中山大学学报（自然科学版）Issue(4)：102-111,10.DOI:10.13471/j.cnki.acta.snus.2015.04.020
基于 WorldView-2数据和支持向量机的红树林群落分类研究
Mangrove Community Classification Based on WorldView-2 Image and SVM Method
摘要
Abstract
Using remote sensing technology in Mangrove Community Classification is very significant for surveying,taking advantage of and protecting Mangrove resource.In this study,based on the spectrum characteristics of mangroves,vegetation index and texture information calculated from WorldView-2 satel-lite imagery,we used object-oriented classification method,SVM (Support Vector Machine),in con-junction with field surveys to map mangrove forest at communities’level in Daweiwan District,Qi’ao Is-land,Zhuhai.The single-scale and multi-scale classification were also compared.The results indicated that WorldView-2 data,a very high-resolution satellite remote sensing imagery with 8 bands are very suit-able for mangrove forest classification using object-oriented and SVM method.The overall accuracy and Kappa indices for mangrove forest classification at the species level in the study area were 84.2% and 0.794 for multi-scaled analysis and 69.8% and 0.616 for the single-scaled.关键词
红树林群落/面向对象/支持向量机/多尺度分类Key words
mangrove/object-oriented/SVM/multi-scale classification分类
信息技术与安全科学引用本文复制引用
唐焕丽,刘凯,朱远辉,王树功,柳林,宋莎..基于 WorldView-2数据和支持向量机的红树林群落分类研究[J].中山大学学报（自然科学版）,2015,(4):102-111,10.基金项目
国家自然科学基金资助项目（41001291）；中山大学高校基本科研业务费专项资金资助项目（13lgpy61）；教育部重点实验室系统基金资助项目 （）
