基于像素递归失真估计的率失真优化模式选择算法  

Rate-distortion optimized mode selection algorithm based on recursive optimal per-pixel estimation

作　　者：唐浩漾[1] 王文庆[1] 王曙光[1] 

机构地区：[1]西安邮电大学自动化学院,陕西西安710121

出　　处：《西北大学学报（自然科学版）》2014年第1期51-56,共6页Journal of Northwest University（Natural Science Edition）

基　　金：国家自然科学基金资助项目(60902052);陕西省自然科学基金资助项目(2012JM8022;2011JM8003);陕西省教育厅自然科学基金资助项目(12JK0540)

摘　　要：为了改善视频数据在差错信道上传输的鲁棒性,结合H.264/AVC标准的多模式划分特点,提出了一种基于像素递归失真估计的率失真优化模式选择算法。该算法针对H.264/AVC中的多种帧内和帧间预测模式,对像素的递归失真估计方法进行改进,准确估计了差错环境下的视频失真,并采用二次率失真模型预测运动补偿编码的总码率以进行运动估计,最后运用率失真优化模型进行编码模式判决。实验结果显示,相对于H.264参考软件的模式选择算法,该算法提高了视频的差错恢复性能,能有效改善视频传输的鲁棒性。To improve the error resilient performance of video data through error-prone channel, a novel RDO mode selection algorithm based on the recursive optimal per-pixel estimate （ROPE） method is proposed in this paper. Combined with various modes prediction of H. 264/AVC, the ROPE algorithm has been modified and used to estimate the end-to-end reconstructed distortion. Then the total bit rate for motion-compensated enco- ding is predicted and performs motion estimation by a suitable rate distortion model. Finally, rate-distortion optimization is applied again to estimate the macroblock mode among inter prediction mode, skip mode and in- tra prediction mode. Compared with the mode selection algorithm in H. 264 reference software, the proposed algorithm substantially and consistently outperforms state-of-the-art RD-based mode decision methods and gets better error resilient performance.

关 键 词：视频编码 像素递归失真 率失真优化 模式选择 

分 类 号：TN919[电子电信—通信与信息系统]