Severity analysis of red-light–running behavior at signalized intersections

Abstract

Red-light running (RLR) is one of the riskiest behaviors at signalized intersections. This study utilizes intersection- and corridor-level characteristics to identify variables that impact the frequency and severity of RLR violations. The severity of RLR is defined based on the time when the violations happened. That is, less severe violations are the ones that occur within 3 seconds of the signal light turning red (RLR3), while more severe violations happen between 3 and 10 seconds of the signal light turning red (RLR10). Results of the zero-inflated negative binomial model showed that an increase in intersection delay and split failure increases the frequency of both types of RLR severities. An increase in the yellow interval, cycle length, and number of lanes reduces the frequency of RLR3 but increases the frequency of RLR10. Furthermore, based on the factor importance analysis conducted through the random forest, it was shown that split failure is one of the most predictive variables for RLR3 and RLR10. The findings of this research could help transportation agencies in different geographic jurisdictions utilize the calibrated models to understand the impact of varying intersection- and corridor-based characteristics on the frequency and severity of RLR.

Keywords:

• Red-light running
• severity
• random forest
• yellow light
• high-resolution event-based data

Acknowledgments

The authors would like to thank the Town of Marana, Pima County, and the City of Phoenix for recognizing the seriousness of RLR and providing a “living laboratory” to develop this model. Special thanks to Diahn Swartz, Simon Ramos, Fausto Burruel, and Lauren Fecteau for their support of this project. The authors appreciate Gabriel Geffen for his help in proofreading. The authors would also like to thank the Miovision team for data support.

Disclosure statement

No potential conflict of interest was reported by the authors.