Automated Turning Movement Counts for Shared Lanes

This project will demonstrate the use of vehicle trajectory data (obtained from an existing vehicle detection system) to produce turning movement count statistics at signalized intersections with exclusive as well as shared lanes. Work on the project will be carried out in two stages. Stage 1 will focus on identifying promising techniques for counting vehicle turning movement, adapting data collection equipment to meet project needs, and identifying and scheduling of data collection sites. The most promising approach to obtain turning movement counts from trajectory data will be identified along with a list of candidate locations for collecting trajectory data from shared lanes at signalized intersections. Based on identified candidate intersections, the research team will configure and test data collection equipment to ascertain its applicability and suitability for selected intersections. The work will include scouting of sites, meeting with agencies in charge of locations, and identifying and addressing issues prior to data collection and will allow configuring data collection units for field deployment without major modifications. Work in Stage 2 will focus on collecting traffic count data and developing an algorithm for producing turning movement count statistics when connected to a live trajectory data feed. Trajectory data will be collected at up to four candidate locations for a period of up to three weeks at each location. If available, the research team will also consider logging signal status information along with the trajectory data. Using the obtained dataset, the research team will develop an algorithm capable of classifying the trajectory of a vehicle into a left, thru, and right movements. To validate this algorithm, trajectory data will be supplemented with up to 36 hours of simultaneously-collected video from candidate locations. Finally, the research team will combine a streamlined version of the data collection tool used in Stage 1 and the turning movement count classification algorithm into a software module, which, when provided with a live trajectory data feed, will output turning movement count statistics. The module will be field evaluated to validate its performance and, if necessary, to make appropriate changes to the system. The final report will provide all data and test results along with details on using the methodology as well as plans for its implementation and commercialization.


  • English


  • Status: Active
  • Funding: $78097.00
  • Contract Numbers:

    Project 20-30, IDEA

  • Sponsor Organizations:

    Federal Highway Administration

    1200 New Jersey Avenue, SE
    Washington, DC  United States  20590

    American Association of State Highway & Transportation Officials (AASHTO)

    444 North Capitol Street, NW, Suite 225
    Washington, DC  United States  20001

    National Cooperative Highway Research Program

    Transportation Research Board
    500 Fifth Street, NW
    Washington, DC  United States  20001
  • Project Managers:

    Jawed, Inam

  • Performing Organizations:

    University of Wisconsin, Madison

    Department of Civil and Environmental Engineering
    1415 Engineering Drive
    Madison, WI  United States  53706
  • Principal Investigators:

    Noyce, David

  • Start Date: 20141113
  • Expected Completion Date: 0
  • Actual Completion Date: 0
  • Source Data: RiP Project 37594

Subject/Index Terms

Filing Info

  • Accession Number: 01543403
  • Record Type: Research project
  • Source Agency: Transportation Research Board
  • Contract Numbers: Project 20-30, IDEA
  • Files: TRB, RiP
  • Created Date: Nov 14 2014 1:01AM