用户名: 密码: 验证码:
高光谱图像的分类技术研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
高光谱遥感是当前遥感技术发展的一个前沿领域,它利用很多很窄的电磁波波段从感兴趣的物体获得有用信息。高光谱图像作为遥感领域的一项重大突破,在保留较高空间分辨率同时,其光谱分辨率有极大的提高,达到了纳米的数量级,可以用来探测和识别传统全色和多光谱遥感中不可探测的地物类别。与传统的多光谱遥感图像相比,高光谱遥感图像有着信息量大、光谱分辨率高等特点,这使得在描述与区分地物类别方面的能力有了大幅提高,进而为地物光谱信息的精确处理与分析提供了可能。高光谱遥感系统已在全球许多国家的先进对地观察遥感系统中占有重要的位置,己成为地球陆地、海洋、大气观察的生力军。但是由于高光谱图像具有较高的数据维数,常规的图像分类方法在处理高光谱图像时有较大的限制,如何从大量的高光谱数据中快速而准确地挖掘出所需要的信息,实现高精度的分类,仍是一个亟待解决的问题。本文从高光谱图像数据的特点入手,在对现有算法进行分析的基础上,针对高光谱遥感图像分类算法进行深入研究。主要的研究工作如下:
     ①在对高光谱遥感影像进行预处理之后,对所用高光谱图像做了大气校正。几何校正选取为二次多项式模型,重采样采用的是最近邻插值法,精度方面的要求得到了充分保证,为下一步的正确分类打下了坚实的基础。
     ②提出了一种基于自适应粒子群优化算法的RBF神经网络高光谱遥感图像分类方法。由于人工神经网络具有并行处理、模糊识别和非线性映射等优点,很适合高光谱图像分类,但是其参数难选。采用自适应粒子群优化算法对RBF神经网络的参数进行了优化,建立了基于粒子群优化算法的的RBF神经网络模型,分类实验结果表明了基于粒子群优化的RBF神经网络模型具有很高的分类精度。
     ③提出了一种基于自适应粒子群优化算法的SVR高光谱遥感图像分类方法。首先分析了支持向量回归的核函数的构造和模型参数的优选问题。由于本文数据样本较少,模型参数优选的比较复杂,本文采用了CV估计模型推广误差,并使用自适应粒子群优化算法来优选SVR模型参数,构建了基于粒子群优化算法的SVR高光谱遥感图像分类模型,在一定程度上解决了高光谱数据标记样本不足的问题。
     ④从稀疏表示的基本理论出发提出了一种基于自适应稀疏表示的高光谱分类方法。利用训练样本构建字典,聚类每一步迭代所产生的余项,将聚类中心作为新的字典原子,然后将测试样本看成冗余字典中训练样本的线性组合,令字典能够更适应于样本的稀疏表示。通过对高光谱图像的分类实验,验证了自适应稀疏表示算法的有效性。
Hyperspectral remote sensing is a frontier field in the development of remotesensing technology, and it obtains useful information from interesting objects by usingnarrow bands of electromagnetic waves. Hyperspectral remote sensing image is a majorbreakthrough in the field of remote sensing, and spectral resolution was greatlyimproved while retaining a high spatial resolution. As a result, it can be used to detectthe land-cover types which could not be detected with traditional panchromatic andmulti-spectral images. Compared with the traditional multi-spectral remote sensingimage, hyperspectral image (HSI) provides a large amount of information and highspectral resolution, and the ability in description and analysis of land-cover types hasbeen improved greatly, which makes it possible to process and analyze the spectralinformation of land-cover types more precisely. In many countries, hyperspectral remotesensing play an important role in the earth observation system, and it has become a newforce to the observation of earth’s land, ocean and atmosphere. Due to the highdimension of HSI, traditional classification methods have some limitations whendealing with HSI. How to accurately exploit the information from a large amount ofhyperspectral data for achieving high-precision classification, is still a serious problem.Based on the characteristics of HSI, this paper focuses on the research of HSIclassification. The main research contents are as follows:
     ①After the preprocessing of HSI, atmospheric correction was carried out on HSI.The quadratic polynomial mode was selected for geometric correction, and the nearestneighbor interpolation method was used for resampling. Then the requirements foraccuracy are fully guaranteed, which lays a solid foundation for classification.
     ②A RBF neural network method based on adaptive particle swarm optimization(PSO) was proposed for HSI classification. The neural network has the merits ofparallel processing, fuzzy recognition, and nonlinear mopping, which gives the benefitto the classification of HSI. However, it is very difficult to choose proper parameters.An adaptive PSO algorithm is used to optimize the parameters, and the RBF neuralnetwork model based on PSO is constructed for classification. Experimental resultsshow that the RBF neural network based on PSO has a better classification accuracy forHSI classification.
     ③The support vector regression (SVR) with adaptive PSO is proposed for HSI classification. At first, the construction of kernel functions and the optimization ofmodel parameters are introduced. For the conditions of small number of data samplesand the complexity of model parameters, the CV estimation model is used. The adaptivePSO method is used to choose the parameters for the model of SVR in hyperspectralremote sensing classification, which is useful to solve the problem of insufficienttraining samples in HSI.
