决策树与SVM相结合的影像分类方法研究
|
摘要
遥感技术自二十世纪六时年代提出以来,已经为很多领域的具体应用提供了强大的信息支持,为了更好的利用遥感技术,人们在遥感各个方向上的研究都有了长足的进步。遥感影像需要首先通过解译,获取相关的专题信息后才能应用于地学以及其他工作中,计算机自动解译虽然在精度上与人工解译存在差距,但具有先天的速度优势。随着分类算法研究的不断深入,使计算机自动解译的精度不断提高,已能满足一定具体工作的需要。但在如今的技术飞速发展的时代,随着遥感数据的海量化以及某些领域对于信息迅速获取的迫切需求,分类的速度已经越来越得到人们的重视,这也就催生了提升分类速度算法的研究。本文则从分类效率入手,对分类算法进行相关研究。旨在满足精度要求的前提下,寻找提高分类效率,节省分类时间的改进算法。
计算机自动分类方法应用较多的传统的模式识别方法,如非监督分类的ISODATA分类法,监督分类的最大似然法等。但这些传统方法受到遥感影像分辨率以及“同物异谱”、“异物同谱”现象的影响,出现较多错分、漏分,导致分类精度不高。目前也提出了一些改进算法,使其分类精度有了大幅的提高。随着遥感技术的发展,近年来出现了一些新的倾向于句法模式的分类方法,如人工神经网络方法、模糊数学方法、决策树方法、支持向量机方法等。本文选取了两类方法中的典型,包括ISODATA法、最大似然法、决策树法以及支持向量机(SVM)法进行对比研究,并最终提出决策树与SVM相结合的分类方法。
经过研究,四种方法在分类精度上存在较大差异。支持向量机方法精度最高;决策树与最大似然法精度相当,位居次席;ISODATA法精度最低。但在分类效率上决策树法消耗时间最少,最大似然法与ISODATA法相当,支持向量机法消耗时间最多。本文提出的决策树与SVM相结合的方法精度上基本与单独使用支持向量机法相同,但消耗时间却大幅减少,略少于单独使用最大似然法或ISODATA法。达到了在精度基本不变的前提下,提高分类效率的目的,显示出此方法具有分类效率与精度上的综合优势。
Since remote sensing technology was brought forward in 1960s, it has provided information to many areas powerfully. In order to using remote sensing technology better, people has had significant progress in all directions of the remote sensing research. Remote sensing image need to be interpreted at first, to get the thematic information, then it can be used in Geography and other works. Automatic interpretation of computer is lower in accuracy than manual interpretation, but it has advantage in efficiency innately. With the development of classification research, the accuracy of automatic interpretation of computer has improved continuously, and it can meet the demand of certain specific works. Because of the magnanimity of the remote sensing data, and the urgent need of getting information rapidly in some areas, the speed of has been paid more and more attention, and that gives the birth to the research in algorithm of improving the speed of classification. In this paper, it starts from the classification efficiency to study the classification algorithm. It designed to meet the requirements of accuracy, finding algorithm that can improve classification efficiency.
Traditional methods of pattern recognition are widely used in automatic interpretation of computer, such as the ISODATA of unsupervised classification, the Maximum likelihood of supervised classification. But these methods are affected by the resolution of remote sensing images and the phenomenon of "the same thing different features" and "different things the same feature", so it makes wrong classification with low accuracy. With the development of remote sensing technology, classification of syntactic patterns has occurred in years, such as ANN, Fuzzy Models, Decision tree, Support Vector Machine (SVM). In this paper, typical methods of tows are selected to execute the comparative study, including the ISODATA, Maximum likelihood, Decision tree and Support Vector Machine (SVM). And classification method of combining Decision tree and Support Vector Machine (SVM) together is brought forward ultimately.
