Multi-Sensor Gesture Recognition for Fewer False Positives
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing gesture recognition systems based on direction of view recognition or radar sensors suffer from limited reliability and are prone to false positives, necessitating an improvement in gesture recognition accuracy.
Innovation Solution
A gesture recognition system that combines the use of a first sensor to determine user gestures and a second sensor to determine the user's intention to act, thereby minimizing false recognitions by ensuring consistency between the user gesture and intended action.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If gesture recognition is performed using a single sensor (radar or direction of view), then the system complexity is low, but the recognition reliability is limited and false positives occur
Solution Approach 1:
The patent combines radar sensor data (for detecting hand gestures) with direction of view sensor data (for detecting user gaze) to create a multi-sensor gesture recognition system. This merging of different sensor types allows the system to cross-validate gestures with user intent, significantly improving recognition reliability and reducing false positives compared to single-sensor systems
2Reliability
If the second sensor continuously evaluates sensor data to determine user intention, then the accuracy of gesture recognition improves, but the energy consumption increases
Solution Approach 1:
The system implements periodic evaluation of direction of view data rather than continuous monitoring. The control unit determines user intention to act at specific intervals or triggered by gesture detection events, maintaining high recognition accuracy while significantly reducing the energy consumption associated with continuous sensor operation and data processing
Data Source
AI summary
A method for a gesture recognition system improves gesture recognition. The gesture recognition system has at least a first sensor and a second sensor. The method includes determining a user gesture by means of the first sensor, and determining a user's intention to act using the second sensor in order to improve the determination of the user gesture. The method further includes determining a user input based on the determined user gesture and the determined intention to act. The method also includes carrying out an operation based on the user input.