Please wait a minute...
img

官方微信

遥感技术与应用  2012, Vol. 27 Issue (3): 353-358    DOI: 10.11873/j.issn.1004-0323.2012.3.353
图像与数据处理     
基于模糊双支持向量机的遥感图像分类研究
丁胜锋1,2,孙劲光1,陈东莉3,姜晓林2
(1.辽宁工程技术大学,辽宁 阜新 123000;2.辽宁石油化工大学经济管理学院,辽宁 抚顺 113001;
3.中国石油抚顺石化公司石油二厂科技信息部,辽宁 抚顺 113004)
Research of Remote Sensing Image Classification based on Fuzzy Twin Support Vector Machine
Ding Shengfeng1,2,Sun Jingguang1,Chen Dongli3,Jiang Xiaolin2
(1.Liaoning Technical University,Fuxin 123000,China;2.School of Economics and Management,Liaoning Shihua University,Fushun 113001,China;3.PetroChina Fushun PetroChemical Company Refinery NO.2 Science & Technology Department,Fushun 113004,China)
 全文: PDF(1977 KB)  
摘要:

遥感图像的分类是研究土地利用变化的基础。传统的遥感图像分类方法存在运算速度慢、精度比较低和难以收敛等问题。提出了一种基于模糊双支持向量机的多类分类方法,将模糊技术引入到双支持向量机中,赋予不同样本以不同的模糊隶属度,然后将模糊双支持向量机推广到多类分类中,最后将新方法应用到遥感图像分类中。实验表明,新方法比传统的支持向量机多类分类方法有较高的分类精度,并且有较强的抗噪声能力,在运行时间上也是可行的。模糊双支持向量机是一种有效的遥感图像分类方法。

关键词: 遥感图像双支持向量机模糊隶属度模糊双支持向量机    
Abstract:

The classification of remote sensing image is the basis of studying the land change.Some traditional algorithms of remote sensing image classification have some problems such as low computing rate,low accuracy and hard for convergence.A multi-classification algorithm based on fuzzy twin support vector machine is presented.First,fuzziness is inducted into twin support vector machine by applying the fuzzy membership to every training sample,then fuzzy twin support vector machine is extended to multi-classification,finally,remote sensing image classification is achieved by the proposed method.The study indicate the proposed method is more precise than traditional support vector machine multi-classification algorithm,and has high anti-noise performance and feasible runtime.Fuzzy twin support vector machine is an effective method of remote sensing image classification.

Key words: Remote sensing image    Twin support vector machine    Fuzzy membership    Fuzzy twin support vector machine
收稿日期: 2011-08-11 出版日期: 2013-01-23
:  TP 753  
基金资助:

辽宁省科技计划项目(2010401010)。

作者简介: 丁胜锋(1981-),男,湖北蕲春人,博士研究生,讲师,主要从事数据挖掘和图像研究。Email:jgdsf@163.com。
服务  
把本文推荐给朋友
加入引用管理器
E-mail Alert
RSS
作者相关文章  

引用本文:

丁胜锋,孙劲光,陈东莉,姜晓林. 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, 27(3): 353-358.

Ding Shengfeng,Sun Jingguang,Chen Dongli,Jiang Xiaolin. Research of Remote Sensing Image Classification based on Fuzzy Twin Support Vector Machine. Remote Sensing Technology and Application, 2012, 27(3): 353-358.

链接本文:

http://www.rsta.ac.cn/CN/10.11873/j.issn.1004-0323.2012.3.353        http://www.rsta.ac.cn/CN/Y2012/V27/I3/353

