Wearable Gesture Recognition Through Location-Based Candidate Filtering
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional wearable devices struggle to accurately identify specific gestures such as eating or drinking gestures due to excessive processing power and unreliable detection when matching motion data to hundreds of potential gestures, leading to inefficiency and reduced accuracy.
Innovation Solution
Leverage geographical location data and time of day information to narrow down the list of candidate gestures, using physiological data from wearable devices in conjunction with GPS and calendar applications to identify gesture profiles, and compare motion segments to these profiles for improved recognition.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If conventional wearable devices match motion data to hundreds of potential gestures, then gesture recognition coverage is improved, but processing power requirements increase and accuracy decreases
Solution Approach 1:
The gesture recognition process is segmented into two stages: first, motion data is segmented into discrete motion segments with specific characteristics (duration, amplitude, velocity); second, these segmented motion data are matched against gesture templates. This segmentation reduces the computational complexity of comparing continuous motion data against hundreds of gestures, while maintaining comprehensive gesture recognition coverage.
Solution Approach 2:
The system performs preliminary processing of motion data by identifying and segmenting distinct motion events before gesture recognition. Motion segments are pre-characterized with key features (duration, amplitude, velocity) and stored as templates. This preliminary action prepares the data in advance, reducing the processing power needed during actual gesture recognition while maintaining high accuracy across multiple gesture types.
2Adaptability or versatility
If conventional wearable devices match motion data to hundreds of potential gestures, then gesture recognition coverage is improved, but detection reliability deteriorates
Solution Approach 1:
The system changes the parameters used for gesture recognition by focusing on specific motion segment characteristics (duration, amplitude, velocity) rather than comparing raw motion data across all dimensions. By transforming the recognition parameters to these key features, the system achieves reliable detection with reduced computational complexity, maintaining high gesture recognition coverage while improving detection reliability through more robust feature-based comparison.
3Measurement precision
If wearable devices process large quantities of motion data for gesture identification, then gesture recognition accuracy is improved, but energy consumption increases
Solution Approach 1:
The system extracts only the essential features from large quantities of motion data - specifically motion segment duration, amplitude, and velocity characteristics. By taking out only these critical parameters needed for accurate gesture recognition rather than processing the complete motion data stream, the system maintains high gesture recognition accuracy while significantly reducing the computational load and energy consumption on wearable devices.
Data Source
AI summary
Methods, systems, and devices for gesture recognition are described. A system may identify geographical location data associated with a user throughout a time interval and may identify a set of gesture profiles corresponding to a set of gestures associated with the geographical location data of the user. The system may additionally acquire physiological data, including motion data, associated with the user from a wearable device worn by the user and may identify a set of motion segments within the time interval based on the motion data. Additionally, the system may identify a gesture the user engaged in based on matching a motion segment of the set of motion segments to a gesture profile of the set of gesture profiles and may cause a graphical user interface (GUI) of a user device running the application to display an indication of the gesture.