MOTION ESTIMATION AND SEGMENTATION

In the general structure-from-motion (SFM) problem involving several m oving objects in a scene, the essential first step is to segment movin g objects independently. We attempt to deal with the problem of optica l flow estimation and motion segmentation over a pair of images. We ap ply a mean field technique to determine optical flow and motion bounda ries and present a deterministic algorithm. Since motion discontinuiti es represented by line process are embedded in the estimation of the o ptical flow, our algorithm provides accurate estimates of optical flow especially along motion boundaries and handles occlusion and multiple motions. We show that the proposed algorithm outperforms other well-k nown algorithms in terms of estimation accuracy and timing.