Technical Paper
Validation and Analysis of Driving Safety Assessment Metrics in Real-world Car-Following Scenarios with Aerial Videos
2024-04-09
2024-01-2020
Data-driven driving safety assessment is crucial in understanding the insights of traffic accidents caused by dangerous driving behaviors. Meanwhile, quantifying driving safety through well-defined metrics in real-world naturalistic driving data is also an important step for operational safety assurance of automated vehicles (AV). However, the lack of comprehensive data and methodologies for fine-grained analysis has hindered progress in this critical area. In response to this challenge, we propose a novel dataset for driving safety metrics analysis specifically tailored to car-following situations. Leveraging state-of-the-art technology, we employ drones to capture high-resolution video data at 12 different traffic scenes in the Phoenix metropolitan area, deploy advanced Artificial Intelligence (AI) algorithms to extract precise vehicle trajectories, and utilize semantic maps to discern leader-follower relations among vehicles.