Citation

Zaman A, Huang Z, Li W, Qin H, Kang D, Liu X. Transp. Res. Rec. 2023; 2677(10): 688-706.

Copyright

(Copyright © 2023, Transportation Research Board, National Research Council, National Academy of Sciences USA, Publisher SAGE Publishing)

DOI

10.1177/03611981231163824

PMID

unavailable

Abstract

Fatalities at grade crossings accounted for an average of 33% of all railroad industry fatalities occurring in the past 10 years. As road traffic increases and high-speed rail deployments become more common in the United States, the number of fatalities is expected to remain a concern. Railroads have tackled this challenge through a combination of engineering, education, and enforcement campaigns. One of these efforts has been the increased deployment of security cameras throughout railroad networks. These video sources allow for the collection of big data to better understand grade crossing violation behaviors. However, monitoring these video feeds and extracting useful information requires prohibitive amounts of manual labor. This research utilizes state-of-the-art vision-based artificial intelligence (AI) techniques to record, recognize, and understand railroad video data in real time. This system's understanding of active grade crossing violations helps to develop precise long-term grade crossing violation prevention strategies. This study explains how this AI-aided algorithm is used to monitor 1 year's worth of violations at an active grade crossing in New Jersey and provides an overview of the observed trends. These data can be used to develop better engineering enforcement and education strategies for the mitigation of active grade crossing violations.

Language: en