Gait recognition is the problem of identifying or verifying individuals based on the unique patterns of their walking motion, as captured through wireless channel perturbations in Wi-Fi sensing systems without requiring the subject to carry any device. It matters to the field because it enables passive, unobtrusive identity authentication and person identification in smart environments using commodity hardware, serving as a key benchmark task for evaluating the discriminative power of CSI-based sensing pipelines. Key variants include closed-set identification, where the system classifies a subject among a known set of individuals, and open-set or verification scenarios, where generalizability across different environments, device configurations, and walking speeds remains a central challenge.
Source Papers
- A Survey on Wi-Fi Sensing Generalizability: Taxonomy, Techniques, Datasets, and Future Research Prospects ↗ — A Survey on Wi-Fi Sensing Generalizability: Taxonomy, Techni
- Channel State Information from Pure Communication to Sense and Track Human Motion: A Survey ↗ — Channel State Information from Pure Communication to Sense a
- CrossSense: Towards Cross-Site and Large-Scale WiFi Sensing ↗ — CrossSense: Towards Cross-Site and Large-Scale WiFi Sensing
- Deep Learning-Enhanced Human Sensing with Channel State Information: A Survey ↗ — Deep Learning-Enhanced Human Sensing with Channel State Info
- Device-Free Passive Identity Identification via WiFi Signals ↗ — Device-Free Passive Identity Identification via WiFi Signals