• DocumentCode
    442443
  • Title

    Dense optical flow by iterative local window registration

  • Author

    Le Besnerais, Guy ; Champagnat, Frédéric

  • Author_Institution
    Office Nat. d´´Etudes et de Recherches Aerospatiales, Chatillon, France
  • Volume
    1
  • fYear
    2005
  • fDate
    11-14 Sept. 2005
  • Abstract
    We study dense optical flow estimation using iterative registration of local window, also known as iterative Lucas-Kanade (LK) [B. Lucas et al, 1981]. We show that the usual iterative-warping scheme encounters divergence problems and propose a modified scheme with better behavior. It yields good results with a much lower cost than the exact dense LK algorithm, on simulated and real sequences.
  • Keywords
    image registration; image sequences; iterative methods; convergent scheme; dense optical flow estimation; iterative Lucas-Kanade algorithm; iterative local window registration; Design for disassembly; Image motion analysis; Interpolation; Iterative algorithms; Least squares methods; Newton method; Nonlinear optics; Optical filters; Recursive estimation; Spline;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Image Processing, 2005. ICIP 2005. IEEE International Conference on
  • Print_ISBN
    0-7803-9134-9
  • Type

    conf

  • DOI
    10.1109/ICIP.2005.1529706
  • Filename
    1529706
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=442443