Leveraging Artificial Occluded Samples for Data Augmentation in Human Activity Recognition
Sensors · 2025
DOI: 10.3390/s25041163 ↗Kurz gefasst
Fachartikel in der Zeitschrift Sensors, 2025. Verfasst von Eirini Mathe und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Informatics and Computer Engineering, University of West Attica, 12243 Athens, Greece. Hauptthemen laut MEDLINE: Human Activities, Pattern Recognition, Automated. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 41 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
A significant challenge in human activity recognition lies in the limited size and diversity of training datasets, which can lead to overfitting and the poor generalization of deep learning models. Common solutions include data augmentation and transfer learning. This paper introduces a novel data augmentation method that simulates occlusion by artificially removing body parts from skeleton representations in training datasets. This contrasts with previous approaches that focused on augmenting data with rotated skeletons. The proposed method increases dataset size and diversity, enabling models to handle a broader range of scenarios. Occlusion, a common challenge in real-world HAR, occurs when body parts or external objects block visibility, disrupting activity recognition. By leveraging artificially occluded samples, the proposed methodology enhances model robustness, leading to improved recognition performance, even on non-occluded activities.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Informatics and Computer Engineering, University of West Attica, 12243 Athens, Greece.
- Department of Informatics and Telecommunications, University of Thessaly, 35100 Lamia, Greece.
ORCID-Profile: Ioannis Vernikos, Phivos Mylonas
Zitieren
APA
Mathe, E., Vernikos, I., Spyrou, E., & Mylonas, P. (2025). Leveraging Artificial Occluded Samples for Data Augmentation in Human Activity Recognition. Sensors. https://doi.org/10.3390/s25041163
Vancouver
Mathe E, Vernikos I, Spyrou E, Mylonas P. Leveraging Artificial Occluded Samples for Data Augmentation in Human Activity Recognition. Sensors. 2025. doi:10.3390/s25041163
BibTeX
@article{Mathe2025,
author = {Mathe, Eirini and Vernikos, Ioannis and Spyrou, Evaggelos and Mylonas, Phivos},
title = {Leveraging Artificial Occluded Samples for Data Augmentation in Human Activity Recognition},
journal = {Sensors},
year = {2025},
doi = {10.3390/s25041163}
}
EUVIMED