Computer vision-based assessment of cyclist-tram track interactions for predictive modeling of crossing success

Single Bicycle Brashes (SBCs) are common, and underreported in official statistics. In urban environments, light rail tram tracks are a frequent factor, however, they have not yet been the subject of engineering analysis.

This study employs video-based analysis at nine Dublin city centre locations and introduces a predictive model for crossing success on tram tracks, utilising cyclist crossing angles within a Surrogate Measure of Safety (SMoS) framework. Additionally, Convolutional Neural Networks (CNNs) were explored for automatic estimation of crossing angles.

Modelling results indicate that cyclist crossing angle is a strong predictor of crossing success, and that cyclist velocity is not. Findings also highlight the prevalence of external factors which limit crossing angles for cyclists. In particular, kerbs are a common factor, along with passing/approaching vehicles or other cyclists. Furthermore, results indicate that further training on a relatively small sample of 100 domain-specific examples can achieve substantial accuracy improvements for cyclist detection (from 0.31AP_0.5 to 0.98AP_0.5) and crossing angle inference from traffic camera footage.

Ensuring safe crossing angles is important for cyclist safety around tram tracks. Infrastructural planners should aim for intuitive, self-explainable road layouts that allow for and encourage crossing angles of 60° or more - ideally 90°.

The SMoS framework and the open-source SafeCross¹ application offer actionable insights and tools for enhancing cyclist safety around tram tracks.