基于支持向量机的遥感图像分类研究综述

doi:10.11896/j.issn.1002-137X.2016.09.002

摘要/Abstract

摘要： 遥感技术是目前用于研究地球矿产资源与能源的重要技术手段,遥感图像分类在遥感技术应用中起着关键作用。支持向量机(Support Vector Machines,SVM)是基于VC维(Vapnik-Chervonenkis Dimension)理论和结构风险最小化原理的机器学习方法,已被广泛应用于实际的遥感影像分类中。对国内外学者对此做的大量研究成果进行了系统的总结。对基于支持向量机的遥感图像分类方法进行了层次性梳理,不但纵向分析和比较了每类方法的原理及优缺点,而且对各类方法进行了横向比较和分析,较为系统和完整地概括了基于支持向量机的遥感影像分类方法的研究现状。最后指出了支持向量机算法应用于遥感图像分类的未来发展方向。

关键词: 遥感图像,分类,支持向量机

Abstract: Remote sensing technology is an important technology of studying the earth mineral resources and energy.Remote sensing image classification plays a key role in the application of remote sensing technology.Support vector machine(SVM) is a machine learning method based on VC dimension(Vapnik-Chervonenkis Dimension) theory and structural risk minimization principle,which has been widely used in the actual remote sensing image classification.Domestic and foreign scholars have done a lot of research about it and these studies were systematically summarized in this paper.The remote sensing image classification methods based on the support vector machine is reviewed hierarchically,that is,the principle and characteristics of each method were analyzed and compared laterally and vertically.The research status of the remote sensing image classification based on the support vector machine was summarized systematically and completely in this paper.Finally,the future development direction of support vector machine algorithm applied in the remote sensing image classification was pointed out.

Key words: Remote sensing images,Classification,Support vector machine (SVM)

王振武,孙佳骏,于忠义,卜异亚. 基于支持向量机的遥感图像分类研究综述[J]. 计算机科学, 2016, 43(9): 11-17. https://doi.org/10.11896/j.issn.1002-137X.2016.09.002

WANG Zhen-wu, SUN Jai-jun,  YU Zhong-yi and BU Yi-ya. Review of Remote Sensing Image Classification Based on Support Vector Machine[J]. Computer Science, 2016, 43(9): 11-17. https://doi.org/10.11896/j.issn.1002-137X.2016.09.002

