Smart Traffic Control System Using Artificial Intelligence

Urban traffic congestion is increasing at an alarming rate due to fixed-time traffic signals that fail to adapt to real-time variations in vehicle density. This research proposes an AI-based Smart Traffic Control System that uses YOLO object detection and weighted density computation to dynamically adjust green-signal duration for each lane. The system continuously captures live video feeds from cameras installed at intersections, detects and classifies vehicles, calculates lane-wise density scores and allocates signal time proportionally. Experimental analysis demonstrates high detection accuracy (92.5%), reduced average waiting time, improved vehicle throughput and efficient emergency vehicle prioritisation. The proposed architecture is scalable, cost-effective and suitable for deployment in heterogeneous traffic conditions in modern smart cities.