ETRI-Knowledge Sharing Plaform

KOREAN
논문 검색
Type SCI
Year ~ Keyword

Detail

Conference Paper Image Classification on Resource-Constrained Microcontrollers
Cited 1 time in scopus Share share facebook twitter linkedin kakaostory
Authors
Seungtae Hong, Gunju Park, Jeong-Si Kim
Issue Date
2023-10
Citation
International Conference on Information and Communication Technology Convergence (ICTC) 2023, pp.1453-1455
Publisher
IEEE
Language
English
Type
Conference Paper
DOI
https://dx.doi.org/10.1109/ICTC58733.2023.10393661
Abstract
Recently, as IoT devices have become popular, research to perform deep learning in small devices such as microcontrollers has been attempted. Microcontrollers have very limited resources compared to edge devices such as mobiles. Therefore, in order to perform deep learning-based image classification in a microcontroller, an optimization technique considering HW constraints is required. To this end, in this paper, we present a method for light weighting a model so that it can be executed in a microcontroller, and a process for distributing the lightweight model to a microcontroller. Finally, it was confirmed that image classification can be performed in an actual microcontroller through STM32F746G-Discovery.
KSP Keywords
Edge devices, Image classification, IoT Devices, Learning-based, Light weighting, Lightweight model, Limited resources, Optimization techniques(OT), Resource-constrained, Small devices, deep learning(DL)