Real-Time Recognition and Control of Multi-Modal Traffic Flows

This project focuses on the development and use of bus and pedestrian recognition technologies for multi-modal adaptive traffic signal control. A first major project thread builds directly on prior research on real-time recognition of buses from video camera streams. This work has developed a prototype bus recognizer which has shown good performance both in the lab and in preliminary field experiments at the Penn Avenue/Highland Avenue intersection in East Liberty (part of our Surtrac adaptive signal system deployment). During the first 6 months of 2014, the project intends to further test this recognizer in the field, refine the technology as needed, and then perform integrated experimentation with Surtrac (focusing first on better reaction to stopped buses that are blocking traffic and then incorporating bus prioritization). The second major project thread will focus on pedestrian friendly traffic signal control. Starting with state of the art pedestrian recognition technology, the project will investigate possibilities for augmenting presence detection capability with an ability to generate pedestrian density information, develop strategies for incorporating pedestrian traffic directly into adaptive traffic signal control decisions, and conduct experiments (both in simulation and in the field) to analyze and validate opportunities for better overall multi-modal mobility.


    • English


    • Status: Active
    • Contract Numbers:


    • Sponsor Organizations:

      Research and Innovative Technology Administration

      University Transportation Centers Program
      1200 New Jersey Avenue
      Washington, DC  United States  20590

      Carnegie Mellon University

      Pittsburgh, PA  United States 

      Technologies for Safe and Efficient Transportation University Transportation Center

      Carnegie Mellon University
      Pittsburgh, PA  United States  15213
    • Project Managers:

      Ehrlichman, Courtney

    • Principal Investigators:

      Smith, Stephen

    • Start Date: 20140131
    • Expected Completion Date: 0
    • Actual Completion Date: 20141231
    • Source Data: RiP Project 36207

    Subject/Index Terms

    Filing Info

    • Accession Number: 01517371
    • Record Type: Research project
    • Source Agency: Technologies for Safe and Efficient Transportation University Transportation Center
    • Contract Numbers: DTRT12GUTG11
    • Files: UTC, RiP
    • Created Date: Mar 7 2014 1:00AM