A WiFi-Based Passive Fall Detection System
Yuqian Hu, Feng Zhang, Chenshu Wu, Beibei Wang, K. J. Ray Liu
Abstract
Fall detection systems based on WiFi signals are gaining popularity recently. However, most of the existing works relying on training are environment-dependent. In this paper, we propose DeFall, a novel WiFi-based environment-independent fall detection system by leveraging the features inherently associated with human falls - the patterns of speed and acceleration over time. The system consists of an offline template-generating stage and an online decision-making stage. In the offline stage, the speed of human falls is first estimated based on a statistical modeling about the Channel State Information (CSI). Dynamic Time Warping (DTW) based algorithms are applied to generate a representative template for typical human falls. Then fall event is detected in the online stage by evaluating the similarity between the patterns of realtime speed/acceleration estimates and the representative template. Extensive experiment results show that with a single pair of WiFi transceivers, the proposed system can achieve a detection rate of 96% and a false alarm rate smaller than 1.5% under both line-of-sight (LOS) and non-LOS (NLOS) scenarios.
BibTeX
@inproceedings{icassp2020_awifibasedpassiv,
title = {A WiFi-Based Passive Fall Detection System},
author = {Yuqian Hu and Feng Zhang and Chenshu Wu and Beibei Wang and K. J. Ray Liu},
booktitle = {ICASSP 2020},
year = {2020}
}