基于对象建模的遥感影像建筑物提取方法  

A Building Extraction Method Based on Object Modeling in Remote Sensing Image

作　　者：王世伟[1] 方涛[1] 

机构地区：[1]上海交通大学图像处理与模式识别研究所,上海200240

出　　处：《计算机仿真》2010年第12期254-257,311,共5页Computer Simulation

基　　金：国家重点研究基础规划(2006CB701303);国家高技术研究发展计划(2006AA12Z105)

摘　　要：研究城镇建筑物的提取是遥感影像分析应用中的一项重要内容。遥感影像建筑物结构和光谱的多样性,使结构、光谱等特征的建筑物提取变得极其复杂。根据遥感影像的建筑物纹理区别于其它空间对象纹理的特点,为提高影像分辨率,提出Gabor纹理块的遥感影像对象模型方法应用于遥感影像城镇建筑物的提取。以整个城镇为对象,以建筑物、道路、绿地等不同城镇区域为组成对象的纹理块,建立基于纹理块的对象模型,利用模型进行遥感影像对象的纹理标定,最终提取出城镇建筑物。实验结果表明方法克服了建筑物结构复杂性和多样性以及背景环境的影响,能很好地从城镇遥感影像中提取建筑物。Urban buildings extraction is an important part of remote sensing image processing.It is difficult to extract urban buildings in remote sensing image using structural and spectral features because of diversity of structure and spectrum of buildings.This paper applies object model method based on Gabor texture motifs to extract buildings from urban,as texture of buildings is always different from that of other objects of urban in remote sensing image.It takes the whole urban as an object,takes buildings,roads and vegetation as texture motifs of the model,builds the object model with unsupervised method,specifies texture label of each pixel in remote sensing object,and extracts buildings from urban.The result shows that it avoids the affect of structure complexity and diversity and complicated background of buildings,and extracts buildings from urban in remote sensed image effectively.

关 键 词：纹理块 遥感影像 对象模型 建筑物提取 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]