About the authors
| First name, Middle name, Last name, Scientific degree, Scientific rank, Current position. Full and brief name of the organization, The organization address. | Vladimir V. Mokshin, Candidate of Technical Sciences, Associate Professor, Department of Automated Information Processing and Control Systems, Kazan National Research Technical University named after A.N. Tupolev – KAI, Kazan, Russian Federation; E-mail: This e-mail address is being protected from spambots. You need JavaScript enabled to view it ORCID: 0000-0002-7650-3419. Regina V. Nikolaeva, candidate of technical sciences, associate professor, Kazan State University of Architecture and Engineering, Kazan, Russian Federation; E-mail: This e-mail address is being protected from spambots. You need JavaScript enabled to view it , ORCID: 0000-0002-5324-432х. Nelli B. Mavlieva, post-graduate student, Kazan State University of Architecture and Engineering, Kazan, Russian Federation; E-mail: This e-mail address is being protected from spambots. You need JavaScript enabled to view it , ORCID: 0009-0002-9546-5056. Lenar F. Mavliev, candidate of technical sciences, associate professor, head of department, Kazan State University of Architecture and Engineering, Kazan, Russian Federation; E-mail: This e-mail address is being protected from spambots. You need JavaScript enabled to view it , ORCID: 0000-0001-6301-0941. |
| Title of the article | A system for detecting road defects based on computer vision |
| Abstract. | Road defects are one of the constantly emerging problems in the road industry that endanger road safety and require significant costs to eliminate. For effective maintenance of roads and ensuring the safety of road users, it is important to promptly detect defects in the road surface. Traditional defect detection methods take a significant amount of time, are laborious, and are prone to human error. The development of modern computer vision technologies and algorithms can significantly reduce the time needed to solve problems in various fields, including the road industry. Therefore, the purpose of the study is to select methods and algorithms for detecting road defects using computer vision to improve the accuracy and efficiency of detecting damage on highways. This, in turn, optimizes the processes of their operation and maintenance, ensuring more effective preservation of the quality of the road infrastructure. The research tasks are to compare YOLOv8 with other neural network architectures on the same dataset; to develop a system for detecting road defects based on computer vision. Results. The study defines the stages of creating a system for detecting road defects based on computer vision. The YOLOv8 detection quality metrics were obtained based on a test sample of road defects. Conclusions. The significance of the results obtained for the road industry lies in the ability to detect road defects in a timely manner, which in turn contributes to improving the efficiency of managing the condition of highways, reducing maintenance costs, and as a result, provides a higher level of safety and comfort for road users. The results can be used in further scientific developments and for optimizing road surface maintenance and repair processes. |
| Keywords. | highway, road surface, road defects, computer vision, YOLOv8. |
| For citations: | Mokshin V.V., Nikolaeva R.V., Mavlieva N.B., Mavliev L.F. A system for detecting road defects based on computer vision // News of KSUAE, 2026, № 1 (75), p. 344-355, DOI: 10.48612/NewsKSUAE/75.28, EDN: SAWGRQ |
