Smart Traffic Signal Optimization Using Real-Time Vehicle Detection

Traffic congestion has become a major problem in urban areas due to the rapid increase in the number of vehicles. Traditional traffic signal systems operate using fixed timing intervals without considering real-time traffic conditions, which often results in inefficient traffic flow and increased waiting time. This paper proposes a Smart Traffic Signal Optimization System using Real-Time Vehicle Detection to improve traffic management at intersections. The system uses computer vision and deep learning techniques to detect and count vehicles from traffic camera video feeds. A pre-trained YOLO (You Only Look Once) object detection model is used to identify vehicles such as cars, buses, trucks, and motorcycles in real time. Based on the detected vehicle count, the system dynamically calculates the green signal duration using a traffic density-based algorithm. The system is implemented using Python, OpenCV, YOLO, and Flask. Experimental results show that the proposed system improves traffic flow efficiency and reduces waiting time at intersections.