期刊文献+

基于实值遗传算法与TAFSVM的遥感图像分类 被引量:1

Classification of remote sensing images based on total margin-based adaptive fuzzy support vector machine with real-valued genetic algorithms
在线阅读 下载PDF
导出
摘要 支持向量机已经被成功应用于遥感图像分类。一种新型具有良好特性的支持向量机--全间隔自适应模糊支持向量机被提出。这种新型的支持向量机具有通过训练集的模糊性来增强泛化能力;对不平衡训练集具有自适应性,对正负数据采用不同的损失算法,可以提高正确分类率;通过引进全间隔算法来代替软间隔算法,可以得到更低的泛化误差等优良特性,符合遥感图像数据的内在规律。并且运用实值遗传算法对其进行参数优选,得到一种新的分类器——AGATAFSVM。最后将该分类器应用于遥感图像分类。实验结果表明,该分类器非常适用于遥感图像分类,分类精度和稳定性明显高于径向基神经网络分类器、最近邻分类器和标准支持向量机。 SVM has been successfully employed to solve classification of remote sensing images.Total margin-based Adaptive Fuzzy Support Vector Machine (TAFSVM) which has good quality is proposed.TAFSVM not only solves the overfitting problem resulted from the outiiers with the approach of fuzzicafion of the penalty,'but also corrects the skew of the optimal separating hyperplane dut to the very imbalanced data sets by using different cost algorithms.In addition,by introdueting the total margin algorithm to replace the conventional soft margin algorithms,a lower generalization error bound can be obtained.Besides,realvalued genetic algorithms optimize its parameters.Subsequently,AGATAFSVM is used to classify the data of remote sensing images.The experimental results indicate that the proposed AGATAFSVM can achieve higher classification accuracy and is stabler than radial basis functions neural network,K-nearest neighbors classifier and standard SVM.
作者 戴宏亮
出处 《计算机工程与应用》 CSCD 北大核心 2010年第4期4-7,共4页 Computer Engineering and Applications
基金 国家自然科学基金No.10771220 国家教育部高等学校博士点科研基金No.SRFDP-20070558043~~
关键词 全间隔自适应模糊支持向量机 实值遗传算法 遥感图像 分类 Total margin-based Adaptive Fuzzy Support Vector Machine(TAFSVM) real-valued genetic algorithms remote sensingimages classification
作者简介 E-mail: daihongliang@tom.com作者简介:戴宏亮(1978-),男,博士研究生,副教授,研究方向为模式识别与知识发现、小波分析及应用、图像处理等。
  • 相关文献

参考文献21

  • 1Hughes G F.On the mean accuracy of statistical pattern recognizers[J].IEEE Trans Inf Theory, 1968, IT-14( 1 ) : 55-63.
  • 2Hoffbeck J P,Landgrebe D A.Covariance matrix estimation and classification with limited training data[J].IEEE Trans Pattern Anal Maeh Intell, 1996,18(7):763-767.
  • 3Tadjudin S,Landgrebe D A.Covariance estimation with limited training samples[J].IEEE Trans Geosci Remote Sens,1999,37(4):2113- 2118.
  • 4Jarivs C H,Stuart N.The sensitivity of a neural network for classifying remotely sensed imagery[J].Computers & Geoscienees, 1996, 22 (9) : 959-967.
  • 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. 被引量:91
  • 6黎明,严超华,刘高航.具有自适应类警戒参数的模糊ARTMAP神经网络[J].中国图象图形学报(A辑),1999,4(5):377-382. 被引量:14
  • 7Melver D K,Fried M A.Using prior probabilities in decision tree classification of remotely sensed data[J].Remote Sensing of Environment, 2002(81 ) : 253-261.
  • 8John R,Janet F,Dar A R.A comparison of methods for monitoring multitempo ralvegetation ehange using the matie mapper imagery[J]. Remote Sensing of Environment,2002(80): 143-156.
  • 9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,2005,9(4):405-412. 被引量:91
  • 10Foody G M,Mathur A.A relative evaluation of multiclass image classification by support vector machines [J].IEEE Trans Geosci Remote Sens,2004,42(6) : 1335-1343.

二级参考文献26

  • 1梁怡.人工智能、空间分析与空间决策[J].地理学报,1997,52(S1):104-113. 被引量:11
  • 2RichardODuda PeterEHart DavidGStork.模式分类[M].北京:机械工业出版社,2003.134-174.
  • 3王润生,图像理解,1995年
  • 4Fu Limin,Neural Networks in Computer Intelligence,1994年
  • 5胡守仁,神经网络导论,1993年
  • 6沈清,模式识别导论,1991年
  • 7梁怡,地理学报,1997年,52卷,增刊,104页
  • 8Gong P,Photogrammetric Engineering and Remote Sensing,1996年,62卷,5期,513页
  • 9Zhou J,Photogrammetric Engineering and Remote Sensing,1996年,62卷,1期,1287页
  • 10Hanson M C , Dubayah R, DeFries R S. Classification Trees: an Alternative to Traditional Land Cover Classifers[J]. INT. J. Remote Sensing,1996,17:1075-1081.

共引文献191

同被引文献41

  • 1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. 被引量:13
  • 2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. 被引量:48
  • 3杨听,汤国安,邓风东,等.ERDAS遥感数字图像处理实验教程[M].北京:科学出版社,2009.
  • 4居红云,张俊本,李朝峰,王正友.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. 被引量:23
  • 5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. 被引量:10
  • 6Vapnik V N. Statistical Leaming Theory[M]. New York: Wi- ley,1998.
  • 7Wang Yu-jian, Yuan Jia-zheng, Fan Li-li, et al. Application Re- search of Support Vector Machine in Multi-spectra Remote Sensing Image Classification[C]//Proceedings of 2nd Interna- tional Congress on Image and Signal. Tianjing, China: IEEE, September 2009 : 1-5.
  • 8Soliman 0 S, Mahmoud A S, Hassan S M. Remote Sensing Satel- lite Images Classification using Support Vector Machine andParticle Swarm Optimization[C] //Third International Confe- rence on Innovations in Bio-Inspired Computing and Applica- tions. Kaohsiung: IEEE, 2012 : 280-285.
  • 9Moser G, Serpico S B. Contextual Remote-Sensing Image Classi- fication by Support Vector Machines and Markov Random Fields[C]//2010 IEEE International Geoseienee and Remote Sensing Symposium. Honolulu, HI: IEEE, 2010 : 3728-:3731.
  • 10Yu Le, Porwal A, Holden E J, et al. Towards automatic litholo- gical classification from remote sensing data using support vec- tor machines[J].Computers & Geosciences, 2012,45 : 229-239.

引证文献1

二级引证文献54

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部