Real-time Risk Prediction at Signalized Intersections Using a Graph Neural Network

Intersection-related traffic crashes and fatalities are major concerns for road safety. This project aimed to understand the major causes of conflicts at intersections by studying the intricate interplay between roadway agents. The approach involved using the current traffic camera systems to automatically process traffic video data. As manual annotation of video datasets is a very labor-intensive and costly process, this research leveraged modern computer vision algorithms to automatically process these videos and retrieve kinematic behavior of the traffic actors. Results demonstrated how traffic actors and road segments can be modeled independently via graphs and how they can be integrated into a framework that can model traffic systems. The team used a graph neural network to model (a) the interaction of all the roadway agents at any given instance and (b) their role in road safety, both individually and as a composite system. The model reports a near-real-time risk score for a traffic scene. The study concludes with a presentation of a new drone-based trajectory dataset to accelerate research in intersection safety.

• Record URL:
  • https://rosap.ntl.bts.gov/view/dot/73406
• Dataset URL:
  • https://rosap.ntl.bts.gov/view/dot/73500
• Supplemental Notes:
  • This document was sponsored by the U.S. Department of Transportation, University Transportation Centers Program. Supporting dataset available at: https://rosap.ntl.bts.gov/view/dot/73500.
• Corporate Authors:

  Safety through Disruption University Transportation Center (Safe-D)

  Virginia Tech Transportation Institute
  Blacksburg, VA  United States  24060

  Office of the Assistant Secretary for Research and Technology

  University Transportation Centers Program
  Department of Transportation
  Washington, DC  United States  20590
• Authors:
  • Sonth, Akash
  • 0000-0002-5045-5906
  • Sarkar, Abhijit
  • 0000-0003-0525-5240
  • Jain, Sparsh
  • 0000-0002-4368-6108
  • Bhagat, Hirva
  • 0000-0001-7725-4373
  • Doerzaph, Zachary
  • 0000-0002-3897-1430
• Publication Date: 2023-12

Language

• English

Media Info

• Media Type: Digital/other
• Edition: Final Report
• Features: Appendices; Figures; Photos; References; Tables;
• Pagination: 65p

Subject/Index Terms

• TRT Terms: Drones; Machine learning; Neural networks; Risk analysis; Signalized intersections; Traffic crashes; Traffic safety; Traffic surveillance; Video
• Subject Areas: Data and Information Technology; Highways; Operations and Traffic Management; Planning and Forecasting; Safety and Human Factors;

Filing Info

• Accession Number: 01909919
• Record Type: Publication
• Report/Paper Numbers: 06-12
• Contract Numbers: 69A3551747115
• Files: UTC, NTL, TRIS, USDOT
• Created Date: Feb 27 2024 10:08AM