andsystems,1996,43(11):894-906.
【153】. Oja E. Neural networks, principal components, and subspace[J]. International Journalon Neural Syatem,1989,(1):61-68.
【154】.曾生根.快速独立分量分析方法及其在图像分析中的若干应用研究[D].南京理工大学博士学位论文,2004.
【155】.罗江华.贝叶斯网络在机械故障诊断中的应用研究[D].重庆大学博士学位论文,2006.
【156】.刘凯.贝叶斯网络维修决策系统的开发与应用研究[D].国防科学技术大学博士学位论文,2004.
【157】.范涛.基于变分贝叶斯独立分量分析的机械故障诊断方法研究[D].郑州大学硕士学位论文,2009.
【158】. Http://baike.baidu.com/view/943316.htm.
【159】.黄青华.基于原信号模型的盲分离技术研究及应用[D].上海交通大学博士学位论文,2007.
【160】. Finneti B.D. Theory of Probability:A Critical Introductory Treatment[M]. New York:John Wiley＆Sons,1970.
【161】. Gelman A., Carlin J., Stern H. Rubin D. Bayesian data analysis[M]. Boca Raton:Chapman&Hall/CRC Press,1995.
【162】. Miskin J.W. Ensemble Learning for Independent Component Analysis[D]. Ph.D.Thesis, University of Cambridge,2000.
【163】.温奇,马建文.基于贝叶斯网络的遥感数据处理软件[J].2008,34(24):10-12.
【164】.陈雪,马建文,戴芹.基于贝叶斯网络分类的遥感影像变化监测[J].遥感学报,2005,9(6):667-672.
【165】.戴芹,马建文,李启青,陈雪,冯春.遥感数据的贝叶斯网络分类研究[J].电子与信息学报,2005,27(11):1782-1785.
【166】. Cardoso J.F. Blind beam forming for non-Gaussian signals[J]. Radar and SignalProcessing, IEEE Proceedings F,1993,140(6):362-370.
【167】.曾生根,王小敏,范瑞斌,夏德深.基于独立分量分析的遥感图像分类计数[J].遥感学报,2004,8(2):150-157.
【168】. Hyvarinen A. Survey on Independent Component Analysis [J]. Neural ComputingSurveys,1999,(2):94-128.
【169】.王小敏,曾生根,夏德深.基于松弛因子改进FastICA算法的遥感图像分类方法[J].计算机研究与发展,2006,43(4):708-715.
【170】.李国正,王猛,曾华军译,支持向量机导论[M].北京:电子工业出版社,2004.
【171】.曾志华,张银奎等译.机器学习[M].北京:机械工业出版社,2003.
【172】.梁力文.基于支持向量机的小波滤噪短波近红外光谱在药品定量分析中的研究
[D].吉林大学博士学位论文,2009.
【173】. Vapnik V.N. The nature of statistical learning theory[M]. New York: Spring VerlagPress,1995.
【174】.杨强.支持向量机的模型及其在图像分割中的应用[D].重庆大学博士学位论文,2004.
【175】.刘勇.基于空间信息技术的土地生态风险评价研究[D].上海大学博士学位论文,2008.
【176】.张学工.关于统计学习理论与支持向量机[J].自动化学报,2002,16(1):32-42.
【177】.柳回春,马树元.支持向量机的研究现状[J].中国图象图像学报,2002,7(6):618-623.
【178】. Vapnik V.N., Chervonenkis A. Necessary and sufficient sinditions for the uniformconverhence of means to their experctations[J]. Theory of Probability and itsApplications,1981,26(30):532-553.
【179】. Vapnik V.N., Chervonenkis A. The necessary and sufficient conditions for consistencyin the empirical risk minimization method[J]. Pattern Recognition and Image Analysis,1991,1(3):283-305.
【180】. Bishop C.M., Lawrence N.D. Variational Bayesian independent componentanalysis[D]. Ph.D. Thesis, University of Cambridge,2000.
【181】. Choudrey R.A. Variational Methods for Bayesian Independent ComponentAnalysis[D]. Ph.D. Thesis, University of Oxford,2002.
【182】.曲炜.信息论基础与应用[M].北京:清华大学出版社,2005.
【183】.徐尚志.盲信号分离算法的研究[D].中国科学技术大学博士学位论文,2005.
【184】. Choudrey R.A. Flexible Bayesian independent component analysis for blind sourceseparation[C]. Proceeding of ICA-2001, San Diego, USA, December2001.
【185】.许雯,董林,田家斌.一种改进的高斯混合模型算法[J].信息工程大学学报,2005,(2):12-16.
【186】. Jordan M. An introduction to variational methods in graphical models[J]. Mechanicallearning,1999,37(2):183-233.
【187】. Jordan M. Bayesian parameter estimation via variational methods[J]. Statistics andComputing,2000,(10):25-37.
【188】. Http://wenku.baidu.com/view/0690dd0e844769eae009ed43.html.
【189】. Munoz-Mari. J., Bovolo F., Gomez-Chova L., Bruzzone L., Camp-Valls G.Semisupervised one-class support vector machines foe classification of remote sensingdata[J]. IEEE Transactions on Geoscience and Remote Sensing,2010,48(8):3188-3197.
【190】.徐芳,燕琴.基于支持向量机的航空影像纹理特征分类研究[J].武汉大学学报(信息科学版),2003,28(5):517-520.
【191】.夏建涛.基于机器学习的高维多光谱数据分类[D].西北工业大学博士学位论文,2002.
【192】.王双亭,艾泽天,都伟兵,康敏.基于SVM不同核函数的多源遥感影像分类研究[J].河南理工大学学报(自然科学版),2011,30(3):304-310.
【193】. Http://www.docin.com/p-116603825.html#documentinfo.
【194】.张力,周廷刚,李成范,吴忠芳.特大型山地城市动态扩展的遥感研究[J].遥感技术与应用,2009,24(1):77-81.
【195】.周成虎,骆剑承,杨晓梅,杨存建,刘庆生.遥感影像地学理解与分析[M].北京:科学出版社,2001.
【196】.赵英时.遥感应用分析原理与方法[M].北京:科学出版社,2003.
【197】.王均,祝武功.清末明初使其北京市城市社会空间的初步研究[J].地理学报,1999,54(1):69-73.
【198】.赵涛.中国城市用地扩展及其驱动机制[D].中科院研究生院博士学位论文,2005.
【199】. Li L., Sato Y., Zhu H.H. Simulating spatial urban expansion based on a physicalprocess [J]. Landscape and Urban Planning,2003,(64):67-76.
【200】.张有全,宫辉力,赵文吉,李小娟.北京市1990年～2000年土地利用变化机制分析[J].资源科学,2007,29(3):206-213.
【201】. Paclone M. The internal structure of cities in the Third World[J]. Geography,2001,86(3):189-209.
© 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 |