Human tracking in WiFi CSI-based sensing refers to the continuous, device-free localization of one or more individuals over time by monitoring how their movement perturbs wireless channel state information between fixed transmitter-receiver pairs. Unlike static localization or one-shot detection, tracking requires estimating a temporal trajectory, making it critical for applications such as elderly care, security surveillance, and smart building management without the need for wearable devices or cameras. Key variants include single-person tracking, where multipath and Fresnel zone models can be leveraged to map CSI fluctuations to positional estimates, and the more challenging multi-person tracking scenario, which must disentangle overlapping signal contributions from multiple bodies and often demands more sophisticated signal processing or learning-based approaches to maintain distinct identity trajectories over time.
Source Papers
- An Overview on IEEE 802.11bf: WLAN Sensing ↗ — An Overview on IEEE 802.11bf: WLAN Sensing
- Channel State Information from Pure Communication to Sense and Track Human Motion: A Survey ↗ — Channel State Information from Pure Communication to Sense a
- Deep Learning-Enhanced Human Sensing with Channel State Information: A Survey ↗ — Deep Learning-Enhanced Human Sensing with Channel State Info
- Physics of Human Crowds ↗ — Physics of Human Crowds
- Recent trends in crowd analysis: A review ↗ — Recent trends in crowd analysis: A review
- WiFi CSI-based device-free sensing: from Fresnel zone model to CSI-ratio model ↗ — WiFi CSI-based device-free sensing: from Fresnel zone model
- WiFi Sensing with Channel State Information ↗ — WiFi Sensing with Channel State Information