参考文献

[1] 杨听,汤国安,邓凤东,等.ERDAS遥感数字图像处理实验教程[M].北京:科学出版社,2009
[2] Vapnik V N.Statistical Learning Theory[M].New York:Wiley,1998
[3] Wang Yu-jian,Yuan Jia-zheng,Fan Li-li,et al.Application Research of Support Vector Machine in Multi-spectra Remote Sensing Image Classification[C]∥Proceedings of 2nd International Congress on Image and Signal.Tianjing,China:IEEE,September 2009:1-5
[4] Wang Jing, He Jian-nong.New algorithm of remote sensingimage classification based on K-type support vector machine[J].Computer Applications,2012,32(10):2832-2835,2839(in Chinese) 王静,何建农.基于K型支持向量机的遥感图像分类新算法[J].计算机应用,2012,32(10):2832-2835,2839
[5] Soliman O S,Mahmoud A S,Hassan S M.Remote Sensing Satel-lite Images Classification using Support Vector Machine and Particle Swarm Optimization[C]∥Third International Confe-rence on Innovations in Bio-Inspired Computing and Applications.Kaohsiung:IEEE,2012:280-285
[6] Tan Kun,Du Pei-jun.Wavelet support vector machines based on reproducing kernel Hilbert space for hyperspectral remote sen-sing image classification[J].Journal of Surveying and Mapping,2011,40(2):142-147(in Chinese) 谭琨,杜培军.基于再生核Hilbert空间小波核函数支持向量机的高光谱遥感影像分类[J].测绘学报,2011,40(2):142-147
[7] Zhao Chun-hui,Qiao Lei.Classification of hyperspectral remote sensing image using improved LS-SVM [J].Applied Science and Technology,2008,35(1):44-47,2(in Chinese) 赵春晖,乔蕾.基于改进的最小二乘支持向量机的高光谱遥感图像分类[J].应用科技,2008,35(1):44-47,2
[8] Moser G,Serpico S B.Contextual Remote-Sensing Image Classification by Support Vector Machines and Markov Random Fields[C]∥2010 IEEE International Geoscience and Remote Sensing Symposium.Honolulu,HI:IEEE,2010:3728-3731
[9] Lin Yi,Liu Bing,Chen Ying-ying,et al.Change Detection Me-thod Based on Multi-feature Differencing Kernel SVM for Remote Sensing Imagery[J].Journal of Wuhan University(Information Science Edition),2013,38(8):978-982(in Chinese) 林怡,刘冰,陈映鹰,等.多特征差分核支持向量机遥感影像变化检测方法[J].武汉大学学报(信息科学版),2013,38(8):978-982
[10] Yu Le,Porwal A,Holden E J,et al.Towards automatic litholo-gical classification from remote sensing data using support vector machines[J].Computers & Geosciences,2012,45:229-239
[11] Zang Shu-ying,Zhang Ce,Zhang Li-juan,et al.Wet land remote sensing classification using support vector machine optimized with genetic algorithm:a case study in Honghe Nature National Reserve [J].Geographic Sciences,2012,32(4):434-441(in Chinese) 臧淑英,张策,张丽娟,等.遗传算法优化的支持向量机湿地遥感分类——以洪河国家级自然保护区为例[J].地理科学,2012,32(4):434-441
[12] Yao Wei,Han Min.Remote Sensing Image Classification with Parameter Optimized Support Vector Machine based on Evolutionary Computation[C]∥Fourth International Workshop on Advanced Computational Intelligence.Wuhan,China,2011:290-294
[13] Dai Hong-liang.Classification of remote sensing images based on total margin-based adaptive fuzzy support vector machine with real-valued genetic algorithms[J].Computer Engineering and Applications,2010,46(4):4-7(in Chinese) 戴宏亮.基于实值遗传算法与TAFSVM的遥感图像分类[J].计算机工程与应用,2010,46(4):4-7
[14] Liu Qing-jie,Jing Lin-hai,Wang Meng-fei,et al.Hyperspectral remote sensing image classification based on SVM optimized by clonal selection[J].Spectroscopy and Spectral Analysis,2013,3(3):746-751(in Chinese) 刘庆杰,荆林海,王梦飞,等.基于克隆选择支持向量机高光谱遥感影像分类技术[J].光谱学与光谱分析,2013,3(3):746-751
[15] Ding Sheng-feng,Sun Jin-guang,Chen Dong-li,et al.Research of Remote Sensing Image Classification based on Fuzzy Twin Support Vector Machine[J].Remote Sensing Technology and Application,2012,7(3):354-358(in Chinese) 丁胜锋,孙劲光,陈东莉,等.基于模糊双支持向量机的遥感图像分类研究[J].遥感技术与应用,2012,7(3):354-358
