3D People Tracking
The inference of human shape and motion in 3D has become a topic of great
interest in the vision community. The problem is difficult because
people move in complex ways, having with many degrees of freedom. Their
appearance is similarly hard to model due to variations in lighting,
to deformations of clothing, and to occlusions. To constrain people
tracking, most existing methods assume one or more constraints, such as
knowledge of a static background, the existence of multiple views of
the person, or that color can be used to find skin regions. Hedvig
Sidenbladh, Michael Black and I proposed a Bayesian approach
to tracking people in 3D from 2D video. With a motion-based likelihood
function based on a robust form of intensity conservation, a particle
filter to deal with nonlinear dynamics and observations, a learned
parameterized model of human walking motion and manual initialization of
the model, we were able to infer the time-varying 3D structure of a
single person in unknown cluttered backgrounds in monocular, greyscale video.
More recently, in an attempt to provide more efficient stochastic sampling
so that we could handle weaker models of human dynamics, Kiam Choo and
I began to consider the use of particle filters with MCMC updates. Applied to
the inference of 3D joint configuration from 2D motion capture point data,
we found that a particle filter with hybrid Monte Carlo updates produced
an estimator more than 2,000 times faster than a conventional particle
filter, with similar estimator variance. In combination with richer
likelihood functions, combining motion and edge information, I hope
this will lead to more effective tracking in high-dimensional spaces
with complex dynamics and observation equations.
Urtasun, R., Fleet, D.J. and Fua, P.
Motion models for 3D people tracking.
Computer Vision and Image Understanding
Urtasun, R., Fleet, D.J. and Fua, P. (2004)
Monocular 3D tracking of the golf swing.
IEEE Conference on Computer Vision and Pattern Recognition (CVPR),
San Diego, 2005.
- Poon, E. and Fleet, D.J. (2002)
Hybrid Monte Carlo filtering: Edge-based people tracking.
IEEE Workshop on Motion and Video Computing, Orlando, pp. 151-158.
- Ormoneit, D., Lemieux, C., and Fleet, D.J. (2001) Lattice particle
filters. Conference on Uncertainty in Artifical Intelligence,
August 2001, Morgan Kaufmann Press, pp. 395--402
- Choo, K. and Fleet, D.J. (2001) People tracking with hybrid Monte
Carlo. IEEE International Conference on Computer Vision,
Vancouver, Vol II, pp. 321-328
- Sidenbladh, H., Black, M.J., and Fleet, D.J. (2000) Stochastic
tracking of 3D human figures using 2d image motion. European Conference
on Computer Vision, Dublin, Vol. II, pp. 702--718
Return to David Fleet's home page.