Perceiving Systems Conference Paper 1999

Explaining optical flow events with parameterized spatio-temporal models

pdf video
Thumb ticker sm headshot2021
Perceiving Systems
Director
Bildschirmfoto 2013 01 14 um 09.12.47

A spatio-temporal representation for complex optical flow events is developed that generalizes traditional parameterized motion models (e.g. affine). These generative spatio-temporal models may be non-linear or stochastic and are event-specific in that they characterize a particular type of object motion (e.g. sitting or walking). Within a Bayesian framework we seek the appropriate model, phase, rate, spatial position, and scale to account for the image variation. The posterior distribution over this parameter space conditioned on image measurements is typically nonGaussian. The distribution is represented using factored sampling and is predicted and updated over time using the Condensation algorithm. The resulting framework automatically detects, localizes, and recognizes motion events.

Author(s): Black, M. J.
Links:
Book Title: IEEE Proc. Computer Vision and Pattern Recognition, CVPR’99
Pages: 326-332
Year: 1999
Publisher: IEEE
Bibtex Type: Conference Paper (inproceedings)
Address: Fort Collins, CO
Electronic Archiving: grant_archive

BibTex

@inproceedings{Black:IEEE:1999,
  title = {Explaining optical flow events with parameterized spatio-temporal models},
  booktitle = {IEEE Proc. Computer Vision and Pattern Recognition, CVPR'99},
  abstract = {A spatio-temporal representation for complex optical flow events is developed that generalizes traditional parameterized motion models (e.g. affine). These generative spatio-temporal models may be non-linear or stochastic and are event-specific in that they characterize a particular type of object motion (e.g. sitting or walking). Within a Bayesian framework we seek the appropriate model, phase, rate, spatial position, and scale to account for the image variation. The posterior distribution over this parameter space conditioned on image measurements is typically nonGaussian. The distribution is represented using factored sampling and is predicted and updated over time using the Condensation algorithm. The resulting framework automatically detects, localizes, and recognizes motion events.},
  pages = {326-332},
  publisher = {IEEE},
  address = {Fort Collins, CO},
  year = {1999},
  slug = {black-ieee-1999},
  author = {Black, M. J.}
}