Eye-tracking Calibration via Head Rotation and Feedback

Solution Overview

Problem

Current eye-tracking systems require frequent recalibration and are sensitive to the inadvertent slipping of the tracker on the user's face, which disrupts their accuracy and efficiency, especially in applications like Virtual and Augmented Reality, medical ophthalmology, and consumer measurement.

Innovation Solution

An improved calibration method that involves the user looking at a fixed point while rotating their head, collecting head and eye-tracking data to generate a map of eye angles to gaze vectors, allowing for minimal recalibration and real-time compensation for tracker slip, using a combination of transmit and detect modules, head trackers, and vestibulo-ocular reflex techniques.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional eye-tracking calibration methods are used, then the system can provide basic eye-tracking functionality, but the system requires frequent recalibration and is sensitive to tracker slipping

Engineering Contradiction:

Improvecalibration stabilityVSAvoidrecalibration frequency

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary calibration by having the user rotate their head while looking at a fixed point, collecting head positional data and eye-tracking data to generate a comprehensive calibration map. This preliminary calibration accounts for individual anatomical variations and establishes a robust baseline that reduces the need for frequent recalibration.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system continuously monitors eye-tracking data and compares it against the calibration map to detect deviations caused by tracker slipping. When slipping is detected, the system automatically compensates by adjusting the calibration parameters in real-time, maintaining accuracy without requiring user intervention or frequent recalibration.

Inventive Principle:

Principle #23Feedback

2Ease of operation

If traditional eye-tracking calibration methods are used, then the system can operate with simple calibration procedures, but the system is sensitive to inadvertent slipping of the tracker

Engineering Contradiction:

Improvecalibration simplicityVSAvoidaccuracy under slip conditions

Core Design Contradiction:

Ease of operationVSReliability

Solution Approach 1:

The system continuously monitors eye-tracking data and compares it against the calibration map to detect deviations caused by tracker slipping. When slipping is detected, the system automatically compensates by adjusting the calibration parameters in real-time, maintaining accuracy without requiring user intervention or frequent recalibration.

Inventive Principle:

Principle #23Feedback

Solution Approach 2:

The system dynamically adjusts calibration parameters based on detected tracker position changes. By monitoring deviations in eye-tracking data and automatically modifying calibration parameters, the system maintains measurement accuracy even when the tracker slips on the user's face.

Inventive Principle:

Principle #35Parameter changes

3Measurement precision

If comprehensive calibration data is collected through head rotation, then the calibration accuracy is improved, but the calibration process complexity increases

Engineering Contradiction:

Improveeye angle to gaze vector mapping accuracyVSAvoidcalibration process complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system performs preliminary calibration by having the user rotate their head while looking at a fixed point, collecting head positional data and eye-tracking data to generate a comprehensive calibration map. This preliminary calibration accounts for individual anatomical variations and establishes a robust baseline that reduces the need for frequent recalibration.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system automatically processes the calibration data and generates the calibration map without requiring complex manual configuration or expert intervention. The automated processing reduces the perceived complexity for the user while maintaining high measurement precision.

Inventive Principle:

Principle #25Self-service

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

This method provides seamless, intuitive, and non-invasive eye-tracking with reduced recalibration needs and real-time slip compensation, enhancing the accuracy and reliability of eye-tracking systems across various applications.

Implementation Method 1

determining the unique angle at which the beam reflects off the cornea of the eye

Methodology Applied

Scientific EffectReflection: Reflection

Implementation Method 2

having the user rotating his/her head about an axis; collecting head positional and eye-tracking data including eye angle

Methodology Applied

Scientific EffectVestibulo-ocular reflex:

Data Source

PatentUS10908683B2Eye-tracking calibration

Publication Date: 2021.02.02 GOOGLE LLC

AI summary

Aspects of the present disclosure describe an improved calibration method for systems, methods, and structures that provide eye-tracking by 1) steering a beam of light through the effect of a microelectromechanical system (MEMS) onto a surface of the eye and 2) detecting light reflected from features of the eye including corneal surface, pupil, iris—among others. Positional/geometric/feature/structural information pertaining to the eye is determined from timing information associated with the reflected light.