Computer Vision Assisted Artificial Intelligence Enabled Smart Traffic Control System for Urban Transportation Management

Nowadays, computer Vision (CV) and Artificial Intelligence (AI) technologies in traffic management systems has emerged as a potential solution to alleviate traffic-related issues in metropolitan and urban cities. This research presents a novel approach called a Smart Traffic Control System for Urban Transportation Management (STC-UTM), which employs YOLO V8 as the development platform and Raspberry Pi 4 B single-board computer as the deployment platform. YOLO's realtime processing capabilities accurately identify various elements in the traffic environment, including cars, pedestrians, and bicycles. The Raspberry Pi 4 B, equipped with a powerful Graphics Processing Unit (GPU) does realtime data processing and utilizes AI algorithms to make adaptive decisions depending on traffic conditions. These choices include implementing adaptive traffic signal management, detecting congestion, and implementing rerouting schemes to improve vehicle flow and reduce traffic bottlenecks. The STC-UTM framework optimizes resource allocation, resulting in decreased travel time, fuel consumption, and environmental effects. The YOLO V8 model created has achieved a significant F1 score of 0.9634 and a recall rate of 0.9776, demonstrating its exceptional performance. The outcomes of this research have the potential to completely transform traffic management and urban transportation systems, providing advantages in terms of shortened journey durations, diminished environmental consequences, and improved road security.