- A novel real-time vehicle-pedestrian crash risk modelling framework for signalised intersections is proposed.
- A Bayesian Generalised Extreme Value model estimates crash risk in real-time.
- An automated covariate extraction algorithm is proposed for combining multiple data sources.
- The proposed model reasonably estimates historical crash records.
Real-time safety framework identifies safe and risky signal cycles for pedestrians.
Ali, Y., Haque, M., Mannering, F., 2023. A Bayesian generalised extreme value model to estimate real-time pedestrian crash risks at signalised intersections using artificial intelligence-based video analytics. Analytic Methods in Accident Research 38, 100264.