Head-Mounted Display Pose Tracking With Hand-Based Drift Calibration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing head-mounted displays face accuracy issues due to self-tracking device errors, which can lead to incomplete or inaccurate auxiliary data provision, especially when environmental or human factors cause reduced six-degree-of-freedom information, resulting in poor user experience.
Innovation Solution
A head-mounted display system that calculates drift information between hand pose and self-tracking pose to calibrate self-tracking pose information, generating six-degree-of-freedom data even when self-tracking device data is incomplete, and fuses pose information to maintain accurate interaction and display.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Duration of action of moving object
If self-tracking device is used for tracking pose over time, then tracking functionality is provided, but error values accumulate and accuracy reduces
Solution Approach 1:
The system continuously compares the self-tracking pose data with hand pose data derived from image capturing, calculates drift information, and feeds back calibration adjustments to correct accumulated errors. This closed-loop feedback mechanism maintains accuracy over extended tracking durations by periodically correcting drift.
Solution Approach 2:
The system performs self-calibration by using its own image capturing device to generate reference hand pose data, which is then used to correct the self-tracking pose data. This self-service approach allows the system to autonomously correct its own accumulated errors without external intervention.
2Reliability
If self-tracking device operates in blocked environment or relocation mode, then device can continue operation, but only three-degree-of-freedom information is generated instead of complete six-degree-of-freedom information
Solution Approach 1:
The system uses hand pose data derived from image capturing as an intermediary to supplement incomplete self-tracking pose information. When self-tracking provides only three-degree-of-freedom data, the hand pose acts as a mediator to reconstruct the missing three degrees of freedom, restoring complete six-degree-of-freedom pose information.
Solution Approach 2:
The system dynamically changes the source and composition of pose parameters based on operational conditions. In blocked environments, it transitions from relying solely on self-tracking six-degree-of-freedom data to combining self-tracking three-degree-of-freedom data with image-derived hand pose data, effectively changing how pose parameters are obtained and maintained.
3Ease of operation
If drift calibration is not performed on self-tracking device coordinate system, then device operation is simple, but auxiliary data cannot be correctly provided to head-mounted display
Solution Approach 1:
The system performs self-calibration using its own image capturing device to generate reference data for correcting self-tracking pose information. This self-service calibration mechanism maintains data accuracy without requiring complex external calibration equipment or procedures, preserving ease of operation while ensuring precision.
Data Source
AI summary
A head-mounted display, pose tracking system, and method are provided. The head-mounted display generates a plurality of first real-time images including a user holding a self-tracking device in a physical space. The head-mounted display receives first self-tracking pose information from the self-tracking device. The head-mounted display generates a hand pose information based on the first real-time images, and the hand pose information is a six-degree-of-freedom information. The head mounted display calculates drift information of the hand pose information and the first self-tracking pose information. The head mounted display calibrates the first self-tracking pose information based on the drift information.