Emerging mobile virtual reality (VR) systems will require to continuously
perform complex computer vision tasks on ultra-high-resolution video frames
through the execution of deep neural networks (DNNs)-based algorithms. Since
state-of-the-art DNNs require computational power that is excessive for mobile
devices, techniques based on wireless edge computing (WEC) have been recently
proposed. However, existing WEC methods require the transmission and processing
of a high amount of video data which may ultimately saturate the wireless link.
In this paper, we propose a novel Sensing-Assisted Wireless Edge Computing
(SAWEC) paradigm to address this issue. SAWEC leverages knowledge about the
physical environment to reduce the end-to-end latency and overall computational
burden by transmitting to the edge server only the relevant data for the
delivery of the service. Our intuition is that the transmission of the portion
of the video frames where there are no changes with respect to previous frames
can be avoided. Specifically, we leverage wireless sensing techniques to
estimate the location of objects in the environment and obtain insights about
the environment dynamics. Hence, only the part of the frames where any
environmental change is detected is transmitted and processed. We evaluated
SAWEC by using a 10K 360$^{\circ}$ camera with a Wi-Fi 6 sensing system
operating at 160 MHz and performing localization and tracking. We perform
experiments in an anechoic chamber and a hall room with two human subjects in
six different setups. Experimental results show that SAWEC reduces the channel
occupation, and end-to-end latency by 93.81%, and 96.19% respectively while
improving the instance segmentation performance by 46.98% with respect to
state-of-the-art WEC approaches. For reproducibility purposes, we pledge to
share our whole dataset and code repository.

提出了一种新颖的感知辅助无线边缘计算 (SAWEC) 范式来解决基于深度神经网络 (DNNs) 的算法在移动虚拟现实 (VR) 系统中进行复杂计算机视觉任务的问题，SAWEC 通过利用对物理环境的认知来减少端到端延迟和整体计算负担，通过仅传输和处理为服务提供方交付相关数据的视频帧的部分来实现，实验证明 SAWEC 相对于现有的无线边缘计算方法，在减少信道占用和端到端延迟方面分别提高了 93.81% 和 96.19%，同时相对于现有技术的无线边缘计算方法，在实例分割性能方面提高了 46.98%。

SAWEC: 传感辅助无线边缘计算

SAWEC: Sensing-Assisted Wireless Edge Computing

Mobile virtual reality (VR) delivery is gaining increasing attention from
both industry and academia due to its ability to provide an immersive
experience. However, achieving mobile VR delivery requires ultra-high
transmission rate, deemed as a first killer application for 5G wireless
networks. In this paper, in order to alleviate the traffic burden over wireless
networks, we develop an implementation framework for mobile VR delivery by
utilizing caching and computing capabilities of mobile VR device. We then
jointly optimize the caching and computation offloading policy for minimizing
the required average transmission rate under the latency and local average
energy consumption constraints. In a symmetric scenario, we obtain the optimal
joint policy and the closed-form expression of the minimum average transmission
rate. Accordingly, we analyze the tradeoff among communication, computing and
caching, and then reveal analytically the fact that the communication overhead
can be traded by the computing and caching capabilities of mobile VR device,
and also what conditions must be met for it to happen. Finally, we discuss the
optimization problem in a heterogeneous scenario, and propose an efficient
suboptimal algorithm with low computation complexity, which is shown to achieve
good performance in the numerical results.

为了实现移动虚拟现实的传输，利用移动 VR 设备的缓存和计算能力，共同优化缓存和计算卸载策略，以减少网络流量和传输速率，并揭示通信，计算和缓存之间的权衡以及在异构场景中的优化问题。

移动 VR 传递的通讯、计算和缓存：建模与折衷

Communication, Computing and Caching for Mobile VR Delivery: Modeling  and Trade-off

Mobile virtual reality (VR) head mounted displays (HMD) have become popular
among consumers in recent years. In this work, we demonstrate real-time
egocentric hand gesture detection and localization on mobile HMDs. Our main
contributions are: 1) A novel mixed-reality data collection tool to automatic
annotate bounding boxes and gesture labels; 2) The largest-to-date egocentric
hand gesture and bounding box dataset with more than 400,000 annotated frames;
3) A neural network that runs real time on modern mobile CPUs, and achieves
higher than 76% precision on gesture recognition across 8 classes.

本文演示了在移动 VR 头戴式显示器上实时实现自我中心手势检测和定位的方法。通过创新的混合现实数据收集工具，以及超过 400,000 帧的最大自我中心手势和边界框数据集，在现代移动 CPU 上实现的神经网络可以在 8 个类别中实现超过 76％的手势识别精度。