A Lightweight 3D-CNN for Event-Based Human Action Recognition with Privacy-Preserving Potential

TL;DR

This paper introduces a lightweight 3D-CNN for event-based human action recognition that preserves privacy, achieves high accuracy, and is suitable for edge deployment, outperforming existing models.

Contribution

The paper proposes a novel compact 3D-CNN architecture tailored for event-based data, enhancing privacy-preserving human activity recognition with improved accuracy and efficiency.

Findings

Achieved an F1-score of 0.9415 and 94.17% accuracy.

Outperformed benchmark 3D-CNNs like C3D, ResNet3D, and MC3_18.

Demonstrated suitability for real-world edge applications.

Abstract

This paper presents a lightweight three-dimensional convolutional neural network (3DCNN) 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 design suitable for edge deployment. 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%. 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 edge applications.