Indian cities are growing rapidly, therefore traffic management is crucial for sustainable development and urban mobility. A new dynamic traffic signal control system using the powerful YOLOv8 deep learning model is introduced in this paper. The algorithm has been trained on a dataset to identify and classify two-wheelers, autos, and buses in complex metropolitan crossings. Our traffic assessment method incorporates real-time video analysis, unlike fixed-timing signal systems. This method monitors traffic using real-time video processing, unlike fixed-timing signal systems. A specialized algorithm counts and identifies vehicles during a 5-second yellow light interval to compute traffic density. The algorithm automatically sets green light time by weighing vehicle types by size and congestion. This flexible strategy lowers traffic, congestion, and crossing inactivity, especially during peak hours. YOLOv8 in the video pipeline detects even in busy traffic. In cities, the system’s precision and recall showed accuracy and efficiency. This vehicle-centric, scalable traffic management system underpins intelligent urban traffic systems, congestion avoidance, and intersection efficiency. Thus, cities become greener and more efficient.
Real-Time Traffic Intensity Estimation and Management
2025-04-03
520539 byte
Conference paper
Electronic Resource
English
Traffic Prediction for Real Time Traffic Management
British Library Conference Proceedings | 1995
|Real-time traffic estimation using data expansion
Online Contents | 2011
|REAL-TIME TRAFFIC MANAGEMENT USING SMART TRAFFIC SIGNALS
European Patent Office | 2025
|Real-Time Dynamic Traffic Control Based on Traffic-State Estimation
Transportation Research Record | 2019
|