• DocumentCode
    2240673
  • Title

    Layered representation for motion analysis

  • Author

    Wang, John Y A ; Adelson, Edward H.

  • Author_Institution
    MIT Media Lab., Cambridge, MA, USA
  • fYear
    1993
  • fDate
    15-17 Jun 1993
  • Firstpage
    361
  • Lastpage
    366
  • Abstract
    Standard approaches to motion analysis assume that the optic flow is smooth; such techniques have trouble dealing with occlusion boundaries. The image sequence can be decomposed into a set of overlapping layers, where each layer´s motion is described by a smooth flow field. The discontinuities in the description are then attributed to object opacities rather than to the flow itself, mirroring the structure of the scene. A set of techniques is devised for segmenting images into coherently moving regions using affine motion analysis and clustering techniques. It is possible to decompose an image into a set of layers along with information about occlusion and depth ordering. The techniques are applied to a flower garden sequence. The scene can be analyzed into four layers, and, the entire 30-frame sequence can be represented with a single image of each layer, along with associated motion parameters
  • Keywords
    image segmentation; motion estimation; 30-frame sequence; affine motion analysis; clustering techniques; coherently moving regions; depth ordering; discontinuities; flower garden sequence; image segmentation; image sequence decomposition; layered representation; motion analysis; motion parameters; object opacities; occlusion boundaries; overlapping layers; smooth flow field; smooth optic flow; Animation; Image analysis; Image motion analysis; Image segmentation; Image sequence analysis; Image sequences; Laboratories; Layout; Motion analysis; Optical sensors; Smoothing methods;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Computer Vision and Pattern Recognition, 1993. Proceedings CVPR '93., 1993 IEEE Computer Society Conference on
  • Conference_Location
    New York, NY
  • ISSN
    1063-6919
  • Print_ISBN
    0-8186-3880-X
  • Type

    conf

  • DOI
    10.1109/CVPR.1993.341105
  • Filename
    341105