Enhanced Traffic Signal Adaptation with Ambulance Identification and Distance Computation

Abstract

This Paper presents a novel approach for real-time ambulance identification, distance calculation to traffic junctions, and automated traffic signal control. The system utilizes strong computer vision procedures combined with deep learning algorithms (YOLOV7) to accurately discern and follow ambulances despite being fed video and image data, with the major task being to track ambulances. The base of the proposed solution includes designing a strong ambulance identification algorithm by using the convolutional neural networks (CNNs) and distribution algorithms. With this algorithm, not only do the pileups of ambulance navigate the nearby traffic junctions but they also determine their distance from standstill vehicles. The contribution of this approach is found in the potential impact of the real-time adaptive of traffic signals that give the top priority to ambulance lanes by allowing them to travel faster during the home repair time. The following part of the project is implementation of traffic lights established based on the automated system which moves at the speed of an ambulance close to the traffic junctions. Our model impact traffic light control one way by introducing an intelligent system that minimizes delays of the ambulances in intersections. Bright emergencies each second can be a slim window between living and dying that is why the speedy the passage of green light traffic to ambulance lanes will become the main priority in our approach. To close this technical paper, it summarizes the devised comprehensive system which is effective not only in detecting ambulances but also in calculating distances joining the different traffic lights. Our model's integration with traffic control especially during emergency situations through prioritizing ambulance lanes will clear the path for emergencies. The lanes will help reduce the time ambulances use in traffic jams.