     ④According to the sparse representation theory, a new method based on adaptivesparse representation (ASP) is proposed for HSI classification. In this method, thedictionary is constructed with training samples. The remainder of each iteration isclustered, and the center of clustering is considered as the atom of the new dictionary.Furthermore, the testing samples are regarded as the linear combination of trainingsamples in the redundant dictionary, which makes the dictionary adapt to sparserepresentation of samples more effectively. The validity of ASP is verified by theexperiments for HSI classification. The effectiveness of the proposed ASP method isverified on hyperspectral image data sets.
引文
[1]吴静.基于支持向量机与图斑的高光谱分类方法研究[D].西安:长安大学,2010.
    [2]浦瑞良,宫鹏.高光谱遥感及其应用[M].北京:高等教育出版社,2000.
    [3]王学仁,王松桂.实用多元统计分析[M].上海:上海科学技术出版社,1990.
    [4]杨国鹏.基于支持向量机的高光谱影像分类研究[D].郑州:解放军信息工程大学,2010.
    [5]吴昊,郁文贤,匡纲要等.一种模型选择优化准则及其在高光谱图像非监督分类中的应用[J].电子学报,2003,31(12):2154-2157.
    [6]刘建贵.高光谱城市地物及人工目标识别与提取[D].北京:中国科学院,1999.
    [7] Wang J, Chang C I. Independent component analysis based dimensionalityreduction with applications in hyperspectral image analysis[J].IEEE Transactionson Geoscience and Remote Sensing,2006,44(6):1586-1600.
    [8]马莉,范文涛.高光谱影像加权波段指数算法[J].黑龙江自然科学信息,2010,25(3):8-12.
    [9] Serpico S B, Moser G.Extraction of spectral channels from hyperspectral images forclassification purposes[J].IEEE Transanctions on Geoscience and Remote Sensing,2007,45(2):484-495.
    [10] Kalluri H R, Prasad S.Decision level fusion of spectral reflectance and derivative informationfor robust hyperspectral land cover classfications[J].Transanctions on Geoscience and RemoteSensing,2010,48(11):4047-4058.
    [11] Lin K P, Chen M S.On the design of the privacy.preserving SVM classifier[J].IEEETransanctions on Knowledge and Data Engineering,2011,23(11):1704-1717.
    [12] Wei L, Yang Y, Nishikawa R M.Relevance vector machine for automatic detection ofclustered microcalcifications[J].IEEE Transanctions on Medical Imaging,2005,24(10):12780-12785.
    [13] Christophe E, Leger D, Mailhes C. Quality criteria benchmark for hyperspectralimagery[J].IEEE Transanctions on Geoscience and Remote Sensing,2005,43(9):2103-2114.
    [14] Mayer R, Priest R. Object detection using transformed signatures in multi-temporalhyperspectral imagery[J].IEEE Transanctions on Geo-science and Remote Sensing,2002,40(4):831-840.
    [15] Bach H, Mauser W.Methods and examples for remote sensing data assimilation in landsurface process modeling[J].IEEE Transactions on Geo.science and Remote Sensing,2003,41(7):1629-1637.
    [16]万署静,张承明,刘俊华.基于自适应最小距离调整的多光谱遥感图像分类方法[J].测绘通报,2012,20(10):240-243.
    [17]干正如,曾宪珪.基于最小距离原理的自适性分类方法[J].江西理工大学学报,2007,28(4):39-42.
    [18] Shaw G, Manolakis D.Signal Processing for hyperspectral image exploitation[J].IEEE SignalProcessing Magazine,2002,12(1):12-16.
    [19]刘凡.基于神经网络的高光谱图像分类研究[D].哈尔滨:哈尔滨工程大学,2009.
    [20]贾坤,李强子,田亦陈等.遥感图像分类方法研究进展[J].光谱学与光谱分析,2011,31(10):2613-2618.
    [21] Gao C, Goetz H.Column atmospheric water vapor and vegetation liquid water retrievals fromairborne imaging spectrometer data[J]. Journal of Geophysical Research,1990,95(4):3549-3564.
    [22] Demarez V.Seasonal variation of leaf chlorophyll content of a temperature forest inversion ofthe PROSPECT model[J].International Journal of Remote Sensing,1999,20(5):879-894.
    [23] Shave.Tsylor J, Cristianini N.Kernel methods for pattern analysis [M].London: CambridgeUniversiy Press,2004.
    [24] Tenenbaum J B, Silva V, Langford J C.A global geometric framework fornonlinear dimensionality reduction [J].Science,2000,290(12):2319-2323.
    [25] Roweis S T, Saul L K.Nonlinear dimensionality reduction by locally linear embedding[J].Science,2000,290(12):2325-2329.
    [26] Seung H S, Daniel D L.The mani-fold ways of perception[J].Science.2000,290(12):2268-2271.
    [27]陈万海,赵春晖,刘春红.超谱遥感图像的模糊最大似然分类研究[J].哈尔滨工程大学学报,2006,27(5):772-776.
    [28]李永亮,林辉,孙华等.基于BP神经网络的森林树种分类研究[J].中南林业科技大学学报,2011,30(11):243-246.
