Continuous Monitoring of a Signalized Intersection Using Unmanned Aerial Vehicles

The use of drones offers an innovative traffic data collection technique that allows to capture very detailed and accurate vehicle trajectories. However, deploying them for an entire day would be prohibitively expensive due to the limitations of their batteries. In this paper we show how commercial, low-cost drones can be used to monitor traffic during a full day in an efficient way throughout the day. More specifically, we provide a case study of a signalized intersection in the city of Manchester, UK, where traffic streams were recorded during both the morning and afternoon peak hours. Using advanced computer vision techniques, we extract vehicle trajectories that enable us to conduct an in-depth analysis of the intersection. Our analysis includes a comprehensive traffic assessment of the intersection for a complete day with traffic metrics such as OD, turning ratios, fundamental diagrams, and shockwaves.