Intelligent Safety Assessment of Rural Roadways Using Automated Image and Video Analysis

Due to the significant effect of roadside safety on the number and severity of road accidents, many state DOTs are trying to detect road segments with potentially unsafe roadside attributes. This can be achieved by manually inspecting videos and images collected by third-party data providers, such as Mandli. However, this process is both time-consuming and susceptible to human error. Therefore, this project will develop an automated approach that leverages computer vision and machine learning to efficiently evaluate roadside safety.


  • English


  • Status: Completed
  • Funding: $81000
  • Contract Numbers:


  • Sponsor Organizations:

    Office of the Assistant Secretary for Research and Technology

    University Transportation Centers Program
    Department of Transportation
    Washington, DC  United States  20590
  • Managing Organizations:

    Mountain-Plains Consortium

    North Dakota State University
    Fargo, ND  United States  58108
  • Project Managers:

    Tolliver, Denver

  • Performing Organizations:

    Dept. of Civil and Environmental Engineering

    University of Utah
    Salt Lake City, UT  United States 
  • Principal Investigators:

    Markovic, Nikola

    Rashidi, Abbas

  • Start Date: 20210924
  • Expected Completion Date: 20240731
  • Actual Completion Date: 20240114
  • USDOT Program: University Transportation Centers Program
  • Source Data: MPC-669

Subject/Index Terms

Filing Info

  • Accession Number: 01785292
  • Record Type: Research project
  • Source Agency: Mountain-Plains Consortium
  • Contract Numbers: 69A3551747108
  • Files: UTC, RIP
  • Created Date: Oct 22 2021 10:09AM