    [29]赵春晖,刘凡.基于改进自组织竞争神经网络的高光谱图像分类[J].应用科技,2009,36(8):8-12.
    [30]李波,刘占宇,武洪峰等.基于概率神经网络的水稻穗颈瘟高光谱遥感识别初步研究[J].科技通报,2009,25(6):811-815.
    [31]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.
    [32]唐雪飞.基于案例推理的高光谱图像分类研究[D].哈尔滨:哈尔滨工业大学,2010.
    [33] Gustavo V. Kernel based methods for hyperspectral image classification[J]. IEEETransactions on Geoscience and Remote Sensing,2005,43(6):1351-1354.
    [34] Burges C J.Simplified support vector decision rule[C].Proceedings of the13th Int’l Conf onMachine Learning,1996:71–77.
    [35] Lee Y J, Mangasarian O L.RSVM: Reduced support vector machines[C].Proceedings of theFirst SIAM Int’l Conf, on Data Mining,2001:58-62.
    [36] Lin K M, Lin C J.A study on reduced support vector machines[J].IEEE Transactions onNeural Networks,2003,14(6):1449-1559.
    [37] Scholkopf B.New support vector algorithms[J].Neural Computation,2000,12(5):1207-1245.
    [38] Chen P H, Lin C J, Scholkopf B.A tutorial on support vector machines[J].Applied StochasticModels in Business and Industry,2005,21(2):111-136.
    [39]刘向东,陈兆乾.一种快速支持向量机分类算法的研究[J].计算机研究与发展,2004,41(8):1327-1332.
    [40]李红莲.针对大规模训练集的支持向量机的学习策略[J].计算机学报,2004,27(5):716-719.
    [41] Zadeh L.Fuzzy sets [J].Information and Control,1965,8:338-353.
    [42] Van D, Meer F.Bayesian inversion of imaging spectrometer data using afuzzy geological outcrop model [J].International Journal of Remote Sensing,2003,24(22):4301-4310.
    [43]胡运海,简季,刘琰洁.模糊分类在邛崃地区土地利用分类中的应用[J].测绘,2011,34(3):110-114.
    [44]覃先林,李增元,易浩若.高空间分辨率卫星遥感影像树冠信息提取方法研究[J].遥感技术与应用,2005,20(2):228-232.
    [45]刘姣娣,曹卫彬,裴志远等.基于多分辨率数据的干旱和半干旱地区地物模糊分类[J].农业工程学报,2012,28(8):220-223.
    [46]冯益明,郑冬梅,智长贵等.面向对象的沙化土地信息提取[J].林业科学,2013,49(1):126-133.
    [47] Quinlan J R.Induction of decision trees [J].Machine Learning,1986,1(1):812-1061.
    [48]潘琛,杜培军,张海荣.决策树分类法及其在遥感图像处理中的应用[J].测绘科学,2008,33(1):208-211.
    [49]秦文.分类技术中的决策树算法分析[J].深圳信息职业技术学院学报,2004,(1):542-581.
    [50]蔡竞峰,蔡自兴.决策树技术及其当前研究方向[J].控制工程,2005,(1):152-181.
    [51]谭旭,王丽珍,卓明.利用决策树发掘分类规则的算法研究[J].云南大学学报(自然科学版),2000,22(6):4152-4191.
    [52]李宁,乐琦.决策树算法及其常见问题的解决[J].计算机与数字工程,2005,(3):602-614.
    [53]刘勇洪,牛铮,王长耀.基于MODIS数据的决策树分类方法研究与应用[J].遥感学报,2005,(4):4052-4059.
    [54]李春雷,吴虹,侯娜等.基于决策树分类的桂林市岩溶地区水体遥感空间信息提取[J].广西师范学院学报:自然科学版,2010,27(1):165-169.
    [55]周伟,杨峰,钱育蓉等.天山北坡草地遥感分类及其精度分析[J].草业科学,2012,29(10):1526-1532.
    [56]陈可蕴,陈志扬.基于云理论的遥感图像土地利用分割分类方法研究[J].理论研究,2010,28(5):22-25.
    [57]王细元,曹蕾.基于专家分类器的洪泽湖湿地变化分析[J].河南师范大学学报(自然科学版),2013,41(5):149-152.
    [58]甘淑.遥感专家分类系统在滇西北植被信息提取中的应用试验研究[J].云南大学学报(自然科学版),2003,25(6):553-557.
    [59]张晓美,焦伟利,何国金等.多源信息在岷山地区遥感图像分类中的应用[J].测绘信息与工程,2003,28(4):19-25.
    [60]张晓.专家分类方法在森林资源清查中的应用研究[J].林业资源管理,2010,32(1):119-132.
    [61]刘健,余坤勇,亓兴兰等.基于专家分类知识库的林地分类[J].福建农林大学学报(自然科学版),2006,35(1):42-47.
    [62] Kalluri H R, Prasad S, Bruce L M.Decision level fusion of spectral reflectance and derivativeinformation for robust hyperspectral land cover classfication[J].Transanctions on Geoscienceand Remote Sensing,2010,48(11):4047-4058.
