基于SVM邻近同化滤波模型的冰冻湖泊水体精确提取研究
|
摘要
本文依托于国家科技基础性工作专项重点项目“中国湖泊水质、水量和生物资源调查”(2006FY110600)子课题“中国湖泊卫星遥感调查”,采用小样本学习、抗噪声性能好、学习效率高的支持向量机(SVM,Support Vector Machine)方法来提取多光谱遥感影像冰冻湖泊水体。支持向量机最大特点是根据结构风险最小化原则,尽量提高学习机的泛化能力,即由有限的训练集样本得到小的误差能够保证对独立的测试集仍保持小的误差,SVM在遥感信息提取方面,特别是在缺少先验知识的情况下,具有较高的推广能力。
本文分析了冰冻湖泊水体的光谱特征,说明了传统遥感影像分类方法不能达到较高精度的原因,在此基础上利用MATLAB支持向量机工具箱建立了SVM提取模型,并选择了东北地区的查干湖和长白山天池CBERS多光谱遥感影像进行了提取试验。试验表明,两湖提取精度支持向量机较最大似然法提高了3.93%。但仅应用SVM方法提取冰冻湖泊水体,提取结果小图斑多、分类不完整,因此本文在原来模型的基础上加入了邻近同化滤波方法,有效剔除了小图斑。
综合SVM邻近同化滤波模型提取冰冻湖泊水体的研究过程,本文得出的结论如下:
(1)查干湖湖面整体冰冻;据实地考察和相关文献,长白山天池西部由于湖底受温泉影响,湖水冬季不封冻,从影像上看天池西部呈深蓝色的部分就是未冰冻的湖泊水体。应用SVM邻近同化滤波提取模型,不仅实现了对全部冰冻湖泊水体的精确提取,对冰水混合的湖泊水体也同样适用,所以本文的提取模型对冰冻情况复杂的湖泊水体精确提取有着广阔的应用前景。
(2)与长白山天池相比,查干湖结冰湖面破碎度较高,由于处在破碎部分的像元光谱复杂,最大似然法难以达到较高的提取精度。在同样训练区样本下,与最大似然法相比,SVM提取精度提高了5.36%,由此可以看出SVM具有较强的小样本学习能力,提取精度高。
(3)为剔除湖边浅水沼泽和冰冻期湖面雪等干扰地物的影响,本文提出邻近同化滤波方法,这也是本文的创新之处。经邻近同化滤波模型处理后,提取结果小图斑较少,类别完整。
本文在如下两方面还需要进一步研究:
(1)长白山天池处在山区,从图4.17可以看出,其南部的山体阴影影响并未有效去除掉,因此提取山区型冰冻湖泊水体时,如何有效剔除山体阴影的影响有待于进一步研究。
(2)选择邻近同化滤波模板的大小时需要根据实际情况人为设定,模板选择太大会导致分类失真,选择太小又不能有效除去干扰地物,因此如何选择合适的同化滤波模板有待于进一步研究。
This article is based on the program servey of Lakes in China, which is the sub-topics of the program Survey of Water Quality,Volume and Biological Resource of Lakes in China which is belonged to National Fundamental Research Program of China,and adopts SVM (Support Vector Machine) to extract multi-spectral remote sensing image of frozen lake water. This method is learning from small sample, good at noise proof and quite efficient. The most prominent feature of SVM is to improve the generalization ability of the learning machine as much as possible according to the Structure Risk Minimization Principle, which means if the machine gets small errors from limited training sets sample it can also be insure to keep small error in the case of individual training set. The method of SVM possesses great generalization ability in the field of remote sensing information extraction, especially when we are lack of a priori knowledge.
This article analyzed spectral signature of frozen lake water, and explained the reason why they can’t get higher accuracy when using the traditional remote sensing image classification methods. On this basis, writer established the SVM extraction model by utilizing the MATLAB-SVM toolkits, and executed the extraction experiment on CBERS multi-spectral remote sensing image in Lake Balapan and Heaven Pool. The experiment shows that the extraction accuracy increases 3.93% when using SVM method than using Maximum Likelihood. But SVM method also has its weak points, which are smaller extraction result, more marks and the incomplete classification. So this article added the Neighboring Filter Assimilation method to the existed model, which eliminates small marks efficiently.
