Optical flow provides a constraint on the motion of a deformable model. We
derive and solve a dynamic system incorporating flow as a hard constraint,
producing a model-based least-squares optical flow solution. Our solution a
lso ensures the constraint remains satisfied when combined with edge inform
ation, which helps combat tracking error accumulation. Constraint enforceme
nt can be relaxed using a Kalman filter, which permits controlled constrain
t violations based on the noise present in the optical flow information, an
d enables optical flow and edge information to be combined more robustly an
d efficiently. We apply this framework to the estimation of face shape and
motion using a 3D deformable face model. This model uses a small number of
parameters to describe a rich variety of face shapes and facial expressions
. We present experiments in extracting the shape and motion of a face from
image sequences which validate the accuracy of the method. They also demons
trate that our treatment of optical flow as a hard constraint, as well as o
ur use of a Kalman filter to reconcile these constraints with the uncertain
ty in the optical flow, are vital for improving the performance of our syst
em.