Perceiving Systems, Computer Vision

Learning parameterized models of image motion

1997

Conference Paper

ps


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.

Author(s): Black, M. J. and Yacoob, Y. and Jepson, A. D. and Fleet, D. J.
Book Title: IEEE Conf. on Computer Vision and Pattern Recognition, CVPR-97
Pages: 561-567
Year: 1997
Month: June

Department(s): Perceiving Systems
Bibtex Type: Conference Paper (inproceedings)
Paper Type: Conference

Address: Puerto Rico

Links: pdf

BibTex

@inproceedings{Black:IEEE:1997,
  title = {Learning parameterized models of image motion},
  author = {Black, M. J. and Yacoob, Y. and Jepson, A. D. and Fleet, D. J.},
  booktitle = {IEEE Conf. on Computer Vision and Pattern Recognition, CVPR-97},
  pages = {561-567},
  address = {Puerto Rico},
  month = jun,
  year = {1997},
  doi = {},
  month_numeric = {6}
}