Application of Interactive Video Sensing and Management for Pedestrian and Bicycle Safety Studies

In this project, the authors designed and implemented a user-friendly interface for pedestrian crossing and vehicle conflict detection, leveraging the OpenCV computer-vision libraries made available via open-source from Intel. The goal is to allow practitioners to more easily provide the semantics of the information they wish to extract and process into the video-processing algorithms. As a demonstration and development tool, the authors used a complicated mid-block crosswalk located on Southwest 4th Avenue. This is a busy downtown street on the Portland State University (PSU) campus. There are three lanes of heavy one-way motor vehicle traffic; speeds are moderate as most vehicles have just exited Interstate 405 (I-405). The authors used this location to demonstrate how easily and accurately their flexible, user-friendly tool can measure pedestrian wait times, crossing speeds, and near misses (e.g., a car abruptly stopping prior to the crosswalk or a vehicle passing a stopped vehicle). In addition, the system outputs meaningful data about vehicle and pedestrian trajectories for further analysis.

• Record URL:
  http://ppms.trec.pdx.edu/media/project_files/NITC-RR-577.pdf
• Summary URL:
  http://nitc.trec.pdx.edu/research/project/577
• Supplemental Notes:
  • This research was sponsored by the U.S. Department of Transportation, University Transportation Centers Program.
• Corporate Authors:

  Portland State University

  P.O. Box 751
  Portland, Oregon  United States  97207-0751

  National Institute for Transportation and Communities

  Portland State University
  P.O. Box 751
  Portland, OR  United States  97207

  Research and Innovative Technology Administration

  1200 New Jersey Avenue, SE
  Washington, DC  United States  20590
• Authors:
  • Feng, Wu-chi
  • Figliozzi, Miguel
  • Monsere, Christopher
• Publication Date: 2014-9

Language

• English

Media Info

• Media Type: Digital/other
• Edition: Final Report
• Features: Figures; Photos; References;
• Pagination: 22p

Subject/Index Terms

• TRT Terms: Algorithms; Computer vision; Crosswalks; Midblock crossings; Near crashes; Pedestrian vehicle interface; Traffic conflicts; Vehicle trajectories; Video cameras; Waiting time
• Identifier Terms: Portland State University (Oregon)
• Uncontrolled Terms: Pedestrian trajectories; Walking speed
• Geographic Terms: Portland (Oregon)
• Subject Areas: Highways; Pedestrians and Bicyclists; Safety and Human Factors;

Filing Info

• Accession Number: 01641184
• Record Type: Publication
• Report/Paper Numbers: NITC-RR-577
• Files: UTC, TRIS, RITA, ATRI, USDOT
• Created Date: Jul 17 2017 4:25PM