WIFI-Based Robust Child Presence Detection for Smart Cars
Sakila S. Jayaweera, Beibei Wang, Xiaolu Zeng, Wei-Hsiang Wang, K. J. Ray Liu
Abstract
In-car child presence detection (CPD) has gained worldwide attention due to increased child deaths reported yearly when they are left unattended in a car. Existing solutions usually require dedicated sensors and are being surpassed by WiFi-based CPD because the latter can provide broader coverage and can reuse the in-car WiFi devices. However, the existing WiFi-based CPD solutions are not robust and may suffer from miss detection due to the very weak breathing of a young child and high false alarms under unfavorable environmental conditions. In this paper, we propose a WiFi-based robust CPD system consisting of a motion and breathing detector. To improve breathing detection, we propose to treat the intermediate spectrogram for breathing estimation as images and apply image enhancement techniques followed by effective false alarm removal. Extensive experimental results have confirmed the robustness of the proposed system with a 99% detection accuracy and 3% false alarm rate.
BibTeX
@inproceedings{icassp2023_wifibasedrobustc,
title = {WIFI-Based Robust Child Presence Detection for Smart Cars},
author = {Sakila S. Jayaweera and Beibei Wang and Xiaolu Zeng and Wei-Hsiang Wang and K. J. Ray Liu},
booktitle = {ICASSP 2023},
year = {2023}
}