Vehicle classification data are important inputs for pavement maintenance, traffic modeling, and emission evaluation. Various technologies including weight-in-motion (WIM), axle counting with piezo-electric sensors or length measurement from dual loop detectors have been used for vehicle classification. This research extends length based vehicle classification to single loop detectors. It promises a lower cost alternative as well as the potential to use existing detectors already deployed for freeway management. Of course the single loop based estimates could also be easily incorporated in a more sophisticated classification station as an independent validation of its measurements. The main challenge with single loop detector based length based classification comes from accurately estimating speed and thus, length. In this study we develop a methodology to make such accurate speed and length estimates and then use the latter to classify vehicles based on length. Performance is validated against two sources of independent ground truth data with results that approach the accuracy of dual loop detectors. In the process of generating ground truth data a few previously unknown, sight specific problems with existing vehicle classification and detection stations were found and diagnosed, e.g., pulse break-up, as discussed herein.


    Access

    Access via TIB

    Check availability in my library


    Export, share and cite



    Title :

    Vehicle Classification from Single Loop Detectors


    Contributors:
    B. Coifman (author)

    Publication date :

    2007


    Size :

    62 pages


    Type of media :

    Report


    Type of material :

    No indication


    Language :

    English







    A vehicle classification based on inductive loop detectors

    Gajda, J. / Sroka, R. / Stencel, M. et al. | Tema Archive | 2001


    Vehicle Classification Model for Loop Detectors Using Neural Networks

    National Research Council (U.S.) | British Library Conference Proceedings | 2005