This paper takes initial strides at designing and evaluating a vision-based system for privacy ensured activity monitoring. The proposed technology utilizing Artificial Intelligence (AI)-empowered proactive systems offering continuous monitoring, behavioral analysis, and modeling of human activities. To this end, this paper presents Single Run Action Detector (S-RAD) which is a real-time privacy-preserving action detector that performs end-to-end action localization and classification. It is based on Faster-RCNN combined with temporal shift modeling and segment based sampling to capture the human actions. Results on UCF-Sports and UR Fall dataset present comparable accuracy to State-of-the-Art approaches with significantly lower model size and computation demand and the ability for real-time execution on edge embedded device (e.g. Nvidia Jetson Xavier).
@article{arxiv.2102.03391,
title = {Single Run Action Detector over Video Stream -- A Privacy Preserving Approach},
author = {Anbumalar Saravanan and Justin Sanchez and Hassan Ghasemzadeh and Aurelia Macabasco-O'Connell and Hamed Tabkhi},
journal= {arXiv preprint arXiv:2102.03391},
year = {2021}
}