Learning Parameterized Models of Image Motion

Black, Michael J.; Yacoob, Yaser; Jepson, Allan D.; Fleet, David J.

doi:10.1109/CVPR.1997.609381

Learning Parameterized Models of Image Motion

Michael J. Black, Yaser Yacoob, Allan D. Jepson, David J. Fleet

CVPR 1997 pp. 561-567

doi:10.1109/CVPR.1997.609381 /cvpr/1997/black1997cvpr-learning/

Abstract

A framework for learning parameterized models of optical flow from image sequences is presented. A class of motions is represented by a set of orthogonal basis flow fields that are computed from a training set using principal component analysis. Many complex image motions can be represented by a linear combination of a small number of these basis flows. The learned motion models may be used for optical flow estimation and for model-based recognition. For optical flow estimation we describe a robust, multi-resolution scheme for directly computing the parameters of the learned flow models from image derivatives. As examples we consider learning motion discontinuities, non-rigid motion of human mouths, and articulated human motion.

PDF CVPR Semantic Scholar

Cite

Text

Black et al. "Learning Parameterized Models of Image Motion." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997. doi:10.1109/CVPR.1997.609381

Markdown

[Black et al. "Learning Parameterized Models of Image Motion." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 1997.](https://mlanthology.org/cvpr/1997/black1997cvpr-learning/) doi:10.1109/CVPR.1997.609381

BibTeX

@inproceedings{black1997cvpr-learning,
  title     = {{Learning Parameterized Models of Image Motion}},
  author    = {Black, Michael J. and Yacoob, Yaser and Jepson, Allan D. and Fleet, David J.},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {1997},
  pages     = {561-567},
  doi       = {10.1109/CVPR.1997.609381},
  url       = {https://mlanthology.org/cvpr/1997/black1997cvpr-learning/}
}