Monitoring of Urban Roadway Safety Hazards from Existing Bus-based Video Imagery: Phase 3

Traffic safety is diminished by drivers’ changing lanes in queued traffic and mixes of pedestrians and vulnerable vehicles (scooters, bikes, and motorcycles) with large vehicles in the traffic stream. Assessing locations with these recurring but dynamic hazardous conditions requires extensive and ongoing monitoring. Traditional monitoring methods rely on sensors at permanent or temporary fixed locations, which is costly, labor intensive, and provides limited spatial coverage. Moreover, the location of these sensors may be influenced by factors other than optimal sampling, such as requests from well-organized constituencies. Therefore, traditional monitoring of hazards could miss high-risk conditions resulting in decreased safety. Transit buses operate regularly over wide networks, and most bus fleets are already equipped with cameras that record the environment inside and outside buses for liability, security, and safety purposes. Consequently, the imagery is available for other uses at low marginal cost. Coupling the available imagery with the extensive spatial and repeated temporal coverage of transit fleets has been shown by the principal investigators (PIs) to be effective in monitoring traffic volumes across space and time. In the phase 1 project, the PIs investigated the use of available imagery recorded by cameras mounted on transit buses in regular operation to identify hazardous locations associated with recurrent vehicle queuing on urban streets. The phase 2 project is building on the phase 1 investigations by identifying locations with recurring noticeable volumes of vulnerable vehicles to serve as indications of hazardous conditions. The disparity in size and weight between large vehicles and pedestrians and vulnerable vehicles contributes to the increased risk of accident occurrences that lead to serious injuries and fatalities. A deployment partner commented that near misses of such interactions “happen all the time.” Similarly, and as was recently highlighted in The Economist Sept 7, 2024 issue titled “America’s killer cars”, the increasing size and weight of passenger vehicles is leading to an exponentially increasing risk of injuries to and fatalities of pedestrians and passengers of vulnerable vehicles. Therefore, identifying locations on the roadways where such risks are relatively high is critical to informing mitigation efforts. The proposed phase 3 of the study focuses on this identification. The representative quoted above also noted: “We don’t record near misses, so we don’t have any documentation but [they are] frequent”, thus clearly highlighting the need. Therefore, phase 3 builds on phase 2 by considering the presence of near misses between pedestrians or vulnerable vehicles and large vehicles to investigate the potential of using bus imagery to identify locations of recurring high-risk combinations of these elements. The Ohio State University (OSU) campus will again be used as a living lab. The size and diversity of land uses make the campus representative of urban areas, and the close and ongoing collaboration with OSU’s Transportation and Traffic Management, the deployment partner and contributor to the success of the OSU campus transportation living lab, offers insights on safety concerns and the practical validations of the developing safety monitoring scheme.

• Record URL:
  • https://ppms.cit.cmu.edu/projects/detail/601

Language

• English

Project

• Status: Completed
• Funding: $201,595.00
• Contract Numbers:

  69A3552344811

  69A3552348316

• 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:

  Safety21 University Transportation Center

  Carnegie Mellon University
  Pittsburgh, PA  United States  15213

  Carnegie Mellon University

  Pittsburgh, PA  United States 
• Performing Organizations:

  Ohio State University

  Columbus, OH  United States 
• Principal Investigators:

  Mishalani, Rabi

  McCord, Mark

  Baig, Harris

• Start Date: 20250701
• Expected Completion Date: 20260831
• Actual Completion Date: 20260831
• USDOT Program: University Transportation Centers

Subject/Index Terms

• TRT Terms: Data collection; Image analysis; Near crashes; Traffic safety; Traffic surveillance; Transit buses; Vulnerable road users
• Identifier Terms: Ohio State University
• Subject Areas: Data and Information Technology; Pedestrians and Bicyclists; Public Transportation; Safety and Human Factors;

Filing Info

• Accession Number: 02002859
• Record Type: Research project
• Source Agency: Safety21 University Transportation Center
• Contract Numbers: 69A3552344811, 69A3552348316
• Files: UTC, RIP
• Created Date: Sep 17 2026 5:08PM