After research, the classification accuracy of four methods are of great differences. The accuracy of SVM is the highest, Decision tree and Maximum likelihood get the second place, ISODATA is the lowest. However, in the efficiency of classification the Decision tree needs the lest time, Maximum likelihood and ISODATA get the second place, SVM need the most. The method of combining Decision tree and Support Vector Machine (SVM) together in this paper gets the same accuracy as SVM, but the time needing is reduced rapidly, slightly less than ISODATA or Maximum likelihood. It gets the purpose that in premise of accuracy unchanged basically to improve the classification efficiency. It has advantage in both accuracy and efficiency.
计算机自动分类方法应用较多的传统的模式识别方法,如非监督分类的ISODATA分类法,监督分类的最大似然法等。但这些传统方法受到遥感影像分辨率以及“同物异谱”、“异物同谱”现象的影响,出现较多错分、漏分,导致分类精度不高。目前也提出了一些改进算法,使其分类精度有了大幅的提高。随着遥感技术的发展,近年来出现了一些新的倾向于句法模式的分类方法,如人工神经网络方法、模糊数学方法、决策树方法、支持向量机方法等。本文选取了两类方法中的典型,包括ISODATA法、最大似然法、决策树法以及支持向量机(SVM)法进行对比研究,并最终提出决策树与SVM相结合的分类方法。
经过研究,四种方法在分类精度上存在较大差异。支持向量机方法精度最高;决策树与最大似然法精度相当,位居次席;ISODATA法精度最低。但在分类效率上决策树法消耗时间最少,最大似然法与ISODATA法相当,支持向量机法消耗时间最多。本文提出的决策树与SVM相结合的方法精度上基本与单独使用支持向量机法相同,但消耗时间却大幅减少,略少于单独使用最大似然法或ISODATA法。达到了在精度基本不变的前提下,提高分类效率的目的,显示出此方法具有分类效率与精度上的综合优势。
Since remote sensing technology was brought forward in 1960s, it has provided information to many areas powerfully. In order to using remote sensing technology better, people has had significant progress in all directions of the remote sensing research. Remote sensing image need to be interpreted at first, to get the thematic information, then it can be used in Geography and other works. Automatic interpretation of computer is lower in accuracy than manual interpretation, but it has advantage in efficiency innately. With the development of classification research, the accuracy of automatic interpretation of computer has improved continuously, and it can meet the demand of certain specific works. Because of the magnanimity of the remote sensing data, and the urgent need of getting information rapidly in some areas, the speed of has been paid more and more attention, and that gives the birth to the research in algorithm of improving the speed of classification. In this paper, it starts from the classification efficiency to study the classification algorithm. It designed to meet the requirements of accuracy, finding algorithm that can improve classification efficiency.
Traditional methods of pattern recognition are widely used in automatic interpretation of computer, such as the ISODATA of unsupervised classification, the Maximum likelihood of supervised classification. But these methods are affected by the resolution of remote sensing images and the phenomenon of "the same thing different features" and "different things the same feature", so it makes wrong classification with low accuracy. With the development of remote sensing technology, classification of syntactic patterns has occurred in years, such as ANN, Fuzzy Models, Decision tree, Support Vector Machine (SVM). In this paper, typical methods of tows are selected to execute the comparative study, including the ISODATA, Maximum likelihood, Decision tree and Support Vector Machine (SVM). And classification method of combining Decision tree and Support Vector Machine (SVM) together is brought forward ultimately.
After research, the classification accuracy of four methods are of great differences. The accuracy of SVM is the highest, Decision tree and Maximum likelihood get the second place, ISODATA is the lowest. However, in the efficiency of classification the Decision tree needs the lest time, Maximum likelihood and ISODATA get the second place, SVM need the most. The method of combining Decision tree and Support Vector Machine (SVM) together in this paper gets the same accuracy as SVM, but the time needing is reduced rapidly, slightly less than ISODATA or Maximum likelihood. It gets the purpose that in premise of accuracy unchanged basically to improve the classification efficiency. It has advantage in both accuracy and efficiency.
引文
[1]朱述龙,张占睦.遥感图像获取与分析.北京:科学出版社,2000.
[2]张永生.遥感图像信息系统.北京:科学出版社,2000.
[3]张永生,王仁礼.遥感动态监测.北京:解放军出版社,1999.
