基于块匹配的运动估计算法研究和优化  

Study and Optimization on Motion Estimation Algorithm Based on Block-matching

作　　者：王会鲜[1,2] 陈伟[1] 谢涛[1] 郑洪江[1,2] 

机构地区：[1]武汉理工大学信息工程学院,湖北武汉430070 [2]塔里木大学信息工程学院,新疆阿拉尔843300

出　　处：《武汉理工大学学报（信息与管理工程版）》2008年第6期861-864,共4页Journal of Wuhan University of Technology：Information & Management Engineering

基　　金：国家自然科学基金资助项目(40706058)

摘　　要：为了克服视频编码中运动估计运算量大的困难,对HBS和MVCB算法进行了深入讨论;并利用自适应静止块检测准则和基于运动相关性自适应的初始搜索点预测方法,实现了对MVCB算法的优化,减少了算法的搜索点数,有效提高了搜索速度。实验表明,在保证图像质量的前提下,改进后的算法平均搜索点数比HBS和MVCB算法分别下降了48%和29%。To overcome the high computational demands of the video coding in motion estimation, HBS algorithm and MVCB algorithm were discussed. Adaptive Static - block Detection criterion and the adaptive initial search point prediction method based on the motion correlation were used to realize the optimization of the MVCB algorithm, which reduced the search points and effectively improved the search speed of motion estimation. The experiment results show that with the image quality guaranteed the average search points of improved algorithm reduced about 48% amt 29% respectively compared to the HBS algorithm and MVCB algorithm.

关 键 词：运动估计 块匹配 ASD准则 起点预测 

分 类 号：TN911.73[电子电信—通信与信息系统]