Enhancing Traffic Management Through Advanced Vehicle Detection for Congestion Prevention
Published in 2024 IEEE 21st International Conference on Mobile Ad-Hoc and Smart Systems (MASS) at Seoul, South Korea, 2024
Overview
- Urban Congestion Analysis: Investigation of urban traffic congestion issues and inefficiencies in traditional traffic management systems.
- Real-Time Detection with YOLOv8s: Utilization of YOLOv8s deep learning models for real-time detection of cars, two-wheelers, autos, buses, and trucks.
- Performance Evaluation: Achieves 80% precision for cars and a mean average precision (mAP@0.5) of 85.8%, highlighting areas for improvement in other vehicle classes through data augmentation techniques.
- Adaptive Traffic Control Integration: Discussion on integrating the vehicle detection system with adaptive traffic light control to enhance traffic flow and urban safety.
Recommended citation: M. Swaned, S. Javid, S. Humaney, A. Sachan, N. S. Chauhan, and N. Kumar. (2024). "Enhancing Traffic Management Through Advanced Vehicle Detection for Congestion Prevention." 2024 IEEE 21st International Conference on Mobile Ad-Hoc and Smart Systems (MASS). 623–628.
Download Paper | Download Slides | Download Bibtex