@article{ART003329421},
author={Pil-Seong Jeong},
title={Low-Cost Edge AI Accelerators for Real-Time Object Detection: A Comparative Analysis of Inference Performance and Cost Efficiency},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2026},
volume={31},
number={4},
pages={1-9}
TY - JOUR
AU - Pil-Seong Jeong
TI - Low-Cost Edge AI Accelerators for Real-Time Object Detection: A Comparative Analysis of Inference Performance and Cost Efficiency
JO - Journal of The Korea Society of Computer and Information
PY - 2026
VL - 31
IS - 4
PB - The Korean Society Of Computer And Information
SP - 1
EP - 9
SN - 1598-849X
AB - As the edge AI accelerator market rapidly expands, selecting optimal hardware from diverse heterogeneous platforms for real-time object detection has become a critical challenge. However, TOPS (Tera Operations Per Second) figures provided by manufacturers represent only theoretical maximums and fail to reflect real-world performance. This study empirically compares inference performance and cost efficiency for four low-cost heterogeneous edge AI accelerators: Jetson Orin Nano Super, Jetson Orin NX, Hailo-8 M.2, and Rockchip RK3588, using YOLO-series object detection models.
Experimental results demonstrate that Hailo-8 achieved 101.2 FPS for YOLOv8s, approximately 4.6 times faster than Jetson platforms. RK3588 achieved 34.6 FPS for YOLOv8n, outperforming Orin NX and Orin Nano Super. In cost efficiency (measured as FPS per USD), RK3588 and Hailo-8 showed 2.2-7.8 times better performance than Jetson platforms. Notably, YOLOv10n with NMS-free architecture exhibited poor performance on RK3588 NPU, highlighting the importance of model-accelerator compatibility. This study provides a cost-efficiency metric framework for edge AI platform selection.
KW - Edge AI;Heterogeneous Accelerator;Object Detection;YOLO;Benchmarking;Cost Efficiency
DO -
UR -
ER -
Pil-Seong Jeong. (2026). Low-Cost Edge AI Accelerators for Real-Time Object Detection: A Comparative Analysis of Inference Performance and Cost Efficiency. Journal of The Korea Society of Computer and Information, 31(4), 1-9.
Pil-Seong Jeong. 2026, "Low-Cost Edge AI Accelerators for Real-Time Object Detection: A Comparative Analysis of Inference Performance and Cost Efficiency", Journal of The Korea Society of Computer and Information, vol.31, no.4 pp.1-9.
Pil-Seong Jeong "Low-Cost Edge AI Accelerators for Real-Time Object Detection: A Comparative Analysis of Inference Performance and Cost Efficiency" Journal of The Korea Society of Computer and Information 31.4 pp.1-9 (2026) : 1.
Pil-Seong Jeong. Low-Cost Edge AI Accelerators for Real-Time Object Detection: A Comparative Analysis of Inference Performance and Cost Efficiency. 2026; 31(4), 1-9.
Pil-Seong Jeong. "Low-Cost Edge AI Accelerators for Real-Time Object Detection: A Comparative Analysis of Inference Performance and Cost Efficiency" Journal of The Korea Society of Computer and Information 31, no.4 (2026) : 1-9.
Pil-Seong Jeong. Low-Cost Edge AI Accelerators for Real-Time Object Detection: A Comparative Analysis of Inference Performance and Cost Efficiency. Journal of The Korea Society of Computer and Information, 31(4), 1-9.
Pil-Seong Jeong. Low-Cost Edge AI Accelerators for Real-Time Object Detection: A Comparative Analysis of Inference Performance and Cost Efficiency. Journal of The Korea Society of Computer and Information. 2026; 31(4) 1-9.
Pil-Seong Jeong. Low-Cost Edge AI Accelerators for Real-Time Object Detection: A Comparative Analysis of Inference Performance and Cost Efficiency. 2026; 31(4), 1-9.
Pil-Seong Jeong. "Low-Cost Edge AI Accelerators for Real-Time Object Detection: A Comparative Analysis of Inference Performance and Cost Efficiency" Journal of The Korea Society of Computer and Information 31, no.4 (2026) : 1-9.
