Perceiving Systems, Computer Vision

Probabilistic detection and tracking of motion discontinuities

1999

Conference Paper

ps


We propose a Bayesian framework for representing and recognizing local image motion in terms of two primitive models: translation and motion discontinuity. Motion discontinuities are represented using a non-linear generative model that explicitly encodes the orientation of the boundary, the velocities on either side, the motion of the occluding edge over time, and the appearance/disappearance of pixels at the boundary. We represent the posterior distribution over the model parameters given the image data using discrete samples. This distribution is propagated over time using the Condensation algorithm. To efficiently represent such a high-dimensional space we initialize samples using the responses of a low-level motion discontinuity detector.

Award: (Marr Prize, Honorable Mention)
Author(s): Black, M. J. and Fleet, D. J.
Book Title: Int. Conf. on Computer Vision, ICCV-99
Pages: 551-558
Year: 1999
Publisher: ICCV

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

Address: Corfu, Greece
Award Paper: Marr Prize, Honorable Mention

Links: pdf

BibTex

@inproceedings{Black:ICCV:1999,
  title = {Probabilistic detection and tracking of motion discontinuities},
  author = {Black, M. J. and Fleet, D. J.},
  booktitle = {Int. Conf. on Computer Vision, ICCV-99},
  pages = {551-558},
  publisher = {ICCV},
  address = {Corfu, Greece},
  year = {1999},
  doi = {}
}