An Improved DeepSORT Algorithm for Multi-Target Posture Tracking of Firefighters
Automation · 14.06.2026 · 7 (3) · 93
DOI: 10.3390/automation7030093 ↗Kurz gefasst
Fachartikel in der Zeitschrift Automation, online erschienen am 14.06.2026. Verfasst von Huaiyi Li und 5 weiteren Autor:innen. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Ministry of Emergency Management of China, Southwest Jiaotong University.
Abstract (Originalsprache)
Firefighter training requires accurate posture monitoring to reduce injuries and improve performance assessment, yet traditional tracking methods suffer from high occlusion rates and the uniform appearance of trainees. To address these challenges, we propose an improved multi-target tracking algorithm that integrates YOLOX for detection, BlazePose for posture estimation, and a pose-constrained extension of DeepSORT. First, posture features are introduced into the association metric through a posture-cosine distance, which enhances discrimination between visually similar firefighters. Second, a pose-guided bounding-box correction is applied to ensure complete coverage of the human body region, improving the quality of extracted posture information. Experiments were conducted on a custom firefighter training dataset comprising 6602 labeled images and five multi-target video sequences (FM-1 to FM-5). The proposed method achieved a mean Average Precision (mAP) of 97.8% for detection and improved tracking performance compared to baseline DeepSORT, with MOTA rising from 74.72% to 82.96% and IDF1 from 74.77% to 82.36%. These results demonstrate that the algorithm effectively handles severe occlusion and appearance similarity, providing a reliable tool for posture tracking and behavior perception in firefighter training environments.
Förderung
- Ministry of Emergency Management of China
- Southwest Jiaotong University
Zitieren
APA
Li, H., Peng, X., Li, W., Liu, Y., Cai, G., & Sun, H. (2026). An Improved DeepSORT Algorithm for Multi-Target Posture Tracking of Firefighters. Automation, 7(3), 93. https://doi.org/10.3390/automation7030093
Vancouver
Li H, Peng X, Li W, Liu Y, Cai G, Sun H. An Improved DeepSORT Algorithm for Multi-Target Posture Tracking of Firefighters. Automation. 2026;7(3):93. doi:10.3390/automation7030093
BibTeX
@article{Li2026,
author = {Li, Huaiyi and Peng, Xiaogang and Li, Wendi and Liu, Yougen and Cai, Guolin and Sun, Hongxia},
title = {An Improved DeepSORT Algorithm for Multi-Target Posture Tracking of Firefighters},
journal = {Automation},
year = {2026},
volume = {7},
number = {3},
pages = {93},
doi = {10.3390/automation7030093}
}
EUVIMED