Towards video-based injury risk assessment: predicting lifting loads from body pose trajectories
Machine Vision and Applications · 2025-11 · 36 (6)
DOI: 10.1007/s00138-025-01758-w ↗Kurz gefasst
Fachartikel in der Zeitschrift Machine Vision and Applications, online erschienen am 27.10.2025. Verfasst von Zihao Zhu und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Computer Sciences, University of Wisconsin-Madison, 1205 University Ave, Madison, WI 53706 USA. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 54 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: NIOSH CDC HHS, National Institute for Occupational Safety and Health.
Abstract (Originalsprache)
Manual material handling tasks, such as lifting and lowering, are ubiquitous across industry sectors. Overexertion during these tasks is among the leading causes of workplace injuries. Previous studies have shown that lifting load is a key factor in determining the risk of injury. However, existing methods for measuring the lifting load often rely on manual measurements, sensor fusion, or other techniques that are difficult to scale in practice. In this study, we present a vision-based approach to automatically predict lifting load by analyzing human body pose trajectories extracted from video alone. Specifically, our method employs person detection, visual tracking, and human body pose estimation to extract pose trajectories and their kinematic features, which are then used to train a Transformer model for load prediction. To evaluate our method, we conducted a human subjects study of 19 participants performing various lifting and lowering tasks with varying postures. Our method achieved an average accuracy of 74.8% to distinguish between light vs. heavy objects, and an average accuracy of 50.8% to identify three levels of lifting loads (light, medium, heavy) across lifting and lowering tasks. These results demonstrate a first step towards computer vision based solutions for automatic, noninvasive, scalable injury risk assessment for manual material handling tasks.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Computer Sciences, University of Wisconsin-Madison, 1205 University Ave, Madison, WI 53706 USA.
- Department of Industrial and Systems Engineering, University of Wisconsin-Madison, 1415 Engineering Drive, Madison, WI 53706 USA.
- Department of Biomedical Engineering, University of Wisconsin-Madison, 1550 Engineering Drive, Madison, WI 53706 USA.
- Department of Biostatistics and Medical Informatics, University of Wisconsin-Madison, 610 Walnut St Room 201, Madison, WI 53726 USA.
Förderung
- NIOSH CDC HHS
- National Institute for Occupational Safety and Health
Zitieren
APA
Zhu, Z., Mu, F., Radwin, R., & Li, Y. (2025). Towards video-based injury risk assessment: predicting lifting loads from body pose trajectories. Machine Vision and Applications, 36(6). https://doi.org/10.1007/s00138-025-01758-w
Vancouver
Zhu Z, Mu F, Radwin R, Li Y. Towards video-based injury risk assessment: predicting lifting loads from body pose trajectories. Machine Vision and Applications. 2025;36(6). doi:10.1007/s00138-025-01758-w
BibTeX
@article{Zhu2025,
author = {Zhu, Zihao and Mu, Fangzhou and Radwin, Robert and Li, Yin},
title = {Towards video-based injury risk assessment: predicting lifting loads from body pose trajectories},
journal = {Machine Vision and Applications},
year = {2025},
volume = {36},
number = {6},
doi = {10.1007/s00138-025-01758-w}
}
EUVIMED