Traffic Signal Optimization using Real-Time Pedestrian and Vehicle Counts

Urban traffic congestion is a challenge for cities around the globe, prompting the need for the development of more effective and responsive traffic signal systems. This review aims to discuss recent progress in traffic signal optimization, particularly in the integration of real-time data analysis, machine learning, and adaptive algorithms. We discuss several strategies, including Dynamic Traffic Light Scheduling (DTLS), Q-learning, and intelligent traffic light signaling measures, which exploit real-time vehicle detection and adaptive signal control for enhancing traffic flow and minimizing intersection congestion. Additionally, the review emphasizes the promise of enabling emergency vehicle prioritization and the application of real-time video processing for dynamic signal adaptation. Although giving promising results, there are still many areas of research left open, such as the requirement for more integrated optimization algorithms, increased scalability for large cities, and a clearer understanding of the economic and environmental impacts of these systems. This work also addresses a suggested solution that integrates vehicle and pedestrian detection, dynamic traffic signal optimization, and real-time video processing for improved traffic flow, pedestrian safety, and environmental viability. The performance of such systems is measured against important metrics, such as mean wait times, traffic flow efficiency, and environmental cost, demonstrating the potential of smart traffic management systems to solve the challenges of contemporary urban mobility.