    [63] Lin K P, Chen M S. On the design and analysis of the privacy preserving SVMclassifier[J]. IEEE Transanctions on Knowledge and Data Engineering,2011,23(11):1704-1717.
    [64]郭燕,田延峰,吴宏海等.基于多源数据和模糊k-均值方法的农田土壤管理分区研究[J].土壤学报,2013,50(3):141-146.
    [65]邓湘金,王彦平,彭海良.高分辨率遥感图像的聚类[J].电子与信息学报,2003,32(8):1073-1076.
    [66] Mayer R, Priest R. Object detection using transformed signatures in multi.temporalhyperspectral imagery[J].IEEE Transanctions on Geo.science and Remote Sensing,2002,40(4):831-840.
    [67] Bach H, Mauser W.Methods and examples for remote sensing data assimilation in landsurface process modeling[J].IEEE Transactions on Geo-science and Remote Sensing,2003,41(7):1629-1637.
    [68] Wei L, Yang Y, Nishikawa R M.Relevance vector machine for automatic detection ofclustered microcalcifications[J].IEEE Transanctions on Medical Imaging,2005,24(10):12780-1285.
    [69] Christophe E, Leger D, Mailhes C. Quality criteria benchmark for hyperspectralimagery[J].IEEE Transanctions on Geoscience and Remote Sensing,2005,43(9):2103-2114.
    [70]骆剑承,梁怡,周成虎.基于尺度空间的分层聚类方法及其在遥感影像分类中的应用[J].测绘学报,1999,28(4):320-324.
    [71]刘春红,赵春晖,张凌雁.一种新的高光谱遥感图像降维方法[J].中国图象图形学报,2005,10(2):218-222.
    [72]张新乐,张树文,李颖等.基于光谱角度匹配方法提取黑土边界[J].光谱学与光谱分析第,2009,29(4):1056-1059.
    [73]安斌,陈书海,严卫东.SAM法在多光谱图像分类中的应用[J].中国体视学与图像分析,2005,10(1):55-40.
    [74]古丽·加帕尔,陈曦,马忠国等.极端干旱区荒漠稀疏河岸林遥感分类研究[J].中国沙漠,2009,29(6):1154-1141.
    [75] Eismann M T, Hardie R C.Application of the stochastic mixing model to hyperspectralresolution enhancement[J].Geo-science and Remote Sensing,2004,42(9):1924-1933.
    [76]佘红伟,张艳宁.一种针对高光谱图象识别与分类的二进编码方法[J].航空计算技术,2009,39(3):99-102.
    [77]安斌,严卫东,陈华.一种基于多门限二进制编码的多光谱图像分类新方法[J].中国体视学与图像分析,2004,9(3):172-177.
    [78]王晋年,郑兰芬,童庆禧.成像光谱图像光谱吸收鉴别模型与矿物填图研究[J].环境遥感,1996,11(1):20-31.
    [79]李海胜,周萍,韩孟啸等.基于光谱吸收指数的矿物识别软件模块研发[J].计算机与现代化,2012,24(2):70-74.
    [80]张俊,沈亚婷,王学军.基于高光谱吸收特征参数以及光谱吸收指数的藻类叶绿素a反演分离模型研究[J].农业环境科学学报,2011,30(8):1622-1629.
    [81]朱志球.基于数据融合的高光谱遥感图像分类研究[D].哈尔滨:哈尔滨工程大学,2008.
    [82]储美华,陈允芳,洪志刚.数字航测影像盲点消除与病态像元校正方法探讨[J].测绘科学,2007,32(3):42-46.
    [83] Eismann M T, Hardie R C.Application of the stochastic mixing model to hyperspectralresolution enhancement[J].Geo-science and Remote Sensing,2004,42(9):1924-1933.
    [84] Tarabalka Y, Fauvel M, Chanussot J. SVM and MRF based method for accurateclassification of hyperspectral images[J].Geo-science and Remote Sensing Letters,2010,7(4):736-740
    [85] Lee C, Landgrebe D A.Analyzing high.dimensional multispectral data[J].IEEE Transactionson Geo-science and Remote Sensing,1993,31(4):792-800.
    [86] Hoffbeck J P, Landgrebe D A.Covariance matrix estimation and classification with limitedtraining data[J].IEEE Transactions on Pattern Analysis and Machine Intelligence,1996,18(7):763-767.
    [87] Tadjudin S, Landgrebe D A.Covariance estimation with limited training samples[J].IEEETransactions on Geoscience and Remote Sensing,1999,37(4):2113-2118.
    [88] Jackson Q, Landgrebe D A.An adaptive classifier design for high dimensional data analysiswith a limited training data sets[J].IEE Transactions on Geo-science and Remote Sensing,2001,39(12):2664-2679.
    [89] Jackson Q, Landgrebe D A.An adaptive method for combined covariance estimation andclassification[J].IEEE Transactions on Geo-science and Remote Sensing,2002,40(5):1082-1087.
    [90]田庆久,王世新,王乐意等.典型地物标准波谱数据库系统设计明[J].遥感技术与应用,2003,18(4):185-190.
    [91]杨希明.高光谱遥感图像分类方法研究[D].哈尔滨:哈尔滨工程大学,2007.
