Optical See-Through Display Calibration via Automated Head Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional optical see-through display calibration methods for augmented reality systems require multiple manual steps and are prone to errors due to user input, such as head movements and inaccurate measurements, which can undermine the accuracy of the calibration process.
Innovation Solution
An automated calibration method that guides users to align virtual targets with real-world targets, collects multiple pose matrices to account for head movements, and averages readings to smooth out errors, eliminating the need for physical triggers and reducing manual input errors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional manual calibration methods are used, then the calibration process can be completed, but the accuracy is reduced due to user input errors and head movements
Solution Approach 1:
The system performs self-calibration by automatically tracking the user's head movements and eye position through computer vision algorithms. The calibration process no longer requires manual input from the user - the system captures images, detects features automatically, and computes calibration parameters without human intervention, thereby eliminating user input errors while maintaining ease of operation.
Solution Approach 2:
The patent replaces manual mechanical calibration operations with an automated computer vision system. Instead of requiring users to manually adjust components or input data, the system uses image capture, feature detection, and automated computation to perform calibration, substituting mechanical/manual processes with optical and computational processes.
2Reliability
If multiple manual calibration steps are required, then comprehensive calibration can be achieved, but the time consumption and user burden increase
Solution Approach 1:
The system performs preliminary actions by automatically capturing multiple images and pre-processing them to extract features before the actual calibration computation. The user simply needs to wear the device and maintain general positioning, while the system proactively completes all calibration steps including feature detection, coordinate transformation, and parameter computation without requiring sequential manual user actions.
Solution Approach 2:
The calibration process operates continuously by capturing a sequence of images and processing them in real-time. The system maintains continuous tracking of head movements and eye position throughout the calibration period, smoothly transitioning between calibration steps without interruption or manual repositioning, thereby completing comprehensive calibration efficiently.
3Measurement precision
If physical triggers and manual inputs are used, then calibration data can be collected, but errors from user input reduce accuracy
Solution Approach 1:
The system eliminates the need for physical triggers and manual inputs by using automated computer vision to detect and track calibration features. The eye-tracking subsystem automatically monitors the user's gaze position, and the head-tracking system automatically records head movements, collecting all necessary calibration data without requiring the user to press buttons or provide explicit inputs.
Solution Approach 2:
The patent introduces computer vision algorithms and image processing as intermediaries between the physical calibration process and data collection. Instead of directly relying on manual user inputs, the system uses visual feature detection and automated image analysis as intermediary steps to accurately capture calibration information, thereby eliminating direct manual interaction while maintaining high precision.
Data Source
AI summary
Disclosed are a system, apparatus, and method for calibrating an optical see-through display (OSD). The OSD virtual display size is estimated as a starting point for determining an eye to camera distance. In response to determining the eye to camera distance and comparing the result with a measured eye to camera distance an updated display size may be determined. A user's head movement may be tracked in order to determine when a visual alignment based calibration routine is complete. When a user is not viewing a calibration target a request is sent to prompt the user to realign the OSD. When a user is still after a period of alignment with the OSD, the alignment and calibration procedure may be assumed as complete. A buffer may receive calibration values from before and after the calibration procedure is complete and the values may be averaged or filtered for accuracy.