Hand Joint Tracking Using Kinematic Model and Kalman Filter
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for tracking hand joints in augmented and virtual reality devices are not accurate enough, leading to suboptimal performance of functions controlled by hand motions.
Innovation Solution
A method and apparatus for tracking hand joints that involves estimating angle information of finger joints based on initial hand joint positions, generating a kinematic model, and updating positions and angles using an extended Kalman filter.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If existing methods for tracking hand joints are used, then the system is simple to implement, but the tracking accuracy is insufficient
Solution Approach 1:
The hand tracking system is segmented into multiple independent modules: initial position detection module, angle information estimation module, kinematic model generation module, and extended Kalman filter updating module. Each module handles a specific aspect of the tracking process, improving overall accuracy while maintaining manageable system complexity through modular design.
Solution Approach 2:
The system performs preliminary actions by first detecting initial hand joint positions and estimating angle information before generating the kinematic model. This preliminary preparation of accurate initial data and angle estimates enables the subsequent tracking process to achieve higher precision without requiring complex real-time computation.
Solution Approach 3:
The extended Kalman filter implements a feedback mechanism that continuously updates hand joint positions and angles based on the kinematic model and observed data. This feedback loop refines the tracking accuracy over time by correcting deviations and adapting to changes in hand motion, resolving the contradiction between accuracy and complexity.
2Productivity
If simple tracking methods are used, then the computational load is low, but the function control performance is suboptimal
Solution Approach 1:
The system changes key parameters including angle information estimation, kinematic model parameters, and filter updating parameters to optimize tracking accuracy. By dynamically adjusting these parameters based on hand joint configurations and motion patterns, the system achieves high function control performance while managing computational requirements through intelligent parameter selection.
3Reliability
If accurate hand joint tracking is implemented, then function control improves, but the system complexity increases
Solution Approach 1:
The tracking apparatus is designed with multi-functionality, where the extended Kalman filter serves multiple purposes: state prediction, data association, and parameter optimization. The kinematic model simultaneously handles both forward and inverse kinematics, and the angle estimation module works across different hand configurations. This universality reduces overall system complexity while maintaining high reliability for various function control tasks.
Data Source
AI summary
A method and apparatus for tracking hand joints are disclosed, where the method of tracking hand joints includes estimating angle information of finger joints based on initial positions of hand joints obtained from an image, generating a kinematic model of the hand joints based on the initial positions of the hand joints and the angle information of the finger joints, and tracking the hand joints by updating at least one of positions or angles of the hand joints based on the initial positions of the hand joints and the kinematic model.