Edge-Based Video Stream Generation for Multi-Party Mobile Augmented Reality
Edge-Based Video Stream Generation for Multi-Party Mobile Augmented Reality
复制标题
用于多方移动增强现实的基于边缘的视频流生成
DOI：
10.1109/tmc.2022.3232543
复制
发表时间：
2024-01
影响因子：
7.9
通讯作者：
Jiangchuan Liu
中科院分区：
文献类型：
--
作者：
Lei Zhang;Ximing Wu;Feng Wang;Andy Sun;Laizhong Cui;Jiangchuan Liu
随着移动的设备的普及和移动的网络技术的不断进步，在轻量级的移动的设备上运行在线增强现实（AR）比在笨重昂贵、难以满足用户的头戴式设备上运行要理想得多。移动的边缘计算可以帮助支持在移动的设备上运行的AR应用程序，这可以满足计算密集型和延迟敏感型的要求。然而，受限于有限且异构的边缘资源，将任务卸载到边缘设备并不容易，特别是如果应用程序需要多方交互。开发一个可靠的任务放置方案，满足用户体验，灵活地使用边缘资源是具有挑战性的。本文研究了多方移动的增强现实系统中AR叠加渲染的任务卸载布局问题。我们首先提出了我们对边缘设备性能瓶颈的观察，并解释了分割AR叠加渲染管道的必要性。然后，我们制定了一个联合优化问题的任务放置决策，旨在最大限度地提高用户体验的质量和最小化的服务成本。我们开发了一种基于深度强化学习（DRL）的新决策方法来解决这个复杂的问题。最后通过大量的评价实验验证了该方法的有效性和优越性。
With the popularity of mobile devices and the continuous advancement of mobile network technology, running online augmented reality (AR) on lightweight mobile devices is much more desirable than on heavy and expensive head-mounted devices that are difficult to satisfy users. Mobile edge computing can assist in supporting AR applications running on mobile devices, which copes with compute-intensive and delay-sensitive requirements. However, subject to the limited and heterogeneous edge resources, offloading tasks to edge devices is not easy, especially if the application requires multi-party interaction. It is challenging to develop a credible task placement scheme that satisfies user experience with flexible use of edge resources. This article focus on the task offloading placement problem for AR overlay rendering in multi-party mobile augmented reality system. We first present our observations about performance bottlenecks of edge devices and explain the necessity of splitting the AR overlay rendering pipeline. We then formulate a joint optimization problem of task placement decisions, aiming to maximize the user experience of quality and minimize the service cost. We develop a novel decision approach based on deep reinforcement learning (DRL) to address this complex problem. Finally, we verify the effectiveness and superiority of the proposed method through extensive evaluation experiments.
登录
查看更多内容
Cuttlefish：实时增强现实中视频分析的神经配置适应
DOI：
10.1109/tpds.2020.3035044
发表时间：
2021-04
期刊：
IEEE Transactions on Parallel and Distributed Systems (TPDS, CCF-A类期刊)
影响因子：
--
作者：
Ning Chen;Siyi Quan;Sheng Zhang;Zhuzhong Qian;Yibo Jin;Jie Wu;Wenzhong Li;Sanglu Lu
通讯作者：
Sanglu Lu
影响因子：
--
作者：
Duan Li;Xiaoling Sun
通讯作者：
Duan Li;Xiaoling Sun
DOI：
10.13140/rg.2.2.11200.05124/1
发表时间：
2021-10
期刊：
ArXiv
影响因子：
--
作者：
Lik-Hang Lee;Tristan Braud;Pengyuan Zhou;Lin Wang;Dianlei Xu;Zijun Lin;Abhishek Kumar;Carlos Bermejo;Pan Hui
通讯作者：
Lik-Hang Lee;Tristan Braud;Pengyuan Zhou;Lin Wang;Dianlei Xu;Zijun Lin;Abhishek Kumar;Carlos Bermejo;Pan Hui
影响因子：
9.3
作者：
Jinke Ren;Yinghui He;Guan Huang;Guanding Yu;Yunlong Cai;Zhaoyang Zhang
通讯作者：
Jinke Ren;Yinghui He;Guan Huang;Guanding Yu;Yunlong Cai;Zhaoyang Zhang
DOI：
10.1145/2491266.2491273
发表时间：
2013-03
期刊：
ArXiv
影响因子：
--
作者：
Yuehua Wu;Chuan Wu;Bo Li;F. Lau
通讯作者：
Yuehua Wu;Chuan Wu;Bo Li;F. Lau