Lightweight and Energy-Efficient Deep Learning Accelerator for Real-Time Object Detection on Edge Devices
Sensors · 20.01.2023 · 23 (3) · 1185
DOI: 10.3390/s23031185 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, online erschienen am 20.01.2023. Verfasst von Kyungho Kim und 4 weiteren Autor:innen. Beteiligte Einrichtung: Intelligent Image Processing Research Center, Korea Electronics Technology Institute, Seongnam-si 13488, Republic of Korea. Die Arbeit wurde bisher 61-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Korea government (MSIT), Korean government (MSIT).
Abstract (Originalsprache)
Tiny machine learning (TinyML) has become an emerging field according to the rapid growth in the area of the internet of things (IoT). However, most deep learning algorithms are too complex, require a lot of memory to store data, and consume an enormous amount of energy for calculation/data movement; therefore, the algorithms are not suitable for IoT devices such as various sensors and imaging systems. Furthermore, typical hardware accelerators cannot be embedded in these resource-constrained edge devices, and they are difficult to drive real-time inference processing as well. To perform the real-time processing on these battery-operated devices, deep learning models should be compact and hardware-optimized, and hardware accelerator designs also have to be lightweight and consume extremely low energy. Therefore, we present an optimized network model through model simplification and compression for the hardware to be implemented, and propose a hardware architecture for a lightweight and energy-efficient deep learning accelerator. The experimental results demonstrate that our optimized model successfully performs object detection, and the proposed hardware design achieves 1.25× and 4.27× smaller logic and BRAM size, respectively, and its energy consumption is approximately 10.37× lower than previous similar works with 43.95 fps as a real-time process under an operating frequency of 100 MHz on a Xilinx ZC702 FPGA.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Intelligent Image Processing Research Center, Korea Electronics Technology Institute, Seongnam-si 13488, Republic of Korea.
ORCID-Profile: Sung-Joon Jang, Eunchong Lee
Förderung
- Korea government (MSIT)
- Korean government (MSIT)
Zitieren
APA
Kim, K., Jang, S. J., Park, J., Lee, E., & Lee, S. S. (2023). Lightweight and Energy-Efficient Deep Learning Accelerator for Real-Time Object Detection on Edge Devices. Sensors, 23(3), 1185. https://doi.org/10.3390/s23031185
Vancouver
Kim K, Jang SJ, Park J, Lee E, Lee SS. Lightweight and Energy-Efficient Deep Learning Accelerator for Real-Time Object Detection on Edge Devices. Sensors. 2023;23(3):1185. doi:10.3390/s23031185
BibTeX
@article{Kim2023,
author = {Kim, Kyungho and Jang, Sung-Joon and Park, Jonghee and Lee, Eunchong and Lee, Sang-Seol},
title = {Lightweight and Energy-Efficient Deep Learning Accelerator for Real-Time Object Detection on Edge Devices},
journal = {Sensors},
year = {2023},
volume = {23},
number = {3},
pages = {1185},
doi = {10.3390/s23031185}
}
EUVIMED