[16] Xu Jie,Zhang Jian-qi,Liu De-lian,et al.Classification of hyperspectral images with FSVM[J].Optical Technology,2008,34(Suppl):138-140(in Chinese) 徐杰,张建奇,刘德连,等.基于模糊支持向量机的高光谱图像分类[J].光学技术,2008,34(Suppl):138-140
[17] Li Gang,Wan You-chuan.Object-oriented classification method based on Quotient space theory[J].Opto-electronic Enginee-ring,2011,8(2):108-114(in Chinese) 李刚,万幼川.商空间理论下面向对象的遥感影像分类[J].光电工程,2011,38(2):108-114
[18] Yang Jia-jia,Jiang Qi-gang,Chen Yong-liang,et al.Lithology division for large-scale region segmentation based on LS-SVM and high resolution remote sensing images[J].Journal of China University of Petroleum(Natural Science Edition),2012,6(1):60-67(in Chinese) 杨佳佳,姜琦刚,陈永良,等.基于最小二乘支持向量机和高分辨率遥感影像的大尺度区域岩性划分[J].中国石油大学学报(自然科学版),2012,6(1):60-67
[19] Guo Xue-lan,Yang Min-hua,Mao Jun.Application of skew binary tree multi-class LS-SVM classifier in hyperspectral remote sensing image classification[J].Surveying and Mapping Science,2014,39(7):87-89,107(in Chinese) 郭学兰,杨敏华,毛军.利用偏态二叉树最小二乘支持向量机进行高光谱遥感影像分类[J].测绘科学,2014,39(7):87-89,7
[20] Li C H,Kuo B C,Lin C T,et al.A Spatial-Contextual Support Vector Machine for Remotely Sensed Image Classification[J].IEEE Transactions on Geoscience and Remote Sensing,2012,50(3):784-799
[21] Ju Hong-yun,Zhang Jun-ben,Li Chao-feng,et al.Automated remote sensing image classification method based on K-means and SVM [J].Computer Application Research,2007,24(11):318-320(in Chinese) 居红云,张俊本,李朝峰,等.基于K-means与SVM结合的遥感图像全自动分类方法[J].计算机应用研究,2007,24(11):318-320
[22] Qi Heng-nian,Yang Jian-gang,Ding Li-xia.Semi-supervisedClassification Method for Remote Sensing Images Based on Support Vector Machine[C]∥2004 IEEE International Conference on Systems,Man and Cybernetics.IEEE,2004:2357-2361
[23] Muoz-Marí J,Gómez-Chova L, Bruzzone L,et al.Semisuper-vised One-Class Support Vector Machines for Classification of Remote Sensing Data[J].IEEE Transactions G eoscience and Remote Sensing,2010,48(8):3188-3197
[24] Li Guang-shui,Song Ding-quan,Zheng Tao,et al.Research Tri-training SVMs for remote sensing image classification[J].Computer Engineering and Applications,2009,45(29):160-163(in Chinese) 李广水,宋丁全,郑滔,等.协同训练支持向量机对遥感影像的分类研究[J].计算机工程与应用,2009,45(29):160-163
[25] Sun Zhi-chao,Liu Zhi-gang,Liu Su-hong,et al.Active Learning with Support Vector Machines in Remotely Sensed Image Classification[C]∥2nd International Congress on Image and Signal Processing,2009.Tianjin,China:IEEE,2009:1-6
[26] Zhang Lin.Research and implementation of active support vector machine for remote sensing image classification[J].Information and Computer,2009(12):33(in Chinese) 张林.遥感图像分类的主动支持向量机的研究与实现[J].信息与电脑,2009(12):33
[27] Fu Wen-jie,Hong Jin-yi,Lin Ming-sen.A Method of Land Use Classification from Remote Sensing Image Based on Support Vector Machines and Spectral Similarity Scale[J].Remote Sen-sing Technology and Application,2006,21(1):25-30(in Chinese) 傅文杰,洪金益,林明森.基于光谱相似尺度的支持向量机遥感土地利用分类[J].遥感技术与应用,2006,21(1):25-30
[28] Liu Feng,Zhang Li-min,Zhang Rui-feng.Remote sensing image classification based on rough set and support vector machine[J].Electronic Design Engineering,2012,20(23):44-46(in Chinese) 刘峰,张立民,张瑞峰.基于粗糙集支持向量机的遥感影像分类算法研究[J].电子设计工程,2012,20(23):44-46
[29] Qiao Nao-sheng,Zhang Li,Wang Xian-chun.Study for fusion method of remote sensing image[J].Computer Engineering and Applications,2009,45(8):182-185(in Chinese) 乔闹生,张黎,王先春.遥感图像融合方法研究[J].计算机工程与应用,2009,45(8):182-185
