Air gesture recognition methods, devices and storage media
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- SOUTHERN UNIVERSITY OF SCIENCE AND TECHNOLOGY
- Filing Date
- 2026-01-26
- Publication Date
- 2026-05-26
AI Technical Summary
Existing acoustic gesture recognition systems are susceptible to interference from environmental noise, individual user differences, and movement states, resulting in low gesture recognition accuracy.
Acoustic signals reflected from hand gestures are collected by microphones in wearable devices. Potential hand gesture segments are extracted using frequency domain processing and differential processing, and then input into a pre-built hand gesture recognition model for recognition. A multi-channel signal perception mechanism and a deep learning model are used for hand gesture classification.
Without increasing device cost or power consumption, the accuracy and stability of gesture recognition have been improved, and high-precision recognition can be maintained in various environments and among various users.
Smart Images

Figure CN121560170B_ABST