Part of Advances in Neural Information Processing Systems 6 (NIPS 1993)
K. I. Diamantaras, D. Geiger
We address the problem of optical flow reconstruction and in par(cid:173) ticular the problem of resolving ambiguities near edges. They oc(cid:173) cur due to (i) the aperture problem and (ii) the occlusion problem, where pixels on both sides of an intensity edge are assigned the same velocity estimates (and confidence). However, these measurements are correct for just one side of the edge (the non occluded one). Our approach is to introduce an uncertamty field with respect to the estimates and confidence measures. We note that the confi(cid:173) dence measures are large at intensity edges and larger at the con(cid:173) vex sides of the edges, i.e. inside corners, than at the concave side. We resolve the ambiguities through local interactions via coupled Markov random fields (MRF) . The result is the detection of motion for regions of images with large global convexity.