斜拉桥缆索表面缺陷提取方法研究  

Crack Detection Algorithm Design for Cable's Protective Layer Surface on Cable-Stayed Bridge

作　　者：蔡步文[1] 周忆[1] 申超[1] 

机构地区：[1]重庆大学机械工程学院,重庆400030

出　　处：《微计算机信息》2010年第32期188-190,共3页Control & Automation

基　　金：基金申请人:周忆;项目名称:斜拉桥缆索缺陷检测机器人的理论和实验研究;基金颁发部门:重庆市科委(CSTC;2008AC6083);"211工程"三期建设(S-09106)

摘　　要：提出了一种对斜拉桥缆索表面保护层缺陷算法的设计。首先,在图像的预处理阶段,对原始图像进行滤波,运用灰度投影获得缆索轮廓的连续边界;然后利用原始的灰度图像和基于缆索轮廓的掩膜板,获得了无背景的缆索表面图像;最后,利用数学统计,区域分割及数学形态算法提取出了缆索表面缺陷的图像。结果表明该算法能有效地从爬升机器人采集的图像中提取出缆索保护层表面缺陷的图像。In order to crack of cable＇s protective layer surface on cable-stayed bridge,an algorithm design was proposed in this paper.Firstly,filtering processing were used in the phase of image pre-processing.Secondly,the continuous boundary of cable contour was obtained by projection of gray.Subsequently,the stay cable surface image without background was delivered from the original gray image and the mask that was based on the continuous boundary of cable＇s contour.In the last stage,the cable＇s protective layer surface crack image was obtained by using mathematics Statistic,area division and mathematics morphological.The result shows the algorithm can successfully extract the crack the crack image of cable ＇s protective layer from the images that captured by the climbing robot.

关 键 词：缺陷检测 图像提取 斜拉桥 缆索 

分 类 号：U446.2[建筑科学—桥梁与隧道工程]