WiFi for Privacy-Friendly Surveillance
Akhilbaran Ghosh, Arjun Chouksey · 2024
In the ongoing debate between surveillance necessity and privacy concerns, WiFi sensing emerges as a promising solution for efficient data monitoring while safeguarding personal privacy. Unlike traditional surveillance methods relying on camera recordings, WiFi sensing utilizes Channel State Information (CSI) data to detect specific movements, offering advantages such as reduced data storage and processing time. This paper explores the effectiveness of WiFi CSI data in detecting human interactions within radio waves, highlighting its practical usability and enhanced accuracy compared to Received Signal Strength (RSS) measurements. Leveraging Convolutional Neural Networks (CNNs), a blind machine learning paradigm, this study demonstrates the potential of WiFi sensing for human activity recognition (HAR). While previous HAR research predominantly focused on camera feeds and wearable devices, this study pioneers the application of CNNs to WiFi CSI data analysis, showing promising results for occupancy detection, activity recognition, and gesture identification. Although there is room for further improvement in accuracy, this research lays a solid foundation for future studies in the burgeoning field of WiFi sensing-based surveillance.