一种面向MPEG码流的快速视频转码方法  

MPEG Video Transcoding with Adaptive Drifting Error Control

在线阅读下载全文

作  者:袁禄军[1] 高文[1] 吴枫[2] 李世鹏[2] 

机构地区:[1]中国科学院计算技术研究所 [2]微软亚洲研究院,北京100080

出  处:《计算机研究与发展》2006年第1期109-114,共6页Journal of Computer Research and Development

基  金:国家自然科学基金项目(60333020);国家"八六三"高技术研究发展计划基金项目(2002AA119010);国家"九七三"重点基础研究发展规划基金项目(2001CCA03300)

摘  要:将高码率的视频码流转码生成低码率的视频码流,以适应不同网络带宽的需要,这是MPEG视频转码的一个最重要的应用·存在开环和闭环两种不同结构的码率缩减视频转码器,它们在转码速度和转码后的图像质量两方面各有优势·针对这两种转码结构的优缺点,提出了一种新的漂移误差自适应的快速视频转码结构·该结构以块为基本单元自适应地控制漂移误差,同时采用合适的查表算法来降低量化和反量化运算的复杂度·实验结果表明,采用这种结构的视频转码器在转码速度上不仅远远高于闭环结构,而且也超过了传统的开环结构;在转码后的图像质量上接近闭环结构,并且远远好于开环结构·此外,这种结构的视频转码器还可以方便地扩展成为复杂度可伸缩的转码器,根据处理器的有效负荷动态地调整转码器的复杂度,更好地实现实时视频转码服务·A fast video transcoder with adaptive drifting error control is proposed in this paper. Firstly, similar to the traditional close-loop transcoder, the proposed transcoder still accumulates the re-quantization errors of each I or P picture. However, the accumulated errors are not always introduced into the transcoding loop in every block. A triple-threshold algorithm is proposed to adaptively utilize the accumulated errors at block level so as to control the drifting error under an acceptable level. Secondly, the re-quantization process can be simply implemented by looking up table, which significantly reduces the complexity of the re-quantization process. The experimental results show that the picture quality obtained from the proposed transcoder is close to that of the traditional closed-loop one while about 50% blocks are not updated with the accumulated errors. In this case, the speed of the proposed transcoder is much faster than that of the traditional close-loop one, and even faster than that of the traditional open-loop one. Furthermore, the proposed transcoder provides the desired flexibility between picture quality and transcoding complexity in CPU-awareness applications.

关 键 词:视频转码 漂移误差 闭环结构 开环结构 

分 类 号:TP391[自动化与计算机技术—计算机应用技术]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象