Gaze Tracking Eyewear Reflection Separation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Gaze-tracking systems face accuracy issues due to interference from reflections caused by eyewear, which can lead to incorrect identification of ocular features and reduced precision in determining gaze direction.

Innovation Solution

The system employs a method involving multiple images captured at different illumination levels to distinguish between ocular reflections and eyewear reflections by analyzing changes in pixel brightness, using pulse-width modulation to adjust illumination levels and exclude saturated pixels associated with eyewear reflections, thereby improving the accuracy of gaze detection.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If illumination is used to capture eye images for gaze tracking, then gaze detection can be performed, but reflections from eyewear interfere with accurate identification of ocular features

Engineering Contradiction:
Improvegaze detection accuracyVSAvoideyewear reflection interference
Core Design Contradiction:
Measurement precisionVSObject-affected harmful factors

Solution Approach 1:

The system dynamically adjusts illumination intensity between two levels and captures images at each level. By varying the illumination condition, the system creates different reflection patterns where ocular features and eyewear reflections respond differently, enabling separation of the harmful reflections from the useful ocular signals

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent changes the illumination parameter (intensity) to distinguish between ocular features and eyewear reflections. By capturing images at different illumination levels and comparing pixel brightness changes, the system identifies pixels that saturate at high illumination (eyewear reflections) versus pixels that respond proportionally (ocular features), thereby eliminating the harmful interference

Inventive Principle:
Principle #35Parameter changes

2Measurement precision

If multiple images at different illumination levels are captured to distinguish ocular reflections from eyewear reflections, then measurement precision improves, but device complexity and processing time increase

Engineering Contradiction:
Improvegaze detection accuracyVSAvoidillumination control and image processing complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system uses periodic illumination at two distinct intensity levels to capture images sequentially. This periodic action simplifies the control mechanism compared to continuous variable illumination, while still providing sufficient information to distinguish ocular from eyewear reflections through comparison of the two captured images

Inventive Principle:
Principle #19Periodic action

Solution Approach 2:

The patent creates a simplified computational model that copies the physical phenomenon: pixels from ocular features show proportional brightness changes between illumination levels, while eyewear reflection pixels show saturation. This copying approach allows simple threshold-based filtering to eliminate complex reflection interference

Inventive Principle:
Principle #26Copying

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 approach enhances the accuracy of gaze-tracking by effectively differentiating between ocular features and eyewear reflections, reducing noise and improving the reliability of gaze direction computation, even in environments with varying ambient light conditions.

Implementation Method 1

an illumination system configured to provide a first level of illumination to a user's eye

Methodology Applied
Scientific EffectLight emission: Light

Implementation Method 2

compare brightness of corresponding pixels of a selected first image and a selected second image to distinguish a reflection of the illumination by the eye from a reflection of the illumination by eyewear

Methodology Applied
Scientific EffectLight reflection: Reflection

Data Source

PatentEP3204891B1Gaze tracking through eyewear
Publication Date: 2021.08.18 MICROSOFT TECHNOLOGY LICENSING LLC
  • EP3204891B1 patent drawingFigure 1
  • EP3204891B1 patent drawingFigure 2
  • EP3204891B1 patent drawingFigure 3

AI summary

A method (74) to furnish input representing gaze direction in a computer system operatively coupled to a vision system. In this method, a first image of an eye at a first level of illumination is acquired by a camera of the vision system (78). The first image is obtained from the camera, and a second image of the eye corresponding to a second, different level of illumination is also obtained (80). Brightness of corresponding pixels of the first and second images is compared in order to distinguish a reflection of the illumination by the eye from a reflection of the illumination by eyewear (84). The input is then furnished based on the reflection of the illumination by the eye (90).