一种运动搜索算法的优化模型设计  

Optimization model of motion search algorithm

作　　者：史久根[1,2] 张超[1] 许林[1] 

机构地区：[1]合肥工业大学计算机与信息学院,合肥230009 [2]合肥工大高科信息技术有限责任公司,合肥230000

出　　处：《计算机应用研究》2010年第8期3147-3149,共3页Application Research of Computers

基　　金：国家"863"计划资助项目(2004AA001210)

摘　　要：为了减少运动估计中全搜索过程的运算量,提出了一种运动搜索算法的优化模型。通过对运动搜索区域和搜索顺序的优化,缩小了全搜索范围并提高了匹配块搜索的速度。实验结果表明,在图像质量得到优化的前提下,较全搜索算法,该模型在不同频率的视频序列中搜索速度有了大幅的提高。In order to reduce the computation of full-search algorithm in the motion estimation,this paper proposed a optimization model of a motion search algorithm. The model narrowed the scope of the full search and accelerated the search process of the block-matching through optimizing the scope and method of the motion search. The experimental results show that the search speed of the mode has been significantly improved in the video sequences of different frequencies under the premise of optimizing the image quality,compared with the full-search algorithm.

关 键 词：运动估计 全搜索算法 运动搜索 块匹配 

分 类 号：TN919.81[电子电信—通信与信息系统]