Wearable Input Device Using Sensor Fusion for Gesture Recognition
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current input methods for operating devices, such as touch panels and game machines, require users to learn specific operations and can be cumbersome, especially when trying to perform actions like page turning or cursor selection, and are prone to errors due to noise and drift in angular velocity sensors.
Innovation Solution
A wearable input device that uses a combination of triaxial angular velocity and acceleration sensors to detect natural body motions, setting a reference posture and converting these into commands for controlling devices, allowing users to input commands without needing to directly interact with the device screen.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a user directly touches the touch panel to operate the terminal, then the input operation is simple and direct, but the user cannot operate from a free position or posture
Solution Approach 1:
The patent introduces a wearable input device as an intermediary between the user's body movements and the terminal operation. This device captures motion data from the user's natural movements and translates it into commands for the touch panel, eliminating the need for direct contact while maintaining operational simplicity.
Solution Approach 2:
The patent replaces the mechanical direct-touch system with a sensor-based system. Motion sensors detect the user's body movements and convert them into digital signals that control the terminal, substituting the mechanical contact requirement with an optical/electromagnetic sensing mechanism.
2Measurement precision
If the user learns specific operations for the device, then the control precision is improved, but the operation complexity and learning burden increase
Solution Approach 1:
The system automatically interprets the user's natural movements without requiring learned procedures. The motion sensors and processing unit work together to automatically translate any natural body movement into the corresponding terminal command, making the system self-adapting to the user's actions.
Solution Approach 2:
Instead of teaching the user how to perform specific operations (traditional approach), the system inverts the logic by automatically determining what operation the user intends based on their natural movements. The system adapts to the user's natural behavior patterns rather than requiring the user to adapt to the device's operational conventions.
3Productivity
If the angular velocity sensor continuously integrates angular velocities to detect rotation angles, then the gesture recognition capability is improved, but noise and drift cause accumulation of errors over time
Solution Approach 1:
The patent implements a feedback mechanism where the system periodically detects the user's body posture and uses this information to correct accumulated errors in the rotation angle calculations. The posture detection unit provides feedback signals that allow the processing unit to adjust and recalibrate the integrated angular velocity values.
Solution Approach 2:
The system performs preliminary posture detection and reference frame establishment before the actual gesture recognition begins. By setting up an initial reference posture and detecting posture changes in advance, the system can compensate for sensor drift and noise accumulation before they affect the accuracy of the final gesture recognition.
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 users to operate devices comfortably in any posture and reduces the learning burden by matching natural movements with device controls, providing high gesture recognition rates and minimizing noise-related errors.
Implementation Method 1
an angular velocity sensor, and outputs, to the game machine, a detection signal of an angular velocity detected by the angular velocity sensor. The detection signal of the angular velocity sensor is a signal that is obtained by detecting an angular velocity at which the controller is rotated around each of the coordinate axes
Implementation Method 2
a sensor that obtains an angular velocities and an acceleration in a first coordinate system fixed in the input device
Data Source
AI summary
A device that is worn on a portion of a user's body and inputs a command into a controller, includes a sensor that obtains angular velocities and an acceleration in a first coordinate system fixed in the input device, a processor that performs setting a second coordinate system for a reference posture of the user, calculating a rotation matrix that converts the angular velocities in the first coordinate system into angular velocities in the second coordinate system using the acceleration in the first coordinate system, calculating feature amounts in the second coordinate system using the angular velocities in the second coordinate system, and specifying the command using the feature amounts, and a transmitter that transmits the command to the controller.