Temporal Multi-Scale Models for Flow and Acceleration

Yacoob, Yaser; Davis, Larry S.

doi:10.1109/CVPR.1997.609438

Temporal Multi-Scale Models for Flow and Acceleration

Yaser Yacoob, Larry S. Davis

CVPR 1997 pp. 921-927

doi:10.1109/CVPR.1997.609438 /cvpr/1997/yacoob1997cvpr-temporal/

Abstract

A model for computing image flow in image sequences containing a very wide range of instantaneous flows is proposed. This model integrates the spatio-temporal image derivatives from multiple temporal scales to provide both reliable and accurate instantaneous flow estimates. The integration employs robust regression and automatic scale weighting in a generalized brightness constancy framework. In addition to instantaneous flow estimation the model supports recovery of dense estimates of image acceleration and can be readily combined with parameterized flow and acceleration models. A demonstration of performance on image sequences of typical human actions taken with a high frame-rate camera, is given.

CVPR Semantic Scholar

Cite

Text

Yacoob and Davis. "Temporal Multi-Scale Models for Flow and Acceleration." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997. doi:10.1109/CVPR.1997.609438

Markdown

[Yacoob and Davis. "Temporal Multi-Scale Models for Flow and Acceleration." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997.](https://mlanthology.org/cvpr/1997/yacoob1997cvpr-temporal/) doi:10.1109/CVPR.1997.609438

BibTeX

@inproceedings{yacoob1997cvpr-temporal,
  title     = {{Temporal Multi-Scale Models for Flow and Acceleration}},
  author    = {Yacoob, Yaser and Davis, Larry S.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1997},
  pages     = {921-927},
  doi       = {10.1109/CVPR.1997.609438},
  url       = {https://mlanthology.org/cvpr/1997/yacoob1997cvpr-temporal/}
}