Monitoring and Predicting Pedestrian Behavior using Traffic Cameras

Most intersections lack awareness of pedestrian traffic: their perception infrastructure—when available—is usually limited to the detection of vehicles at very specific places. In this study, the authors consider the use of video cameras to monitor pedestrian traffic in settings where a static camera that has an unobstructed view of the road is used to detect and track pedestrians. In previous research efforts, the authors addressed the detection and placement of pedestrians present at the intersection. This effort focused on the prediction aspects of the monitoring process. In particular, the authors focused on creating interaction models that take into account influences among other agents in the scene (i.e. other pedestrians), rather than independent models for each single agent. A heuristic-based algorithm was developed to predict pedestrian trajectories. In addition, predictions must be generated in real time to be useful. Therefore, the last objective of this work was producing a software implementation capable of generating predictions in real time. The work conducted in this project moves us closer to deploying systems for detecting, tracking, and forecasting human behavior in dynamic environments. This information can be used by other systems as part of an infrastructure-based framework to effectively protect pedestrians: the more vulnerable traffic participants.

  • Record URL:
  • Summary URL:
  • Supplemental Notes:
    • This document was sponsored by the U.S. Department of Transportation, University Transportation Centers Program.
  • Corporate Authors:

    Carnegie Mellon University

    Robotics Institute, 5000 Forbes Avenue
    Pittsburgh, PA  United States  15213-3890

    Technologies for Safe and Efficient Transportation University Transportation Center

    Carnegie Mellon University
    Pittsburgh, PA  United States  15213

    Office of the Assistant Secretary for Research and Technology

    University Transportation Centers Program
    Department of Transportation
    Washington, DC  United States  20590
  • Authors:
    • Navarro-Serment, Luis E
  • Publication Date: 2018-11-25

Language

  • English

Media Info

  • Media Type: Digital/other
  • Edition: Final Research Report
  • Features: Figures; Photos;
  • Pagination: 9p

Subject/Index Terms

Filing Info

  • Accession Number: 01687635
  • Record Type: Publication
  • Files: UTC, TRIS, ATRI, USDOT
  • Created Date: Nov 28 2018 9:55AM