A Lightweight 3D-CNN for Event-Based Human Action Recognition With Privacy-Preserving Potential
IEEE Access · 2026 · 14 · 18193-18205
DOI: 10.1109/access.2026.3660117 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von Mehdi Sefidgar Dilmaghani und 2 weiteren Autor:innen. Die Arbeit wurde bisher 7-mal zitiert (Crossref) und nennt 62 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Research Ireland.
Abstract (Originalsprache)
This paper presents a lightweight three-dimensional convolutional neural network (3D-CNN) for human activity recognition (HAR) using event-based vision data. Privacy preservation is a key challenge in human monitoring systems, as conventional frame-based cameras capture identifiable personal information. In contrast, event cameras record only changes in pixel intensity, providing an inherently privacy-preserving sensing modality. The proposed network effectively models both spatial and temporal dynamics while maintaining a compact and computationally efficient design. To address class imbalance and enhance generalization, focal loss with class reweighting and targeted data augmentation strategies are employed. The model is trained and evaluated on a composite dataset derived from the Toyota Smart Home and ETRI datasets. Experimental results demonstrate an F1-score of 0.9415 and an overall accuracy of 94.17%, outperforming benchmark 3D-CNN architectures such as C3D, ResNet3D, and MC3_18 by up to 3%. It also has approximately 10 times fewer parameters than the second best benchmark network. These results highlight the potential of event-based deep learning for developing accurate, efficient, and privacy-aware human action recognition systems suitable for real-world applications.
Förderung
- Research Ireland
Zitieren
APA
Dilmaghani, M. S., Fowley, F., & Corcoran, P. (2026). A Lightweight 3D-CNN for Event-Based Human Action Recognition With Privacy-Preserving Potential. IEEE Access, 14, 18193-18205. https://doi.org/10.1109/access.2026.3660117
Vancouver
Dilmaghani MS, Fowley F, Corcoran P. A Lightweight 3D-CNN for Event-Based Human Action Recognition With Privacy-Preserving Potential. IEEE Access. 2026;14:18193-18205. doi:10.1109/access.2026.3660117
BibTeX
@article{Dilmaghani2026,
author = {Dilmaghani, Mehdi Sefidgar and Fowley, Frank and Corcoran, Peter},
title = {A Lightweight 3D-CNN for Event-Based Human Action Recognition With Privacy-Preserving Potential},
journal = {IEEE Access},
year = {2026},
volume = {14},
pages = {18193--18205},
doi = {10.1109/access.2026.3660117}
}
EUVIMED