After combining the research proceed of extracting the frozen lake water by means of SVM and Neighboring Filter Assimilation, conclusions come as follow:
(1) The surface of Lake Balapan is frozen completely. According to the field survey and relative documents, the Heaven Pool doesn’t get frozen in winter owing to the hotspring in the bottom. In the images, the navy blue part in the west section is the lake water without frozen. This SVM-Neighboring Filter Assimilation model not only can extract the completely frozen lake water precisely, and also work in ice-water mixed lake water. Therefore, the extraction model in this article has vast application in extracting precisely the complicate-situation lake water.
(2) Comparing to that in Heaven Pool, the degree of fragmentation in the frozen surface of Lake Balapan is higher. Because the pixel spectra in the broken part are quite complicate, Maximum likelihood method can’t work out high extraction accuracy. In the condition of same sample, SVM can increase the accuracy about 5.36% than Maximum likelihood. It shows that SVM is better at small sample learning ability, and has higher extraction accuracy.
(3) In order to eliminate the affection from shallow marsh around the lake and the snow on the lake surface in ice period, this article also provided extraction experiment in Neighboring Filter Assimilation method .This is also the biggest innovation of this article. The result shows that the image is smaller, marks are less and classification is complete.
It still needs development in the future in the following two aspects:
(1) Heaven Pool is in the mountain area, and Figure 4.17 shows that the affection from the shadow of mountain in south hasn’t been eliminated. Therefore, during extracting the frozen lake water in mountain area, it still needs research on how to eliminate the affection of mountain shadow.
(2) When choose the size of Assimilation filtering template, it should be decided dependently according to the practical situation. If the size is too big, the classification will be distorted; if it’s too small, the interferent cannot be eliminated efficiently. So it still needs research on how to choose suitable Assimilation filtering template.
本文分析了冰冻湖泊水体的光谱特征,说明了传统遥感影像分类方法不能达到较高精度的原因,在此基础上利用MATLAB支持向量机工具箱建立了SVM提取模型,并选择了东北地区的查干湖和长白山天池CBERS多光谱遥感影像进行了提取试验。试验表明,两湖提取精度支持向量机较最大似然法提高了3.93%。但仅应用SVM方法提取冰冻湖泊水体,提取结果小图斑多、分类不完整,因此本文在原来模型的基础上加入了邻近同化滤波方法,有效剔除了小图斑。
综合SVM邻近同化滤波模型提取冰冻湖泊水体的研究过程,本文得出的结论如下:
(1)查干湖湖面整体冰冻;据实地考察和相关文献,长白山天池西部由于湖底受温泉影响,湖水冬季不封冻,从影像上看天池西部呈深蓝色的部分就是未冰冻的湖泊水体。应用SVM邻近同化滤波提取模型,不仅实现了对全部冰冻湖泊水体的精确提取,对冰水混合的湖泊水体也同样适用,所以本文的提取模型对冰冻情况复杂的湖泊水体精确提取有着广阔的应用前景。
(2)与长白山天池相比,查干湖结冰湖面破碎度较高,由于处在破碎部分的像元光谱复杂,最大似然法难以达到较高的提取精度。在同样训练区样本下,与最大似然法相比,SVM提取精度提高了5.36%,由此可以看出SVM具有较强的小样本学习能力,提取精度高。
(3)为剔除湖边浅水沼泽和冰冻期湖面雪等干扰地物的影响,本文提出邻近同化滤波方法,这也是本文的创新之处。经邻近同化滤波模型处理后,提取结果小图斑较少,类别完整。
本文在如下两方面还需要进一步研究:
(1)长白山天池处在山区,从图4.17可以看出,其南部的山体阴影影响并未有效去除掉,因此提取山区型冰冻湖泊水体时,如何有效剔除山体阴影的影响有待于进一步研究。
(2)选择邻近同化滤波模板的大小时需要根据实际情况人为设定,模板选择太大会导致分类失真,选择太小又不能有效除去干扰地物,因此如何选择合适的同化滤波模板有待于进一步研究。
This article is based on the program servey of Lakes in China, which is the sub-topics of the program Survey of Water Quality,Volume and Biological Resource of Lakes in China which is belonged to National Fundamental Research Program of China,and adopts SVM (Support Vector Machine) to extract multi-spectral remote sensing image of frozen lake water. This method is learning from small sample, good at noise proof and quite efficient. The most prominent feature of SVM is to improve the generalization ability of the learning machine as much as possible according to the Structure Risk Minimization Principle, which means if the machine gets small errors from limited training sets sample it can also be insure to keep small error in the case of individual training set. The method of SVM possesses great generalization ability in the field of remote sensing information extraction, especially when we are lack of a priori knowledge.
