• DocumentCode
    411529
  • Title

    A robust visual tracking of an arbitrary-shaped object by a new active contour method for a virtual reality application

  • Author

    Huang, Cheng-Ming ; Wang, Su-Chiun ; Fu, Li-Chen ; Chen, Pei-Ying ; Cheng, Yu-Shan

  • Author_Institution
    Dept. of Electr. Eng., Nat. Taiwan Univ., Taipei, Taiwan
  • Volume
    1
  • fYear
    2004
  • fDate
    21-23 March 2004
  • Firstpage
    64
  • Abstract
    This paper presents a real-time, highly reliable, open field visual tracking system, which can automatically detect an arbitrary-shaped object in 3-D space and find out its location so that the 2-DOF camera platform can be controlled to keep the target centered in the monitor image. The total processing period of the proposed visual servo system is less than 34 ms. Next, the visual servo system is to play the role as a military light-of-sight on the air fighter to lock an enemy fighter. Incidentally, the 2-DOF information of the camera platform is adopted to the autopilot control of an air fighter to track the foregoing target. The overall system is experimented and verified in a virtual reality environment, which can further be developed as an entertainment or military training platform.
  • Keywords
    image matching; image motion analysis; object detection; target tracking; virtual reality; 2 DOF camera platform; active contour method; air fighter; arbitrary shaped object detection; autopilot control; enemy fighter; image matching; military light of sight; military training platform; robust visual tracking system; virtual reality; visual servo system; Active contours; Automatic control; Cameras; Control systems; Object detection; Real time systems; Robustness; Servomechanisms; Target tracking; Virtual reality;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Networking, Sensing and Control, 2004 IEEE International Conference on
  • ISSN
    1810-7869
  • Print_ISBN
    0-7803-8193-9
  • Type

    conf

  • DOI
    10.1109/ICNSC.2004.1297410
  • Filename
    1297410