• DocumentCode
    3234239
  • Title

    Tracking an unknown moving target from UAV: Extracting and localizing an moving target with vision sensor based on optical flow

  • Author

    Choi, Jay Hyuk ; Lee, Dongjin ; Bang, Hyochoong

  • Author_Institution
    Div. of Aerosp. Eng., Korea Adv. Inst. of Sci. & Technol., Daejeon, South Korea
  • fYear
    2011
  • fDate
    6-8 Dec. 2011
  • Firstpage
    384
  • Lastpage
    389
  • Abstract
    This paper proposes a novel algorithm for tracking a target from UAV(Unmanned Aerial Vehicle). No knowledge is assumed about the target, apart from being in motion. The algorithm includes optical flow to compute velocity field of sequential frames. Velocity field varies radically near the boundary of the target. This simple fact enables to segregate the target and background from the scene and to obtain their velocities. With the aid of simple geolocation method, we can get the absolute location and velocity of the target and this will enable target tracking for UAV based on optical flow.
  • Keywords
    autonomous aerial vehicles; computer vision; image sensors; image sequences; target tracking; UAV; geolocation method; optical flow; sequential frames; unknown moving target tracking; unmanned aerial vehicle; velocity field; vision sensor; Cameras; Computer vision; Image motion analysis; Optical imaging; Optical sensors; Target tracking; Vectors; Localization; Moving Target; Optical Flow; Target Extraction; Tracking; UAV; Vision Sensor;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Automation, Robotics and Applications (ICARA), 2011 5th International Conference on
  • Conference_Location
    Wellington
  • Print_ISBN
    978-1-4577-0329-4
  • Type

    conf

  • DOI
    10.1109/ICARA.2011.6144914
  • Filename
    6144914