This article analyzed spectral signature of frozen lake water, and explained the reason why they can’t get higher accuracy when using the traditional remote sensing image classification methods. On this basis, writer established the SVM extraction model by utilizing the MATLAB-SVM toolkits, and executed the extraction experiment on CBERS multi-spectral remote sensing image in Lake Balapan and Heaven Pool. The experiment shows that the extraction accuracy increases 3.93% when using SVM method than using Maximum Likelihood. But SVM method also has its weak points, which are smaller extraction result, more marks and the incomplete classification. So this article added the Neighboring Filter Assimilation method to the existed model, which eliminates small marks efficiently.
After combining the research proceed of extracting the frozen lake water by means of SVM and Neighboring Filter Assimilation, conclusions come as follow:
(1) The surface of Lake Balapan is frozen completely. According to the field survey and relative documents, the Heaven Pool doesn’t get frozen in winter owing to the hotspring in the bottom. In the images, the navy blue part in the west section is the lake water without frozen. This SVM-Neighboring Filter Assimilation model not only can extract the completely frozen lake water precisely, and also work in ice-water mixed lake water. Therefore, the extraction model in this article has vast application in extracting precisely the complicate-situation lake water.
(2) Comparing to that in Heaven Pool, the degree of fragmentation in the frozen surface of Lake Balapan is higher. Because the pixel spectra in the broken part are quite complicate, Maximum likelihood method can’t work out high extraction accuracy. In the condition of same sample, SVM can increase the accuracy about 5.36% than Maximum likelihood. It shows that SVM is better at small sample learning ability, and has higher extraction accuracy.
(3) In order to eliminate the affection from shallow marsh around the lake and the snow on the lake surface in ice period, this article also provided extraction experiment in Neighboring Filter Assimilation method .This is also the biggest innovation of this article. The result shows that the image is smaller, marks are less and classification is complete.
It still needs development in the future in the following two aspects:
(1) Heaven Pool is in the mountain area, and Figure 4.17 shows that the affection from the shadow of mountain in south hasn’t been eliminated. Therefore, during extracting the frozen lake water in mountain area, it still needs research on how to eliminate the affection of mountain shadow.
(2) When choose the size of Assimilation filtering template, it should be decided dependently according to the practical situation. If the size is too big, the classification will be distorted; if it’s too small, the interferent cannot be eliminated efficiently. So it still needs research on how to choose suitable Assimilation filtering template.
引文
[1]李晓峰,张树清,庞振平等.矢量景观指数在遥感信息提取中的应用——以乾安湖群为例[J].遥感学报,2008,12(2):291-295
[2]周成虎,骆剑承,杨存建等.遥感影像地学理解与分析[M].北京:科学出版社,2003.
[3]田源,塔西普拉提.特依拜,丁建丽等.基于支持向量机的土地覆被遥感分类[J].资源科学,2008,30(8):1268-1273.
[4]赵萍,冯学智,林广发.SPOT卫星影像居民地信息自动提取的决策树方法研究[J].遥感学报,2003,7(4):309-315.
[5]骆剑承,周成虎,杨艳.人工神经网络遥感影像分类模型及其与知识集成方法研究[J].遥感学报,2001,5(2):122-129.
[6]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.
[7] Chapelle O, Haffner P, Vapnik V N. Support Vector Machines for Histogram2 based Image Classification [ J ]. IEEE Trans. On Neural Networks, 1999, 10(5): 1055-1064.
[8] Vapnik V N. The Nature of Statistical Learning Theory [M] , New York : Springer ,1995.
[9] Cortes C, Vapnik V. Support Vector Networks [J]. Machine Learning, 1995, 20 (3):273-297.
[10] Scholkopf B , Sung K, Burges C , et al. Comparing Support Vector Machines with Gaussian Kernels to Radial Basis Function Classifier[J ]. IEEE Trans. on Signal Processing, 1997, 45 (11): 2758-2765.
