International conference on construction engineering and project management (국제학술발표논문집)

  • 2024.07a
  • /
  • Pages.1035-1040
  • /
  • 2024
  • /
  • 2508-9048(eISSN)
Korea Institute of Construction Engineering and Management (한국건설관리학회)
권호 표지
DOI QR코드

DOI QR Code

Advancing Road Infrastructure Management and Safety Through Pothole Classification Standards and Technology: A South Korean Perspective

  • Wonwoo SHIN (Department of Civil Systems Engineering, College of Engineering, Ajou University) ;
  • Kyubyung KANG (School of Construction Management Technology, Purdue University) ;
  • Sungkon MOON (Department of Civil Systems Engineering, College of Engineering, Ajou University)
  • Published : 2024.07.29
Download PDF
⟨ Previous Next ⟩

Abstract

South Korea has seen an increased demand for road maintenance, since they experienced a rapid industrialization in 1960-70s. Between 2019 and the end of 2022, the total national expenditure on road maintenance steadily rose from KRW 3.4 trillion to KRW 4.5 trillion. Roads, responsible for about 80% of the nation's transportation, significantly affect ride quality, safety and maintenance costs. Among the different perspectives, this study focuses on the prevalence of potholes. Over 24,000 pothole instances are reported on highways in the past five years, which raises concerns due to various direct and indirect effects on road maintenance and safety issues. Various methods, including vision-based, vibration-based, and 3D reconstruction-based techniques, have been proposed for pothole detection and inspection. Vision-based methods effectively count and measure pothole shapes but which are sensitive to lighting conditions. Vibration-based methods offer cost-effectiveness, although it may not provide precise pothole shape information. 3D reconstruction-based methods deliver accurate shape measurements, while it comes with higher costs. To establish an effective road maintenance system, prioritization criteria for potholes is required to be established and applied. These criteria may vary across countries or regions. For example, in the United States, potholes are classified based on depth into Low (<25mm deep), Moderate (25 to 50mm deep), and High (>50mm deep). In conclusion, this research addresses this research challenge of road damage and potholes in South Korea by exploring various pothole classification standards and utilizing advanced technology to develop an efficient road maintenance system. The outcome would benefit improved road infrastructure management and enhanced safety.

Keywords

Acknowledgement

This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science and ICT (Grant Number: 2022R1F1A1074039)

References

  1. Ministry of Land, I.a.T. Management of road frame repair work. 2023.
  2. Ministry of Land, I.a.T.R.o.K. Data Integration Channel of Ministry of Land, Infrastructure and Transport. 2024.
  3. Technology, K.I.o.C.E.a.B., Final-Report of the National Highway Pavement Management System 2021.
  4. Chun, C., et al., Development and evaluation of automatic pothole detection using fully convolutional neural networks. The Journal of the Korea Institute of Intelligent Transport Systems, 2018. 17(5): p. 55-64.
  5. Li, Y., et al., A novel evaluation method for pavement distress based on impact of ride comfort. International Journal of Pavement Engineering, 2022. 23(3): p. 638-650.
  6. Kirbas, U. and M. Karasahin. Estimating PCI using vibration data for asphalt concrete pavements. in Proceedings of the 2nd World Congress on Civil, Structural, and Environmental Engineering (CSEE'17), Barcelona, Spain. 2017.
  7. Inzerillo, L., G. Di Mino, and R. Roberts, Image-based 3D reconstruction using traditional and UAV datasets for analysis of road pavement distress. Automation in Construction, 2018. 96: p. 457-469.
  8. Chu, C., et al., An optimized fringe generator of 3D pavement profilometry based on laser interference fringe. Optics and Lasers in Engineering, 2021. 136: p. 106142.
  9. Bruno, S., et al., Pavement Distress Estimation via Signal on Graph Processing. Sensors, 2022. 22(23): p. 9183.
  10. Liang, X., et al., Automatic classification of pavement distress using 3D ground-penetrating radar and deep convolutional neural network. IEEE Transactions on Intelligent Transportation Systems, 2022. 23(11): p. 22269-22277.
  11. Li, Y., et al., Moving object detection via segmentation and saliency constrained RPCA. Neurocomputing, 2019. 323: p. 352-362.
  12. Song, H., et al., Vision-based vehicle detection and counting system using deep learning in highway scenes. European Transport Research Review, 2019. 11(1): p. 1-16.
  13. Jin, Y., et al. Fast detection of traffic congestion from ultra-low frame rate image based on semantic segmentation. in 2019 14th IEEE Conference on Industrial Electronics and Applications (ICIEA). 2019. IEEE.
  14. Laroca, R., et al. A robust real-time automatic license plate recognition based on the YOLO detector. in 2018 international joint conference on neural networks (ijcnn). 2018. IEEE.
  15. Administration, F.H., Distress Identification Manual for The Long-Term Pavement Performance Program (Fifth Revised Edition). 2014: p. 18.
  16. China, M.o.T.o.t.P.s.R.o., Highway Performance Assessment Standard (JTG H20-2007). 2007.
  17. Raya, M.J.K., A Guide to Visual Assessment of Flexible Pavement Surface Conditions. 1992: Jabatan Kerja Raya.
  18. Highways, N. Categorisation of potholes. 2014 [cited 2023; Available from: https://www.astonlewallsparishcouncil.gov.uk/uploads/potholes0001.pdf.
  19. Council, N.N. Report potholes or a highway problem. 2023 [cited 2023; Available from: https://www.northnorthants.gov.uk/parking-roads-and-transport/report-potholes-or-highwayproblem.
  20. DJI, Support for Phantom 4 Pro. 2023.
  21. Jiang, P., et al., A Review of Yolo algorithm developments. Procedia Computer Science, 2022. 199: p. 1066-1073.