    [92]张杰林,曹代勇.成像光谱数据挖掘与矿物填图技术研究[J].遥感技术与应用,2002,17(8):259-263.
    [93]甘甫平,王润生,郭小方等.利用成像光谱遥感技术识别和提取矿化蚀变信息-以河北赤城一崇礼地区为例[J].现代地质,2000,14(4):465-469.
    [94] Bruce L M, Koger C H, Jiang L.Dimensionality reduction of hyperspectral data usin discretewavelet transform feature extraction[J].IEEE Transactions on Geo-science and RemoteSensing,2002,40(10):2331-2338.
    [95] Plaza A, Martinez P, Plaza J.Dimensionality reduction and classification of hyperspectralimage data using sequences of extended morphological transformations[J].IEEE Transactionson Geo-science and Remote Sensing,2005,43(3):466-479.
    [96]李小梅,谭炳香,李增元等.高光谱图像森林类型分类方法比较研究[J].遥感技术与应用,2010,25(2):227-233.
    [97]齐滨.基于支持向量机的高光谱遥感图像分类[D].哈尔滨:哈尔滨工程大学,2007.
    [98] Thenkabail P S, Enclona E A, Ashton M S et al.Accuracy assessments of hyperspectralwaveband performance for vegetation analysis applications[J]. Remote Sensing ofEnvironment,2004,91(34):354-376.
    [99] Gillespie A R.Spectral mixture analysis of multispectral infrared images[J].Remote Sensingof Environment,1992,42(2):137-145.
    [100]赵英时等.遥感应用分析原理与方法[M].北京:科学出版社,2003.
    [101]任春涛,李畅游,彭芳.基于模糊ISODATA技术和模糊模式识别方法的水环境分区研究[J].中国农村水利水电,2007,3:10-13.
    [102]牛铮.光学遥感大气订正总体思路与最新进展[J].遥感技术与应用,1998,13(1):50-55.
    [103]闻建光,肖青,杨一鹏等.基于高光潜数据提取水体叶绿素a浓度的光谱模型[J].水科学进展,2007,18(2):270-276.
    [104] Zhang Y Z, Jouni P.Application of an empirical neural network to surface water qualityestimation in the gulf of finland using combined optical data and microwave data[J].RemoteSense Environ,2002,8(1):327-336.
    [105]胡雯,杨世植,翟武全等.NOAH卫星监测巢湖蓝藻水华的试验分析[J].环境科学与技术,2002,25(1):16-18.
    [106]常虹,何丕廉.神经网络与模糊技术的结合与发展[J].计算机应用研究,2001,32(5):4-6.
    [107]王庆安,卞维林.利用气象能见度作晴空卫星遥感大气订正的一种实用方法[J].南京大学学报,1994,30(2):363-370.
    [108]苏美娟,邓伟.RBF神经网络的一种快速鲁棒学习算法[J].苏州大学学报(工科版),2007,27(1):17-20.
    [109]亓雪勇,田庆久.光学遥感大气校正研究进展[J].国土资源遥感,2005,12(4):1-6.
    [110]张伟,曹广超.浅析遥感图像的几何校正原理及方法[J].价值工程,2011,7(2):189-190.
    [111]何毅,倪晋仁,汪严明等.人工神经网络在强化一级处理系统过程模拟与优化应用[J].环境污染治理技术与设备,2006,17(8):27-31.
    [112]宁琦.电力变压器油中溶解气体诊断技术的研究[D].北京:华北电力大学,2009.
    [113]阎平凡,张长水.人工神经网络与模拟进化计算[M].北京:清华大学出版社,2005.
    [114]蒋赛,汪西莉,赵玉芹.渭河定量遥感水质反演中的大气校正作用研究[J].遥感技术与应用,2009,24(2):204-209.
    [115]赵玉芹,汪西莉,蒋赛.渭河水质遥感反演的人工神经网络模型研究[J].遥感技术与应用,2009,24(1):63-67.
    [116]刘春艳,汤亚波,徐守时.基于控制点的目标地理位置快速自动精校正新方法[J].测绘信息与工程,2006,31(1):10-13.
    [117]任三孩,常文革,刘向君.基于SAR影像模拟几何校正算法参数误差影响分析[J].信号处理,2010,26(10):1588-1594.
    [118] Seung H S, Daniel D L. The Manifold Ways of Perception[J]. Science,2000,290(12):2268-2269.
    [119]万余庆,谭克龙,周日平.高光谱遥感应用研究[M].北京:科学出版社,2006.
    [120]袁颖,周爱红,李治广.基于GRNN神经网络的桁架结构损伤识别的两步法[J].建筑科学,2013,26(9):18-22.
    [121]刘冬生,赵辉,王红君等.基于小波分析和神经网络的电机故障诊断方法研究[J].天津理工大学学报,2009,25(1):1-14.
    [122]王小红,胡兵华,龚微.GPS高程的神经网络转换方法[J].江西科学,2009,30(3):308-310.
    [123]何毅.基于BP神经网络电容法刨花含水率测试仪的研究玉开发[D].南京:南京农业大学,2006.
    [124]周开利.神经网络模型及其MATLAB仿真程序设计[M].北京:清华大学出版社,2004.
