Eye Tracking Calibration via Touch Offset Correction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Eye tracking systems face challenges in accurately determining user gaze locations due to anatomical differences, such as variations in the location of the fovea, leading to offsets between the visual and optical axes, which complicates precise gaze estimation and can make current calibration processes difficult to use, especially in consumer settings.

Innovation Solution

The system calibrates an eye tracking system using touch inputs on a touch-sensitive display by comparing the gaze location determined by the eye tracking system with the touch location, applying corrections based on the offset, and continuously updating the calibration during ordinary use without interrupting the user experience, utilizing classification algorithms and contextual filters to identify reliable touch inputs.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional calibration methods are used to account for anatomical differences, then measurement precision of gaze location is improved, but device complexity and ease of operation deteriorate due to difficult calibration procedures

Engineering Contradiction:
Improvegaze location accuracyVSAvoidcalibration difficulty
Core Design Contradiction:
Measurement precisionVSEase of operation

Solution Approach 1:

The system performs calibration automatically in the background without requiring user intervention or participation in calibration tasks. The calibration process services itself by utilizing naturally occurring touch inputs and associated gaze data that users provide during normal device operation, eliminating the need for separate calibration sessions while maintaining high measurement precision

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system performs calibration actions preliminarily by continuously updating calibration parameters in the background before they are needed for accurate gaze tracking. Calibration is not waited for but proactively maintained throughout device usage, ensuring precision is already optimized when users interact with the interface

Inventive Principle:
Principle #10Preliminary action

2Measurement precision

If calibration is performed continuously to maintain accuracy, then measurement precision is improved, but loss of time and productivity worsen due to potential interruptions

Engineering Contradiction:
Improvegaze location accuracyVSAvoidcalibration interruption time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The calibration process operates continuously in the background without interruption to users. The system continuously collects touch and gaze data, continuously updates calibration parameters, and maintains accurate gaze tracking throughout device usage, making the useful action of calibration uninterrupted and transparent to users

Inventive Principle:
Principle #20Continuity of useful action

Solution Approach 2:

The system uses touch inputs as an intermediary element to bridge calibration without requiring direct user participation in calibration tasks. By leveraging the intermediary touch interaction that users naturally perform, the system obtains calibration data indirectly, eliminating the need for users to stop their workflow for calibration

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP3005030B1Calibrating eye tracking system by touch input
Publication Date: 2017.09.06 MICROSOFT TECHNOLOGY LICENSING LLC
  • EP3005030B1 patent drawingFigure 1~2
  • EP3005030B1 patent drawingFigure 3~4
  • EP3005030B1 patent drawingFigure 5

AI summary

Embodiments are disclosed that relate to calibrating an eye tracking system via touch inputs. For example, one disclosed embodiment provides, on a computing system comprising a touch sensitive display and an eye tracking system, a method comprising displaying a user interface on the touch sensitive display, determining a gaze location via the eye tracking system, receiving a touch input at a touch location on the touch sensitive display, and calibrating the eye tracking system based upon an offset between the gaze location and the touch location.