A new multiconstraint approach to the estimation of optical flow is pr
esented, which is based on constraint relaxation in the velocity space
. An architecture for a parallel implementation of the algorithm is su
ggested, in which relaxation is accomplished by a mesh grid of loosely
coupled simple computational units, one for each image point where op
tical flow has to be computed. Optical flow smoothing is performed by
a vector median filter, whose nonlinear nature is helpful in preservin
g motion boundaries. Results on both synthetic and real-world sequence
s are presented, which demonstrate that the algorithm behaves well in
the presence of noise and occlusions.