    [125]韩韬,陶智.基于BP神经网络的耳语音转换为正常语音的研究[J].通信技术,2009,42(2),152-1542.
    [126]高隽.人工神经网络原理及仿真实例[M].北京:机械工业出版社,2007.
    [127]苏美娟.径向基函数神经网络学习算法研究[D].苏州:苏州大学,2007.
    [128]王小红.水轮机几何参数反演算法及其应用[D].石家庄:河北工程大学,2009.
    [129]李慧,顾沈明.基于RBF神经网络的赤潮预测方法[J].计算机工程与应用,2011,24(10):10-14.
    [130]陈长万.基于动力特性的桥梁结构损伤识别方法的研究进展[J].中国西部科技,2011,18(10):48-50.
    [131]胡浪涛,何辅云,沈兆鑫.油气管道高速漏磁检测系统中数据压缩研究[J].合肥工业大学学报,2009,32(3):320-323.
    [132]刘永科,赵文忠,何同弟.粒子群优化RBF神经网络的自适应谐波检测[J].自动化与仪器仪表,2011,22(11):60-63.
    [133]卢洁.基于PSO-RBF神经网络的入侵检测系统的研究与实现[D].南京:南京林业大学,2008.
    [134] Keerthi S S, Lin C J. Asymptotic behaviors of support vector machines with gaussiankernel[J].Neural computation,2003,15:1667-1689.
    [135]何同弟,李见为,黄鸿.PSO优选参数的SVR遥感分类研究[J].计算机工程与应用,2010,46(24):11-14.
    [136]杨淑莹.模式识别玉智能计算-Matlab技术实现[M].北京:电子工业出版社,2008.
    [137]蚩志锋,杨先武.基于改进粒子群优化RBF神经网络的地理信息预测[J].测绘科学,2012,37(3):139-141.
    [138]丁阳,张玉峰,李忠献.大跨度空间网格结构的损伤定位[J].建筑结构学报,2006,27(1):16-23.
    [139]宋蓥潮,韩宝平.基于径向基神经网络的徐州区域经济预测模型[J].内蒙古煤炭经济,2010,25(1):465-469.
    [140]何茂亭.空调系统能耗监测及故障诊断[D].哈尔滨:哈尔滨工业大学,2009.
    [141]陈云浩,冯通,史培军等.基于面向对象和规则的遥感影像分类研究[J].武汉大学学报(信息科学版),2006,31(4):316-320.
    [142]王学厚,韩璞,李岩等.基于PSO的RBF神经网络在热工系统辨识中的应用[J].华北电力大学学报,2008,35(1):52-56.
    [143]何晓群,刘文卿.应用回归分析[M].北京:中国人民大学出版社,2001.
    [144]刘勇,廖士中.基于支持向量机泛化误差界的多核学习方法[J].武汉大学(理工版),2012,58(2):149-156.
    [145] Vapnik V N著,张学工译.统计学习理论的本质[M].北京:清华大学出版社,2000.
    [146]谭琨,杜培军.基于支持向量机的高光谱遥感图像分类[J].红外与毫米波学报,2008,27(2):123-129.
    [147]陶亮,庄镇泉.个人身份认证的正面人脸识别算法[J].中国图象图形学报,2003,18(8):860-865.
    [148]马清峰,潘宏侠.粒子群优化神经网络的齿轮箱故障诊断研究[J].机械工程,2006,17(8):332-334.
    [149]杨芳.基于支持向量回归(SVR)的材料热加工过程建模[D].上海:上海交通大学,2010.
    [150] Vapnik V N.Estimation of dependences based on empirical data[M].London: CambridgeUniversiy Press,1992.
    [151] Moody J E, Darken C J. Fast learning in networks of locally.tuned processingunits[J].Neural Computation,1989,31(2):281-294.
    [152] Specht F, General A.Regression neural network[J].IEEE Transactions on Neural Networks,1991,32(6):568-576.
    [153] Weston J.Leave one out support vector machines[C].IJCAI,1999:727-733.
    [154] Anthony M, Bartlett P.Learning in neural networks[M].Cambridge University Press,Cambridge,1999.
    [155] John S T, Cristianini N.Margin distribution and soft margin[M].Advances in LargeMargin Classifiers, MIT Press, Cambridge,2000.
    [156]张学工.关于统计学习理论与支持向量机[J].自动化学报,2000,26(1):32-42.
    [157]张铃.支持向量机理论与基于规划的神经网络学习算法[J].计算机学报,2001,24(2):113-118.
    [158]刘靖旭,蔡怀平,谭跃进.支持向量回归参数调整的一种启发式算法[J].系统与仿真学报,2007,19(7):1540-1543.
    [159]叶俊勇,汪同庆,杨波.基于支持向量机的人脸检测算法[J].计算机工程,2003,29(2):23-24.
    [160] Amari, S W. Improving support vector machines classifiers by modifying kernelfunction[J].Neural Networks,1999,12:783-789.
    [161]王晓月,王积勤.支持向量机研究与应用[J].空军工程大学学报(自然科学版),2004,15(3):49-55.
    [162] Nello C, John S T.An introduction to support vector machines and other kernel basedlearning methods[M].Beijing Publishing House of Electronics Industry, Beijin,2004.
