Video-Based Lifting Action Recognition Using Rank-Altered Kinematic Feature Pairs
Human Factors: The Journal of the Human Factors and Ergonomics Society · 2025-07 · 67 (7) · 656-672
DOI: 10.1177/00187208241309748 ↗Kurz gefasst
Fachartikel in der Zeitschrift Human Factors: The Journal of the Human Factors and Ergonomics Society, online erschienen am 26.12.2024. Verfasst von SeHee Jung und 4 weiteren Autor:innen. Beteiligte Einrichtung: North Carolina State University, USA. Hauptthemen laut MEDLINE: Video Recording, Lifting. Die Arbeit wurde bisher 4-mal zitiert (Crossref) und nennt 45 Literaturangaben. Gefördert von: National Science Foundation.
Abstract (Originalsprache)
Objective
To identify lifting actions and count the number of lifts performed in videos based on robust class prediction and a streamlined process for reliable real-time monitoring of lifting tasks.
Background
Traditional methods for recognizing lifting actions often rely on deep learning classifiers applied to human motion data collected from wearable sensors. Despite their high performance, these methods can be difficult to implement on systems with limited hardware resources.
Method
The proposed method follows a five-stage process: (1) BlazePose, a real-time pose estimation model, detects key joints of the human body. (2) These joints are preprocessed by smoothing, centering, and scaling techniques. (3) Kinematic features are extracted from the preprocessed joints. (4) Video frames are classified as lifting or nonlifting using rank-altered kinematic feature pairs. (5) A lifting counting algorithm counts the number of lifts based on the class predictions.
Results
Nine rank-altered kinematic feature pairs are identified as key pairs. These pairs were used to construct an ensemble classifier, which achieved 0.89 or above in classification metrics, including accuracy, precision, recall, and F1 score. This classifier showed an accuracy of 0.90 in lifting counting and a latency of 0.06 ms, which is at least 12.5 times faster than baseline classifiers.
Conclusion
This study demonstrates that computer vision-based kinematic features could be adopted to effectively and efficiently recognize lifting actions. Application The proposed method could be deployed on various platforms, including mobile devices and embedded systems, to monitor lifting tasks in real-time for the proactive prevention of work-related low-back injuries.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- North Carolina State University, USA.
ORCID-Profile: Xu Xu
Förderung
- National Science Foundation
Zitieren
APA
Jung, S., Su, B., Lu, L., Qing, L., & Xu, X. (2025). Video-Based Lifting Action Recognition Using Rank-Altered Kinematic Feature Pairs. Human Factors: The Journal of the Human Factors and Ergonomics Society, 67(7), 656-672. https://doi.org/10.1177/00187208241309748
Vancouver
Jung S, Su B, Lu L, Qing L, Xu X. Video-Based Lifting Action Recognition Using Rank-Altered Kinematic Feature Pairs. Human Factors: The Journal of the Human Factors and Ergonomics Society. 2025;67(7):656-672. doi:10.1177/00187208241309748
BibTeX
@article{Jung2025,
author = {Jung, SeHee and Su, Bingyi and Lu, Lu and Qing, Liwei and Xu, Xu},
title = {Video-Based Lifting Action Recognition Using Rank-Altered Kinematic Feature Pairs},
journal = {Human Factors: The Journal of the Human Factors and Ergonomics Society},
year = {2025},
volume = {67},
number = {7},
pages = {656--672},
doi = {10.1177/00187208241309748}
}
EUVIMED