Non-Contact Gesture Recognition Using IMU Motion Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Non-contact gesture recognition in electronic devices is hindered by unintentional movements causing incorrect gesture identification due to relative movement between the device and the user's hands or fingers, leading to undesired command execution.
Innovation Solution
A method and device utilizing an inertial measurement unit (IMU) to detect inertial events and differentiate them from user gestures, ensuring accurate gesture recognition by processing image sensing data only when no inertial events occur, thereby preventing incorrect command triggering.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If non-contact gesture recognition is implemented using image sensors, then user interaction convenience is improved, but gesture recognition accuracy deteriorates due to unintentional device movement
Solution Approach 1:
An inertial measurement unit (IMU) is introduced as an intermediary component to detect device movement. The IMU acts as a mediator between the image sensor system and the gesture recognition algorithm, providing motion compensation data that allows the system to distinguish between device movement and actual user gestures, thereby maintaining high accuracy despite device motion
Solution Approach 2:
The system implements feedback by continuously monitoring IMU data and using this information to adjust gesture recognition decisions in real-time. When the IMU detects significant device movement, the system receives feedback to ignore or adjust the corresponding image sensor data, preventing false gesture recognition and maintaining accuracy during device motion
2Productivity
If image sensing data is continuously processed to detect gestures, then gesture detection capability is improved, but energy consumption increases
Solution Approach 1:
The system uses periodic action by having the IMU continuously sample at a high frequency while the image sensor and processing occur at lower, event-driven intervals. The IMU operates periodically to detect motion events, and only triggers full image processing when motion thresholds are exceeded, reducing overall energy consumption while maintaining gesture detection capability
Solution Approach 2:
The IMU serves itself as a motion-triggered gatekeeper that automatically determines when image processing should occur. By using the IMU's self-contained motion detection capability to control the activation of the more energy-intensive image sensor and processing pipeline, the system achieves energy-efficient operation without sacrificing gesture detection responsiveness
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
Enhances the accuracy of non-contact gesture recognition by eliminating the influence of inertial events such as accidental vibrations or movements, resulting in more precise gesture determination and reduced energy consumption.
Implementation Method 1
detecting an inertial sensing signal of the non-contact sensing device itself
Implementation Method 2
uses image sensors to capture the moving distance, speed, angle and so on of the user's palms or fingers waving in the air
Data Source
AI summary
A method for determining non-contact gesture is applied to a device for the same. The device has an image sensor to detect an image sensing data, an inertial measurement sensor to detect an inertial sensing data, and a processor to determine if an object data is detected and to determine if an inertial event is occurred. The image sensing data in the same and/or adjacent image frame with the inertial events are excluded so that the image sensing data used to determine the gesture are those not influenced by the inertial events. Therefore, the accuracy of determining the gesture is enhanced.