[11] Burges C J C.A Tutorial on Support Vector Machines for Pattern Recognition [J] .Data Mining and Knowledge Discovery, 1998, 2(2):955-974.
[12]赵书河,冯学智,都金康,林广发.基于支持向量机的SPIN-2影像与SPOT-4多光谱影像融合研究[J].遥感学报,2003,7(5): 407-411.
[13] Vapnik V N. An Overview of Statistical Learning Theory [J] . IEEE Trans. On Neural Networks, 1999, 10(5): 988-999.
[14] Cherkassky V, Mulier F. Learning from Data: Concepts, Theory and Methods [M].N Y: John Viley & Sons, 1997
[15] Vapnik VN. Estimation of Dependencies Based on Empirical Data. Berlin: Springer-Verlag [M]. 1982
[16] Vapnik V, Levin E, Le Cun Y. Measuring the VC-dimension of a learning machine. Neural Computation [M]. 1994,6: 851～876.
[17] Huang C,Davis L S, Townshend J R G. An assessment of support vector machine for land cover classification [J] . International Journal of Remote Sensing . 2002, 23,725-749.
[18] Martin Brown, Hugh G Lewis, Steve R Gunn. Linear Spectral Mixture Model and support vector machine for Remote Sensing[J] . IEEE Trans. on Signal Processing, 2000, 38 (5):2346-2360.
[19]董广军,张永生,范永弘.基于多特征多分辨率融合的高光谱图像分类[J].红外与毫米波学报,2006,25 (2):123-126.
[20] Zhang J, Zhang Y, Zhou T. Classification of hyperspectral data using support vector machine[C]. IEEE Trans. on Signal Processing, 2001, 38 (5):882-885.
[21]潭琨,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):123-128
[22]何灵敏.支持向量机集成及在遥感分类中的应用[博士论文].浙江大学.2006
[23]杨青生,黎夏.基于支持向量机的元胞自动机及土地利用变化模拟[J].遥感学报,2006,10(6):836-845
[24]张风丽,尹球,匡定波等.草地光谱分类最佳时相选择分析[J].遥感学报,2006,10(4):482-488
[25]张景雄.遥感影像的全模糊监督分类[J].武汉测绘科技大学学报.1998, 23(3):211214.
[26]杨健.人工神经网络在植被遥感影像分类中的应用研究[中科院植物所硕士文].2000.
[27]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):139143.
[28]朱长青,杨晓梅.具有更佳分辨率小波分解的遥感影像纹理分类[J].地理研究,1997,16(1):5359.
[29]程昌秀,严泰来,朱德海等.GIS和RS集成的高分辨率遥感影像分类技术在地学识别中的应用[J].中国农业大学学报,2001,6(3):5054.
[30]戴昌达,姜小光,唐伶俐.遥感图像应用处理与分析[M].北京:清华大学出版社,2004.
[31]梅安新,彭望琭,秦其明,刘慧平.遥感导论[M].北京:高等教育出版社,2002.
[32]钱乐祥等.遥感数字影像处理与地理特征提取[M].北京:科学出版社,2005.
[33]赵英时等.遥感应用分析原理与方法[M].北京:科学出版社,2003.
[34]彭望琭,白振平,刘湘南,曹彤.遥感导论[M].北京:高等教育出版社,2003.
[35]陈华芳,王金亮,陈忠等.山地高原地区TM影像水体信息提取方法比较--以香格里拉县部分地区为例[J].遥感技术与应用,2004,19(6)
[36] Barzilay O, Brailovsky VL. On Domain Knowledge and Feature Selection Using a Support Vector Machine[J].Pattern Recognition Letters. 1999,20(5):475-484
[37]李红莲,王春花,袁保宗.一种改进的支持向量机NN-SVM[J].计算机学报, 2003,26(8): 1015-1020.
[38]李蓉,叶世伟,史忠植. SVM-KNN分类器-一种提高SVM分类精度的新方法[J].电子学报, 2002, 30(5): 745-748.
[39]孙德山,吴今培.支持向量回归中的预测信任度[J].计算机科学, 2003, 30(8): 126-127.
[40] Platt J . Fast training of support vector machines using sequential minimal optimization [J]. Cambridge: MIT Press, 1999. 185-208.
