On-Device Optimisation and Implementation of Deep Learning-Based Ultra-High-Resolution Camera Solutions

IF 0.8 4区 工程技术 Q4 ENGINEERING, ELECTRICAL & ELECTRONIC
Hyunhee Park, Kyeongjun Kim, Sangmin Lee, Minkyu Park, Youngjo Kim
{"title":"On-Device Optimisation and Implementation of Deep Learning-Based Ultra-High-Resolution Camera Solutions","authors":"Hyunhee Park,&nbsp;Kyeongjun Kim,&nbsp;Sangmin Lee,&nbsp;Minkyu Park,&nbsp;Youngjo Kim","doi":"10.1049/ell2.70425","DOIUrl":null,"url":null,"abstract":"<p>This paper presents an optimisation method to enhance the operating speed and reduce memory usage for implementing deep learning-based ultra-high-resolution camera solutions on mobile devices. We detail the final implementation results and propose practical methodologies for deploying high-resolution and computationally complex image solutions on mobile platforms. Specifically, we demonstrate an optimised implementation of a deep learning-based camera solution pipeline by leveraging heterogeneous computing, processor-specific optimisations and memory reuse techniques. The proposed approach is applied to a 200 MP camera solution and commercialised for the Samsung Galaxy S23 Ultra. Experimental evaluations on the S23 Ultra device reveal that while the initial implementation required 2.79 GB of memory exceeding the operational capacity of mobile devices, our optimisation techniques reduced memory usage to 490 MB and achieved a processing time of 3.95 s that enables efficient on-device operation.</p>","PeriodicalId":11556,"journal":{"name":"Electronics Letters","volume":"61 1","pages":""},"PeriodicalIF":0.8000,"publicationDate":"2025-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ietresearch.onlinelibrary.wiley.com/doi/epdf/10.1049/ell2.70425","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Electronics Letters","FirstCategoryId":"5","ListUrlMain":"https://ietresearch.onlinelibrary.wiley.com/doi/10.1049/ell2.70425","RegionNum":4,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q4","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0

Abstract

This paper presents an optimisation method to enhance the operating speed and reduce memory usage for implementing deep learning-based ultra-high-resolution camera solutions on mobile devices. We detail the final implementation results and propose practical methodologies for deploying high-resolution and computationally complex image solutions on mobile platforms. Specifically, we demonstrate an optimised implementation of a deep learning-based camera solution pipeline by leveraging heterogeneous computing, processor-specific optimisations and memory reuse techniques. The proposed approach is applied to a 200 MP camera solution and commercialised for the Samsung Galaxy S23 Ultra. Experimental evaluations on the S23 Ultra device reveal that while the initial implementation required 2.79 GB of memory exceeding the operational capacity of mobile devices, our optimisation techniques reduced memory usage to 490 MB and achieved a processing time of 3.95 s that enables efficient on-device operation.

Abstract Image

Abstract Image

Abstract Image

Abstract Image

基于深度学习的超高分辨率相机解决方案的设备上优化和实现
本文提出了一种在移动设备上实现基于深度学习的超高分辨率相机解决方案的优化方法,以提高操作速度并减少内存使用。我们详细介绍了最终的实施结果,并提出了在移动平台上部署高分辨率和计算复杂图像解决方案的实用方法。具体来说,我们通过利用异构计算、处理器特定优化和内存重用技术,展示了基于深度学习的相机解决方案管道的优化实现。该方法将应用于200万像素的摄像头解决方案,并将在三星Galaxy S23 Ultra上实现商业化。对S23 Ultra设备的实验评估显示,虽然最初的实现需要2.79 GB的内存,超过了移动设备的操作容量,但我们的优化技术将内存使用量减少到490 MB,并实现了3.95 s的处理时间,从而实现了高效的设备上操作。
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
Electronics Letters
Electronics Letters 工程技术-工程:电子与电气
CiteScore
2.70
自引率
0.00%
发文量
268
审稿时长
3.6 months
期刊介绍: Electronics Letters is an internationally renowned peer-reviewed rapid-communication journal that publishes short original research papers every two weeks. Its broad and interdisciplinary scope covers the latest developments in all electronic engineering related fields including communication, biomedical, optical and device technologies. Electronics Letters also provides further insight into some of the latest developments through special features and interviews. Scope As a journal at the forefront of its field, Electronics Letters publishes papers covering all themes of electronic and electrical engineering. The major themes of the journal are listed below. Antennas and Propagation Biomedical and Bioinspired Technologies, Signal Processing and Applications Control Engineering Electromagnetism: Theory, Materials and Devices Electronic Circuits and Systems Image, Video and Vision Processing and Applications Information, Computing and Communications Instrumentation and Measurement Microwave Technology Optical Communications Photonics and Opto-Electronics Power Electronics, Energy and Sustainability Radar, Sonar and Navigation Semiconductor Technology Signal Processing MIMO
×
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:604180095
Book学术官方微信