Abstract
Crack junction is the crossing or branching point of different cracks in the pavement image. It represents the branch of transverse crack or longitudinal crack, and describes the interlaced network of alligator crack. It is a simple yet important factor to characterize the type and severity level of crack. This paper is motivated to robustly detect crack junctions of any type and size in pavement image, regardless of the pavement interferences. In this paper, the contrast between the crack junction and pavement background is first enhanced by removing the large interferences and background. Then, based on the structure characteristic of crack curves, correlation structure index is proposed to locate candidates of crack junctions. Actual junctions are extracted among the candidates with the unified ball tensor structure after the iterative tensor voting. The proposed method is tested with the concrete pavement images of public data set of SDNET2018 and asphalt pavement images collected by the unmanned aerial vehicle on the highway G45 in China. Experimental results demonstrate that the proposed method can detect crack junctions with the correctness of 0.891 and completeness of 0.887. It can be applied to junction detection on concrete and alligator pavement with different noise and interference, and is promising to classify the crack type and quantify the severity level.
Highlights
After the vast investment into the construction of transportation infrastructure, the post-construction maintenance has become a crucial problem for transportation agencies around the world
The average correctness and completeness of B-COSFIRE method are 0.597 and 0.630, respectively. It demonstrates the proposed method can be applied to junction detection on concrete pavement and alligator pavement images
The proposed method is based on the structure characterization of crack junction that is generic and robust to different imaging conditions
Summary
After the vast investment into the construction of transportation infrastructure, the post-construction maintenance has become a crucial problem for transportation agencies around the world. Crack junction of different size can get enough structure indications from their neighbouring crack curves and detected well by the proposed method as shown in the stick tensor images and ball tensor images. The intensity of crack curves and pavement background are various, the significant ball-like structure of crack junctions is the same and well detected by the proposed tensor characterization from the structure perspective as shown in the ball tensor images. C. CRACK JUNCTIONS WITH DIFFERENT INTERFERENCES AND IMAGING CONDITIONS To obtain the hair-line crack curves, some stone mixtures are mistakenly extracted in enhanced image and correlation structure index image owing to the linear structure of FIGURE 16. Lane marking cannot be removed from the pavement image and the junction-like structures caused by the lane marking edge and crack are mistakenly detected as shown in the yellow rectangles in Figure 18(b) and (d). The proposed method is robust enough to get a good detection result regardless of the pavement interferences and imaging conditions
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
