摘要
针对高效率视频编码(HEVC)帧间预测高额的计算复杂度,提出一种利用已编码块的相关信息进行快速帧间预测的算法.首先,在每个深度级上,利用当前编码单元联合其时空上最近的所有已编码单元的运动矢量(MV)长度,提前决定2 N×2 N的预测单元(PU)分割尺寸.其次,利用当前深度层获得的率失真代价(RDcost),结合离线统计出设置的阈值,终止满足条件的编码单元的进一步分割进程.实验结果表明:文中算法可以节省37.8%的编码时间,并取得与原始算法几乎相同的率失真性能.
In order to further reduce the great computational complexity for high efficiency video coding (HEVC)inter prediction,a novel algorithm using the information of encoded CUs has been proposed in this paper.Firstly,at each depth level,the lengths of all the MVs which are from current CU and spatially or tem-porarily adjacent CUs are used to decide 2N×2N partition early.Secondly,by using the minimum RDcost of current CU and the off-line pre-set threshold values,the split of CUs which meet the requirements can be early termination.Experimental results show that the proposed algorithm can save an average of 37.8% of the enco-ding time with negligible loss of coding efficiency compared with the original algorithm.
出处
《华侨大学学报(自然科学版)》
CAS
北大核心
2016年第4期486-491,共6页
Journal of Huaqiao University(Natural Science)
基金
福建省自然科学基金资助项目(2012J01275)