The Short-Time Fourier Transform (STFT) is a signal processing technique that segments a time-domain signal into successive short, overlapping windows and applies the Fourier Transform to each window, producing a time-frequency representation that reveals how spectral content evolves over time. In WiFi CSI-based sensing, STFT is used to extract dynamic features from CSI amplitude or phase signals — such as motion-induced Doppler shifts or periodic breathing patterns — that would be obscured by a global frequency analysis, making it particularly valuable for detecting and characterizing human activities and vital signs. Key variants and considerations include the choice of window function (e.g., Hann or Hamming), window length, and hop size, which govern the trade-off between time resolution and frequency resolution and directly affect the system's ability to distinguish fine-grained temporal events, such as the subtle movements of multiple co-located individuals in multi-person sensing scenarios.
Source Papers
- MUSE-Fi: Contactless MUti-person SEnsing Exploiting Near-field Wi-Fi Channel Variation ↗ — MUSE-Fi: Contactless MUti-person SEnsing Exploiting Near-fie
- OPERAnet, a multimodal activity recognition dataset acquired from radio frequency and vision-based sensors ↗ — OPERAnet, a multimodal activity recognition dataset acquired
- Understanding and Modeling of WiFi Signal Based Human Activity Recognition ↗ — Understanding and Modeling of WiFi Signal Based Human Activi
- WiFi CSI-based device-free sensing: from Fresnel zone model to CSI-ratio model ↗ — WiFi CSI-based device-free sensing: from Fresnel zone model
- WiGNN: WiFi-Based Cross-Domain Gesture Recognition Inspired by Dynamic Topology Structure ↗ — WiGNN: WiFi-Based Cross-Domain Gesture Recognition Inspired