[41] Platt J C , Cristianini N , Shawe-Taylor J . Large margin DAG’s for multiclass classification Advances in Neural Information Processing Systems[J]. Cambridge, MA: MIT Press, 2000 , 12 : 547-553.
[42] Weston J , Watkins C. Multi-class support vector machines : [Technical Report SD2 TR298204]. Department of Computer Science , Royal Holloway University of London ,1998
[43] Inoue T , Abe S. Fuzzy Support Vector Machines for Pattern Classification[J]. In: Proceedings of International Joint Conference on Neural Networks, 2001.1449-1454.
[44]张学工.关于统计学习理论与支持向量机[J].自动化学报,2000,1(26): 32-42.
[45]董云杰,邱熔胜.基于支持向量机与极端保守在线算法相结合的多类分类器[J].模式识别与人工智能,2003,16(4):476-481
[46]谷雨,郑锦辉、戴明伟等.基于Bagging支持向量机集成的入侵监测研究[J].微电子与计算机,2005,22(5):17-19
[47]孔安生,王洪澄,李国正.神经网络集成与支持向量机在多值分类问题上的比较研究[J].计算机工程与应用,2005,22(1):46-48
[48]李建民,张钵林,福宗.支持向量机的训练算法[J].清华大学学报,自然科学,2003,43(1):120-124
[49]李烨,蔡云泽,许晓鸣.基于支持向量机集成的故障诊断[J].控制工程,2005(12):170-173
[50]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
[51]唐春生,金以慧.基于全信息矩阵的多分类器机集成方法[J].软件学报,2003,16(6):1103-1109
[52]唐伟,周志华.基于Bagging的选择性聚类集成[J].软件学报,2005,16(4):496-502
[53]魏玲.基于支持向量机集成的分类[博士论文],西安交通大学,2004
[54]叶芗芸,戚飞虎,朱国霞.一种多极分类器集成的字符识别方法[J].电子学报,1998,26(11):15-19
[55]邓乃扬,田英杰.数据挖掘中的新方法——支持向量机[M].北京:科学出版社,2004
[56]曾华军,张银奎等译.机器学习[M].北京:机械工业出版社,2003
[57] Dong B,Cao C, Lee S E. Applying Support Vector Machines to Predict Building Energy Consumption in Tropical Region[J]. Energy and Buildings, 2005, 37:545-553.
[58] Cherkassky V,Ma Y. Practical Selection of SVM Parameters and Noise Estimation for SVM Regression[J]. Neural Network, 2004, 17:113-126.
[59] David V, A Sanchez.Advanced Support Vector Machines and Kemel Methods [J]. Neurocan putting, 2003, 55:5-20
[60] Chang C C, Lin C J. Training Support Vector Classifiers Theory and Algorithms [J]. Neural Computation, 2001, 13(9):2119-2147.
[61] Ana M B, Dragan N, Leopold C. Prohabilistic SVM Outputs for Pattem Recognition Analytical Geometry [J]. Neurocan putting, 2004, 62:293-303
[62]刘星,胡光道.高光谱遥感图像品与自适应同态滤波薄云去除[J].物探化探计算技术,2008,30(2):163-168
[63]卢桂林,谢海元,李媛媛等.雷达信号的非线性滤波方法的基础理论综述[J].工程技术,2008,1:31-32
[64]李刚,杨武年,翁韬.一种基于同态滤波的遥感图像薄云去除算法[J].测绘科学,2007,32(3):47-48
[65]贾承丽,匡纲要. SAR图像去斑方法[J].中国图像图形学报,2005,10(2):135-141
[66]飞思科技产品研发中心.MATLAB7基础与提高[M].北京:电子工业出版社.2007.
[67]阮秋琦等译.数字图像处理(MATLAB版)[M].北京:电子工业出版社.2006.
[68]周开利,康耀红.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,2005.
[69]兰雪梅,米键,黄承明.BP网络的MATLAB实现[J].研究与设计微电脑应用,2003,12(01):6-8.
[70]阮秋琦等译.数字图像处理(MATLAB版)[M].北京:电子工业出版社.2006.
[71]闻新,周露,李翔.MATLAB神经网络仿真与应用[M].北京:科学出版社,2003
[72]吕金福,肖荣寰,李志民等.松嫩平原湖泊综合分类研究[J].东北师范大学报自然科学版,2000,32(2):92-98.
