Development of Railroad Trespassing Database Using Artificial Intelligence

The Federal Railroad Administration (FRA) sponsored a research team from Rutgers University to develop a proof-of-concept Trespassing Database using Artificial Intelligence (AI) technology to automatically process large volumes of live or recorded video data. The team used the Rutgers AI algorithm to analyze over 27,000 hours of live video data and 1,176 hours of recorded video data from right-of-ways and grade crossings at 11 locations in 6 states. The AI algorithm collected trespassing-related data, including traffic, rail signal activations, train events, and trespass events. Trespass event data were automatically collected for each trespasser, including date, time, type (e.g., person, car, truck, bus, motorcycle), weather, trespasser’s path, and a video clip. The team manually validated all trespass event detection results to ensure that accurate data were included in the database. Over 29,000 trespass events were detected by the AI algorithm across all studied locations in this research. This report also presents two year-long, in-depth case studies of one grade crossing in New Jersey (21,202 trespass events) and one right-of-way (ROW) location in North Carolina (476 trespass events). This report provides temporal and spatial analyses of trespass events and discusses AI-informed mitigation strategies.

• Record URL:
  https://railroads.fra.dot.gov/elibrary/development-railroad-trespassing-database-using-artificial-intelligence
• Record URL:
  https://rosap.ntl.bts.gov/view/dot/73444
• Corporate Authors:

  Rutgers University, New Brunswick

  57 US Highway 1
  New Brunswick, NJ  United States  08901-8554

  Federal Railroad Administration

  Office of Railroad Policy and Development, 1200 New Jersey Avenue, SE
  Washington, DC  United States  20590

  Federal Railroad Administration

  Office of Research, Development, and Technology
  Washington, DC  United States 
• Authors:
  • Zaman, Asim
  • 0000-0002-0117-2475
  • Huang, Zhe
  • 0000-0002-8627-5122
  • Li, Weitian
  • 0000-0003-1835-8230
  • Qin, Huixiong
  • 0000-0002-9732-8832
  • Kang, Di
  • 0000-0003-3337-2815
  • Liu, Xiang
  • 0000-0002-4348-7432
• Publication Date: 2024-2

Language

• English

Media Info

• Media Type: Digital/other
• Edition: Final Report; Technical Report
• Features: Appendices; Figures; Photos; References; Tables;
• Pagination: 80p

Subject/Index Terms

• TRT Terms: Artificial intelligence; Case studies; Databases; Railroad grade crossings; Right of way (Land); Trespassers; Video
• Geographic Terms: New Jersey; North Carolina
• Subject Areas: Data and Information Technology; Railroads; Safety and Human Factors; Security and Emergencies;

Filing Info

• Accession Number: 01908349
• Record Type: Publication
• Report/Paper Numbers: DOT/FRA/ORD-24/09
• Contract Numbers: 693JJ620C000009
• Files: NTL, TRIS, USDOT
• Created Date: Feb 18 2024 4:02PM