    [163]肖轩.灰色神绎网络与支持向量机预测模型研究[D].武汉:武汉理工大学,2009.
    [164]林红华.电子商务环境下企业信息的智能统计分析方法研究[D].重庆:重庆大学,2004.
    [165]赵晶,高隽,张旭东等.支出向量机综述[C].全国第15届计算机科学与技术应用学术会议,2003:576-581.
    [166]阎辉,张学工,李衍达.支持向量机与最小二乘法的关系研究[J].清华大学学报,2001,41(9):77-80.
    [167] Ge M, Du R, Zhang C C.Fault diagnosis using support vector machine with an application insheet metal stamping operations[J]. Mechanical Systems and Signal Processing,2004,18:143-159.
    [168] Deniz O, Casterillon M, Hernandez M.Face recognition using Iindependent componentanalysis and support vector machines[J].Pattern Recognition Letters,2003,24(2):2153-2157.
    [169] Bottou L, Dcnker C.Comparison of classifier methods: A case study in handwriting digitrecognition[C].proceedings of Int’l Conf on Patten Recognition, New York,1994:77-87.
    [170]李建伟,杨晓光,汪友华.多维输出SVR的ECT两相流图像重建方法[J].计算机工程与应用,2010,46(31):157-160.
    [171]刘江华,程君实,陈佳品.支持向量机训练算法综述[J].信息与控制,2002,31(1):45-50.
    [172] Martin B,Hugh G L,Steve R G.Linear spectral mixture models and support vector machinesfor remote sensing[J].IEEE Transactions0n Geo-science and Remote Sensing,2000,38(5):2346-2360.
    [173] Hsu C W, Lin c J. A comparison of methods for multi-class support vectormachines[J].IEEE Transaction Neural Networks,2002,13(2):415-425.
    [174] Smola J,Scholkopf B.A tutorial on support vector regression[J].Technical Report NeuroTechnical Renort Series,1998:1-20.
    [175]邓先礼.最优化技术[M].重庆:重庆大学出版社,1998.
    [176] Amari S W. Improving support vector machines classifiers by modifying kernelfunction[J].Neural Networks,1999,12:783-789.
    [177]朱永生,张优云.支持向量机分类问题中几个问题的研究[J].计算机工程与应用,2003,39(13):36-38.
    [178]于宁锋,杨化超.一种用于高光谱遥感影像分类的改进多类支持向量机[J].理论研究,2007,20(5):7-10.
    [179] Yang A Y, Wright J.Feature selection in face recognition: a sparse representationperspective[J].Technical Reporty,2007,20(4):1024-1029.
    [180] Wright A J, Yang A, Ganesh Y, et al. Robust face recognition via sparserepresentation[C].Pattern Analysis and Machine intelligence,2009,31(2):210-227.
    [181] Ranzato M A, Boureau Y L, Cun Y L. Sparse feature learning for deep beliefnetworks[J].Advances in Neural Information Processing Systems,2007,20(4):1-8.
    [182] Raina R, Battle A, Lee H, et al.Self-taught learning: Transfer learning from unlabeleddata[C].International conference on Machine learning,2007:759-766.
    [183] Kavukcuoglu K, Ranzato M, Fergus R, et al.Learning invariant features throughtopographic filter maps[J].Pattern Recognition,2009,30(6):1605-1612.
    [184] Zhi R, Flied M, Ruan Q, et al.Graph preserving sparse nonnegative matrix factorizationwith application to facial expression recognition[J].Transactions on Systems,2011,41(1):38-52.
    [185] Yuan X T, Yan S. Visual classification with multi-task joint sparserepresentation[J].Computer Vision and Pattern Recognition.2010,41(1):3493-3500.
    [186] Ramirez I, Sprechmann P, Sapiro G.Classification and clustering via dictionary learningwith structured incoherence and shared features[J]. Computer Vision and PatternRecognition,2010,48(12):3501-3508.
    [187]李民,李世华,乐翔.基于学习字典的图像修复算法[J].仪器仪表学报,2012,23(9):2041-2047.
    [188]何艳敏,甘涛,陈武凡.基于稀疏表示的两级图像去噪[J].电子与信息学报,2012,34(9):2268-2271.
    [189] Bruckstein A M, Donoho D L, Elad M.From sparse solutions of systems of equations tosparse modeling of signals and images[J].SIAM Review,2009,51(1):34-81.
    [190] Gibbs G.Learning by doing: a guide to teaching and learning methods[M]. CambridgeUniversity Press, Cambridge,1988.
    [191] Elad M, Figueiredo M A, Ma Y.On the role of sparse and redundant representations inimage processing[J].Applications of Sparse Representation and Compressive Sensing,2010,98(6):972-982.
    [192] Wang Z, Bovik A C.A universal image quality index[J].Signal Processing Letters,2002,9(3):81-84.
    [193] Olshausen B A, Field D J.Emergence of simple-cell receptive field properties by learning asparse code for natural images[J].Nature,1996,38(1):607-609.
    [194]焦李成,谭山.图像的多尺度几何分析[J].电了学报,2003,31(12):1975-1981.
