Probabilistic Detection and Tracking of Motion Boundaries

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.

• Type: Journal
• Year: 2000
• Where: IJCV
• Authors: Michael J. Black, David J. Fleet
• Keywords: IJCV 2000, Local Image Motion, Motion Boundaries, Non-linear Generative Model