• DocumentCode
    2466450
  • Title

    Region-based optical flow estimation

  • Author

    Fuh, Chiou-Shann ; Maragos, Petros

  • Author_Institution
    Div. of Appl. Sci., Harvard Univ., Cambridge, MA, USA
  • fYear
    1989
  • fDate
    4-8 Jun 1989
  • Firstpage
    130
  • Lastpage
    135
  • Abstract
    A correspondence method is developed for determining optical flow where the primitive motion tokens to be matched between consecutive time frames are regions. The computation of optical flow consists of three stages: region extraction, region matching, and optical flow smoothing. The computation is completed by smoothing the initial optical flow, where the sparse velocity data are either smoothed with a vector median filter or interpolated to obtain dense velocity estimates by using a motion-coherence regularization. The proposed region-based method for optical flow is simple, computationally efficient, and more robust than iterative gradient methods, especially for medium-range motion
  • Keywords
    optical information processing; pattern recognition; picture processing; correspondence method; dense velocity estimates; motion-coherence regularization; optical flow estimation; pattern recognition; picture processing; primitive motion tokens; region extraction; region matching; smoothing; sparse velocity data; vector median filter; Data flow computing; Data mining; Gradient methods; Image motion analysis; Iterative methods; Motion estimation; Optical computing; Optical filters; Robustness; Smoothing methods;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer Vision and Pattern Recognition, 1989. Proceedings CVPR '89., IEEE Computer Society Conference on
  • Conference_Location
    San Diego, CA
  • ISSN
    1063-6919
  • Print_ISBN
    0-8186-1952-x
  • Type

    conf

  • DOI
    10.1109/CVPR.1989.37840
  • Filename
    37840