[4]章孝灿,黄智才,赵元洪.遥感数字图像处理.杭州:浙江大学出版社,1997.
[5]周海芳.遥感图像并行处理算法的研究与应用:[博士学位论文].长沙:国防科技大学,2003.
[6]曾志远.卫星遥感图像计算机分类与地学应用研究.北京:科学出版社,2004.
[7]汤国安,张友顺,刘咏梅,等.遥感数字图像处理.北京:科学出版社,2004.
[8]贾海峰,刘雪华,等.环境遥感原理与应用.北京:清华大学出版社,2006.
[9]马建文,李启青,哈斯巴干,戴芹,等.遥感数据智能处理方法与程序设计.北京:科学出版社,2005.
[10]赵忠明.基于小波提取边缘特征点的遥感图像配准技术:[硕士学位论文].西安:西北工业大学,2002.
[11]杨建刚.人工神经网络实用教程.杭州:浙江大学出版社,2001.
[12]颜宏娟.面向对象的遥感影像模糊分类方法研究:[硕士学位论文].西安:西安科技大学,2008.
[13]Bandemer,H.,Gottwald,S.:Fuzzy Sets,Fuzzy Logic,Fuzzy Methods with Applications.New York:Wiley Press,1995.
[14]Haralick,R.Shanmugan,K.I.Dinstein:Textural features for image classification.IEEE Transactions on Systems,Man and Cybernetics.1973,3(1),610-621.
[15]Bezdek,J,Pal,S.Fuzzy Models for Pattern Recognition,Methods that Search for Structures in Data.New,York:IEEE Press,1992.
[16]Manjunath,B.,Chellappa,R..Unsupervised texture segmentation using Markov random field models.IEEE Transactions on Pattern Analysis and Machine Intelligence,1991,13(5),478-482.
[17]李爽,张二勋.基于决策树的遥感影像分类方法研究.地域研究与开发,2003,22(1):17-21.
[18]庞新华.基于决策树和混合像元分解的P6AWiFS遥感影像小麦播种面积测量方法研究:[硕士学位论文].北京:北京师范大学,2008.
[19]Robert A Schowengerdt.Remote Sensing Models and Methods for Image Processing.Academic Press,1997.
[20]Hansen M,Dubayah R,Defries R.Classification Trees:An Alternative to Traditional LandCover Classifier.Int.J.Remote Sensing,1996,17(5):1075-1081.
[21]韩立建,潘耀忠,贾斌,等.基于多时相IRS-P6卫星AWiFS影像的水稻种植面积提取方法.农业工程学报,2007,23(5):137-144.
[22]Hansen M,Dubayah R,Defries R.Classification Trees:An Alternative to Traditional Land Cover Classifiers.Int.J.Remote Sensing,1996,17(5):1075-1081.
[23]FRIEDL M A,BRODLEY C E.Decision tree classification of land cover from remotely sensed data.Remote Sensing of Environment,1997,61(3):399-409.
[24]C.J.C.Burges.A tutorial on support vector machines for pattern recognition.Data Mining and Knowledge Discovery,(1998)2(2):121-167.
[25]C.Cortes,V.N.Vapnik.Support vector networks.Machine Learning,(1995):273-297.
[26]萧嵘,王继成,张福炎.支持向量机理论综述.计算机科学,(2000)26(3):1-3.
[27]E.Osuna,R.Freund,E.Girosi.Training support vector machines:An application to face detection.In Proceedings of IEEE Computer Society Conference on Vision and Pattern Recognition,1997.
[28]王胡永.支持向量机若干算法及研究:[博士学位论文].吉林:吉林大学,2008.
[29]陈万海,赵春晖,刘春红.超谱遥感图像的模糊最大似然分类研究.哈尔滨工程大学学报,2006,27(5):772-776.
[30]李春华,沙晋明.基于知识的遥感影像的BAYES分类方法研究.水土保持研究,2006,13(6):126-128.
