Evaluating the impacts of vehicle-mounted Variable Message Signs on passing vehicles: implications for protecting roadside incident and service personnel

Abstract

This study aims to evaluate the Variable Message Signs (VMS) mounted over the cab of emergency vehicles as a safety countermeasure to protect roadside incident and service personnel. The research team collaborated with the Alabama Department of Transportation’s Safety Service Patrol (SSP) program, specifically the Alabama Service Assistance Patrol (ASAP) in the West Central Alabama region, to collect video data from their service vehicles. Deep learning techniques were employed to detect vehicles in the recorded videos. A total of 11,338 passing vehicles were detected in 135,946 frames of video footage, and their trajectories were extracted for analysis. The study focused on examining the behaviors and movements of passing vehicles, including their speed and lane change behaviors, and developed statistical models to systematically investigate the impact of VMS on these behaviors. Random intercept models were utilized to account for unobserved factors associated with different stop locations. The modeling results revealed significant relationships between the use of VMS and the behaviors of passing motorists. When the VMS was active, drivers were more likely to change lanes and reduce their speed compared to situations where the VMS was not active. The odds of a vehicle changing lanes were found to be 95% higher when the VMS was in use. These findings suggest that the utilization of VMS can have a positive impact on traffic, particularly for passenger vehicles. The study outcomes imply that the use of VMS could be an effective countermeasure in protecting roadside incidents and ensuring the safety of service personnel.

Keywords:

• deep learning
• emergency response
• responder safety
• safety service patrol
• vehicle-mounted Variable Message Signs

Acknowledgements

We would like to express our acknowledgment and gratitude to the AAA Foundation for Traffic Safety for their support in funding this project (Contract number: 4035-51184). We are grateful to Kenneth Colvert and Jonathan Mills from the Alabama Department of Transportation (ALDOT) for their assistance in collecting video data from one of the Alabama Service Assistance Patrol (ASAP) vehicles. Special thanks go to Ricky Hendon for providing valuable input and insights for this study. We also extend our thanks to the Department of Civil, Construction, and Environmental Engineering and the Alabama Transportation Institute at the University of Alabama for their administrative support. The views presented in this paper are solely those of the authors, who take full responsibility for the accuracy and factual correctness of the information provided.

Author contributions

The authors confirm contribution to the paper as follows: study conception and design: Liu, Villavicencio; data collection: Hainen, Liu; analysis and interpretation of results: Liu, Fu; draft manuscript preparation: Liu, Yang, Villavicencio, Horrey. All authors reviewed the results and approved the final version of the manuscript.

Disclosure statement

No potential conflict of interest was reported by the authors.

Additional information

Funding

This work was supported by AAA Foundation for Traffic Safety.