Aerial video & trajectory dataset of vehicles on circular road

This article presents aerial video and vehicle trajectory data collected during a phantom traffic jam experiment with the Swiss television (SRF) at the driving test centre TCS Derendingen, Solothurn, from March 12th 2024. 14 vehicles were recorded for a total duration of 40 minutes with a drone from above, and vehicle trajectories were extracted using computer vision and Kalman filtering methodology. The observed vehicles differ by their power train (combustion, electric, hybrid), gearbox (manual, automatic), and equipment with advanced driver assistance systems. The data provided in this article offers a valuable resource for researchers, industry representatives, public authorities, and other parties interested in mixed-traffic dynamics, traffic flow theory, computer vision. This dataset can for instance be used: (i) to explore how gearbox, powertrain, and assistance systems affect the propagation of traffic jams on highways, and (ii) to provide a benchmark dataset for visual vehicle trajectory extraction using computer vision methods.