基于块特征分类的运动估计算法

Motion estimation based on block feature classification

运动估计作为H.264中最重要最耗时的部分,大量的算法研究都是通过减少搜索点数来降低计算量。视频序列中,人们感兴趣的往往是运动的物体,背景部分一般拥有大量的静止块,帧间背景间的运动可以认为完全是由摄像机的运动引起的。利用背景块与前景块的图像特征结合MV预测提出一种新算法。该算法包括以下策略:静止块判断、背景块、前景块和边缘块的检测、起点预测和搜索窗口的改进,同时引进了边缘检测技术。实验结果表明,该算法与全搜索算法(FS)、UMHex、SUMHex相比,搜索时间减少了,而搜索精度接近FS,码率只有很小的增加。

Motion estimation is the most important and time-consuming part in H. 264. A large number of algorithms are based on the reduction of search points to reduce the computational complexity. In video sequence, people are often interested in moving objects. There are many static blocks in background, and the movement between the two different background of inter-frames is often considered as a result of camera moving. According to image feature of background block and foreground block and using M.V prediction, we propose a new algorithm. [t is based on these strategies, including static block determination, background-block, foreground-block and edge-block detection, start point prediction and the improvement of search window. Comparing with fast-full search algorithm （FFS）, UMHex and SUMHex, experimental results reveal that our algorithm can reduce motion estimation time, while the PSNR value is kept approximate to FFS,with a slight increase in bit rate.