Probabilistic Detection and Tracking of Motion Boundaries

  • Authors:

  • Michael J. Black;David J. Fleet

  • Affiliations:

  • Xerox Palo Alto Research Center, 3333 Coyote Hill Road, Palo Alto, CA 94304, USA&semi/ Department of Computer Science, Brown University, Box 1910, Providence, RI 02912, USA. black@cs.brow ...;Xerox Palo Alto Research Center, 3333 Coyote Hill Road, Palo Alto, CA 94304, USA&semi/ Department of Computing Science, Queen's University, Kingston, K7L 3N6, Canada. fleet@cs.queensu.ca< ...

  • Venue:
  • International Journal of Computer Vision - Special issue on Genomic Signal Processing
  • Year:
  • 2000

Quantified Score

Hi-index 0.00

Visualization

Abstract

We propose a Bayesian framework for representing and recognizing local image motion in terms of two basic models: translational motion and motion boundaries. Motion boundaries 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 probability distribution over the model parameters given the image data using discrete samples. This distribution is propagated over time using a particle filtering algorithm. To efficiently represent such a high-dimensional space we initialize samples using the responses of a low-level motion discontinuity detector. The formulation and computational model provide a general probabilistic framework for motion estimation with multiple, non-linear, models.