[73]郭跃东,何艳芬.松嫩平原湿地动态变化及其驱动力研究[J].湿地科学,2005,3(1):54-59.
[74]介冬梅,吕金福.松嫩平原湖滩土地类型与利用对策研究[J].东北师范大学报自然科学版,2000,32(2):112-116.
[75]吕金福,肖荣寰,李志民等.松嫩平原湖泊类型组合的区域分类[J].东北师范大学自然科学版,2000,32(2):99-105.
[76]吕金福,李志民,冷雪天等.松嫩平原湖泊的分类与分区[J].地理科学,1998,18(6):524-530 .
[77]王苏民,窦鸿身.中国湖泊志[M].北京:科学出版社,1998,519-520.
[78]赵书河,冯学智,都金康.中巴资源一号卫星水体信息提取方法研究[J].南京大学学报(自然科学),2003,39(1):102-112
[79]杜云艳,周成虎.水体的遥感信息自动提取方法[J].遥感学报,1998,2(4):264-269
[80]李晶晶,贾建华,郝景研.基于RS的松嫩平原大安湖泊群面积提取与动态变化分析[J].遥感信息,2009,4(2)
[81]赵英时等.遥感应用分析原理与方法[M].北京:科学出版社,2003,204-207
[82]吕诚然,刘斌,谢红等.遥感图像处理与信息提取方法的研究[J].吉林地质,2004,23(4):264-26
[2]周成虎,骆剑承,杨存建等.遥感影像地学理解与分析[M].北京:科学出版社,2003.
[3]田源,塔西普拉提.特依拜,丁建丽等.基于支持向量机的土地覆被遥感分类[J].资源科学,2008,30(8):1268-1273.
[4]赵萍,冯学智,林广发.SPOT卫星影像居民地信息自动提取的决策树方法研究[J].遥感学报,2003,7(4):309-315.
[5]骆剑承,周成虎,杨艳.人工神经网络遥感影像分类模型及其与知识集成方法研究[J].遥感学报,2001,5(2):122-129.
[6]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.
[7] Chapelle O, Haffner P, Vapnik V N. Support Vector Machines for Histogram2 based Image Classification [ J ]. IEEE Trans. On Neural Networks, 1999, 10(5): 1055-1064.
[8] Vapnik V N. The Nature of Statistical Learning Theory [M] , New York : Springer ,1995.
[9] Cortes C, Vapnik V. Support Vector Networks [J]. Machine Learning, 1995, 20 (3):273-297.
[10] Scholkopf B , Sung K, Burges C , et al. Comparing Support Vector Machines with Gaussian Kernels to Radial Basis Function Classifier[J ]. IEEE Trans. on Signal Processing, 1997, 45 (11): 2758-2765.
[11] Burges C J C.A Tutorial on Support Vector Machines for Pattern Recognition [J] .Data Mining and Knowledge Discovery, 1998, 2(2):955-974.
[12]赵书河,冯学智,都金康,林广发.基于支持向量机的SPIN-2影像与SPOT-4多光谱影像融合研究[J].遥感学报,2003,7(5): 407-411.
[13] Vapnik V N. An Overview of Statistical Learning Theory [J] . IEEE Trans. On Neural Networks, 1999, 10(5): 988-999.
[14] Cherkassky V, Mulier F. Learning from Data: Concepts, Theory and Methods [M].N Y: John Viley & Sons, 1997
[15] Vapnik VN. Estimation of Dependencies Based on Empirical Data. Berlin: Springer-Verlag [M]. 1982
[16] Vapnik V, Levin E, Le Cun Y. Measuring the VC-dimension of a learning machine. Neural Computation [M]. 1994,6: 851～876.
[17] Huang C,Davis L S, Townshend J R G. An assessment of support vector machine for land cover classification [J] . International Journal of Remote Sensing . 2002, 23,725-749.
[18] Martin Brown, Hugh G Lewis, Steve R Gunn. Linear Spectral Mixture Model and support vector machine for Remote Sensing[J] . IEEE Trans. on Signal Processing, 2000, 38 (5):2346-2360.
[19]董广军,张永生,范永弘.基于多特征多分辨率融合的高光谱图像分类[J].红外与毫米波学报,2006,25 (2):123-126.
