The Body-coordinate Velocity Profile (BVP) is a signal representation method used in WiFi CSI-based human sensing that captures the Doppler velocity components of different body parts relative to a body-centered coordinate frame, effectively decomposing the motion of limbs and torso into structured velocity signatures. By normalizing movement with respect to the body's own orientation rather than a fixed environmental reference, BVP enables more robust and view-independent recognition of human activities and gestures, making it particularly valuable for generalizing across different subject positions and orientations relative to the antenna array. Key variants include time-series BVP representations that track velocity evolution over action sequences, which have been leveraged as input features for deep learning models such as CNNs and RNNs to improve classification accuracy in activity recognition benchmarks.
Source Papers
- A Survey on Wireless Device-free Human Sensing: Application Scenarios, Current Solutions, and Open Issues ↗ — A Survey on Wireless Device-free Human Sensing: Application
- Deep Learning-Enhanced Human Sensing with Channel State Information: A Survey ↗ — Deep Learning-Enhanced Human Sensing with Channel State Info
- SenseFi: A library and benchmark on deep-learning-empowered WiFi human sensing ↗ — SenseFi: A library and benchmark on deep-learning-empowered
- WiGNN: WiFi-Based Cross-Domain Gesture Recognition Inspired by Dynamic Topology Structure ↗ — WiGNN: WiFi-Based Cross-Domain Gesture Recognition Inspired