Header logo is ps

Bayesian Inference of Visual Motion Boundaries


Book Chapter


This chapter addresses an open problem in visual motion analysis, the estimation of image motion in the vicinity of occlusion boundaries. With a Bayesian formulation, local image motion is explained in terms of multiple, competing, nonlinear models, including models for smooth (translational) motion and for motion boundaries. The generative model for motion boundaries 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 formulate the posterior probability distribution over the models and model parameters, conditioned on the image sequence. Approximate inference is achieved with a combination of tools: A Bayesian filter provides for online computation; factored sampling allows us to represent multimodal non-Gaussian distributions and to propagate beliefs with nonlinear dynamics from one time to the next; and mixture models are used to simplify the computation of joint prediction distributions in the Bayesian filter. To efficiently represent such a high-dimensional space, we also initialize samples using the responses of a low-level motion-discontinuity detector. The basic formulation and computational model provide a general probabilistic framework for motion estimation with multiple, nonlinear models.

Author(s): Fleet, D. J. and Black, M. J. and Nestares, O.
Book Title: Exploring Artificial Intelligence in the New Millennium
Pages: 139-174
Year: 2002
Month: July
Editors: Lakemeyer, G. and Nebel, B.
Publisher: Morgan Kaufmann Pub.

Department(s): Perceiving Systems
Bibtex Type: Book Chapter (incollection)
Paper Type: Book Chapter

Links: pdf


  title = {Bayesian Inference of Visual Motion Boundaries},
  author = {Fleet, D. J. and Black, M. J. and Nestares, O.},
  booktitle = {Exploring Artificial Intelligence in the New Millennium},
  pages = {139-174},
  editors = {Lakemeyer, G. and Nebel, B.},
  publisher = {Morgan Kaufmann Pub.},
  month = jul,
  year = {2002},
  month_numeric = {7}