Motion (Occlusion) Boundaries
One of the most significant remaining problems in early motion estimation
concerns occlusion boundaries, where the two key assumptions of current
optical flow methods, brightness conservation and motion smoothness,
are typically violated.
Michael Black and I recently formulated a probabilistic solution to this
problem with a hybrid state-space model and a particle filter for approximate
inference. The state space model included a discrete random variable to
represent different motion classes (e.g., smooth motion, or discontinuous
motion), and continuous variables to represent the parameters of each
motion class. This work won Honorable Mention for the Marr Prize (runner-up
for best paper) at the International Conference on Computer Vision in 1999.
Although these initial experiments produced encouraging results the method
proved to be unreliable. Oscar Nestares and I have since improved the
method by introducing a random field of local neighborhoods to encourage
spatiotemporal continuity of the inferred surface boundaries, and an empirical
edge-based likelihood function to improve boundary localization.
- Fleet, D.J., Black, M.J. and Nestares O. (2003)
Bayesian inference of visual motion boundaries.
in Exploring Artificial Intelligence in the New Millennium,
G. Lakemeyer and B. Nebel (eds.), Morgan Kaufmann Press, pp. 139-173
- Black, M.J. and Fleet, D.J. (2000) Probabilistic detection and
tracking of motion discontinuities. International Journal of Computer
Vision 38(3):229--243 (abstract)
- Nestares, O. and Fleet, D.J. (2001) Detection and tracking of motion
boundaries. IEEE Conference on Computer Vision and Pattern
Recognition, Kauai, Vol. II. pp. 358--365
- Black, M.J. and Fleet, D.J. (1999) Probabilistic detection and tracking
of motion discontinuities. IEEE International Conference on
Computer Vision, Corfu, Greece, September, pp. 551-558
[Runner-Up for best paper]
Return to David Fleet's home page.