Real-Time Object Detection with Automatic Switching between Single-Board Computers and the Cloud
Osman, Ahmed and Abozariba, Raouf and Asyhari, A. Taufiq and Aneiba, Adel and Hussain, Ambreen and Barua, Bidushi and Azeem, Moazam (2022) Real-Time Object Detection with Automatic Switching between Single-Board Computers and the Cloud. In: 2021 IEEE Symposium Series on Computational Intelligence (SSCI), December 5th – 7th 2021, Orlando, Florida, USA.
Preview |
Text
SSCI_Object_detection__Copy_-2.pdf - Accepted Version Download (654kB) |
Abstract
We present a wireless real-time object detection system utilizing single-board devices, cloud computing platforms and web-streaming. Currently, most inference applications stat- ically perform tasks either on local machines or remote cloud servers. However, devices connected through cellular technolo- gies face volatile network conditions, compromising detection performance. Furthermore, while the limited computing power of single-board computers degrade detection correctness, exces- sive power consumption of machine learning models used for inference reduces operation time. In this paper, we propose a dynamic system that monitors embedded device’s wireless link quality and battery level to decide on detecting objects locally or remotely. The experimental results show that our dynamic offloading approach could reduce devices’ energy usage while achieving high accuracy, real-time object detection.
Index Terms—Machine learning, WebRTC, object detection.
Item Type: | Conference or Workshop Item (Paper) |
---|---|
Identification Number: | 10.1109/SSCI50451.2021.9660166 |
Dates: | Date Event 2 October 2021 Accepted 24 January 2022 Published Online |
Uncontrolled Keywords: | Machine learning, WebRTC, object detection |
Subjects: | CAH11 - computing > CAH11-01 - computing > CAH11-01-01 - computer science |
Divisions: | Faculty of Computing, Engineering and the Built Environment > College of Computing |
Depositing User: | Ahmed Osman |
Date Deposited: | 06 Dec 2021 10:28 |
Last Modified: | 24 Jan 2023 03:00 |
URI: | https://www.open-access.bcu.ac.uk/id/eprint/12504 |
Actions (login required)
![]() |
View Item |