Radar Gesture Recognition with Distance-Speed-Angle Filtering

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional gesture recognition technologies based on optical principles face limitations such as poor performance in varying light conditions, line-of-sight requirements, high storage and computing costs, and privacy leakage risks, making them inefficient and insecure for widespread application.

Innovation Solution

A radar-based gesture recognition method that filters echo data by speed, distance, or angle to obtain gesture data with reduced interference, enabling accurate recognition without privacy risks and improving user experience across different lighting conditions.

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 gesture recognition system with a radar-based system. The radar uses electromagnetic wave reflection to detect hand gestures, eliminating dependency on ambient light conditions. The radar transmitter sends electromagnetic waves that reflect off the user's hand, and the receiver captures these reflected waves to extract gesture information, providing reliable performance in both strong light and dim light scenarios.

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

2Loss of information

If optical camera is used for gesture recognition, then gesture data can be obtained, but storage costs and computing costs increase

Engineering Contradiction:
Improvegesture data acquisitionVSAvoidstorage and computing costs
Core Design Contradiction:
Loss of informationVSLoss of energy

Solution Approach 1:

The patent extracts only the essential gesture-related information from the radar echo data through targeted signal processing. Instead of processing complete optical images, the system extracts key parameters such as hand position, movement trajectory, and gesture type directly from the reflected electromagnetic wave signals. This extraction approach significantly reduces data volume and associated storage and computing costs while maintaining gesture recognition accuracy.

Inventive Principle:
Principle #2Taking out (Extraction)

3Ease of operation

If optical camera is used for gesture recognition, then gesture recognition can be implemented, but privacy leakage risk increases due to facial image capture

Engineering Contradiction:
Improvegesture recognition capabilityVSAvoidprivacy leakage risk
Core Design Contradiction:
Ease of operationVSObject-affected harmful factors

Solution Approach 1:

The patent extracts only the necessary gesture motion information from the radar data while deliberately excluding any information that could identify the user's face or personal characteristics. The system processes only the reflected wave signals from the hand region, extracting parameters such as hand position, velocity, and gesture patterns, while discarding any data that might contain facial features or biometric information, thereby eliminating privacy leakage risks.

Inventive Principle:
Principle #2Taking out (Extraction)

4Measurement precision

If optical camera is used for gesture recognition, then gesture detection can be performed, but line-of-sight requirement and obstacle sensitivity increase system complexity

Engineering Contradiction:
Improvegesture detection capabilityVSAvoidline-of-sight and spatial constraint requirements
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent implements a radar system that can detect gestures through obstacles and without strict line-of-sight requirements, making the gesture recognition capability universal across various spatial configurations. The electromagnetic waves can penetrate through certain obstacles and reflect off the hand from multiple angles, allowing the system to recognize gestures regardless of the user's position or intervening objects, thereby simplifying system deployment and usage constraints.

Inventive Principle:
Principle #6Universality (Multi-functionality)

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 radar-based method provides accurate and efficient gesture recognition that is not limited by ambient light, reduces computing costs, and minimizes privacy risks, allowing for widespread application and improved 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

Implementation Method 2

obtaining echo data of a radar

Methodology Applied
Scientific EffectEcho: Echo

Data Source

PatentUS20230333209A1Gesture recognition method and apparatus
Publication Date: 2023.10.19 HUAWEI TECH CO LTD
  • US20230333209A1 patent drawing
  • US20230333209A1 patent drawing
  • US20230333209A1 patent drawing

AI summary

This application discloses a gesture recognition method and apparatus accurately recognizes a gesture of a user and improves 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.