Trespassing is the leading cause of rail-related deaths and has been on the rise for the past 10 years. Detection of unsafe trespassing of railroad tracks is critical for understanding and preventing fatalities. Witnessing these events has become possible with the widespread deployment of large volumes of surveillance video data in the railroad industry. This potential source of information requires immense labor to monitor in real time. To address this challenge this paper describes an artificial intelligence (AI) framework for the automatic detection of trespassing events in real time. This framework was implemented on three railroad video live streams, a grade crossing and two right-of-ways, in the United States. The AI algorithm automatically detects trespassing events, differentiates between the type of violator (car, motorcycle, truck, pedestrian, etc.) and sends an alert text message to a designated destination with important information including a video clip of the trespassing event. In this study, the AI has analyzed hours of live footage with no false positives or missed detections yet. This paper and its subsequent studies aim to provide the railroad industry with state-of-the-art AI tools to harness the untapped potential of an existing closed-circuit television infrastructure through the real-time analysis of their data feeds. The data generated from these studies will potentially help researchers understand human factors in railroad safety research and give them a real-time edge on tackling the critical challenges of trespassing in the railroad industry.

No abstract

The volume of video data in the railroad industry has increased significantly in recent years. Surveillance cameras are situated on nearly every part of the railroad system, such as inside the cab, along the track, at grade crossings, and in stations. These camera systems are manually monitored, either live or subsequently reviewed in an archive, which requires an immense amount of human resources. To make the video analysis much less labor-intensive, this paper develops a framework for utilizing artificial intelligence (AI) technologies for the extraction of useful information from these big video datasets. This framework has been implemented based on the video data from one grade crossing in New Jersey. The AI algorithm can automatically detect unsafe trespassing of railroad tracks (called near-miss events in this paper). To date, the AI algorithm has analyzed hours of video data and correctly detected all near-misses. This pilot study indicates the promise of using AI for automated analysis of railroad video big data, thereby supporting data-driven railroad safety research. For practical use, our AI algorithm has been packaged into a computer-aided decision support tool (named AI-Grade) that outputs near-miss video clips based on user-provided raw video data. This paper and its sequent studies aim to provide the railroad industry with next-generation big data analysis methods and tools for quickly and reliably processing large volumes of video data in order to better understand human factors in railroad safety research.

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.

This paper completes the series of three articles devoted to automated forecasting of flash floods [3,5] and describes an effective approach of forecast updating through post-processing operations, which can be useful only in conjunction with such fast and efficient real-time re-calibration algorithms as SLS-based methods are. In particular, a proposed methodology is aimed to reduce negative consequences of scarce or low-quality data that can corrupt optimized parameters and, therefore, lower forecasting efficiency. A new modification of SLS-based optimization that supposes simultaneous re-calibration of the model and correction of the model input by generating of ensemble noises (SLS-E) is presented.