AI-Driven Emergency Vehicle Detection for Signal Optimization Using YOLOv8

Traffic congestion in urban environments presents a persistent challenge, resulting in increased travel time, fuel consumption, and environmental degradation. Conventional traffic signal systems rely on fixed-time operations, which are often inadequate in responding to fluctuating traffic densities and emergencies. This study proposes an Intelligent Traffic Signal Optimization System leveraging YOLOv8, an advanced deep learning-based object detection algorithm, to enhance traffic management and emergency response. The system captures real-time traffic video footage and processes individual frames using OpenCV to improve the detection of emergency vehicles such as ambulances, fire engines, and police cars. YOLOv8 is employed to accurately identify these vehicles, enabling the dynamic adjustment of traffic signal durations based on real-time data. In emergency scenarios, the signal duration is extended automatically, ensuring the priority passage of essential services. This adaptive approach not only improves traffic flow efficiency but also reduces overall congestion. Integrating computer vision and artificial intelligence in this context highlights its potential contribution to sustainable urban planning