Multiple constraints for optical flow

The computation of the optical flow field from an image sequences requires the definition of constraints on the temporal change of image features to limit the motion of the body in space and of the features on the image plane.

Abstract

The computation of the optical flow field from an image sequences requires the definition of constraints on the temporal change of image features. In general, these constraints limit the motion of the body in space and/or of the features on the image plane. In this paper the implications in the use of multiple constraints in the computational schema are considered. It is shown that differential constraints correspond to an implicit feature tracking. Consequently, the results strictly depend upon the local gray level structure. The best results (either in terms of measurement accuracy and speed in the computation) are obtained by selecting and applying the constraints which are best "tuned" to the particular image feature under consideration. Several experiments are presented both from a synthetic scene and from real image sequences.