Radar Gesture Recognition Using Echo Filtering by Distance, Speed, and Angle

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional gesture recognition technologies face limitations such as poor performance in varying light conditions, reliance on line of sight, high storage and computing costs, and privacy leakage risks, particularly in optical-based systems.

Innovation Solution

A gesture recognition method using millimeter-wave radar to filter echo data by dimensions like speed, distance, and angle to obtain accurate gesture data, reducing interference and privacy risks, enabling recognition in various lighting conditions with reduced computational demands.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If optical camera is used for gesture recognition, then gesture shape can be clearly indicated, but performance deteriorates in strong light or dim light conditions

Engineering Contradiction:
Improvegesture shape indicationVSAvoidperformance in varying light conditions
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The patent replaces the optical camera-based recognition system with a radar-based detection system. The radar uses electromagnetic wave reflection to detect gesture movements, completely avoiding dependency on visible light conditions. This substitution enables reliable gesture recognition in both strong light and dim light environments while maintaining measurement precision through multidimensional parameter detection.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If optical camera is used for gesture recognition, then gesture can be recognized, but line of sight is highly demanded and obstacles cannot exist between camera and hand

Engineering Contradiction:
Improvegesture recognition accuracyVSAvoidoperational flexibility with obstacles
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent substitutes optical line-of-sight detection with radar electromagnetic wave detection. Radar waves can penetrate through certain obstacles and reflect off the target object regardless of direct line of sight requirements. This enables gesture recognition even when obstacles exist between the radar and the user's hand, significantly improving operational flexibility while maintaining recognition accuracy.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

3Loss of information

If optical image is used for gesture recognition, then gesture information can be obtained, but storage costs and computing costs are high

Engineering Contradiction:
Improvegesture information acquisitionVSAvoidstorage costs and computing costs
Core Design Contradiction:
Loss of informationVSQuantity of substance

Solution Approach 1:

The patent extracts only the essential gesture-related parameters (distance, speed, angle) directly from radar echo data, eliminating the need to process and store large volumes of optical image data. By directly detecting physical movement parameters through radar, the system obtains sufficient gesture information with dramatically reduced data storage requirements and computational processing costs.

Inventive Principle:
Principle #2Taking out (Extraction)

4Measurement precision

If facial image is obtained during gesture recognition according to optical principle, then gesture can be recognized, but privacy leakage risk increases

Engineering Contradiction:
Improvegesture recognition capabilityVSAvoidprivacy leakage risk
Core Design Contradiction:
Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The patent replaces optical facial image capture with radar-based gesture detection. The radar system only detects physical movement parameters such as distance, speed, and angle of hand gestures, completely avoiding capture of facial images or other personal identifiable information. This substitution maintains gesture recognition capability while eliminating privacy leakage risks associated with facial image processing.

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

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

The method achieves accurate and efficient gesture recognition, including subtle movements, without privacy concerns, and allows for user control in diverse environments, enhancing user experience.

Implementation Method 1

obtaining echo data of a radar, where the echo data includes information generated when an object moves in a detection range of the radar

Methodology Applied
Scientific EffectRadar: Radar

Data Source

PatentEP4254137B1Gesture recognition method and apparatus
Publication Date: 2026.01.07 HUAWEI TECH CO LTD
  • EP4254137B1 patent drawingFigure 1~2
  • EP4254137B1 patent drawingFigure 3~4
  • EP4254137B1 patent drawingFigure 5~7A

AI summary

This application discloses a gesture recognition method and apparatus, to filter echo data in a dimension such as a speed, a distance, or an angle, to obtain gesture data with less interference. This can accurately recognize a gesture of a user, and improve user experience. The method includes: obtaining echo data of a radar, where the echo data includes information generated when an object moves in a detection range of the radar; filtering out, from the echo data, information that does not meet a preset condition, to obtain gesture data, where the preset condition includes at least two of a distance, a speed, or an angle, the distance includes a distance between the object and the radar, the speed includes a speed of the object relative to the radar, and the angle includes an azimuth or a pitch angle of the object in the detection range of the radar; extracting a feature from the gesture data, to obtain gesture feature information; and obtaining a target gesture based on the gesture feature information.