首页 | 本学科首页   官方微博 | 高级检索  
     

基于数学形态学的高分辨率遥感影像道路提取
引用本文:李利伟,刘吉平,尹作为.基于数学形态学的高分辨率遥感影像道路提取[J].遥感信息,2005(5):9-11.
作者姓名:李利伟  刘吉平  尹作为
作者单位:武汉大学资源与环境科学学院,湖北武汉,430079
摘    要:利用数学形态学的方法对高分辨率遥感影像道路提取进行了研究,通过对影像进行预处理增强道路信息,依据影像灰度直方图信息,对预处理后的影像进行阈值分割,得到一个包含道路信息的二值影像;进一步使用形态开运算去除细小噪声,同时将一部分粘连在道路上的噪声与道路信息进一步分割;接着结合形态腐蚀和形态重建运算获取影像中主要道路网络信息,并用形态闭运算完善道路网络信息;最后对道路网络信息进行形态细化和一定次数的形态修剪处理,得到单像素宽的道路中心线信息.利用数学计算软件MATLAB在高分辨率遥感影像上作了实验,并进行了总结和分析.

关 键 词:数学形态学  影像道路信息提取  阈值化  形态重建
文章编号:1000-3177(2005)81-0009-03
收稿时间:03 10 2005 12:00AM
修稿时间:2005-03-102005-04-26

Road Extraction from High Resolution Remote Sensing Image Based on Mathematic Morphology
LI Li-wei,LIU Ji-ping,YIN Zuo-wei.Road Extraction from High Resolution Remote Sensing Image Based on Mathematic Morphology[J].Remote Sensing Information,2005(5):9-11.
Authors:LI Li-wei  LIU Ji-ping  YIN Zuo-wei
Affiliation:Wuhan University College of Resources and Environmental Science, Hubei Wuhan 430079, China
Abstract:In the paper, an approach to extract road network in the high resolution remote sensing image based on mathematic morphology is presented. Firstly, preproeess the image to enhance the road information and threshold it into binary image according to its histogram; .Secondly, remove tiny noise with morphological opening, meanwhile it separates the road from some noise attached to it; Thirdly, Morphological reconstruction is adopted to avoid noise including objects that have similar spectral characteristics as road surfaces; Finally, determine the centerline of the road network by Morphological thinning and cropping. The developed method has tested on high resolution remote sensing image under MATLAB.
Keywords:mathematic morphology  road extraction  threshold  morphological reconstruction
本文献已被 CNKI 维普 万方数据 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