[30] Cui Yu-yong,Zeng Zhi-yuan.Remote Sensing Image Classification Based on the HSI Transformation and Fuzzy Support Vector Machine[C]∥2009 International Conference on Future Computer and Communication.Kuala Lumpar:IEEE,April,2009:632-635
[31] Ding Hai-yong,Bian Zheng-fu.Remote sensing image classification based on SVM algorithm and texture feature extraction[J].Computer Engineering and Design,2008,29(8):2131-2132,2136(in Chinese) 丁海勇,卞正富.基于SVM算法和纹理特征提取的遥感图像分类[J].计算机工程与设计,2008,29(8):2131-2132,6
[32] Chen Jie,Deng Min,Xiao Peng-feng,et al.Object-oriented Classification of High Resolution Imagery Combining Support Vector Machine with Granular Computing[J].Journal of Surveying and Mapping,2014,40(2):135-141,147(in Chinese) 陈杰,邓敏,肖鹏峰,等.结合支持向量机与粒度计算的高分辨率遥感影像面向对象分类[J].测绘学报,2014,40(2):135-141,7
[33] Hu He-shan,Qin Ya-li.Classification of Multispectral RemoteSensing Image Based on ACO[J].Journal of Hangzhou Dianzi University,2012,32(4):88-91(in Chinese) 胡河山,覃亚丽.基于蚁群算法的多光谱遥感图像分类[J].杭州电子科技大学学报,2012,32(4):88-91
[34] Feng Xiao,Xiao Peng-feng,Li Qi,et al.Hyperspectral ImageClassification Based on 3-D Gabor Filter and Support Vector Machines[J].Spectroscopy and Spectral Analysis,2014,34(8):2218-2224(in Chinese) 冯逍,肖鹏峰,李琦,等.三维Gabor滤波器与支持向量机的高光谱遥感图像分类[J].光谱学与光谱分析,2014,34(8):2218-2224
[35] Wu Wei,Gao Guang-lai.Remote Sensing Image Classification with Multiple Classifiers based on Support Vector Machines[C]∥2012 Fifth International Symposium on Computational Intelligence and Design.Hangzhou,China:IEEE,2012:188-191
[36] Huang Xin,Zhang Liang-pei,Li Ping-xiang.Classification ofHigh Spatial Resolution Remotely Sensed Imagery Based Upon Fusion of Multiscale Features and SVM[J].Journal of Remote Sensing,2007,11(1):48-54(in Chinese) 黄昕,张良培,李平湘.基于多尺度特征融合和支持向量机的高分辨率遥感影像分类[J].遥感学报,2007,11(1):48-54
[37] Zhang Deng-hui,Yu Le.Support Vector Machine Based Classification for Hyperspectral Remote Sensing Images after Minimum Noise Fraction Rotation Transformation[C]∥2011 Internatio-nal Conference on Internet Computing and Information Ser-vices.HongKong,China:IEEE,September,2011:132-135
[38] Xu Han,Sun Yong-hua,Li Xiao-juan.Unmixing of RemoteSensing Images Based on Weighted Posterior Probability Support Vector Machines[J].Journal of the Earth Information Scie-nce,2013,15(2):249-254(in Chinese) 许菡,孙永华,李小娟.遥感影像混合像元的分解—基于加权后验概率的支持向量机分类算法[J].地球信息科学学报,2013,15(2):249-254
[39] Zhang Hua,Shi Wen-zhong,Liu K.Fuzzy-Topology-IntegratedSupport Vector Machine for Remotely Sensed Image Classification[J].IEEE Transactions on Geoscience and Remote Sensing,2012,50(3):850-862
[40] Han Ling,Wu Jing,Zhang Ruo-lan.The Classification Research of Support Vector Machine Based on Spot for Hyperspectral Remote Sensing Application[C]∥2010 International Conference on Computational and Information Sciences.Chengdu,China:IEEE,2010:1009-1012
[41] Li Cheng-fan,Yin Jing-yuan.Variational Bayesian independentcomponent analysis-support vector machine for remote sensing classification[J].Computers and Electrical Engineering,2013,9(3):717-726
[42] Tan Kun,Du Pei-jun,Wang Xiao-mei.Multi-Class Support Vector Machine Classifier Based on Separability Measure for Hyperspectral Remote Sensing Image Classification[J].Journal of Wuhan University(Information Science),2011,36(2):171-175(in Chinese) 谭琨,杜培军,王小美.利用分离性测度多类支持向量机进行高光谱遥感影像分类[J].武汉大学学报(信息科学版),2011,36(2):171-175

Metrics

Viewed

Full text

Abstract

Cited

Shared

Discussed