• DocumentCode
    2385454
  • Title

    Vehicle Speed Measurement for Accident Scene Investigation

  • Author

    Tan, Huachun ; Zhang, Jie ; Feng, Jianshuai ; Li, Feng

  • Author_Institution
    Dept. Transp. Eng., Beijing Inst. of Technol., Beijing, China
  • fYear
    2010
  • fDate
    10-12 Nov. 2010
  • Firstpage
    389
  • Lastpage
    392
  • Abstract
    Overspeed is a major factor causing road traffic accidents in China. Since the early 1980s, researchers have developed various algorithms to extract speed information from traffic image sequences. In this paper, an algorithm is proposed to evaluate the speed of the accident vehicle by videos. With human interaction, control points are refined by corner detector and then used for two-dimension geometric correction. The frame difference method is employed to capture the accident vehicle in images. Once the velocity curve is obtained and smoothed, the motion trajectory and speed of an accident vehicle at collision can be captured as well. Experimental results show that the proposed method is more accurate in speed measurement. It will facilitate the traffic police to deal with traffic collision cases in a real world.
  • Keywords
    image sequences; motion estimation; object detection; road accidents; road traffic; traffic engineering computing; video signal processing; 2D geometric correction; China; accident scene investigation; accident vehicle speed evaluation; corner detector; frame difference method; motion trajectory; overspeeding; road traffic accident; speed information extraction; traffic collision; traffic image sequence; vehicle collision; vehicle speed measurement; velocity curve; Accidents; Detectors; Manuals; Roads; Trajectory; Vehicles; Velocity measurement; accident vehicle; frame difference; two-dimensional geometric correction; velocity curve;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    e-Business Engineering (ICEBE), 2010 IEEE 7th International Conference on
  • Conference_Location
    Shanghai
  • Print_ISBN
    978-1-4244-8386-0
  • Electronic_ISBN
    978-0-7695-4227-0
  • Type

    conf

  • DOI
    10.1109/ICEBE.2010.74
  • Filename
    5704346