首页 | 本学科首页   官方微博 | 高级检索  
     

椭球径向基模型及其遥感分类方法研究
引用本文:骆剑承,明冬萍,沈占锋,陈秋晓,郑江.椭球径向基模型及其遥感分类方法研究[J].数据采集与处理,2005,20(1):8-12.
作者姓名:骆剑承  明冬萍  沈占锋  陈秋晓  郑江
作者单位:中国科学院地理科学与资源研究所,北京,100101
基金项目:国家自然科学基金 ( 4 0 1 0 1 0 2 1 )资助项目,中国科学院地理科学与资源研究所知识创新 ( CXIOG-D0 2 -0 1 )资助项目
摘    要:椭球径向基函数神经网络(EBF)是在径向基函数(RBF)映射理论基础上的改进。在保留RBF三层网络结构基础上,EBF采用了EM算法来估计特征空间的混合密度分布参数,用椭球体集合来分解混合密度分布,从而构造了神经网络的中间层基函数的状态。由于在遥感数据的特征空间中通常表现为混合密度分布,EBF模型能够充分利用EM算法获得的最大似然参数估计得到更合理的特征空间的密度分解模型,从而使得EBF模型能够在保留了RBF非线性复杂映射能力的同时,获得更合理的分类结果。本文提出了基于EBF的遥感分类方法,试验结果表明EBF方法比RBF方法训练速度更快、网络连接更简单、分类精度更高。

关 键 词:RBF  特征空间  遥感分类  EM算法  网络连接  径向基函数神经网络  分解模型  基模  最大似然  三层网络结构
文章编号:1004-9037(2005)01-0008-05

Elliptical Basis Function Network for Classification of Remote-Sensing Images
LUO Jian-cheng,MING Dong-ping,SHEN Zhan-feng,CHEN Qiu-xiao,ZHENG Jiang.Elliptical Basis Function Network for Classification of Remote-Sensing Images[J].Journal of Data Acquisition & Processing,2005,20(1):8-12.
Authors:LUO Jian-cheng  MING Dong-ping  SHEN Zhan-feng  CHEN Qiu-xiao  ZHENG Jiang
Abstract:An elliptical basis function (EBF) network is proposed for the classification of remote-sensing images. Though they are similar in structure, the EBF network differs from the well-known radial basis function (RBF) network by incorporating full covariance matrices and uses the expectation-maximization (EM) algorithm to estimate the basis functions. Since remotely sensed data often take on mixture-density distributions in the feature space, the proposed network possesses the advantage of the RBF mechanism and utilizes the EM algorithm to compute the maximum likelihood estimates of the mean vectors and covariance matrices of a Gaussian mixture distribution in the training phase. Experimental results show that the EM-based EBF network is faster in training, more accurate, and simpler in structure.
Keywords:remote-sensing classification  elliptical basis functions  EM algorithm  mixture densities
本文献已被 CNKI 维普 万方数据 等数据库收录!
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号