[31]张秀英,冯学智,刘伟.基于多分类器结合的IKONOS影像城市植被类型识别.东南大学学报(自然科学版),2007,37(3):399-403.
[32]张强,周秋生.利用一种模糊神经网络对遥感影像进行分类的研究.测绘工程,2006,15(5):42-46.
[33]骆成风,刘正军,王长耀,等.基于遗传算法优化的BP神经网络遥感数据土地覆盖分类.农业工程学报,2006,22(12):133-137.
[34]于君娜,赵春晖.一种基于BP网络和决策融合的高光谱遥感图像分类方法.应用科技,2007,34(1):13-16.
[35]郭春燕,赵春晖.基于模糊支持向量机的超光谱遥感图像分类.应用科技,2007,34(3):36-38.
[36]许将军,赵辉.高光谱遥感图像特征提取及分类研究.佳木斯大学学报(自然科学版),2006,24(4):468-470.
[37]阳松.面向对象的遥感影像的模糊分类:[硕士学位论文].徐州:中国矿业大学,2007.
[38]周春艳.面向对象的高分辨率遥感影像信息提取技术:[硕士学位论文].济南:山东科技大学,2006.
[39]eCognition:object oriented image classification.http://www.definiens-imaging.comldocuments/reference2000.htm
[40]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.遥感学报,2003,7(4):309-314.
[41]刘学工.多层感知神经网络在遥感影像解译中的应用.人民黄河,2007,29(1):3-4.
[42]巴雅尔,敖登高娃,沈彦俊等.地理信息系统支持下Spot/vegetation NDVI影像的大尺度神经网络分类.红外与毫米波学报,2005,24(6):427-431.
[43]许将军,赵辉.高光谱遥感图像特征提取及分类研究.佳木斯大学学报(自然科学版),2006,24(4):468-470.
[44]杨国鹏,余旭初.高光谱遥感影像的广义判别分析特征提取.测绘科学技术学报,2007,24(2):130-132.
[45]王大鹏,王周龙,李德一.基于SPOT-5卫星影像的胶东地区果园信息分区分层提取方法研究.国土资源遥感,2006,3:61-6.
[46]邓书斌,武红敢,江涛.基于PCA/NDVI的森林覆盖遥感信息提取方法研究.国土资源遥感,2007,2:82-85.
[47]练秋生,尚燕,陈书贞,王林.基于DT-CWT利SVM的纹理分类算法.光电工程,2007,34(4):109-113.
[48]程彬,姜琦刚,周云轩,湛邵斌.基于ASTER数据遥感影像的决策树分类.吉林大学学报(地球科学版),2007,37(1):179-184.
[49]王亮申,欧宗瑛,朱玉才等.基于SVM的图像分类.计算机应用与软件,2005,22(5): 98-99.
[50]王陈飞,肖诗斌.基于SVM的图像分类研究.计算机与数字工程,2006,34(8):74-76.
[51]刘安斐,李弼程,张先飞等.基于数据融合的多特征遥感图像分类.数据采集与处理,2006,21(4):463-467.
[52]罗来平,宫辉力,刘先林等.基于决策树算法的遥感图像分类研究与实现.计算机应用研究,2007,1:207-209.
[53]龚衍,舒宁.基于马尔柯夫随机场的多波段遥感影像纹理分割研究.武汉大学学报·信息科学版,2007,32(3):212-215.
[54]张海龙,蒋建军,解修平,等.基于改进的BP神经网络模型的遥感影像分类法.农机化研究,2006,10:55-57.
[55]毛建旭,王耀南.基于神经网络的遥感图像分类.测控技术,2001,20(5):29-30.
[56]吴柯,方强,张俊玲等.基于改进Kohonen神经网络的遥感影像分类.测绘信息与工程,2007,32(2):47-49.
[57]薛欣,贺国平.基于多个混合核函数的SVM决策树算法设计.计算机工程与应用,2007,43(8):142-144.
[58]蔡银桥,毛政元.基于多特征对象的高分辨率遥感影像分类方法及其应用.国土资源遥感,2007,1:77-81.
