运动矢量场自适应搜索算法  

A Fast Motion Estimation Algorithm Using Adaptive Motion Vector Field Search

作　　者：李炜[1] 周兵[1] 李波[1] 

机构地区：[1]北京航空航天大学计算机系数字媒体室,北京100083

出　　处：《计算机学报》2003年第2期168-173,共6页Chinese Journal of Computers

基　　金：国家自然科学基金 ( 6 0 0 75 0 0 6 );国家"八六三"高技术研究发展计划项目 ( 2 0 0 1AA114 14 2 )资助 .

摘　　要：运动估计是影响基于帧间视频压缩速度的关键 ,快速运动估计算法一直是视频压缩中的研究热点 .该文从运动矢量的均匀性出发 ,提出了由搜索起点预测、自适应搜索模式和高效搜索中止准则等策略构成的运动矢量场自适应搜索算法 .实验表明 ,该文算法以极小的搜索代价得到了与全搜索相当的效果 ,并在搜索速度和搜索效果方面优于MPEG 4最新推荐的快速运动估计算法 .Motion estimation is rather complex in computation and spends much time in the inter-frame video compression. Fast motion estimation has always been a favorite to the researchers in the field. From the viewpoint of making motion vector field more homogenous, this paper proposed a novel fast algorithm, which is composed of the prediction of initial search point, adaptive search modes for the video sequences with different motion, and effective half-stop criteria. Experiments show that the algorithm could obtain almost the same PSNR as the full search at very low computation cost, and outperforms both MVFAST and PMVFAST, which were adopted by the current MPEG-4, in terms of speed and quality.

关 键 词：运动矢量场自适应搜索算法 快速运动估计算法 视频压缩编码 块匹配 MPEG 图像质量 视频编码器 

分 类 号：TN919.81[电子电信—通信与信息系统] TP391.41[电子电信—信息与通信工程]