一种快速块运动估计的分级筛选方法

A Multi-level Elimination Algorithm for Fast Block Motion Estimation

该文提出了一种新的快速块匹配运动估计方法,分级筛选法.该方法将搜索最佳匹配块的过程分为若干个筛选级别,在初始的级别中用很少的运算代价通过简单的特征匹配先淘汰一部分候选块;然后在上一级剩余的候选块中,逐级用更加细致的特征继续筛选;直至找到最佳匹配块.实验结果表明,在估计精度非常相近的前提下,该文方法的速度是全搜索方法的12～14倍,而且该方法有很好的稳定性.

A multi-level elimination algorithm for fast motion estimation is proposed in this paper. The most matched block of the current block is detected in the next frame with a multi-level elimination strategy in this algorithm. In the first level, some candidate blocks are eliminated by simple characters based block-matching, needing only very few computation costs. Then in further levels, more detailed characters are used for block-matching to eliminate more candidate blocks until the most matched block is selected in the last level. Experimental results show that the proposed algorithm can work steadily and get very close performance to the full-search algorithm while a computation reduction of about 12~14 times, with respect to the full-search algorithm.