Road surface damages allocation with RTI-IMS software based on YOLO V5 model

ABSTRACT

Research on applying artificial intelligence to autonomously detect road surface damages contributes positively to road traffic maintenance and management. This study introduces the Road Traffic Infrastructure Intelligent Management System (RTI IMS) software, utilizing the Yolo V5 programming platform. This software is designed to automatically identify road surface damages during operation. Based on machine learning image recognition technology, the model is trained with a diverse database of road surface damage images from Japan, India, and Vietnam. Additionally, to improve the inference efficiency of the RTI IMS software, the study uses the Mosaic method, tripling the variation to diversify input data during training, thereby minimizing prediction errors. The research results in the successful development of the RTI IMS software, capable of autonomously detecting road surface damages and providing corresponding images to traffic management authorities. This study significantly contributes to the modernization of current road traffic management practices.

KEYWORDS:

• Road damage detection
• Yolo V5
• RTI–IMS
• machine learning
• intelligent management system

Acknowledgments

We acknowledge Ho Chi Minh City University of Technology (HCMUT), VNU-HCM for supporting this study.

Disclosure statement

The authors have no relevant financial or non-financial interests to disclose.

Author contributions

All three authors wrote, prepared and reviewed the manuscript.

Data availability statement

The data generated in this research are available from the corresponding author on request.

Additional information

Funding

The authors declare that no funds, grants or other support were received during the preparation of this manuscript.

Notes on contributors

Son Vu Hong Pham

Dr. Son Vu Hong Pham received his Master and PhD in Construction Management from National Taiwan University of Science and Technology (Taiwan Tech). Son is a lecturer in the Department of Construction Engineering and Management at HCMUT-VNU. He has over a decade of practical experience in engineering management and consulting services for the private and public sectors. He is a member of several international and domestic professional organizations. His teaching and research interests primarily involve Artificial Intelligent (AI), Project Management (PM) related to knowledge discovery in databases (KDD), data mining, game theory, decision support systems, construction procurement, risk management and computational optimization. https://orcid.org/0000-0002-9788-0627

Khoi Van Tien Nguyen

Khoi Van Tien Nguyen is a postgraduate student majoring in Faculty of Civil Engineering, Ho Chi Minh City University of Technology (HCMUT), Vietnam. Mr. Nguyen holds a Master’s degree in Construction Management from the Ho Chi Minh City University of Technology, Vietnam, with a specialization in urban infrastructure and transportation technical management. His academic and research interests focus on the management of transportation infrastructure projects and the application of artificial intelligence to automate construction management tasks. https://orcid.org/0009-0002-9725-6514

Huy Quang Le

Huy Quang Le is a university student in Faculty of Civil Engineering, Ho Chi Minh City University of Technology (HCMUT), Vietnam.

Phuc Le Hoang Tran

Phuc Le Hoang Tran is a M.Sc. Student in Faculty of Civil Engineering, Ho Chi Minh City University of Technology (HCMUT), Vietnam.