Optical flow from an extended frame sequence

A technique for computing optical flow from an extended (more than two) sequence of images is proposed. The technique explicitly exploits the additional information present in the extended frame sequence by utilizing the smoothness of trajectory of brightness points as a constraint. Optical flow estimation is formulated as an optimization problem which requires the minimization of a cost function involving the data conservation error and the deviation from the smoothness of brightness trajectory over the entire spatiotemporal volume. An alternative formulation as a Bayesian maximum a posteriori (MAP) probability estimation problem is shown. The corresponding distribution is shown to be a Gibbs distribution (equivalently a Markov random field). The most probable velocity state is then found by a stochastic relaxation algorithm capable of handling discontinuities in the motion field