Joint Encoding and Enhancement for Low-Light Video Analytics in Mobile Edge Networks

IF 7.7 2区 计算机科学 Q1 COMPUTER SCIENCE, INFORMATION SYSTEMS
Yuanyi He;Peng Yang;Tian Qin;Jiawei Hou;Ning Zhang
{"title":"Joint Encoding and Enhancement for Low-Light Video Analytics in Mobile Edge Networks","authors":"Yuanyi He;Peng Yang;Tian Qin;Jiawei Hou;Ning Zhang","doi":"10.1109/TMC.2024.3514214","DOIUrl":null,"url":null,"abstract":"In this paper, we present our design and analysis of a Joint Encoding and Enhancement (JEE) system for low-light video analytics in mobile edge networks. First, it is observed that, relying solely on a single pipeline for encoding and enhancement of mobile videos proves insufficient, because of the fluctuations in end-edge bandwidth and computing resources. Therefore, two distinct pipelines are introduced in the JEE system, namely, the encode-decode-enhance pipeline and the enhance-encode-decode pipeline. We then characterize the relationship of accuracy, transmission overhead, and computing overhead of these two pipelines through extensive experiments. Considering the significant demands of transmission and computing for low-light videos, we formulate an optimization problem to strike a balance between accuracy and delay, where the available end-edge bandwidth and computing resources are unknown in advance. To solve this mixed-integer nonlinear programming problem, we propose an algorithm based on online gradient descent, enabling adaptive pipeline selection and joint encoding and enhancement configuration. Theoretical analysis indicates that the proposed algorithm achieves sub-linear dynamic regret, highlighting its capability to the accuracy improvement and delay reduction in online environments. Experimental comparison against baselines demonstrates that, JEE can achieve up to a 27.32% increase in accuracy and a 26.18% reduction in delay.","PeriodicalId":50389,"journal":{"name":"IEEE Transactions on Mobile Computing","volume":"24 4","pages":"3330-3345"},"PeriodicalIF":7.7000,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Transactions on Mobile Computing","FirstCategoryId":"94","ListUrlMain":"https://ieeexplore.ieee.org/document/10787093/","RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"COMPUTER SCIENCE, INFORMATION SYSTEMS","Score":null,"Total":0}
引用次数: 0

Abstract

In this paper, we present our design and analysis of a Joint Encoding and Enhancement (JEE) system for low-light video analytics in mobile edge networks. First, it is observed that, relying solely on a single pipeline for encoding and enhancement of mobile videos proves insufficient, because of the fluctuations in end-edge bandwidth and computing resources. Therefore, two distinct pipelines are introduced in the JEE system, namely, the encode-decode-enhance pipeline and the enhance-encode-decode pipeline. We then characterize the relationship of accuracy, transmission overhead, and computing overhead of these two pipelines through extensive experiments. Considering the significant demands of transmission and computing for low-light videos, we formulate an optimization problem to strike a balance between accuracy and delay, where the available end-edge bandwidth and computing resources are unknown in advance. To solve this mixed-integer nonlinear programming problem, we propose an algorithm based on online gradient descent, enabling adaptive pipeline selection and joint encoding and enhancement configuration. Theoretical analysis indicates that the proposed algorithm achieves sub-linear dynamic regret, highlighting its capability to the accuracy improvement and delay reduction in online environments. Experimental comparison against baselines demonstrates that, JEE can achieve up to a 27.32% increase in accuracy and a 26.18% reduction in delay.
移动边缘网络中微光视频分析的联合编码与增强
在本文中,我们提出了一个联合编码和增强(JEE)系统的设计和分析,用于移动边缘网络中的低光视频分析。首先,由于端缘带宽和计算资源的波动,仅依靠单一管道对移动视频进行编码和增强是不够的。因此,在JEE系统中引入了两种不同的管道,即编码-解码-增强管道和增强-编码-解码管道。然后,我们通过大量的实验来表征这两种管道的精度、传输开销和计算开销之间的关系。考虑到弱光视频在传输和计算方面的巨大需求,我们制定了一个优化问题,以在精度和延迟之间取得平衡,其中可用的端边缘带宽和计算资源是未知的。为了解决这一混合整数非线性规划问题,我们提出了一种基于在线梯度下降的自适应管道选择和联合编码和增强配置的算法。理论分析表明,该算法实现了亚线性动态遗憾,突出了其在线环境下提高精度和降低延迟的能力。与基线的实验比较表明,JEE的准确率提高了27.32%,延迟减少了26.18%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
IEEE Transactions on Mobile Computing
IEEE Transactions on Mobile Computing 工程技术-电信学
CiteScore
12.90
自引率
2.50%
发文量
403
审稿时长
6.6 months
期刊介绍: IEEE Transactions on Mobile Computing addresses key technical issues related to various aspects of mobile computing. This includes (a) architectures, (b) support services, (c) algorithm/protocol design and analysis, (d) mobile environments, (e) mobile communication systems, (f) applications, and (g) emerging technologies. Topics of interest span a wide range, covering aspects like mobile networks and hosts, mobility management, multimedia, operating system support, power management, online and mobile environments, security, scalability, reliability, and emerging technologies such as wearable computers, body area networks, and wireless sensor networks. The journal serves as a comprehensive platform for advancements in mobile computing research.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信