Computing optical flow for motion images sequences by applying multi-constraints to multi-locations

Computing optical flow is one of the most fundamental problem to the motion image analysis. Many methods have been proposed for comput.ing opt#ical flow! among them gradient.-based methods arc t,he most well-known and most used. In the paper, a new gradient-based method for the computation of optical flow is proposed. In this method, opt.ical flow is computed by minimizing a weight,cd leastsquares error estimator for a constant motion vcct,or model in a local spatial neighborhood, where the weight of each image location in the neighborhood is det,ermined by its multiple constraints. Several experimcnt,s on real and synthet,ic image sequences have been carried out to verify the efficacy and the reliabilit,y of the new method.