Young Chang Cho, Tai Hong Yi

The KIPS Transactions:PartB , Vol. 8, No. 5, pp. 557-564, Oct. 2001
10.3745/KIPSTB.2001.8.5.557,   PDF Download:

Abstract

In general, several moving regions with different motions coexist in a block located on motion boundaries in the block-based motion estimation. In this case the motion compensation errors(MCEs) are different with the moving regions. This is inclined to deteriorate the quality of motion compensated images because of the inaccurate motions estimated from the conventional mean absolute error(MAE) based matching function in which the matching error per pixel is accumulated throughout the block. In this paper, we divided a block into the regions according to their motions using the motion information of the spatio-temporally neighboring blocks and calculated the average MCE for each moving region. And we proposed the new matching function considering the minimal deviation of MCEs between the moving regions to solve the problems mentioned. From the simulation results, we showed the improved performance of the proposed method by comparing the results from other methods such as the full search method and the edge oriented block matching algorithm. Especially, we improved the quality of the motion compensated images of blocks on motion boundaries.

Statistics
Cite this article