摘要
公路路面裂缝类病害是公路路面的主要病害之一。在对公路路面裂缝类病害的检测中,将CCD摄像机作为探测系统安装在一个专用测试车上,对路面进行扫描,得到路面图像。构造了8个方向的Sobel模板对路面裂缝类病害图像进行边缘检测,边缘检测处理后,结合加权的邻域平均噪声滤除算法和Ostu图像分割算法对病害图像进行处理。处理结果相对于其他经典算法,裂缝边缘宽度较细,并且裂缝的边缘保护很好,裂缝边缘的连续性也比较好。用图像处理的方法检测公路路面裂缝类病害,检测精度和检测效果都比较满意。
The crack disease is one of the main diseases of pavement. Installing the CCD camera on a test car to scan the pavement, and get the images of pavement. Because there are many kinds of diseases, the detecting of the diseases is difficult. A new Sobel algorithm was structured in eight directions to detect the crack edges. The crack disease images were detected by the noise filtrating algorithm of neighborhood weighted averaging and Ostu image fractionating algorithm. The results show that the width of crack edge detected by the new algorithm is more thin than the one detected by other classic algorithms. The edges of cracks are properly protected and the images of cracks are clear and continuous. The detecting precision and effectiveness of the new algorithm are good for the detecting of pavement crack diseases.
出处
《长安大学学报（自然科学版）》
EI
CAS
CSCD
北大核心
2004年第3期24-29,共6页
Journal of Chang’an University(Natural Science Edition)
基金
陕西省教育厅重点科研计划项目(99JK157)
陕西省科技厅科技计划项目(2000X06)
