Probabilistic detection and tracking of motion boundaries, ICCV '99, IJCV'00

Probabilistic detection and tracking of motion boundaries
Black, M. J. and Fleet, D. J.,
Int. J. of Computer Vision, 38(3):231-245, July 2000. 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.

Probabilistic detection and tracking of motion discontinuities,
Black, M. J. and Fleet, D. J.,
Int. Conf. on Computer Vision, ICCV-99, Corfu, Greece, Sept. 1999, pp. 551-558.
(Marr Prize, Honorable Mention.)

Category:

Science & Technology

Tags:

• computer
• vision
• graphics
• image
• processing
• optical
• flow
• motion
• occlusion
• boundaries
• discontinuity
• particle
• filtering
• condensation
• Bayesian