A Support Vector Machine-Based Particle Filter Method for Improved Flooding Classification

作者:Insom, P (Insom, Patcharin)[ 1,2 ] ; Cao, CX (Cao, Chunxiang)[ 1 ] ; Boonsrimuang, P (Boonsrimuang, Pisit)[ 3 ] ; Liu, D (Liu, Di)[ 1,2 ] ; Saokarn, A (Saokarn, Apitach)[ 1,2,4 ] ; Yomwan, P (Yomwan, Peera)[ 5 ] ; Xu, YF (Xu, Yunfei)[ 1 ]

IEEE GEOSCIENCE AND REMOTE SENSING LETTERS

卷: 12  期: 9  页: 1943-1947

DOI: 10.1109/LGRS.2015.2439575

出版年: SEP 2015

摘要

Support vector machines (SVMs) have been applied to land cover classification, and a number of studies have demonstrated their ability to increase classification accuracy. The high correlation between the data set and SVM training model parameters indicates the high performance of the classification model. To improve the correlation, research has focused on the integration of SVMs and other algorithms for data set selection and SVM training model parameter estimation. This letter proposes a novel method, based on a particle filter (PF), of estimating SVM training model parameters according to an observation system. By treating the SVM training function as the observation system of the PF, the new method automatically updates the SVM training model parameters to values that are more appropriate for the data set and can provide a better classification model than can the original model, wherein the parameters are set by trial and error. Various experiments were conducted using Radarsat-2 synthetic aperture radar data from the 2011 Thailand flood. The proposed method provides superior performance and a more accurate analysis compared with the standard SVM.

通讯作者地址: Insom, P (通讯作者)

Chinese Acad Sci, Inst Remote Sensing & Digital Earth, State Key Lab Remote Sensing Sci, Beijing 100094, Peoples R China.

地址:

[ 1 ] Chinese Acad Sci, Inst Remote Sensing & Digital Earth, State Key Lab Remote Sensing Sci, Beijing 100094, Peoples R China

[ 2 ] Univ Chinese Acad Sci, Beijing 100094, Peoples R China

[ 3 ] King Mongkuts Inst Technol Ladkrabang, Fac Engn, Telecommun Engn Dept, Bangkok 10520, Thailand

[ 4 ] Royal Thai Survey Dept, Bangkok 10520, Thailand

[ 5 ] Bur Mapping Technol, Dept Lands, Nonthaburi 11120, Thailand