Smart Traffic Management System with Real-Time Ambulance Detection

Abstract

More urbanisation and the increasing number of vehicles have worsened traffic congestion, significantly hindering emergency medical services. Ambulances lose precious time navigating through busy intersections where fixed-cycle traffic signals lack real-time priority scheduling. This paper proposes a Smart Traffic Management System (STMS) that can detect ambulances and dynamically regulate traffic signals to grant them unhindered passage. The proposed framework integrates the Internet of Things (IoT), computer vision, and artificial intelligence for multi-modal emergency detection. Siren sound detection is achieved through a hybrid model of Mel-Frequency Cepstral Coefficients (MFCC) and Long Short-Term Memory (LSTM) networks, whereas the YOLOv8 algorithm achieves high-precision visual recognition regardless of weather. Detected signals are processed on the edge layer and transmitted over Vehicle-to-Infrastructure (V2I) links to reconfigure nearby intersections. Simulation results indicate that the ambulances' delay time decreases by about 45% relative to conventional systems. Scalability, low latency, and future interoperability with 5G and 6G networks are enabled by the design. By improving emergency response efficiency and reducing urban traffic, the concept of STMS assists in creating more secure, sustainable cities.