Some of the current methods are computationally expensive and have labor-intensive learning processes, so they are not usable in local-level projects with limited resources and budget, or they are only suitable for specific pavement types. This paper aims to develop an automatic crack assessment method to detect and classify cracks from 2-D and 3-D pavement images with the minimum cost. For longitudinal and transverse cracking, a curve is then fitted on the cracked tiles to connect them.Ī tile-based image processing method was proposed to apply a localized thresholding technique on each tile and detect the cracked ones (tiles containing cracks) based on crack pixels' spatial distribution. Next, these cracks are classified, and their lengths are measured based on the orientation axes and length of the crack curves. This method is not limited to the texture type, and it is cost-efficient as it takes less than 20 seconds per image for a commodity computer to generate results.
0 kommentar(er)
