Monitoring of Urban Roadway Safety Hazards from Existing Bus-Based Video Imagery

Details

• Creators:
  Mishalani, Rabi G. ; McCord, Mark R. ; Redmill, Keith A ; Shah, Harsh
• Corporate Creators:
  Ohio State University ; Carnegie Mellon University. Traffic21 University Transportation Center (UTC)
• Subject/TRT Terms:
  • Buses
  • Data collection
  • Image analysis
  • Lane changing
  • Traffic queuing
  • Traffic safety
  • Vehicle mix
  • Video
• Publication/ Report Number:
  444
• Resource Type:
  Tech Report
• Geographical Coverage:
  United States
• Edition:
  Final Report
• Corporate Publisher:
  Carnegie Mellon University. Traffic21 Institute. Safety21 University Transportation Center (UTC)
• Abstract:
  Contributors to traffic safety hazards include lane changes in the presence of queues at signalized intersections and bus stops, mixes of vehicle classes, speed variability, and vehicle overtaking. Traditional data collection methods that are constrained in time and space are prone to biased sampling. Taking advantage of video imagery recorded by transit bus-mounted cameras for other purposes offers an opportunity to overcome this bias. In this project the available, repeated, and extensive imagery recorded by such cameras for identifying queue presence and length related safety hazards is investigated. An automatic queue presence and length identification method is developed and evaluated using the campus of The Ohio State University as a living lab testbed. The results are promising, but further improvements and extensions are desirable to achieve a robust and reliable networkwide safety hazard identification tool.
• Format:
  PDF
• Funding:
  69A3552344811
• Download URL:
  https://rosap.ntl.bts.gov/view/dot/78033/dot_78033_DS1.pdf
• File Type:
  [PDF - 3.85 MB]
• Collection(s):
  University Transportation Centers
• Main Document Checksum:
  urn:sha-512:32d26ddb1bb795e81867adee9ae8037b3fe2dc2025b904e4b01db92038bbe33cf22edd983c2dbff94e3a81ddaf823e15326e1703dcc462813f847187dfb9b00e