Recovery of motion vectors by detecting homogeneous movements for H.263 video communications

Abstract

In this paper, a new approach for the recovery of lost or erroneous motion vector(MV)s by classifying the movements of neighboring blocks by their homogeneity is proposed. MVs of the neighboring blocks are classified according to the direction of MVs and a representative value for each class is determined to obtain the candidate MV with the minimum distortion is selected. Experimental results show that the proposed algorithm exhibits better performance in many cases than existing methods.