Affiliation:
1. School of Civil Engineering, Chongqing Jiaotong University, Chongqing 400074, China
2. Merchant Chongqing Communication Research & Design Institute Co., Ltd., Chongqing 400067, China
3. School of Civil and Transportation Engineering, Shenzhen University, Shenzhen 518060, China
Abstract
To improve the accuracy of concrete crack measurement with a machine vision method in structural health monitoring and in technical status evaluation, a subpixel crack measurement method based on the partial area effect was proposed. (1) First, a pixelwise crack image segmentation method was established through a multi-step process of multi-threshold fusion and morphology operation, and a novel pixel degree crack width calculation method was developed with the extraction of the middle points, the center line and its normal, and the intersection of the center line normal and crack edges. (2) Then, a subpixel algorithm based on the partial area effect was introduced to locate vertical, horizontal, and oblique cracks in subpixel crack edges, and the subpixel crack width could be calculated along the crack center line pixelwise. (3) Finally, the proposed method was verified by indoor concrete beam crack measurement tests with a digital microscope, and the results show that the maximum relative errors of the subpixel width of the horizontal, vertical, and oblique straight cracks measured by the proposed method were 3.06%, 8.97%, and 5.16%, respectively. The absolute error of the crack length was less than 0.30 mm, and the measurement accuracy could reach 0.01 pixels. The subpixel crack measurement method provides a novel possible solution for structural health monitoring.
Funder
National Natural Science Foundation of China
Chongqing graduate joint training base construction project
Graduate Tutor Team Construction Project of Chongqing
Transportation Science and Technology Project of Sichuan Province
Scientific Research Innovation Project of Chongqing
State Key Laboratory of Mountain Bridge and Tunnel Engineering
Reference32 articles.
1. UAV bridge inspection through evaluated 3D reconstructions;Chen;J. Bridge Eng.,2019
2. A Brief Review and a New Graph-Based Image Analysis for Concrete Crack Quantification;Payab;Arch. Comput. Methods Eng.,2019
3. Yang, G.J., Qi, Y.H., and Shi, X.M. (2023). Review of bridge crack detection based on digital image technology. J. Jilin Univ. (Eng. Technol. Ed.), 1–20.
4. Automated defect inspection of concrete structures;Chow;Autom. Constr.,2021
5. Ali, L., Harous, S., Zaki, N., Khan, W., Alnajjar, F., and Jassmi, H.A. (2021, January 19–21). Performance evaluation of different algorithms for crack detection in concrete structures. Proceedings of the 2021 2nd International Conference on Computation, Automation and Knowledge Management, ICCAKM, Dubai, United Arab Emirates.
Cited by
2 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献