    [195] Temlyakov V.Nonlinear methods of approximation[J].Foundations of Comp Math,2002,3(1):33-107.
    [196] Mallat S, Zhang Z.Matching pursuit with time frequency dictionaries[J].Signal Process,1993,41(12):3397-3415.
    [197] Huo X. Sparse image representation via combined transforms[D]. California:Stanford Univ,1999.
    [198] Do M, Vetterli M.Framing Pyramids[J].Signal Processing,2003,51(9):2329-2342.
    [199]霍承福.超光谱遥感图像压缩技术研究[D].合肥:中国科技大学,2012.
    [200] Tian X, Zhang X, Ding T. Wavelet based contourlet coding using speckalgorithm[C].International Conference on Signal Processing,2008,(10):1203-1206.
    [201] Mallat S, Zhang Z.Matching pursuits with time frequency dictionaries[J].SignalProcessing,1993,41(12):3397-3415.
    [202] Pati Y, Rezaiifar R. Recursive function approximation with applications to waveletdecomposition[J].Sistems and Computers,1993,11(3):40-44.
    [203] Tropp J.Algorithmic results for sparse approximation[J].Information Theory,2004,50(10):2231-2242.
    [204] Zhang S, Moloney C. A Multi.resolution and Multi.direction ImageRepresentation[C].Canadian Conference on Elecmical and Computer Engineering, Canada,2004,1323-1326.
    [205] Oshe S, Burge M, Goldfarb D et al. An iterative regularization method for totalvariation.based image restoration[J].Multiscale Modeling&Simulation,2005,4(2):460-489.
    [206] Cai J, Osher S, Shen Z. Linearized bregman iteration for frame based imagedeblurring[J].Imaging Sciences archive,2009,2(1):143-168.
    [207] Burger M, Osher S, Xu J, et al. Nonlinear inverse scale space methods for imagerestoration[R].Lecture Notes in Computer Science,2005,3752:25-36.
    [208] Yin W, Osher S, Goldfarb D, et al.Bregman iterative algorithms for11.minimization withapplications to compressed sensing[J].Imaging Sciences (SUMS),2008,1(1):143-168.
    [209] Xu J, Osher S.Iterative regularization and nonlinear inverse scale space applied towavelet.based denoising[J].Image Processing,2006,16(2):534-544.
    [210] Afonso M V, Bioucas.Dias J M, Figueiredo M A.Image denoising with compoundregularization using a bregman iterative algorithm[C].Conference on Telecommunications,Portugal,2009,1046-1054.
    [211] Marquina A, Osher S J. Image super-resolution by TV regularization and bregmaniteration[J].Journal of Scientific Computing,2008,37(3):367-382.
    [212] Rudin L I, Osher, S, Fatemi E. Nonlinear total variation based noise removalalgorithms[J].Physica D,1992,60(14):259-268.
    [213]石光明,刘丹华,高大化等.压缩感知理论及其研究进展[J].电子学报,2009,37(5):1070-1081.
    [214] Baron D, Sarvotham S R.Bayesian compressive sensing via belief propagation[J].SignalProcessing,2010,58(1):269-280.
    [215] Tipping M E.Sparse bayesian learning and the relevance vector machine[J].Journal ofMachine Learning Research,2001,21(1):241-244.
    [216] Wipf D P, Rao B D.Sparse bayesian learning for basis selection[J].Signal Processing,2004,52(8):2153-2164.
    [217] Kanemura A, Maeda S, Ishii S.Sparse bayesian learning of filters for efficient imageexpansion[J].Image Processing,2010,19(6):1480-1490.
    [218] Rubinstein R, Zibulevsky M, Elad M.Double sparsity:learning sparse dictionaries for sparsesignal approximation[J].Signal Processing,2009,58(2):1553-1564.
    [219] Lewicki M S, Sejnowski T J.Learning overcomplete representations[J].Neural Computer,2000,12(2):337-365.
    [220] Engan K, Aase S O, Husey J H.Method of optimal directions for frame design[J].ComputerSociety,1999,5:2443-2446.
    [221] Skretting K, Engan K.Recursive Least Squares Dictionary Learning Algorittun[J].SignalProcessing,2010,58(4):2121-2130.
    [222] Mairal J, Bach F, Ponce J.Online Dictionary Learning for Sparse Coding[C].InternationalConference on Machine Learning,2009, Canada,14(7):689-696.
    [223] Bruno B,Olshausen P.Emergence of simple.cell receptive field properties by learning asparse code for natural images[J].Nature,1996,381(3):607-609.
    [224]赵佳佳,唐峥远,杨杰.基于图像稀疏表示的红外小目标检测算法[J].红外与毫米波学报,2011,30(2):156-161.
    [225]徐健,常志国.基于聚类的自适应图像稀疏表示算法及其应用[J].光子学报,2011,40(2):317-319.
    [226]宋相法,焦李成.基于稀疏表示及光谱信息的高光谱遥感图像分类[J].电子与信息学报,2012,34(2):268-272.
    [227]何同弟,李见为.基于自适应稀疏表示的高光谱图像分类[J].系统工程与电子技术,2013,35(9):1194-1198.

© 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