Enhancing Road Safety: Automated Traffic Violation Detection and Counting System Using YOLO Algorithm

Ensuring compliance with traffic regulations, such as wearing helmets and obeying traffic signals, is crucial for enhancing road safety, particularly among motorcycle riders. In this study, we propose an automated approach for detecting helmet wearing and traffic light violations using computer vision techniques. Our methodology involves leveraging the YOLO-v8 object detection model pretrained on the COCO dataset to identify motorcycles, persons, traffic lights, and helmets in video footage captured at intersections in Marrakech. We conducted manual counting as a benchmark for evaluating the performance of our automated system. Our results demonstrate a strong alignment between our automated approach and manual counting for both helmet detection and traffic light violations. However, occasional discrepancies were observed, particularly during specific time slots characterized by high motorcycle speeds. Contextual factors such as traffic density and vehicle speed were identified as influencing factors. Despite these challenges, our automated system shows promise as a valuable tool for monitoring and enforcing traffic regulations. Ongoing refinement and optimization are essential to address these challenges and enhance the accuracy and reliability of automated detection systems. Our study highlights the potential of automated technologies in improving road safety measures and underscores the importance of considering contextual factors in interpreting detection results.