移动P2P视频流媒体体系下的帧位分配算法  

Frame bit assignment algorithm in mobile P2P video streaming media architecture

在线阅读下载全文

作  者:谢满德[1] 凌云[1] 魏贵义[1] 

机构地区:[1]浙江工商大学计算机与信息工程学院,浙江杭州310018

出  处:《电路与系统学报》2010年第5期46-51,共6页Journal of Circuits and Systems

基  金:国家自然科学基金项目资助项目(60673179);浙江省自然科学基金项目资助(Z106727)

摘  要:针对移动P2P流媒体系统中存在多视频源的特点,提出了多视频源串行和并行调度算法。串行调度算法,接收Peer通过实时侦测的QoS变化触发视频源的更换,并通过流序列时间模型来同步各个视频源。并行调度算法,多个视频源同时提供服务,并通过帧位分配算法分配各视频源的传输任务。帧位分配算法首先将视频序列分成包含固定帧数的块系列,然后进行块级位分配以充分考虑帧间效应。对于单个帧块位分配问题,算法将其建模成了非线性规划问题,通过引入分段线性R-D模型将该问题进一步转换成了普通的线性规划问题,并提出了一个贪婪实现策略。实验结果显示流分配算法能获得高效、平稳的视频质量,而且时间效率也非常高,能较好的满足移动P2P视频流媒体系统的实时性。In a mobile P2P architecture for streaming media system, there are multi-video-sources. Based on the feature, a serial scheduling algorithm and a parallel scheduling algorithm are proposed. If the QoS, monitored by the receiving-peer, is degraded, the serial scheduling algorithm triggers the video source change event and the multi-video source is synchronized by the time model of the streaming sequence. If the multi-video source concurrently sends the data to the receiving-peer, the parallel scheduling algorithm assigns the transmission task by frame-bit assignment strategy. The frame bit algorithm firstly divides the video sequence into a series of blocks where there is the fixed number of frames, and then assigns all bits in block level to consider the frame interaction. For a bits allocation problem of each block, it is models as a nonlinear programming problem, and then it is transformed into a general linear programming based on the piece linear R-I) model. At last a greedy algorithm is proposed. The experiment results show our algorithm has the high and smooth video quality and its time complexity is lower, which can meet with the real time requirement of mobile P2P video streaming media system.

关 键 词:移动P2P 流媒体 服务质量 分段线性R-D模型 

分 类 号:TP393.09[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