Vehicle Classification Based on the Radar Measurement of Height Profiles

In this paper the authors present a method for vehicle classification using the feature extraction of road vehicle height profiles. The sensor in question is a spread-spectrum microwave (MW) radar that, once it has detected that a vehicle's profile fits certain requirements and a feature vector is extracted, can then apply a simple deterministic algorithm to determine the vehicle in question's class. The authors here show that height and length can unambiguously determine vehicle class, which allows height profiles to only be used in a smaller portion of candidate vehicles. Advantages for the use of such systems include high accuracy and low cost. The system is mostly immune to vibration and adverse weather and has observational accuracy equivalent to that of toll collection systems in New York City.

  • Availability:
  • Authors:
    • Urazghildiiev, Ildar
    • Ragnarsson, Rolf
    • Ridderstrom, Pierre
    • Rydberg, Anders
    • Ojefors, Eric
    • Wallin, Kjell
    • Enochsson, Per
    • Ericson, Magnus
    • Lofqvist, Goran
  • Publication Date: 2007-6

Language

  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 01054471
  • Record Type: Publication
  • Source Agency: UC Berkeley Transportation Library
  • Files: BTRIS, TRIS
  • Created Date: Jun 18 2007 6:51PM