Mathematical Morphology Based Asphalt Pavement Crack Detection

Abstract

Conventional visual and manual analysis approaches to pavement crack detection are costly, time-consuming, labor-intensive, and subjective. This paper proposed a scheme of automated detection of asphalt pavement surface images. Image enhancement based on mathematical morphologic operations was first performed, then the image is segmented based on the threshold method. The main idea of the proposed image segmentation method is that the threshold values of gray-level pavement images are strongly related with the values of the mean and standard deviation of the pixel intensities. The experimental results have demonstrated that the proposed approach can determine the threshold values accurately and quickly.