Key points are not available for this paper at this time.
Abstract: Urban traffic congestion is a significant challenge globally, impacting transportation efficiency, environmental sustainability, and urban liveability. Traditional traffic control systems often struggle to adapt to changing traffic dynamics, leading to increased congestion and delays. This paper presents a novel traffic management system developed by our team, leveraging cutting-edge technologies such as computer vision, artificial intelligence (AI), and the Internet of Things (IoT). Deployed at intersections, our system utilizes real-time CCTV feeds for traffic analysis, employing advanced image processing and machine learning algorithms, including YOLO V7, to dynamically assess traffic density. These insights inform adaptive adjustments to traffic light timings, with the aim of reducing congestion, enhancing transit efficiency, and mitigating pollution. Our signal switching algorithm, incorporating dynamic logic developed by our team, iteratively adjusts signal timings based on real-time traffic conditions, ensuring responsive and efficient traffic flow management. Through the integration of our innovative technologies, our system seeks to revolutionize urban transportation networks, promoting smarter, more adaptive, and sustainable urban environments.
Phand et al. (Tue,) studied this question.