Do We Need Sophisticated System Design for Edge-assisted Augmented Reality?

被引：3

作者：

Meng, Jiayi ^{[1
]}

Kong, Jonny ^{[1
]}

Hu, Charlie ^{[1
]}

Choi, Mun Gi ^{[2
]}

Lal, Dhananjay ^{[2
]}

机构：

[1] Purdue Univ, W Lafayette, IN 47907 USA

[2] Charter Commun, Stamford, CT USA

来源：

PROCEEDINGS OF THE 5TH INTERNATIONAL WORKSHOP ON EDGE SYSTEMS, ANALYTICS AND NETWORKING (EDGESYS'22) | 2022年

基金：

美国国家科学基金会;

关键词：

Edge-assisted Augmented Reality; Deep Neural Network; Object Detection; Video Compression;

D O I：

10.1145/3517206.3526267

中图分类号：

TP3 [计算技术、计算机技术];

学科分类号：

0812 ;

摘要：

We revisit the performance of a canonical system design for edge-assisted AR that simply combines off-the-shelf H.264 video encoding with a standard object tracking technique. Our experimental analysis shows that the simple canonical design for edge-assisted object detection can achieve within 3.07%/1.51% of the accuracy of ideal offloading (which assumes infinite network bandwidth and the total network transmission time of a single RTT) under LTE/5G mmWave networks. Our findings suggest that recent trend towards sophisticated system architecture design for edge-assisted AR appears unnecessary. We provide insights for why video compression plus on-device object tracking is so effective in edge-assisted object detection, draw implications to edge-assisted AR research, and pose open problems that warrant further investigation into this surprise finding.

引用

页码：7 / 12

页数：6

共 50 条

[21] A Performance Analysis Modeling Framework for Extended Reality Applications in Edge-Assisted Wireless Networks
Mallik, Anik
Xie, Jiang
Hank, Zhu
2024 IEEE 44TH INTERNATIONAL CONFERENCE ON DISTRIBUTED COMPUTING SYSTEMS, ICDCS 2024, 2024, : 726 - 737
[22] Edge-Assisted Object Detection Using Eye Tracking Function of Mixed Reality Devices
Yamashita, Mitsuhiro
Bandai, Masaki
2023 IEEE INTERNATIONAL CONFERENCE ON CONSUMER ELECTRONICS, ICCE, 2023,
[23] Distributed Query Processing in the Edge-Assisted IoT Data Monitoring System
Cai, Zhipeng
Shi, Tuo
IEEE INTERNET OF THINGS JOURNAL, 2021, 8 (16) : 12679 - 12693
[24] WHY, TO MANIPULATE REALITY, DO WE NEED TO REDUCE IT?
Demo, Pedro
da Silva, Renan Antonio
REVISTA PRAXIS EDUCACIONAL, 2020, 16 (40): : 457 - 474
[25] DO WE NEED SOPHISTICATED MEASUREMENTS FOR BONE-MINERAL ANALYSIS - COMMENTARY
CANN, CE
JOURNAL OF COMPUTER ASSISTED TOMOGRAPHY, 1985, 9 (03) : 639 - 641
[26] An Edge-Assisted and Smart System for Real-Time Pain Monitoring
Naeini, Emad Kasaeyan
Shahhosseini, Sina
Subramanian, Ajan
Yin, Tingjue
Rahmani, Amir M.
Dutt, Nikil
2019 4TH IEEE/ACM INTERNATIONAL CONFERENCE ON CONNECTED HEALTH: APPLICATIONS, SYSTEMS AND ENGINEERING TECHNOLOGIES (CHASE), 2019, : 47 - 52
[27] Measurement-driven Analysis of an Edge-Assisted Object Recognition System
Galanopoulos, Apostolos
Valls, Victor
Iosifidis, George
Leith, Douglas J.
ICC 2020 - 2020 IEEE INTERNATIONAL CONFERENCE ON COMMUNICATIONS (ICC), 2020,
[28] Learning-Based Edge-Assisted UAV Object Detection Against Jamming for Extended Reality
Ye, Liqing
Zhang, Jinming
Chen, Haoyu
Lin, Zhiping
Li, Jieling
Lv, Zefang
Xiao, Liang
2024 IEEE/CIC INTERNATIONAL CONFERENCE ON COMMUNICATIONS IN CHINA, ICCC, 2024,
[29] Demo Abstract: Pixel Similarity-Based Content Reuse in Edge-Assisted Virtual Reality
Chen, Ying
Inaltekin, Hazer
Gorlatova, Maria
IEEE INFOCOM 2022 - IEEE CONFERENCE ON COMPUTER COMMUNICATIONS WORKSHOPS (INFOCOM WKSHPS), 2022,
[30] KIND OF SYSTEM WE DO NOT NEED
不详
WEST VIRGINIA MEDICAL JOURNAL, 1977, 73 (11) : 306 - 307

← 1 2 3 4 5 →