[20] Zhang J, Zhang Y, Zhou T. Classification of hyperspectral data using support vector machine[C]. IEEE Trans. on Signal Processing, 2001, 38 (5):882-885.
[21]潭琨,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):123-128
[22]何灵敏.支持向量机集成及在遥感分类中的应用[博士论文].浙江大学.2006
[23]杨青生,黎夏.基于支持向量机的元胞自动机及土地利用变化模拟[J].遥感学报,2006,10(6):836-845
[24]张风丽,尹球,匡定波等.草地光谱分类最佳时相选择分析[J].遥感学报,2006,10(4):482-488
[25]张景雄.遥感影像的全模糊监督分类[J].武汉测绘科技大学学报.1998, 23(3):211214.
[26]杨健.人工神经网络在植被遥感影像分类中的应用研究[中科院植物所硕士文].2000.
[27]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):139143.
[28]朱长青,杨晓梅.具有更佳分辨率小波分解的遥感影像纹理分类[J].地理研究,1997,16(1):5359.
[29]程昌秀,严泰来,朱德海等.GIS和RS集成的高分辨率遥感影像分类技术在地学识别中的应用[J].中国农业大学学报,2001,6(3):5054.
[30]戴昌达,姜小光,唐伶俐.遥感图像应用处理与分析[M].北京:清华大学出版社,2004.
[31]梅安新,彭望琭,秦其明,刘慧平.遥感导论[M].北京:高等教育出版社,2002.
[32]钱乐祥等.遥感数字影像处理与地理特征提取[M].北京:科学出版社,2005.
[33]赵英时等.遥感应用分析原理与方法[M].北京:科学出版社,2003.
[34]彭望琭,白振平,刘湘南,曹彤.遥感导论[M].北京:高等教育出版社,2003.
[35]陈华芳,王金亮,陈忠等.山地高原地区TM影像水体信息提取方法比较--以香格里拉县部分地区为例[J].遥感技术与应用,2004,19(6)
[36] Barzilay O, Brailovsky VL. On Domain Knowledge and Feature Selection Using a Support Vector Machine[J].Pattern Recognition Letters. 1999,20(5):475-484
[37]李红莲,王春花,袁保宗.一种改进的支持向量机NN-SVM[J].计算机学报, 2003,26(8): 1015-1020.
[38]李蓉,叶世伟,史忠植. SVM-KNN分类器-一种提高SVM分类精度的新方法[J].电子学报, 2002, 30(5): 745-748.
[39]孙德山,吴今培.支持向量回归中的预测信任度[J].计算机科学, 2003, 30(8): 126-127.
[40] Platt J . Fast training of support vector machines using sequential minimal optimization [J]. Cambridge: MIT Press, 1999. 185-208.
[41] Platt J C , Cristianini N , Shawe-Taylor J . Large margin DAG’s for multiclass classification Advances in Neural Information Processing Systems[J]. Cambridge, MA: MIT Press, 2000 , 12 : 547-553.
[42] Weston J , Watkins C. Multi-class support vector machines : [Technical Report SD2 TR298204]. Department of Computer Science , Royal Holloway University of London ,1998
[43] Inoue T , Abe S. Fuzzy Support Vector Machines for Pattern Classification[J]. In: Proceedings of International Joint Conference on Neural Networks, 2001.1449-1454.
[44]张学工.关于统计学习理论与支持向量机[J].自动化学报,2000,1(26): 32-42.
