Hand gesture recognition is the task of identifying and classifying specific hand or finger movements using wireless channel perturbations, particularly CSI fluctuations caused by the subtle multipath interference introduced by hand motion in the signal environment, without requiring any device to be worn or held by the user. It matters to the field because it enables natural, touch-free human-computer interaction for applications such as smart home control, sign language interpretation, and virtual reality interfaces, demonstrating that wireless sensing can resolve fine-grained, small-scale movements beyond coarse whole-body activities. Key variants include static gesture recognition, which classifies discrete hand poses or positions, and dynamic gesture recognition, which captures the temporal trajectory of continuous hand movements, with systems differing further in whether they operate at close range using dedicated CSI processing or at broader scales using received signal strength or Doppler-based approaches.
Source Papers
- A survey on CSI-based Wi-Fi sensing datasets and models with a focus on reproducibility ↗ — A survey on CSI-based Wi-Fi sensing datasets and models with
- Channel State Information from Pure Communication to Sense and Track Human Motion: A Survey ↗ — Channel State Information from Pure Communication to Sense a
- Human Activity Recognition via Wi-Fi and Inertial Sensors With Machine Learning ↗ — Human Activity Recognition via Wi-Fi and Inertial Sensors Wi
- WiGNN: WiFi-Based Cross-Domain Gesture Recognition Inspired by Dynamic Topology Structure ↗ — WiGNN: WiFi-Based Cross-Domain Gesture Recognition Inspired