International Journal of Scientific Research and Engineering Development

Traffic congestion in urban areas often causes delays for emergency vehicles such as ambulances, fire engines, and police vehicles. These delays can reduce the efficiency of emergency response and may lead to serious consequences in critical situations. Traditional traffic signal systems operate based on fixed timing schedules and do not provide priority to emergency vehicles. This research proposes an intelligent traffic light control system for automatic identification of emergency vehicles using computer vision and acoustic signals. The system uses the YOLO (You Only Look Once) deep learning model to detect ambulances from real-time traffic video captured by surveillance cameras. In addition, acoustic signal analysis is used to detect ambulance sirens. A Convolutional Neural Network (CNN) is used to improve detection accuracy and classification reliability. When an emergency vehicle is detected, the system automatically changes the traffic signal to green for the corresponding lane, allowing the vehicle to pass without delay. This approach reduces response time for emergency services and improves traffic management efficiency. The proposed system can be integrated into smart city traffic management infrastructure to enhance public safety and reduce traffic congestion.

Hema R, Gopika D, Mahathii G, Sowmiya A,"SmartFlow: A Machine Learning-Based Adaptive Traffic Signal Control System" International Journal of Scientific Research and Engineering Development, V9(2): Page(809-813) Mar-Apr 2026. ISSN: 2581-7175. www.ijsred.com. Published by Scientific and Academic Research Publishing.