Present-days, traffic flow on highways, urban roads, and particularly in metropolitan areas is significantly impacted. The swift expansion of metropolitan areas and the increase in vehicle numbers have heightened the necessity for efficient and prompt traffic monitoring systems. Consequently, a computer vision-based road traffic monitoring system is crucial for detecting the movement of many vehicle classes and for tracking purposes. Furthermore, it is essential to enumerate the various cars captured in the security camera footage with computer vision technology. This proposal entails the development of a deep learning framework utilizing YOLOv11 for the analysis of traffic photos, with the Bytetrack algorithm implemented for tracking purposes. The system will oversee vehicle count, vehicle classification, road signal aspect monitoring, pedestrian surveillance, road congestion, accidents involving crowds, peak hour traffic assessment, vehicle tracking, junction oversight, traffic flow analysis, and traffic violation detection. The model is evaluated in real-time traffic and operates with the necessary performance standards.
Real Time Implementation of Computer Vision based Road Traffic Monitoring System using YOLO 11
25.06.2025
799387 byte
Aufsatz (Konferenz)
Elektronische Ressource
Englisch
Computer vision-aided road traffic monitoring
Kraftfahrwesen | 1991
|Vision-based real-time road detection in urban traffic
SPIE | 2002
|