[45]董云杰,邱熔胜.基于支持向量机与极端保守在线算法相结合的多类分类器[J].模式识别与人工智能,2003,16(4):476-481
[46]谷雨,郑锦辉、戴明伟等.基于Bagging支持向量机集成的入侵监测研究[J].微电子与计算机,2005,22(5):17-19
[47]孔安生,王洪澄,李国正.神经网络集成与支持向量机在多值分类问题上的比较研究[J].计算机工程与应用,2005,22(1):46-48
[48]李建民,张钵林,福宗.支持向量机的训练算法[J].清华大学学报,自然科学,2003,43(1):120-124
[49]李烨,蔡云泽,许晓鸣.基于支持向量机集成的故障诊断[J].控制工程,2005(12):170-173
[50]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
[51]唐春生,金以慧.基于全信息矩阵的多分类器机集成方法[J].软件学报,2003,16(6):1103-1109
[52]唐伟,周志华.基于Bagging的选择性聚类集成[J].软件学报,2005,16(4):496-502
[53]魏玲.基于支持向量机集成的分类[博士论文],西安交通大学,2004
[54]叶芗芸,戚飞虎,朱国霞.一种多极分类器集成的字符识别方法[J].电子学报,1998,26(11):15-19
[55]邓乃扬,田英杰.数据挖掘中的新方法——支持向量机[M].北京:科学出版社,2004
[56]曾华军,张银奎等译.机器学习[M].北京:机械工业出版社,2003
[57] Dong B,Cao C, Lee S E. Applying Support Vector Machines to Predict Building Energy Consumption in Tropical Region[J]. Energy and Buildings, 2005, 37:545-553.
[58] Cherkassky V,Ma Y. Practical Selection of SVM Parameters and Noise Estimation for SVM Regression[J]. Neural Network, 2004, 17:113-126.
[59] David V, A Sanchez.Advanced Support Vector Machines and Kemel Methods [J]. Neurocan putting, 2003, 55:5-20
[60] Chang C C, Lin C J. Training Support Vector Classifiers Theory and Algorithms [J]. Neural Computation, 2001, 13(9):2119-2147.
[61] Ana M B, Dragan N, Leopold C. Prohabilistic SVM Outputs for Pattem Recognition Analytical Geometry [J]. Neurocan putting, 2004, 62:293-303
[62]刘星,胡光道.高光谱遥感图像品与自适应同态滤波薄云去除[J].物探化探计算技术,2008,30(2):163-168
[63]卢桂林,谢海元,李媛媛等.雷达信号的非线性滤波方法的基础理论综述[J].工程技术,2008,1:31-32
[64]李刚,杨武年,翁韬.一种基于同态滤波的遥感图像薄云去除算法[J].测绘科学,2007,32(3):47-48
[65]贾承丽,匡纲要. SAR图像去斑方法[J].中国图像图形学报,2005,10(2):135-141
[66]飞思科技产品研发中心.MATLAB7基础与提高[M].北京:电子工业出版社.2007.
[67]阮秋琦等译.数字图像处理(MATLAB版)[M].北京:电子工业出版社.2006.
[68]周开利,康耀红.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,2005.
[69]兰雪梅,米键,黄承明.BP网络的MATLAB实现[J].研究与设计微电脑应用,2003,12(01):6-8.
[70]阮秋琦等译.数字图像处理(MATLAB版)[M].北京:电子工业出版社.2006.
[71]闻新,周露,李翔.MATLAB神经网络仿真与应用[M].北京:科学出版社,2003
[72]吕金福,肖荣寰,李志民等.松嫩平原湖泊综合分类研究[J].东北师范大学报自然科学版,2000,32(2):92-98.
[73]郭跃东,何艳芬.松嫩平原湿地动态变化及其驱动力研究[J].湿地科学,2005,3(1):54-59.
[74]介冬梅,吕金福.松嫩平原湖滩土地类型与利用对策研究[J].东北师范大学报自然科学版,2000,32(2):112-116.
[75]吕金福,肖荣寰,李志民等.松嫩平原湖泊类型组合的区域分类[J].东北师范大学自然科学版,2000,32(2):99-105.
[76]吕金福,李志民,冷雪天等.松嫩平原湖泊的分类与分区[J].地理科学,1998,18(6):524-530 .
[77]王苏民,窦鸿身.中国湖泊志[M].北京:科学出版社,1998,519-520.
[78]赵书河,冯学智,都金康.中巴资源一号卫星水体信息提取方法研究[J].南京大学学报(自然科学),2003,39(1):102-112
[79]杜云艳,周成虎.水体的遥感信息自动提取方法[J].遥感学报,1998,2(4):264-269
[80]李晶晶,贾建华,郝景研.基于RS的松嫩平原大安湖泊群面积提取与动态变化分析[J].遥感信息,2009,4(2)
[81]赵英时等.遥感应用分析原理与方法[M].北京:科学出版社,2003,204-207
[82]吕诚然,刘斌,谢红等.遥感图像处理与信息提取方法的研究[J].吉林地质,2004,23(4):264-26