AI Motion Gesture Recognition for Poor-Visibility Control

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing gesture recognition systems, particularly those using cameras and computer vision, face limitations in functionality when visibility is poor or when a mobile device is used as a controller, restricting their use cases.

Innovation Solution

A gesture recognition system comprising a mobile device with sensors for detecting motion data, a first control device for determining user gestures using artificial intelligence, and a second control device for processing these gestures to generate control commands for applications, allowing for gesture recognition independent of camera visibility and expanding functionality.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If camera-based gesture recognition is used, then gesture control functionality is achieved, but the system fails to work in poor visibility conditions

Engineering Contradiction:
Improvegesture recognition reliabilityVSAvoidoperational environment adaptability
Core Design Contradiction:
ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent replaces the optical camera-based gesture recognition system with a mechanical sensor-based system using accelerometers and gyroscopes in the mobile device. This substitution allows gesture detection to work independently of visual conditions, resolving the contradiction between reliability in gesture recognition and adaptability to poor visibility environments.

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

Solution Approach 2:

The patent introduces a mediator component - the mobile device with motion sensors - that acts as an intermediary between the user's hand gestures and the vehicle's control system. This mediator captures gestures through accelerometers and gyroscopes, enabling reliable gesture recognition that works in all visibility conditions while maintaining adaptability to different environments.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Device complexity

If a single integrated control device is used for gesture recognition, then the system structure is simplified, but the development and extension of gesture capabilities becomes more difficult

Engineering Contradiction:
Improvesystem structure complexityVSAvoiddevelopment ease
Core Design Contradiction:
Device complexityVSEase of manufacture

Solution Approach 1:

The patent segments the gesture recognition system into two independent parts: the mobile device with sensors and AI processing capabilities, and the vehicle's control device that receives and executes gesture commands. This segmentation allows each component to be developed and manufactured independently, making the system easier to develop and extend while maintaining manageable complexity.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent creates a universal interface where the mobile device can recognize various gestures through its sensors and communicate them to the vehicle's control system. This multi-functional approach allows the same sensor-based system to support multiple gesture types and applications, facilitating easier development and extension of gesture capabilities across different use cases.

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

Enables effective gesture recognition in poor lighting conditions and obstructed views, with clear separation of duties between control devices, facilitating easier development and extension of gesture recognition capabilities, and integration with vehicle systems for controlling various functions.

Implementation Method 1

The mobile device comprises at least one sensor for detecting motion data

Methodology Applied
Scientific EffectInertial measurement: Inertia

Data Source

PatentEP4478157A1Gesture recognition system and method for gesture recognition
Publication Date: 2024.12.18 BAYERISCHE MOTOREN WERKE AG
  • EP4478157A1 patent drawingFigure 1~2
  • EP4478157A1 patent drawingFigure 3
  • EP4478157A1 patent drawing

AI summary

Provided is a gesture recognition system (1) comprising a mobile device (10) holdable or held in a hand of a user, the mobile device (10) having at least one sensor (12) for detecting motion data and a first control device (11), and at least one second control device (20) for controlling at least one application. The first control device (11) is configured to obtain (S1) motion data detected by the at least one sensor (12), determine (S2) a gesture of the user based on the obtained motion data using artificial intelligence, and notify (S3) the at least one second control device (20) of the determined gesture. The at least one second control device (20) is configured to determine a control command for the at least one application depending on the determined gesture (S4), and to output the determined control command to the at least one application (S5).