一种基于马尔科夫链模型的运动估计新方法  

A new method of motion estimation algorithm based on markov chain

作　　者：吴云[1] 曹志民[1] 唐世伟[2] 

机构地区：[1]东北石油大学电子科学学院,黑龙江大庆163318 [2]东北石油大学计算机与信息工程学院,黑龙江大庆163318

出　　处：《光学仪器》2012年第3期25-28,共4页Optical Instruments

基　　金：黑龙江省教育厅科学技术研究项目(11553011)

摘　　要：运动估计是视频编解码系统中的关键技术,而运动估计的快速块匹配算法主要是通过采用初始搜索点预测,提前退出技术以及不同的搜索模板来提高算法的效率。通过引入马尔科夫链模型实现了对初始搜索点的准确预测,以及利用模糊逻辑和遗传算法以避免搜索过程陷入局部最优点等方法,提出了一种基于马尔科夫链模型的运动估计新方法。实验结果表明,该方法能够对不同性质视频序列有很好的适应能力,并在计算成本和图像重建质量上得到了很好的折中。Motion estimation is one of the most important parts of the video encoding/decoding system. Techniques of starting point prediction, stopping if good enough, as well as the different searching pattern are always adopted by fast block-matching motion estimation algorithms to improve their efficiency. A new method based on Markov Chain Model is proposed. By inducting the MarkowChain model, accuracy prediction of the starting point is achieved. And, by exploiting genetic algorithm and fuzzy logic, it can efficiently avoid being trapped in local optimum. Experimental results illustrate that the proposed method can attain good performance among different video sequences with different motion activity.

关 键 词：运动估计 视频编解码系统 马尔科夫链模型 模糊逻辑 遗传算法 

分 类 号：TN391[电子电信—物理电子学]