Training-Free and Environment-Robust Human Motion Segmentation with Commercial WiFi Device: An Image Perspective
Open Access
- 29 December 2025
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 16 (1) , 373
Abstract
WiFi sensing relies on capturing channel state information (CSI) fluctuations induced by human activities. Accurate motion segmentation is crucial for applications ranging from intrusion detection to activity recognition. However, prevailing methods based on variance, correlation coefficients, or deep learning are often constrained by complex threshold-setting procedures and dependence on high-quality sample data. To address these limitations, this paper proposes a training-free and environment-independent motion segmentation system using commercial WiFi devices from an image-processing perspective. The system employs a novel quasi-envelope to characterize CSI fluctuations and an iterative segmentation algorithm based on an improved Otsu thresholding method. Furthermore, a dedicated motion detection algorithm, leveraging the grayscale distribution of variance images, provides a precise termination criterion for the iterative process. Real-world experiments demonstrate that our system achieves an E-FPR of 0.33% and an E-FNR of 0.20% in counting motion events, with average temporal errors of 0.26 s and 0.29 s in locating the start and end points of human activity, respectively, confirming its effectiveness and robustness.Keywords
Funding Information
- National Natural Science Foundation of China (62371253)
- Natural Science Foundation of Hunan Province (2025JJ70469)
- Research Foundation of Education Bureau of Hunan Province (24B0717)
- Postgraduate Research and Practice Innovation Program of Jiangsu Province (KYCX20_0739)
This publication has 27 references indexed in Scilit:
- LowDetrack: A Human Detection and Tracking System for Wi-Fi Low Packet RatesIEEE Internet of Things Journal, 2025
- Toward Cross-Environment Continuous Gesture User Authentication With Commercial Wi-FiIEEE Transactions on Networking, 2025
- Development of an iterative Otsu method for vision-based structural displacement measurement under low-light conditionsMeasurement, 2024
- CSI-based passive intrusion detection bound estimation in indoor NLoS scenarioFundamental Research, 2023
- Device-Free Human Motion Detection Using Single Link WiFi Channel Measurements for Building Energy ManagementIEEE Embedded Systems Letters, 2022
- DeepSeg: Deep-Learning-Based Activity Segmentation Framework for Activity Recognition Using WiFiIEEE Internet of Things Journal, 2020
- A dataset for Wi-Fi-based human-to-human interaction recognitionData in Brief, 2020
- Revisiting Indoor Intrusion Detection With WiFi Signals: Do Not Panic Over a Pet!IEEE Internet of Things Journal, 2020
- MoSense: An RF-Based Motion Detection System via Off-the-Shelf WiFi DevicesIEEE Internet of Things Journal, 2017
- Bfp: Behavior-Free Passive Motion Detection Using PHY InformationWireless Personal Communications, 2015