Urtasun, R., Fleet, D.J. and Fua, P.
Motion models for 3D people tracking.
Computer Vision and Image Understanding,
We explore an approach to 3D people tracking with learned
motion models and deterministic optimization. The tracking
problem is formulated as the minimization of a differentiable
criterion whose differential structure is rich enough for
optimization to be accomplished via hill-climbing. This avoids
the computational expense of Monte Carlo methods, while
yielding good results under challenging conditions.
To demonstrate the generality of the approach we show that we
can learn and track cyclic motions such as walking and running,
as well as acyclic motions such as a golf swing.
We also show results from both monocular and multi-camera tracking.
Finally, we provide results with a motion model learned from
multiple activities, and show how this models might be used for recognition.
Return to David Fleet's home page.