Improved motion estimation based on motion region identification
Dongming Zhang, Gang Cao, Xiaoguang Gu · 2012
Motion estimation is always regarded as the most time consuming module in video coding, and many fast motion estimation algorithms have been proposed to speed-up it. However one fact that motion regions need more complex search whereas still regions does not instead is often ignored. On the other hand, the analysis of the distribution of motion vector difference shows that the predicted motion vector is very near to real motion vector. Herein, in this improved motion estimation algorithm, motion region is first identified using improved visual rhythm analysis and then one efficient search scheme, named search center adaptive motion estimation, is carried out according the MB motion. In the simulations, the algorithm is verified on platform JM7.3. The results show that the search scheme can great speed-up the motion estimation of still MBs, and it can eliminate about 25% integer pixel search process of motion MBs as well. The encoding performance loss is negligible for low motion video and trifling for video sequences with complex motion.