面向稳健传输的SVC视频层次自适应选择算法  

Layer adaptive selecting algorithm of SVC video for robust transmission

作　　者：钱洋 龚秋石[2] Qian Yang;Gong Qiushi(School of Cyber Science and Engineering,Southeast University,Jiangsu Nanjing 211189;Research Base of International Cyberspace Governance(Southeast University),Jiangsu Nanjing 211189)

机构地区：[1]东南大学网络空间安全学院,江苏南京211189 [2]网络空间国际治理研究基地(东南大学),江苏南京211189

出　　处：《网络空间安全》2020年第8期92-97,125,共7页Cyberspace Security

基　　金：赛尔网络下一代互联网技术创新项目(项目编号:NGII20180114)。

摘　　要：文章针对动态网络环境中视频自适应传输问题,提出了一种可伸缩视频层次自适应选择算法。算法从提升用户体验质量的角度出发,将层次决策问题建模为一个马尔可夫决策过程模型,每次决策前计算出在当前状态下能够获得的最大的长期回报,以此为根据选择合适的层次提取发送。同时,通过仿真实验,分析这种本算法在有丢包与带宽波动的网络环境下的算法性能,算法能够保证较高的视频质量和均衡的缓存,带给用户更好的体验质量。Aiming at the problem of video transmission in the fluctuating network,this paper employs scalable video coding and proposes an adaptive layer selecting algorithm for scalable video.The algorithm models the adaptive transmission problem as a Markov decision process model,and calculates the maximum long-term reward that can be obtained in the current state before each decision,and then selects the appropriate layer to extract and send to optimize the quantitative QoE of the user.The simulation is conducted under scenarios with packet loss and bandwidth fluctuations respectively and the numerical results show that the algorithm can ensure higher video quality and balanced cache,and bring users a better experience quality.

关 键 词：可伸缩视频编码 层次自适应选择 马尔科夫决策过程 用户体验质量 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]