Wrist-Worn Antenna Impedance Sensing for Occlusion-Free Hand Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing hand pose tracking systems using optical methods are sensitive to occlusion from clothing and raise privacy concerns, limiting their effectiveness and consumer acceptance.
Innovation Solution
A wrist-worn antenna system that uses real-time antenna complex impedance characteristics to predict hand poses, employing machine learning to interpret sensor data and provide continuous 3D hand tracking even when the hand is covered in fabric, with the option to track two degrees of freedom and micro-gestures.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If optical methods (RGB cameras, thermal cameras, range finders) are used for hand pose tracking, then hand pose tracking capability is provided, but the system becomes sensitive to occlusion from clothing and raises privacy concerns
Solution Approach 1:
The patent replaces optical sensing systems (cameras, range finders) with electromagnetic sensing systems (antennas that detect impedance changes). This substitution eliminates the need for line-of-sight optical detection, making the system immune to occlusion by clothing while maintaining hand pose tracking capability. The electromagnetic field penetrates fabric without being blocked, solving the occlusion sensitivity problem inherent in optical methods.
2Ease of operation
If wrist-worn camera-based methods are used for hand pose tracking, then hand pose tracking is enabled, but privacy implications arise that can deter consumers
Solution Approach 1:
The patent substitutes camera-based optical systems with antenna-based electromagnetic impedance sensing. This replacement eliminates the capture and processing of visual images, thereby removing the privacy concerns associated with camera-based tracking. The electromagnetic sensing method detects hand poses through impedance changes without creating visual records, thus maintaining functionality while eliminating privacy implications.
3Object-affected harmful factors
If antenna impedance sensing is used for hand pose tracking, then occlusion resistance and privacy protection are achieved, but measurement precision requirements increase
Solution Approach 1:
The patent introduces machine learning algorithms as an intermediary between the raw antenna impedance measurements and the final hand pose determination. The machine learning model processes the impedance characteristic data, extracting meaningful patterns and compensating for measurement noise or variations. This intermediary processing layer enables the system to achieve accurate hand pose tracking from impedance measurements without requiring extremely high measurement precision at the sensor level.
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
The system effectively tracks hand poses without occlusion issues and privacy concerns, providing accurate and continuous 3D hand tracking, enhancing applications like virtual and augmented reality and sign language recognition.
Implementation Method 1
determining, with at least one processor of a wrist-worn device, an impedance characteristic variation based on a dynamic finite electric ground plane of at least one antenna coupled to the device
Data Source
AI summary
Embodiments are disclosed for a continuous hand pose tracking system employing at least one wrist-worn antenna, from which real-time dielectric loading resulting from different hand poses). The sensor data is interpreted by a machine learning backend, which outputs a fully-posed three-dimensional (3D) hand that can be continuously tracked. In some embodiments, two degrees of freedom (2DOF) wrist angle and micro-gestures are tracked. The hand pose tracking system can be extended to include two or more and/or different types of antennas operating at different self-resonances. In an embodiment, a method comprises: determining, with at least one processor of a wrist-worn device, a complex impedance characteristic variation based on a dynamic finite electric ground plane of at least one antenna coupled to the device; and predicting, with the at least one processor, a hand pose of a user wearing the device on a their wrist based on the determined complex impedance characteristic variation.