首页 | 本学科首页   官方微博 | 高级检索  
     

面向对象的eCognition遥感影像分类识别技术应用
引用本文:宋杨,李长辉,林鸿. 面向对象的eCognition遥感影像分类识别技术应用[J]. 地理空间信息, 2012, 0(2): 64-66
作者姓名:宋杨  李长辉  林鸿
作者单位:广州市城市规划勘测设计研究院,广东广州510060
基金项目:广州市城市规划勘测设计研究院2011年度院科研资助课题
摘    要:以位于印度尼西亚Kalimantan热带雨林地区的1幅具有3个通道的雷达图像为研究对象,利用面向对象方法对高分辨率遥感影像的水体进行提取,在分割的基础上,经过分层分类,充分利用影像的光谱信息、拓扑信息、形状特征等构建知识库进行分类,实验结果理想,相对传统基于像素的图像分类分析方法结果图斑完整,提高了分类精度。

关 键 词:面向对象  遥感影像  分类  eCognition

Object Extration Techniques of Remote Sensing Images Based on Object-oriented Ecognition Software
Abstract:This paper took Kalimantan as study area.Object-oriented information extraction technology was use to extract water bodies.Based on multiresolution segmentation,we carried out a classification of twolayered.Through the whole process,the image information of spectrum,topology,shape were adequately used.The results of experiment were famous,the classification objects of water were integrate contrasting to the traditional classification based on pixel analysis.
Keywords:object-oriented  remote sensing image  classification  eCognition
本文献已被 CNKI 维普 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