AI for Tracking Overloaded Commercial Vehicles
The paper emphasizes the significance of monitoring and enforcing vehicle weight limits for road authorities, underscoring the potential adverse effects of overloaded vehicles, such as road infrastructure damage, heightened maintenance expenses, and compromised road safety. It advocates for the utilization of IT technologies like sensors, measurement tools, and data processing for actively controlling the excess weight carried by overloaded vehicles. Moreover, the paper explores the deployment of AI and object detection technology for identifying overloaded commercial vehicles, particularly highlighting the YOLO (You Only Look Once) model, a prevalent deep learning- based object detection algorithm, for this purpose. The paper underscores the potential of AI-based approaches to deliver high accuracy and reliability in detecting overloaded vehicles, proposing their integration with existing weigh measurement systems to establish a comprehensive detection framework. Additionally, it introduces a real-time, precise truck overload detection system that capitalizes on existing surveillance cameras installed at weighing stations. This system employs two cameras, an indoor one capturing the weighbridge’s numeric digit display indicating the truck’s actual weight, and an outdoor one capturing the truck’s wheel layout to estimate its maximum load capacity. The paper accentuates the benefits of this system, including its cost-effectiveness, accuracy, and real-time detection capabilities. Moreover, it highlights that the system’s implementation requires no additional infrastructure or equipment, as it can leverage existing surveillance cameras at weigh stations. Overall, the paper underscores the importance of monitoring and enforcing vehicle weight limits while presenting IT technologies, such as AI and object detection, as effective means for actively controlling additional weight carried by overloaded vehicles. It also introduces a practical, real-time truck overload detection system utilizing existing surveillance cameras, offering a cost- effective and efficient solution for detecting overloaded vehicles at weigh stations.
Authors
- G.K. Dey (ORCID: https://orcid.org/0000-0003-1416-6223)
- S Parthiban
- Sawai Singh Rathore (ORCID: https://orcid.org/0000-0003-1954-094X)
- Gaurav Sharma (ORCID: https://orcid.org/0000-0002-5010-1710)
- Mohan Maheshwari
Institutions
- Mangalayatan University (IN)
- Dhanalakshmi Srinivasan Group of Institutions (IN)
- Usha Martin (India) (IN)
Publication Details
- Published
- 2024-11-22
- DOI
- https://doi.org/10.1109/aece62803.2024.10911354
- Primary Topic
- Autonomous Vehicle Technology and Safety
- Type
- article
- Field-Weighted Citation Impact
- 0.00