Gaze Tracking Calibration via Offset Vector Adjustment

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Gaze tracking systems require frequent recalibration due to user changes or environmental factors, disrupting user experience by necessitating explicit calibration procedures that interfere with immersion in content.

Innovation Solution

A method that uses gaze tracking data to identify target visuals within image data and calculates an offset vector to update the estimated gaze location without user input, allowing for continuous calibration during system operation without interrupting the user experience.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If dedicated calibration procedures are performed to improve measurement precision of gaze tracking, then calibration accuracy is improved, but user immersion and ease of operation deteriorate due to interruptions

Engineering Contradiction:
Improvegaze tracking accuracyVSAvoiduser immersion
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The system performs calibration automatically without requiring user participation. The gaze tracking system monitors user gaze behavior during content consumption and autonomously adjusts calibration parameters based on detected gaze patterns, eliminating the need for explicit calibration procedures and maintaining user immersion throughout the process

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

Calibration is performed continuously in the background during normal system operation rather than through discrete interruption-based procedures. The system continuously monitors gaze data and incrementally adjusts calibration parameters, ensuring both accurate tracking and uninterrupted user experience

Inventive Principle:
Principle #20Continuity of useful action

2Reliability

If frequent recalibration is performed to maintain measurement precision under changing conditions, then gaze tracking reliability is improved, but user frustration and loss of time increase

Engineering Contradiction:
Improvegaze tracking reliabilityVSAvoidcalibration time
Core Design Contradiction:
ReliabilityVSLoss of time

Solution Approach 1:

The system performs calibration continuously during normal operation rather than through periodic interruptions. Gaze data is constantly monitored and calibration parameters are incrementally adjusted in real-time, maintaining reliability without requiring users to pause their activities for recalibration

Inventive Principle:
Principle #20Continuity of useful action

Solution Approach 2:

The system autonomously detects when recalibration is needed based on changes in gaze patterns or environmental conditions and performs adjustment automatically without user involvement, eliminating time loss associated with explicit calibration procedures

Inventive Principle:
Principle #25Self-service

3Measurement precision

If explicit calibration procedures are required to ensure measurement precision, then calibration accuracy is improved, but device complexity and ease of operation worsen

Engineering Contradiction:
Improvecalibration accuracyVSAvoidcalibration procedure complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The gaze tracking system performs self-calibration by automatically analyzing user gaze behavior patterns during content consumption and adjusting calibration parameters without requiring users to follow complex calibration procedures, thereby maintaining accuracy while eliminating operational complexity

Inventive Principle:
Principle #25Self-service

Data Source

PatentEP3146465B1Gaze detection calibration
Publication Date: 2024.07.10 MICROSOFT TECHNOLOGY LICENSING LLC
  • EP3146465B1 patent drawingFigure 1
  • EP3146465B1 patent drawingFigure 2
  • EP3146465B1 patent drawingFigure 3

AI summary

Examples relating calibrating an estimated gaze location are disclosed. One example method comprises monitoring the estimated gaze location of a viewer (22, 62) using gaze tracking data (50) from a gaze tracking system (54). Image data (64) for display via a display device (14) is received and, without using input from the viewer (22, 62), at least one target visual that may attract a gaze of the viewer (22, 62) and a target location of the target visual are identified within the image data (64). The estimated gaze location of the viewer (22, 62) is compared with the target location of the target visual. An offset vector is calculated based on the estimated gaze location and the target location. The gaze tracking system is calibrated using the offset vector.