Towards Position-Independent Sensing for Gesture Recognition with Wi-Fi
summary
Claims a hand-oriented view and a concrete feature called Motion Navigation Primitive (MNP) that uses the ratio of dynamic phase changes from two pairs of Wi‑Fi transceivers (CSI) to recover hand moving‑direction changes. Gestures are converted into sequences of strokes — line, arc and corner — and matched in real time by a prototype named WiGesture. Evaluation on three gesture sets reports over 92% average accuracy and demonstrates robustness to user location and orientation.
AI-written summary · about
chapters (3)
related talks
49mTurn your smartphone into Nintendo Wii-like controller
20mAdvancing Hand Gesture Recognition with High Resolution Electrical Impedance Tomography
19mBackHand: Sensing Hand Gestures via Back of the Hand
28mStrike a Pose - Gesture recognition in JavaScript w/ ML & Arduino
14mBack-Hand-Pose: 3D Hand Pose Estimation for a Wrist-worn Camera via Dorsum Deformation Network
18mInfiniTouch: Finger-Aware Interaction on Fully Touch Sensitive Smartphones
20mInteracting with Soli: Exploring Fine-Grained Dynamic Gesture Recognition in the Radio-Frequency ...
22mStrike a Pose: Gesture Recognition in JS with Machine Learning