摘要
道路信息在城市规划和经济建设中具有非常重要的作用和意义,因而从高分辨率遥感影像中提取道路信息成为当今学术研究热点之一.针对道路信息提取中存在的问题,本文采用面向对象的方法对道路信息进行提取.论文在对影像进行多尺度分割的基础上,采用最近邻分类法结合影像的光谱信息、几何特征及纹理特征所构建的道路对象的知识库对影像中的道路信息进行提取.试验结果表明采用面向对象的方法对道路信息进行提取效果良好.
Due to the road information in urban planning and economic construction plays a very important role and significance,thus it is a hot spot that from high-resolution remote sensing image extracted road information in academic research.According to the problems of extracted the road information.In this paper,using object-oriented method to extracted road information.In this paper,based on multiresolution segmentation of image,we using nearest neighbor method combine with knowledge database of road information which constructed by the spectral information,geometrics features and texture features to extract the road information from image.The experiment results show that the object-oriented information extraction effect is good.
出处
《昆明理工大学学报（理工版）》
北大核心
2010年第6期6-10,共5页
Journal of Kunming University of Science and Technology(Natural Science Edition)
基金
云南省自然科学基金(2007D042M)
关键词
信息提取
面向对象
高分辨率卫星影像
道路
易康
information extraction
object-oriented
high-resolution satellite image
road
eCongnition