[59]甘淑,袁希平,何大明.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.云南大学学报(自然科学版),2003,25(6):553-557.
[60]赵鹏祥,强建华,张会儒,等.基于遥感的黄土高原天然林林地信息提取及计算机分类研究.西北农林科技大学学报(自然科学版),2006,34(10):75-80.
[61]王蕾,黄华国,张晓丽等.基于知识规则的马尾松林遥感信息提取技术研究.北京林业大学学报,2007,29(3):124-129.
[62]张文元,秦昆,张成才等.基于知识的遥感图像地物提取方法研究.地理空间信息,2007,5(1):66-69.
[63]胡文英,角媛梅.遥感图像纹理信息提取方法综述.云南地理环境研究,2007,19(3):66-70.
[64]李启青,程承旗,郭仕德等.面向遥感图像BNs分类的预处理技术及算法实现.计算机工程2006,32(16):271-273.
[65]周峰,李杏梅,刘福江,等.基于主成分分析的自组织竞争神经网络在多光谱遥感影像分类中的应用.光学与光电技术,2007,5(3):43-46.
[66]王一达,沈熙玲,谢炯.遥感图像分类方法综述.遥感信息,2006,5:67-71.
[67]钱永兰,杨邦杰,雷廷武.用基于IHS变换的SPOT-5遥感图像融合进行作物识别.农业工程学报,2005,21(1):102-105.
[68]孙昌儿,刘秉瀚.一种新的SVM决策树.福州大学学报(自然科学版),2007,35(3):361-364.
[69]刘治国.应用SVM算法进行TM多光谱图像地物分类.信息技术,2007,5:105-108.
[70]陈敬柱,贺瑞霞,郭恒亮.最大似然法在植被信息识别提取中的应用.水文地质工程地质,2004,2:94-96.
[71]韩玲,王翠平,于润平.一种建立在CPN基础上的分类方法在遥感影像分类中的应用研究.测绘科学,2007,32(3):26-27.
[2]张永生.遥感图像信息系统.北京:科学出版社,2000.
[3]张永生,王仁礼.遥感动态监测.北京:解放军出版社,1999.
[4]章孝灿,黄智才,赵元洪.遥感数字图像处理.杭州:浙江大学出版社,1997.
[5]周海芳.遥感图像并行处理算法的研究与应用:[博士学位论文].长沙:国防科技大学,2003.
[6]曾志远.卫星遥感图像计算机分类与地学应用研究.北京:科学出版社,2004.
[7]汤国安,张友顺,刘咏梅,等.遥感数字图像处理.北京:科学出版社,2004.
[8]贾海峰,刘雪华,等.环境遥感原理与应用.北京:清华大学出版社,2006.
[9]马建文,李启青,哈斯巴干,戴芹,等.遥感数据智能处理方法与程序设计.北京:科学出版社,2005.
[10]赵忠明.基于小波提取边缘特征点的遥感图像配准技术:[硕士学位论文].西安:西北工业大学,2002.
[11]杨建刚.人工神经网络实用教程.杭州:浙江大学出版社,2001.
[12]颜宏娟.面向对象的遥感影像模糊分类方法研究:[硕士学位论文].西安:西安科技大学,2008.
[13]Bandemer,H.,Gottwald,S.:Fuzzy Sets,Fuzzy Logic,Fuzzy Methods with Applications.New York:Wiley Press,1995.
[14]Haralick,R.Shanmugan,K.I.Dinstein:Textural features for image classification.IEEE Transactions on Systems,Man and Cybernetics.1973,3(1),610-621.
[15]Bezdek,J,Pal,S.Fuzzy Models for Pattern Recognition,Methods that Search for Structures in Data.New,York:IEEE Press,1992.
[16]Manjunath,B.,Chellappa,R..Unsupervised texture segmentation using Markov random field models.IEEE Transactions on Pattern Analysis and Machine Intelligence,1991,13(5),478-482.
[17]李爽,张二勋.基于决策树的遥感影像分类方法研究.地域研究与开发,2003,22(1):17-21.
