The Pulse of Allegheny County and Pittsburgh

Cities are increasingly equipped with low-resolution cameras. They are cheap to buy, install, and maintain, and thus are usually the choice of departments of transportation and their contractors. Pittsburgh or New York City have networks of hundreds of cameras. Video from some of these cameras is publicly accessible in real time. In this project, the project team addressed the problem of building a traffic model for parts of the roads visible from publicly accessible cameras. In particular, the team's end goal is to build a model capable of detecting different types of vehicles in images in various weather conditions and times of the day except night. Models learn different appearance of vehicles as seen from different viewpoints. A major difficulty with any type of analysis like this is the need for large amounts of training data. In this case, it is easy to collect unlabeled data from publicly available low-resolution low-frame rate cameras in Pittsburgh or New York City (NYC). Some contractors from industry recently made substantial investments into the manual labelling of millions of cars. Such a large-scale approach allowed them to come up with a complex cascade detector built on hand crafted Haar-like image representation. They report reaching 98% precision - 98% recall point. In this work, the project team aims to achieve similar performance, but without the prohibitively expensive human labelling.


    • English


    • Status: Completed
    • Sponsor Organizations:

      Carnegie Mellon University

      Pittsburgh, PA  United States 

      Office of the Assistant Secretary for Research and Technology

      University Transportation Centers Program
      Department of Transportation
      Washington, DC  United States  20590
    • Project Managers:

      Ehrlichman, Courtney

    • Start Date: 20160101
    • Expected Completion Date: 0
    • Actual Completion Date: 0

    Subject/Index Terms

    Filing Info

    • Accession Number: 01595814
    • Record Type: Research project
    • Source Agency: Technologies for Safe and Efficient Transportation University Transportation Center
    • Files: UTC, RiP
    • Created Date: Apr 8 2016 2:18PM