Eye Gaze Calibration Using Multi-View Image Coordinates
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing ophthalmic devices face inaccuracies in eye tracking due to human error during patient fixation, which can lead to incorrect readings and require cumbersome initialization procedures, and the operation of retina scanning systems can interfere with diagnostic procedures.
Innovation Solution
An automated method for initializing and calibrating a camera-based gaze tracking system using multiple image capture devices and a control processor to detect eye characteristics, determine calibration offsets and gains, and track eye position and orientation relative to the optical axis, allowing for accurate eye fixation determination and alignment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If human operators monitor patient fixation and guide initialization procedures, then eye alignment accuracy can be maintained, but human error and operational complexity increase
Solution Approach 1:
The system performs self-calibration by automatically capturing images at multiple locations, detecting eye characteristics, and computing calibration parameters without human intervention. The eye tracker and control processor work autonomously to initialize and calibrate the system, eliminating the need for operators to guide patients through manual fixation procedures.
Solution Approach 2:
The patent replaces manual monitoring and guidance operations with an automated image processing system. The control processor analyzes captured images, detects eye characteristics, and determines calibration parameters automatically, substituting human cognitive and manual operations with computational algorithms.
2Measurement precision
If retina scanning systems are used to track eye position, then accurate eye fixation can be determined, but interference with diagnostic procedures occurs
Solution Approach 1:
The system uses an intermediary image capture device that records eye characteristics without performing active retina scanning. This intermediary imaging approach provides sufficient eye position data for calibration while avoiding the interference problems associated with active retina scanning systems during diagnostic procedures.
Solution Approach 2:
The system creates a simplified copy of retina scanning functionality using standard image capture and processing. Instead of implementing full retina scanning capability, the patent uses captured images to extract eye characteristic information, providing a lighter-weight solution that achieves the necessary eye tracking without the drawbacks of complete retina scanning systems.
3Measurement precision
If multiple image capture devices are used for calibration, then calibration accuracy improves, but device complexity increases
Solution Approach 1:
The eye tracker serves multiple functions: it captures images for calibration, tracks eye position during procedures, and provides data for both initialization and ongoing monitoring. This multi-functional device eliminates the need for separate calibration equipment and retina scanning systems, reducing overall system complexity while maintaining calibration accuracy.
Solution Approach 2:
The patent combines the calibration function and eye tracking function into a single integrated system. The same image capture device and processing algorithms are used for both initialization calibration and procedural eye position monitoring, merging what could be separate systems into one unified solution.
Data Source
AI summary
Systems and methods for initializing and calibrating an eye tracking system include an eye tracker configured to capture a first image of an eye from a first location and a second image of the eye from a second location, and a control processor configured to detect a first plurality of eye characteristics from the first image, the eye characteristics having first corresponding image coordinates, detect a second plurality of eye characteristics from the second image, the eye characteristics having second corresponding image coordinates, and determine a calibration offset and a calibration gain. The control processor may be further configured to determine an eye fixation position and orientation relative to an optical axis of the eye tracker based at least in part on the first corresponding image coordinates and/or the second corresponding image coordinates.