An Investigation in the Use of Inductive Loop Signatures for Vehicle Classification

This report presents an advanced traffic surveillance technique that is based on pattern recognition and the use of current inductive loop technology. Focus was on studying the feasibility of using inductive loop signatures for obtaining vehicle classification information on a network-wide level. Included as potential benefits from the vehicle classification information are improvements in vehicle reidentification algorithms, road maintenance, vehicle emissions management, roadway design, traffic modeling and simulation, traffic safety, and automated toll collection. The research involved the use of different pattern recognition techniques for vehicle classification, such as classical decision theoretic approach and advanced neural networks. Vehicle classification algorithms were tested using inductive signatures. Using different datasets classification rates of greater than 80% were obtained. The results proved the feasibility and potential of using this method for collecting vehicle classification data.

  • Record URL:
  • Availability:
  • Supplemental Notes:
    • Publication Date: 2000 California PATH Program, Institute of Transportation Studies University of California, Berkeley CA Remarks: Also available in PDF format from the California PATH website
  • Corporate Authors:

    University of California, Berkeley

    California PATH Program, Institute of Transportation Studies
    Richmond Field Station, 1357 South 46th Street
    Richmond, CA  United States  94804-4648

    California Department of Transportation

    1120 N Street
    Sacramento, CA  United States  95814
  • Authors:
  • Publication Date: 2000-3


  • English

Media Info

  • Media Type: Digital/other
  • Pagination: ix, 129 p.
  • Serial:

Subject/Index Terms

Filing Info

  • Accession Number: 00799500
  • Record Type: Publication
  • Source Agency: UC Berkeley Transportation Library
  • Report/Paper Numbers: UCB-ITS-PRR-2000-4
  • Files: STATEDOT
  • Created Date: Oct 6 2000 12:00AM