@article{ART003266042},
author={Dong-Hyun Kim and Du-Hwan Hur and Jeong-Hun Ha and SeungHwan Bae and Kang-Won Seo and Seung-Hwan Bae},
title={Multiprocessing-Based Parallel Pipeline for Real-Time Multi-Target Tracking on Embedded Systems},
journal={Journal of The Korea Society of Computer and Information},
issn={1598-849X},
year={2025},
volume={30},
number={11},
pages={1-10}
TY - JOUR
AU - Dong-Hyun Kim
AU - Du-Hwan Hur
AU - Jeong-Hun Ha
AU - SeungHwan Bae
AU - Kang-Won Seo
AU - Seung-Hwan Bae
TI - Multiprocessing-Based Parallel Pipeline for Real-Time Multi-Target Tracking on Embedded Systems
JO - Journal of The Korea Society of Computer and Information
PY - 2025
VL - 30
IS - 11
PB - The Korean Society Of Computer And Information
SP - 1
EP - 10
SN - 1598-849X
AB - In this paper, we propose a multiprocessing-based parallel pipeline architecture for robust real-time implementation of multi-target designation and tracking algorithms in embedded environments. While the demand for on-site complex AI vision is surging in advanced industries, real-time processing on resource-constrained embedded systems remains a significant technical challenge. The proposed architecture addresses this by separating pre-processing, inference, and post-processing into independent processes, enabling frame-level parallelism. Furthermore, it efficiently distributes computations across CPU, GPU, and NPU resources to minimize idle time and improve overall throughput. On the Jetson AGX Orin platform, the architecture achieves an 88% improvement in FPS compared to a single-process baseline with stable enhancements in tracking accuracy. In contrast, on a server using the TensorRT runtime, performance gains were limited due to conflicts with its internal optimizations. These findings demonstrate that our architecture enables the on-device implementation of complex vision AI models without high-performance servers, making it a key technology for applications such as precision-guided weapons and autonomous drones.
KW - Multi-target Tracking;Embedded System;Multiprocessing;Real-time Processing;;Parallel Execution
DO -
UR -
ER -
Dong-Hyun Kim, Du-Hwan Hur, Jeong-Hun Ha, SeungHwan Bae, Kang-Won Seo and Seung-Hwan Bae. (2025). Multiprocessing-Based Parallel Pipeline for Real-Time Multi-Target Tracking on Embedded Systems. Journal of The Korea Society of Computer and Information, 30(11), 1-10.
Dong-Hyun Kim, Du-Hwan Hur, Jeong-Hun Ha, SeungHwan Bae, Kang-Won Seo and Seung-Hwan Bae. 2025, "Multiprocessing-Based Parallel Pipeline for Real-Time Multi-Target Tracking on Embedded Systems", Journal of The Korea Society of Computer and Information, vol.30, no.11 pp.1-10.
Dong-Hyun Kim, Du-Hwan Hur, Jeong-Hun Ha, SeungHwan Bae, Kang-Won Seo, Seung-Hwan Bae "Multiprocessing-Based Parallel Pipeline for Real-Time Multi-Target Tracking on Embedded Systems" Journal of The Korea Society of Computer and Information 30.11 pp.1-10 (2025) : 1.
Dong-Hyun Kim, Du-Hwan Hur, Jeong-Hun Ha, SeungHwan Bae, Kang-Won Seo, Seung-Hwan Bae. Multiprocessing-Based Parallel Pipeline for Real-Time Multi-Target Tracking on Embedded Systems. 2025; 30(11), 1-10.
Dong-Hyun Kim, Du-Hwan Hur, Jeong-Hun Ha, SeungHwan Bae, Kang-Won Seo and Seung-Hwan Bae. "Multiprocessing-Based Parallel Pipeline for Real-Time Multi-Target Tracking on Embedded Systems" Journal of The Korea Society of Computer and Information 30, no.11 (2025) : 1-10.
Dong-Hyun Kim; Du-Hwan Hur; Jeong-Hun Ha; SeungHwan Bae; Kang-Won Seo; Seung-Hwan Bae. Multiprocessing-Based Parallel Pipeline for Real-Time Multi-Target Tracking on Embedded Systems. Journal of The Korea Society of Computer and Information, 30(11), 1-10.
Dong-Hyun Kim; Du-Hwan Hur; Jeong-Hun Ha; SeungHwan Bae; Kang-Won Seo; Seung-Hwan Bae. Multiprocessing-Based Parallel Pipeline for Real-Time Multi-Target Tracking on Embedded Systems. Journal of The Korea Society of Computer and Information. 2025; 30(11) 1-10.
Dong-Hyun Kim, Du-Hwan Hur, Jeong-Hun Ha, SeungHwan Bae, Kang-Won Seo, Seung-Hwan Bae. Multiprocessing-Based Parallel Pipeline for Real-Time Multi-Target Tracking on Embedded Systems. 2025; 30(11), 1-10.
Dong-Hyun Kim, Du-Hwan Hur, Jeong-Hun Ha, SeungHwan Bae, Kang-Won Seo and Seung-Hwan Bae. "Multiprocessing-Based Parallel Pipeline for Real-Time Multi-Target Tracking on Embedded Systems" Journal of The Korea Society of Computer and Information 30, no.11 (2025) : 1-10.
