Air gesture recognition methods, devices and storage media

CN121560170BActive Publication Date: 2026-05-26SOUTHERN UNIVERSITY OF SCIENCE AND TECHNOLOGY
View PDF 2 Cites 0 Cited by

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

Technical Problem

Existing acoustic gesture recognition systems are susceptible to interference from environmental noise, individual user differences, and movement states, resulting in low gesture recognition accuracy.

Method used

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.

Benefits of technology

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.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121560170B_ABST
    Figure CN121560170B_ABST
Patent Text Reader

Abstract

This application discloses a method, device, and storage medium for air gesture recognition, relating to the field of gesture recognition technology. The method includes: acquiring reflected signals after a hand gesture reflects a target acoustic signal through at least one microphone in a wearable device, wherein the target acoustic signal is constructed from a signal emitted by at least one speaker in the wearable device; performing frequency domain processing on each reflected signal to obtain target time-series spectrum information; performing differential processing on each target time-series spectrum information to obtain differential spectrum information; extracting potential gesture segments based on each differential spectrum information; inputting each potential gesture segment into a pre-constructed gesture recognition model, and outputting gesture recognition results. This application can improve the accuracy of gesture recognition during interaction.
Need to check novelty before this filing date? Find Prior Art