首页 | 本学科首页   官方微博 | 高级检索  
     检索      

决策树在遥感影像分类中的应用
引用本文:巴桑,刘志红,张正健,李奇穗.决策树在遥感影像分类中的应用[J].高原山地气象研究,2011,31(2):31-34.
作者姓名:巴桑  刘志红  张正健  李奇穗
作者单位:1. 西藏高原大气环境科学研究所, 拉萨 850001;
基金项目:国家发改委“十一五”重点项目“西藏自治区生态环境遥感监测与服务系统”
摘    要:在充分了解决策二叉树分类过程的基础上, 以西藏波密地区的TM遥感影像为研究对象, 提取并分析各种典型地物的反射光谱特征, 利用不同地物的光谱差异并结合人工目视判读建立了一组能够精确、快速划分遥感影像的分类规则。用ENVI建立分类决策树对实验区遥感影像进行分类, 并将分类结果和传统的最大似然法相比较。结果表明:决策树分类的总体精度和Kappa分别为97.15%和0.9644, 优于传统的最大似然法, 取得了较为满意的分类结果。 

关 键 词:决策树    遥感影像    最大似然法    分类    误差矩阵
收稿时间:2011-04-15

Decision Tree and Its Application in Remote Sensing Image Classification
BA Sang,LIU Zhihong,ZHANG Zhengjian,LI Qisui.Decision Tree and Its Application in Remote Sensing Image Classification[J].Plateau and Mountain Meteorology Research,2011,31(2):31-34.
Authors:BA Sang  LIU Zhihong  ZHANG Zhengjian  LI Qisui
Institution:1. Tibet Institute of Plateau Atmospheric and Environmcntal Sciences,Lasa 850001;2. Chengdu University of Information Technology,Chengdu,610225;3. Meteorological Bureau of Meishan County,Meishan,620010
Abstract:Taking TM images in Bomi county of Tibet as the object to study, choosing and analyzing the reflect spectral characteristics of typical land-cover types, a set of accurately and fast rules for TM images classification has been established based on spectral characteristics diversity of different land-cover types and artificial visual interpretation.The classification decision tree was applied to classify the TM images in experimental area, and the classification results were compared with traditional maximum likelihood.The results show that: the overall accuracy and Kappa coefficient of decision tree reach 97.15% and 0.9644, respectively, whose performance is more excellent than the traditional maximum likelihood method, and obtain a more satisfactory classification. 
Keywords:
本文献已被 万方数据 等数据库收录!
点击此处可从《高原山地气象研究》浏览原始摘要信息
点击此处可从《高原山地气象研究》下载免费的PDF全文
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