[18]庞新华.基于决策树和混合像元分解的P6AWiFS遥感影像小麦播种面积测量方法研究:[硕士学位论文].北京:北京师范大学,2008.
[19]Robert A Schowengerdt.Remote Sensing Models and Methods for Image Processing.Academic Press,1997.
[20]Hansen M,Dubayah R,Defries R.Classification Trees:An Alternative to Traditional LandCover Classifier.Int.J.Remote Sensing,1996,17(5):1075-1081.
[21]韩立建,潘耀忠,贾斌,等.基于多时相IRS-P6卫星AWiFS影像的水稻种植面积提取方法.农业工程学报,2007,23(5):137-144.
[22]Hansen M,Dubayah R,Defries R.Classification Trees:An Alternative to Traditional Land Cover Classifiers.Int.J.Remote Sensing,1996,17(5):1075-1081.
[23]FRIEDL M A,BRODLEY C E.Decision tree classification of land cover from remotely sensed data.Remote Sensing of Environment,1997,61(3):399-409.
[24]C.J.C.Burges.A tutorial on support vector machines for pattern recognition.Data Mining and Knowledge Discovery,(1998)2(2):121-167.
[25]C.Cortes,V.N.Vapnik.Support vector networks.Machine Learning,(1995):273-297.
[26]萧嵘,王继成,张福炎.支持向量机理论综述.计算机科学,(2000)26(3):1-3.
[27]E.Osuna,R.Freund,E.Girosi.Training support vector machines:An application to face detection.In Proceedings of IEEE Computer Society Conference on Vision and Pattern Recognition,1997.
[28]王胡永.支持向量机若干算法及研究:[博士学位论文].吉林:吉林大学,2008.
[29]陈万海,赵春晖,刘春红.超谱遥感图像的模糊最大似然分类研究.哈尔滨工程大学学报,2006,27(5):772-776.
[30]李春华,沙晋明.基于知识的遥感影像的BAYES分类方法研究.水土保持研究,2006,13(6):126-128.
[31]张秀英,冯学智,刘伟.基于多分类器结合的IKONOS影像城市植被类型识别.东南大学学报(自然科学版),2007,37(3):399-403.
[32]张强,周秋生.利用一种模糊神经网络对遥感影像进行分类的研究.测绘工程,2006,15(5):42-46.
[33]骆成风,刘正军,王长耀,等.基于遗传算法优化的BP神经网络遥感数据土地覆盖分类.农业工程学报,2006,22(12):133-137.
[34]于君娜,赵春晖.一种基于BP网络和决策融合的高光谱遥感图像分类方法.应用科技,2007,34(1):13-16.
[35]郭春燕,赵春晖.基于模糊支持向量机的超光谱遥感图像分类.应用科技,2007,34(3):36-38.
[36]许将军,赵辉.高光谱遥感图像特征提取及分类研究.佳木斯大学学报(自然科学版),2006,24(4):468-470.
[37]阳松.面向对象的遥感影像的模糊分类:[硕士学位论文].徐州:中国矿业大学,2007.
[38]周春艳.面向对象的高分辨率遥感影像信息提取技术:[硕士学位论文].济南:山东科技大学,2006.
[39]eCognition:object oriented image classification.http://www.definiens-imaging.comldocuments/reference2000.htm
[40]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.遥感学报,2003,7(4):309-314.
[41]刘学工.多层感知神经网络在遥感影像解译中的应用.人民黄河,2007,29(1):3-4.
[42]巴雅尔,敖登高娃,沈彦俊等.地理信息系统支持下Spot/vegetation NDVI影像的大尺度神经网络分类.红外与毫米波学报,2005,24(6):427-431.
[43]许将军,赵辉.高光谱遥感图像特征提取及分类研究.佳木斯大学学报(自然科学版),2006,24(4):468-470.
[44]杨国鹏,余旭初.高光谱遥感影像的广义判别分析特征提取.测绘科学技术学报,2007,24(2):130-132.
