• DocumentCode
    3176827
  • Title

    Detecting moving objects from a moving platform

  • Author

    Frazier, J. ; Nevatia, R.

  • Author_Institution
    Inst. for Robotics & Intelligent Syst., Univ. of Southern California, Los Angeles, CA, USA
  • fYear
    1992
  • fDate
    12-14 May 1992
  • Firstpage
    1627
  • Abstract
    The authors present a system that successfully detects edge segments of moving objects viewed by a translating camera. The system uses two key concepts. First, a complex logarithmic mapping (CLM) is used to simplify detection of the desired movement. This converts the problem from one of detecting a complex motion along both the X and Y axes, to one of detecting vertical motion along an angular axis. Second, a mechanism to detect vertically moving edges has been developed to detect the requisite vertical motion within the CLM image. Results of processing both synthetic and real image sequences are shown. The synthetic sequence consisted of imagery, containing a moving truck, taken from an observation vehicle that was following a road. The system correctly detected portions of the truck as it passed the observer. Important similarities exist between biological vision systems and the techniques presented for motion detection
  • Keywords
    edge detection; image sequences; motion estimation; biological vision systems; complex logarithmic mapping; complex motion; edge detection; motion detection; motion estimation; moving objects detection; moving platform; moving truck; observation vehicle; real image sequences; synthetic images; translating camera; vertical motion detection; Cameras; Detectors; Image converters; Image edge detection; Image motion analysis; Image sequences; Intelligent robots; Layout; Motion detection; Object detection;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Robotics and Automation, 1992. Proceedings., 1992 IEEE International Conference on
  • Conference_Location
    Nice
  • Print_ISBN
    0-8186-2720-4
  • Type

    conf

  • DOI
    10.1109/ROBOT.1992.220019
  • Filename
    220019