arrow
返回

Optimizing Face Recognition Inference with a Collaborative Edge-Cloud Network

delete2022-11-01
delete5
delete
OA
AI
O
Oroceo, Paul P.
J
Jeongin Kim
E
Ej Miguel Francisco Caliwag
S
Sangho Kim *
W
Wansu Lim *
DOI:10.3390/s22218371delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
The rapid development of deep-learning-based edge artificial intelligence applications and their data-driven nature has led to several research issues. One key issue is the collaboration of the edge and cloud to optimize such applications by increasing inference speed and reducing latency. Some researchers have focused on simulations that verify that a collaborative edge-cloud network would be optimal, but the real-world implementation is not considered. Most researchers focus on the accuracy of the detection and recognition algorithm but not the inference speed in actual deployment. Others have implemented such networks with minimal pressure on the cloud node, thus defeating the purpose of an edge-cloud collaboration. In this study, we propose a method to increase inference speed and reduce latency by implementing a real-time face recognition system in which all face detection tasks are handled on the edge device and by forwarding cropped face images that are significantly smaller than the whole video frame, while face recognition tasks are processed at the cloud. In this system, both devices communicate using the TCP/IP protocol of wireless communication. Our experiment is executed using a Jetson Nano GPU board and a PC as the cloud. This framework is studied in terms of the frame-per-second (FPS) rate. We further compare our framework using two scenarios in which face detection and recognition tasks are deployed on the (1) edge and (2) cloud. The experimental results show that combining the edge and cloud is an effective way to accelerate the inferencing process because the maximum FPS achieved by the edge-cloud deployment was 1.91x more than the cloud deployment and 8.5x more than the edge deployment.
Keyword:
deep learning
edge-cloud
face recognition
real-time
TCP
IP
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Sensors 封面图
Sensors
IF:
3.5
论文数:
7.3W
被引数:
26.5W

机构

K
kumoh national university technology
学者数:
38
论文数: 64
被引数: 1.1K
引用论文

引用论文

Regulation and Functions of the lms Homeobox Gene during Development of Embryonic Lateral Transverse Muscles and Direct Flight Muscles in Drosophila
err2010-12-15
err0
errOAAI
errDominik Müller; Teresa Jagla; Ludivine Mihaila Bodart; Nina Jährling; Hans-Ulrich Dodt; Krzysztof Jagla; Manfred Frasch
err分享
err收藏
Advances in the Chemistry of AliphaticN-Nitrosamines
err2007-10-17
err0
PREAI
errA L Fridman; F M Mukhametshin; Sergei S Novikov
err分享
err收藏
Combined Pharmacophore Modeling, 3D-QSAR, Molecular Docking and Molecular Dynamics Study on Indolyl-aryl-sulfone Derivatives as New HIV1 Inhibitors
err2022-06-15
err0
errOAAI
errMebarka Ouassaf; Faizan Abul Qais; Salah Belaidi; Mohamed Bakhouch; Ahmed Said Mohamed; Samir Chtita
err分享
err收藏
An IoT Machine Learning-Based Mobile Sensors Unit for Visually Impaired People
errSENSORS
IF3.5
err2022-07-12
err12
errOAAI
errDhou, Salam; Alnabulsi, Ahmad; Al-Ali, A. R.; Arshi, Mariam; Darwish, Fatima; Almaazmi, Sara; Alameeri, Reem
err分享
err收藏
Joint Face Detection and Alignment Using Multitask Cascaded Convolutional Networks
err2016-10-01
err1.7K
errOAAI
errZhang, Kaipeng; Zhang, Zhanpeng; Li, Zhifeng; Qiao, Yu
err分享
err收藏
Manganese transport through human erythrocyte membranes. An EPR study
err1997-09-01
err0
PREAI
errConstantin Mihai Lucaciu; Cristina Dragu; Lorelai Copăescu; Vasile V Morariu
err分享
err收藏
学者 查看更多内容