首页 | 本学科首页   官方微博 | 高级检索  
     

基于Mumford-Shah模型的水上桥梁目标分割与识别
引用本文:闵莉,唐延东,史泽林.基于Mumford-Shah模型的水上桥梁目标分割与识别[J].红外与激光工程,2006,35(4):499-504.
作者姓名:闵莉  唐延东  史泽林
作者单位:1. 中国科学院沈阳自动化研究所,辽宁,沈阳,110016;中国科学院研究生院,北京,100039
2. 中国科学院沈阳自动化研究所,辽宁,沈阳,110016
基金项目:中国科学院知识创新工程项目
摘    要:在桥梁知识的基础上,从河流和陆地的区域特性出发,提出了一种基于Mumford-Shah(MS)模型的水上桥梁分割算法.首先对Mumford-Shah模型中的区域权重进行相关性定义,实现对水域的分割,然后根据桥梁与河流区域边界的几何位置关系实现对桥梁目标的提取和识别.实验表明,该算法能够实现对水上桥梁目标的提取,尤其对远距离小目标水上桥梁及灰度梯度较弱图像的桥梁分割更有效.

关 键 词:水上桥梁识别
文章编号:1007-2276(2006)04-0499-06
收稿时间:2005-08-20
修稿时间:2005-09-10

Segmentation and recognition of bridge over water based on Mumford-Shah model
MIN Li,TANG Yan-dong,SHI Ze-lin.Segmentation and recognition of bridge over water based on Mumford-Shah model[J].Infrared and Laser Engineering,2006,35(4):499-504.
Authors:MIN Li  TANG Yan-dong  SHI Ze-lin
Affiliation:1.Shenyang Institute of Automation, Chinese Academy of Sciences, Shenyang 110016,China; 2.Graduate School of Chinese Academy of Sciences, Beijing 100039,China
Abstract:A method of segmentation and recognition of bridge over water based on Mumford-Shah model and the bridge knowledge was proposed. The region-correlating weighted Mumford-Shah model was used to segment the water region on the smoothed image, and then the bridge was detected and recognized by the segmentation result and the geometrical knowledge of bridge and water region. Experimental results show that the method is effective and exact for bridge detection and recognition, especially when the bridge is a small object or the intensity gradient is not strong.
Keywords:Mumford-Shah  Level  set
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