ML Anthology

Layered Representation for Motion Analysis

John Y. A. Wang, Edward H. Adelson
CVPR 1993 pp. 361-366
doi:10.1109/CVPR.1993.341105 /cvpr/1993/wang1993cvpr-layered/

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.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

CVPR Semantic Scholar

Cite

Text

Wang and Adelson. "Layered Representation for Motion Analysis." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1993. doi:10.1109/CVPR.1993.341105

Markdown

[Wang and Adelson. "Layered Representation for Motion Analysis." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1993.](https://mlanthology.org/cvpr/1993/wang1993cvpr-layered/) doi:10.1109/CVPR.1993.341105

BibTeX

@inproceedings{wang1993cvpr-layered,
  title     = {{Layered Representation for Motion Analysis}},
  author    = {Wang, John Y. A. and Adelson, Edward H.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1993},
  pages     = {361-366},
  doi       = {10.1109/CVPR.1993.341105},
  url       = {https://mlanthology.org/cvpr/1993/wang1993cvpr-layered/}
}