Published Paper Details:

In big cities, traffic congestion is a major problem that is frequently brought on by static traffic light systems that don't take into account the flow of vehicles in real time. Due to their reliance on pre-programmed timings, traditional traffic signals cause needless delays, fuel waste, and ineffective traffic management. This study suggests an intelligent and well-coordinated traffic light control system that uses real-time video surveillance and artificial intelligence (AI). Using video feeds at crossings, the system analyses and detects vehicle density using computer vision algorithms. This analysis is used to dynamically modify signal timings in order to give priority to lanes with greater congestion. Additionally, by connecting several traffic lights via a communication protocol, the system allows neighbouring junctions to synchronize their signal phases. Green corridors are created, stop-and-go traffic is decreased, and general urban mobility is enhanced by this networked strategy. A centralized communication layer facilitates inter-signal data exchange, signal timing adjustment techniques, and real-time vehicle recognition utilizing YOLO models. To test the system, real-world circumstances are replicated through simulation using Python and OpenCV. According to preliminary findings, when compared to fixed-timer systems, the suggested approach greatly lowers vehicle waiting times and enhances traffic flow efficiency. This study advances the creation of intelligent transportation systems and offers smart cities dealing with escalating traffic problems a scalable answer.