• DocumentCode
    3546032
  • Title

    Novel vehicle detection system based on line scan camera

  • Author

    Xu, Zhigang ; Zhao, Xiangmo ; Li, Na

  • Author_Institution
    Sch. of Inf. Eng., Chang´´an Univ., Xi´´an, China
  • fYear
    2009
  • fDate
    16-19 Aug. 2009
  • Abstract
    In order to improve the precision and real-time character of the traditional video-based traffic detector, a novel vehicle detection system based on line scan camera is developed. In this system, the vertical view images of vehicles are captured by two line scan cameras which are mounted on the pole´s arm over the roadway; The distance between two cameras is 2 meters along the road. The vehicle´s outline region in the captured image is extracted with a wavelet transform algorithm, and the vehicle´s speed is estimated by a curve correlation method. Compared with video camera, the line scan camera only detects the moving objects and the static background of the pavement in the captured image hardly changes, hence the vehicle detection algorithm has a lower complexity and consumes less time. Moreover, the measurement precision of the vehicle´s speed is much higher than the video-based traffic detector since the line scan camera has a frame rate of 1000Frames/s, while the rate of video camera is only 25~30 Frames/s.
  • Keywords
    image motion analysis; object detection; road traffic; traffic engineering computing; video signal processing; wavelet transforms; line scan camera; moving object detection; vehicle detection system; video-based traffic detector; wavelet transform algorithm; Automotive engineering; Cameras; Detectors; Object detection; Rain; Road vehicles; Snow; Vehicle detection; Velocity measurement; Wavelet transforms; Intelligent transportation system; image processing; line scan camera; vehicle detection system; wavelet transform;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Electronic Measurement & Instruments, 2009. ICEMI '09. 9th International Conference on
  • Conference_Location
    Beijing
  • Print_ISBN
    978-1-4244-3863-1
  • Electronic_ISBN
    978-1-4244-3864-8
  • Type

    conf

  • DOI
    10.1109/ICEMI.2009.5274703
  • Filename
    5274703