[1]Hui Wenhua.TM Image Classification based on Support Vector Machine[J].Journal of Earth Sciences and Environment,2006,8(2):93-95.[惠文华.基于支持向量机的遥感图像分类方法[J].地球科学与环境学报,2006,8(2):93-95.]
[2]Yuan Changan.The Principle of Data Mining and the Application of SPSS Clementine [M].Beijing:Publishing House of Electronics Industry,2009.[元昌安.数据挖掘原理与SPSS Clementine应用宝典[M].北京:电子工业出版社,2009.]
[3]Burges C J C.A Tutorial on Support Vector Machines for Pattern Recognition[J].Data Mining and Knowledge Discovery,1998,2(2):121-167.
[4]Vapnik V N.The Nature of Statistical Learning Theory (Second Edition)[M].New York:Springer,2000.〖HJ2mm〗
[5]Song Cuiyu,Li Peijun,Yang Fengjie.Remote Sensing Image Classification based on Texture Features by Multivariate Local Binary Pattern[J].Remote Sensing Technology and Application,2011,26(3):322-327.[宋翠玉,李培军,杨锋杰.基于多元局部二值模式的遥感图象纹理提取与分类[J].遥感技术与应用,2011,26(3):322-327.]
[6]Jayadcva R,Khemchandani S C.Twin Support Vector Mac-hines for Pattern Classification[J].IEEE Transaction on Pattern Analysis and Machinc Intelligence,2007,29(5):905-910.
[7]Ye Q L,Zhao C X,Ye N.Least Squares Twin Support Vector Machine Classification Via Maximum One-class within Class Variance[J].Optimization Methods & Software,2010,(iFirst):1-17.
[8]Du Peijun,Lin Hui,Sun Dunxin.On Progress of Support Vector Machine based Hyperspectral RS Classification[J].Bulletin of Surveying and Mapping,2006,(12):37-40.[杜培军,林卉,孙敦新.基于支持向量机的高光谱遥感分类进展[J].测绘通报,2006,(12):37-40.]
[9]University of California UCI Repository of Machine Learning Databases and Domain Theories[DB/OL].ftp:// ftp.ics.uci.edu/pub/ machine-learning-databases/ statlog/satimage/.
[10]Gidudu Anthony,Hulley Gregg,Marwala Tshilidzi.Image Cl-assification Using SVMs:One-Against-One Vs One-Against-All[C]//Proccedings of the 28th Asian Conference on Remote Sensing,2007:2909-2914.
[11]Liu Y,Wang R,Zeng Y S.An Improvement of One-Against-One Method for Multi-class Support Vector Machine[C]//2009 International Conference on,Machine Learning and Cybernetics,Changsha,China,2009:2915-2920.
[12]Arun Kumar M,Gopal M.Fast Multiclass SVM Classification Using Decision Tree based One-Against-All Method[J].Neural Processing Letters,December,2010,32(3):311-323.

[1] 秦振涛,杨茹,张靖,杨武年. 基于聚类结构自适应稀疏表示的高光谱遥感图像修复研究[J]. 遥感技术与应用, 2018, 33(2): 212-215.
[2] 王俊,秦其明,叶昕,王建华,秦雪彬,杨绣丞. 高分辨率光学遥感图像建筑物提取研究进展[J]. 遥感技术与应用, 2016, 31(4): 653-662.
[3] 张从梅,孙权森,王超,封磊,顾一禾. 基于非局部自相似性的遥感图像稀疏去噪算法[J]. 遥感技术与应用, 2016, 31(4): 739-747.
[4] 赵永光,李传荣,马灵玲,唐伶俐,王宁. 一种遥感图像太阳—观测几何归一化方法[J]. 遥感技术与应用, 2016, 31(2): 260-266.
[5] 肖新耀,许宁,尤红建. 一种基于à trous小波和联合稀疏表示的遥感图像融合方法[J]. 遥感技术与应用, 2015, 30(5): 1021-1026.
[6] 苏腾飞,李洪玉. 一种两阶段区域生长的遥感图像分割算法[J]. 遥感技术与应用, 2015, 30(3): 476-485.
[7] 侯鹏洋,季艳,高峰,胡蕾. 一种基于SIFT特征的快速逐层遥感图像配准方法[J]. 遥感技术与应用, 2014, 29(5): 873-877.
[8] 万智萍. 结合方向小波的多光谱与全色遥感图像融合算法[J]. 遥感技术与应用, 2014, 29(4): 660-668.
[9] 李青松,覃锡忠,贾振红,杨杰,胡英杰. 基于非下采样Shearlet和几何结构的遥感图像无监督变化检测[J]. 遥感技术与应用, 2014, 29(3): 482-488.
[10] 姜澒月,周坚华. 遥感图像薄云雾的梯度改正[J]. 遥感技术与应用, 2013, 28(4): 640-646.
[11] 欧阳能钧,李伟彤,韦蔚,潘晴. 基于SIFT与Contourlet变换的高分辨遥感图像配准[J]. 遥感技术与应用, 2013, 28(1): 58-64.
[12] 骆仁波,皮佑国,廖文志. 超光谱遥感图像有监督LPP特征提取研究[J]. 遥感技术与应用, 2012, 27(6): 850-856.
[13] 陈超,秦其明,池长艳,蒋洪波,刘明超. 一种Curvelet变换和IHS变换相结合的遥感图像融合方法[J]. 遥感技术与应用, 2011, 26(4): 444-449.
[14] 周 全,张 荣,尹 东. 基于高斯金字塔的遥感云图多尺度特征提取[J]. 遥感技术与应用, 2010, 25(5): 604-608.
[15] 张九星, 黑保琴, 李盛阳, 李绪志. 基于变分方法的遥感图像去噪研究[J]. 遥感技术与应用, 2010, 25(4): 560-566.