Automated Measurements of Road Cracks Using Line-Scan Imaging

Abstract

This paper presents a new line-scan imaging system for automated measurements of road crack. The system consists of off-the-shelf hardware for real-time image acquisition and the customized image-analysis software for crack detection. A line-scan camera with 2 k pixels, a GigE interface, and a line rate up to 36 kHz was used to scan 3.6-m wide pavements at highway speeds, and a laser line projector was used to cast a transverse beam that overlays the scanline of the camera to eliminate shadows of vehicles and roadside objects and to maintain consistent lighting conditions. In the crack detection algorithms, a pavement image was first divided into grids of 8×8 pixels, and each grid was classified either as a non-crack or crack grid (called seed) using the pixel information of the grid and the overall background. Then, seeds in the vicinity were connected based on geometrical and intensity constrains. The connected seeds served as a candidate for a crack, which were further verified by using the contrast to the pixels along its trace. The paper also reports the experimental results on a designated pavement that was manually rated by an expert, and scanned three-times by the system. The statistic analysis showed that the difference in crack length between the manual and automatic measurements was less than 10 %, and no significant difference among the multiple scans by the system.

Pavement cracking measurements using 3D laser-scan images

“…For the last two decades, automatic pavement condition survey (APCS) systems have been developed with various degrees of success to supplant the manual method. Digital pavement images were collected into films, videos or high resolution digital images, and were analyzed with commercial APCS systems, such as Laser Crack Measurement System (Laurent et al 2012), Waylink (Waylink 2007), Pathway (Pathway Services 2010), uniAMS (uniAMS 2010), IDEA (Applied Pavement Technology I 2005) and Crackscope (Yao et al 2011). In general, pavement cracking detection in a 2D image can be considered as extracting curvilinear features from grainy pavement background.…”

“…Overall, the results from these algorithms lack consistency when pavement textures and lighting conditions change. Recently, seed-growing algorithms (Li et al 2011, Huang and Xu 2006, Yao et al 2011 were developed by utilizing both micro and macro texture information in detecting cracks and demonstrated high robustness with a wide range of pavement textures. This method divided the pavement image into small grids to determine possible crack seeds according to localized features of individual grids, and then examined if seeds geometrically satisfied chain structures in larger scales.…”

Fusing complementary images for pavement cracking measurements

“…Crack detection is the step to trace and measure cracks in the fused image by using a seed-growing algorithm developed in our previous project [30]. The procedures of the crack detection algorithm includes grid feature extraction, seed identification and seed connection.…”

“…Results from automatic crack detection were mostly consistent with visual evaluation. The difference in crack length between the automatic and manual measurement was less than 10%, most of which comes from the fact that some shallow and narrow cracks are not captured with good contrast [30]. Figure 8 presents two examples of the detected cracks in the fused pavement images of the two pairs of complementary images in figure 2.…”