[45]王大鹏,王周龙,李德一.基于SPOT-5卫星影像的胶东地区果园信息分区分层提取方法研究.国土资源遥感,2006,3:61-6.
[46]邓书斌,武红敢,江涛.基于PCA/NDVI的森林覆盖遥感信息提取方法研究.国土资源遥感,2007,2:82-85.
[47]练秋生,尚燕,陈书贞,王林.基于DT-CWT利SVM的纹理分类算法.光电工程,2007,34(4):109-113.
[48]程彬,姜琦刚,周云轩,湛邵斌.基于ASTER数据遥感影像的决策树分类.吉林大学学报(地球科学版),2007,37(1):179-184.
[49]王亮申,欧宗瑛,朱玉才等.基于SVM的图像分类.计算机应用与软件,2005,22(5): 98-99.
[50]王陈飞,肖诗斌.基于SVM的图像分类研究.计算机与数字工程,2006,34(8):74-76.
[51]刘安斐,李弼程,张先飞等.基于数据融合的多特征遥感图像分类.数据采集与处理,2006,21(4):463-467.
[52]罗来平,宫辉力,刘先林等.基于决策树算法的遥感图像分类研究与实现.计算机应用研究,2007,1:207-209.
[53]龚衍,舒宁.基于马尔柯夫随机场的多波段遥感影像纹理分割研究.武汉大学学报·信息科学版,2007,32(3):212-215.
[54]张海龙,蒋建军,解修平,等.基于改进的BP神经网络模型的遥感影像分类法.农机化研究,2006,10:55-57.
[55]毛建旭,王耀南.基于神经网络的遥感图像分类.测控技术,2001,20(5):29-30.
[56]吴柯,方强,张俊玲等.基于改进Kohonen神经网络的遥感影像分类.测绘信息与工程,2007,32(2):47-49.
[57]薛欣,贺国平.基于多个混合核函数的SVM决策树算法设计.计算机工程与应用,2007,43(8):142-144.
[58]蔡银桥,毛政元.基于多特征对象的高分辨率遥感影像分类方法及其应用.国土资源遥感,2007,1:77-81.
[59]甘淑,袁希平,何大明.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.云南大学学报(自然科学版),2003,25(6):553-557.
[60]赵鹏祥,强建华,张会儒,等.基于遥感的黄土高原天然林林地信息提取及计算机分类研究.西北农林科技大学学报(自然科学版),2006,34(10):75-80.
[61]王蕾,黄华国,张晓丽等.基于知识规则的马尾松林遥感信息提取技术研究.北京林业大学学报,2007,29(3):124-129.
[62]张文元,秦昆,张成才等.基于知识的遥感图像地物提取方法研究.地理空间信息,2007,5(1):66-69.
[63]胡文英,角媛梅.遥感图像纹理信息提取方法综述.云南地理环境研究,2007,19(3):66-70.
[64]李启青,程承旗,郭仕德等.面向遥感图像BNs分类的预处理技术及算法实现.计算机工程2006,32(16):271-273.
[65]周峰,李杏梅,刘福江,等.基于主成分分析的自组织竞争神经网络在多光谱遥感影像分类中的应用.光学与光电技术,2007,5(3):43-46.
[66]王一达,沈熙玲,谢炯.遥感图像分类方法综述.遥感信息,2006,5:67-71.
[67]钱永兰,杨邦杰,雷廷武.用基于IHS变换的SPOT-5遥感图像融合进行作物识别.农业工程学报,2005,21(1):102-105.
[68]孙昌儿,刘秉瀚.一种新的SVM决策树.福州大学学报(自然科学版),2007,35(3):361-364.
[69]刘治国.应用SVM算法进行TM多光谱图像地物分类.信息技术,2007,5:105-108.
[70]陈敬柱,贺瑞霞,郭恒亮.最大似然法在植被信息识别提取中的应用.水文地质工程地质,2004,2:94-96.
[71]韩玲,王翠平,于润平.一种建立在CPN基础上的分类方法在遥感影像分类中的应用研究.测绘科学,2007,32(3):26-27.