This study aimed to quantitatively measure object recognition inference performance, a representative application in edge computing environments. For this purpose, YOLOv8n was executed by applying PyTorch versions 1.11, 2.0, 2.4, and 2.7 to Raspberry Pi 4, Raspberry Pi 5, LattePanda 3 Delta, Jetson Nano, and Jetson AGX Orin boards, as well as an x86 legacy server. Experimental results showed that boards equipped with GPUs recorded faster inference speeds than CPU-based boards. Among these, despite its lower CPU performance, the Jetson Nano, leveraging GPU acceleration, reduced processing time by approximately 29% compared to the LattePanda 3 Delta. Particularly, the Jetson AGX Orin exhibited the fastest performance in both GPU and CPU environments, recording 14ms in the GPU environment and 170ms in the CPU environment. It was also confirmed that differences in PyTorch versions could affect performance. Furthermore, applicable edge computing application areas for each board were suggested based on the observed performance.
목차
Abstract 1. INTRODUCTION 2. EMBEDDED BOARDS 3. YOLOv8 MODEL AND PYTORCH FRAMEWORK 4. EXPERIMENTS AND RESULTS 5. CONCLUSION Acknowledgement REFERENCES
국제문화기술진흥원 [The International Promotion Agency of Culture Technology]
설립연도
2009
분야
공학>공학일반
소개
본 진흥원은 문화기술(Culture Technology) 관련 산·학·연·관으로 구성된 비영리 단체이다. 문화기술(CT)은 정보통신기술(ICT), 문화적 사고 기반의 예술, 인문학, 디자인, 사회과학기술이 접목된 신융합기술(New Convergence Technology, NCT)로 정의한다. 인간의 삶의 질을 향상시키고, 진보된 방향으로 변화시키고, 문화기술 관련 분야의 학술 및 기술의 발전과 진흥에 공헌하기 위하여, 제3조의 필요한 사업을 행함을 그 목적으로 한다.
간행물
간행물명
International Journal of Advanced Culture Technology(IJACT)
간기
계간
pISSN
2288-7202
eISSN
2288-7318
수록기간
2013~2025
등재여부
KCI 등재
십진분류
KDC 600DDC 700
이 권호 내 다른 논문 / International Journal of Advanced Culture Technology(IJACT) Volume 13 Number 4