当前位置: X-MOL 学术arXiv.cs.MM › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Reinforcement Learning Driven Adaptive VR Streaming with Optical Flow Based QoE
arXiv - CS - Multimedia Pub Date : 2020-03-17 , DOI: arxiv-2003.07583
Wei Quan, Yuxuan Pan, Bin Xiang, Lin Zhang

With the merit of containing full panoramic content in one camera, Virtual Reality (VR) and 360-degree videos have attracted more and more attention in the field of industrial cloud manufacturing and training. Industrial Internet of Things (IoT), where many VR terminals needed to be online at the same time, can hardly guarantee VR's bandwidth requirement. However, by making use of users' quality of experience (QoE) awareness factors, including the relative moving speed and depth difference between the viewpoint and other content, bandwidth consumption can be reduced. In this paper, we propose OFB-VR (Optical Flow Based VR), an interactive method of VR streaming that can make use of VR users' QoE awareness to ease the bandwidth pressure. The Just-Noticeable Difference through Optical Flow Estimation (JND-OFE) is explored to quantify users' awareness of quality distortion in 360-degree videos. Accordingly, a novel 360-degree videos QoE metric based on PSNR and JND-OFE (PSNR-OF) is proposed. With the help of PSNR-OF, OFB-VR proposes a versatile-size tiling scheme to lessen the tiling overhead. A Reinforcement Learning(RL) method is implemented to make use of historical data to perform Adaptive BitRate(ABR). For evaluation, we take two prior VR streaming schemes, Pano and Plato, as baselines. Vast evaluations show that our system can increase the mean PSNR-OF score by 9.5-15.8% while maintaining the same rebuffer ratio compared with Pano and Plato in a fluctuate LTE bandwidth dataset. Evaluation results show that OFB-VR is a promising prototype for actual interactive industrial VR. A prototype of OFB-VR can be found in https://github.com/buptexplorers/OFB-VR.

中文翻译:

基于光流 QoE 的强化学习驱动的自适应 VR 流媒体

虚拟现实(VR)和360度视频凭借一个摄像头包含全全景内容的优点,在工业云制造和培训领域越来越受到关注。工业物联网(IoT),需要多台VR终端同时在线,很难保证VR的带宽需求。但是,通过利用用户的体验质量(QoE)感知因素,包括视点与其他内容之间的相对移动速度和深度差异,可以减少带宽消耗。在本文中,我们提出了 OFB-VR(基于光流的 VR),这是一种 VR 流媒体交互方法,可以利用 VR 用户的 QoE 意识来缓解带宽压力。探索了通过光流估计 (JND-OFE) 的可察觉差异,以量化用户对 360 度视频质量失真的认识。因此,提出了一种基于 PSNR 和 JND-OFE (PSNR-OF) 的新型 360 度视频 QoE 度量。在 PSNR-OF 的帮助下,OFB-VR 提出了一种通用大小的平铺方案来减少平铺开销。实施强化学习(RL)方法以利用历史数据执行自适应比特率(ABR)。为了进行评估,我们以两个先前的 VR 流媒体方案 Pano 和 Plato 作为基准。大量评估表明,在波动的 LTE 带宽数据集中,与 Pano 和 Plato 相比,我们的系统可以将平均 PSNR-OF 分数提高 9.5-15.8%,同时保持相同的重新缓冲率。评估结果表明,OFB-VR 是用于实际交互式工业 VR 的有前途的原型。OFB-VR 的原型可以在 https://github.com/buptexplorers/OFB-VR 中找到。
更新日期:2020-03-24
down
wechat
bug