Abstract: Conventional visual and manual road crack detection method is labor-consuming, non-precise, dangerous, costly and it affect transportation as well. An automatic road crack detection method was described based on image process. It enhances the road image by using a mask filtrating method in the first, then segments the image by the maximum of class distance. The detecting effectiveness of the algorithm is good for the detecton of pavement crack diseases.

Key words: pavement crack, threshold segmentation, image processing

摘要： 传统的人工视觉检测裂缝方法具有耗力、耗时、不精确、影响交通、危险、花费高等缺点。这里介绍一种基于图像处理的路面裂缝类病害自动识别方法。首先使用一种掩膜平滑法,对有大量噪音的路面图像进行增强,再采用最大类间、类内距离准则对图像进行阈值分割,提取图像上的裂缝特征,实验结果表明了该方法的有效性。

关键词: 路面裂缝, 阈值分割, 图像处理