基于图像处理的沥青路面裂缝测量算法研究  

Research on Measuring Algorithm of Asphalt Pavement Crack Based on Image Processing

作　　者：伯绍波[1] 闫茂德[1] 何靓俊[1] 贺昱曜[1] 

机构地区：[1]长安大学信息工程学院,陕西西安710064

出　　处：《计算机测量与控制》2007年第10期1305-1307,共3页Computer Measurement &Control

基　　金：教育部特殊地区公路工程重点实验室资助项目(KLP200501)

摘　　要：针对传统的人工视觉测量沥青路面裂缝方法的多种弊端,提出一种测量沥青路面裂缝的图像处理新算法;对规则裂缝图像,该算法将形态学的腐蚀算子加以改进,对裂缝进行细化获得裂缝的骨架并求出斜率,结合计数的方法测量裂缝的长度和宽度;对不规则裂缝图像,该算法利用蚕食的方法测量裂缝的面积;最后,在Visual C++6.0编程环境下进行了算法的实现;实验结果表明,可以较精确地测量出规则裂缝的长度和宽度,以及不规则裂缝的面积,为沥青路面裂缝的分析和管理提供了技术基础。It is bad to measure the asphalt pavement cracks by conventional artificial vision methods. In order to solve these questions, a novel image processing algorithm to measure asphalt pavement crack is presented. To the regular crack image, our algorithm improves the morphological Erosion operator to thin the crack, gains the skeleton and slop of the crack, then employs counting method to measure the length and width of the crack. To the irregular crack image, our algorithm adopts nibble method to measure the area of the crack. At last, it is implemented in the programming environment of Visual C＋＋ 6.0. The experimental results indicate that we can accurately obtain the length and width of regular crack and the area of irregular crack. Moreover, it can provide the techno--guarantees for the analysis and management of the asphalt pavement cracks.

关 键 词：形态学 沥青路面 图像处理 裂缝 蚕食 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]