Gesture Detection Using Radar Motion Correction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing gesture detection methods in mobile terminals face inaccuracies due to the unstable vertical attitude of the mobile device, leading to recognition errors during movement or inclination.

Innovation Solution

A method for gesture detection that involves detecting terminal motion parameters of a mobile terminal and correcting the first relative motion parameter of an object to the mobile terminal, using these parameters to obtain a more accurate second relative motion parameter, which is then processed through a machine learning-based gesture recognition model.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If the mobile terminal is used in a mobile state with unstable attitude, then the ease of operation is improved, but the measurement precision of gesture detection deteriorates

Engineering Contradiction:
Improvemobile usage convenienceVSAvoidgesture detection accuracy
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The patent introduces an intermediary coordinate transformation process that converts radar-detected gestures from the terminal's coordinate system to a standard vertical coordinate system. This mediator (coordinate transformation) eliminates the impact of terminal attitude angles, allowing accurate gesture recognition even when the terminal is held at various angles or moved, thus resolving the contradiction between mobile convenience and detection accuracy

Inventive Principle:
Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent changes the parameter reference frame by detecting the terminal's attitude angle and using it to transform the gesture coordinate system. By dynamically adjusting the coordinate system parameters based on terminal orientation, the system maintains accurate gesture detection across different terminal positions and movement states, solving the accuracy deterioration problem while preserving mobile usability

Inventive Principle:
Principle #35Parameter changes

2Adaptability or versatility

If the terminal attitude angle varies during use, then the adaptability to different usage scenarios is improved, but the reliability of gesture recognition deteriorates

Engineering Contradiction:
Improveusage scenario flexibilityVSAvoidgesture recognition accuracy
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The patent implements a dynamic coordinate transformation system that continuously adapts to changing terminal attitudes. By real-time detection of attitude angles and dynamic adjustment of the gesture recognition coordinate system, the system maintains reliable gesture recognition across diverse usage scenarios including different holding angles, device orientations, and movement states, thus achieving both adaptability and reliability

Inventive Principle:
Principle #15Dynamics

Applied Scientific Principles

This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.

Function Achieved in This Case

This approach enhances the accuracy of gesture recognition by accounting for the mobile terminal's motion, reducing recognition errors and improving the reliability of gesture detection in dynamic conditions.

Implementation Method 1

a radar sensor mounted in the mobile terminal transmits a radar wave and receives an echo returned based on the radar wave

Methodology Applied
Scientific EffectRadar: Radar

Data Source

PatentEP3889637B1Method and device for gesture detection, mobile terminal and storage medium
Publication Date: 2025.02.12 BEIJING XIAOMI MOBILE SOFTWARE CO LTD
  • EP3889637B1 patent drawingFigure 1
  • EP3889637B1 patent drawingFigure 2
  • EP3889637B1 patent drawingFigure 3

AI summary

Provided are a method and device for gesture detection, a mobile terminal and a storage medium. The method is applied to a mobile terminal and includes: transmitting (101) a radar wave; receiving an echo returned in response to the radar wave; determining (102) a first relative motion parameter of an object to be detected in an influence scope of the radar wave relative to the mobile terminal based on a transmitting parameter for the radar wave and a receiving parameter for the echo; detecting (103) a terminal motion parameter of the mobile terminal; correcting the first relative motion parameter based on the terminal motion parameter to obtain a second relative motion parameter; and performing machine learning (105) on the second relative motion parameter through a preset gesture recognition model to obtain a gesture recognition result.