不同尺度下高分辨率遥感影像道路信息提取  

Road Information Extraction from High-resolution Remote Sensing Image in Different Research Scales

作　　者：沈占锋[1] 骆剑承[1] 郜丽静[1] 刘雯[1] 

机构地区：[1]中国科学院遥感应用研究所,北京100101

出　　处：《四川师范大学学报（自然科学版）》2009年第6期812-815,共4页Journal of Sichuan Normal University（Natural Science）

基　　金：国家"863"计划基金(2009AA12Z123;2007AA12Z141);国家自然科学基金(40971228;40601057)资助项目

摘　　要：道路作为衡量城市发展的主要因素,是城市发展过程中更新最快的要素之一,其发展直接影响城市功能用地的布局,因此基于高分辨率遥感影像的道路信息提取具有重要而现实的意义.在综合分析各种高分辨率影像道路提取方法的基础上,提出了基于不同尺度进行影像特征基元分割、并结合知识辅助实现基元分析的方法.该方法能够有效地通过面向对象方式将影像中的道路进行精确地提取,并可根据用户研究尺度的不同提取出不同规模的城市道路,最后结合具体实例对这种方法进行了分析.As a main factor of evaluating city development speed, the road is one of the fast and updating elements during city development. Road information extraction based on high-resolution remote sensing images has very important significance because road affects city land use and distribution. Based on the synthetical analysis for all kinds of road extraction method from high-resolution remote sensing images, this paper presents this road extraction method that firstly extracts elementary units from the experimental images based on different scales, and then analyzes the elementary units assisted by relative knowledge. This method can extract road information by object-oriented means, and can put forward different-scale roads according to the user＇s requirement. At last this paper gives the analysis with the experimental samples.

关 键 词：全色影像 道路提取 目标识别 基元 尺度 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术] TP751[自动化与计算机技术—计算机科学与技术]