Classification of multisource remote sensing imagery using a Genetic Algorithm and Markov random fields

作     者：Tso, BCK Mather, PM 

作者机构：Univ Nottingham Sch Geog Nottingham NG7 2RD England 

出 版 物：《IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING》 (IEEE Trans Geosci Remote Sens)

年 卷 期：1999年第37卷第3期

页      面：1255-1260页

核心收录：

学科分类：0808[工学-电气工程] 1002[医学-临床医学] 08[工学] 0708[理学-地球物理学] 0816[工学-测绘科学与技术] 

基　　金：The SIR-C radar data were kindly made available by the NASA Jet Propulsion Laboratory  Pasadena  CA. The first author’s graduate studies were supported by a scholarship from the Taiwan  R.O.C.  government. The authors are grateful to Dr. M. Koch  Remote Sensing Center  Boston University  who provided the geological data and assisted in their interpretation. The School of Geography  University of Nottingham  made available the necessary computing facilities. The comments of several anonymous referees were invaluable in helping us focus and reorientate the original draft 

主　　题：model parameters remote-sensing data Sorting algorithm remote sensing mass function Parameter estimation Markov random fields Genetic Algorithm (GA) 

摘      要：The use of contextual information for modeling the prior probability mass function has found applications in the classification of remotely sensed data, With the increasing availability of multisource remotely sensed data sets, random field models, especially Markov random fields (MRF), have been found to pro,ide a theoretically robust yet mathematical tractable way of coding multisource information and of modeling contextual behavior. It is well known that the performance of a model is dependent both on its functional form (in this case, the classification algorithm) and on the accuracy of the estimates of model parameters, In dealing with multisource data, the determination of source weighting and MRF model parameters is a difficult issue. We extend the methodology proposed in [1] by demonstrating that the use of an effective search procedure, the Genetic Algorithm, leads to improved parameter estimation and hence higher classification accuracies.