Eye Tracking Accuracy via Pupil Shape Modeling

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current eye tracking methods in VR/AR systems face challenges in accurately determining gazing vectors and head center positions, leading to reduced accuracy and user experience in virtual reality environments.

Innovation Solution

An eye tracking method and electronic device that constructs an eye model using pupil shape information, captures images of the eye, and adjusts the head center position based on actual and simulated pupil shape information to improve gazing vector determination and accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional eye tracking methods are used in VR/AR systems, then the system can provide basic eye tracking functionality, but the accuracy of gazing vector determination and head center position is reduced

Engineering Contradiction:
Improvegazing vector determination accuracyVSAvoidhead center position accuracy
Core Design Contradiction:
Measurement precisionVSReliability

Solution Approach 1:

The system performs preliminary calibration by capturing multiple images of the user's eye at different known gazing positions before actual eye tracking begins. These pre-captured images are used to establish the relationship between pupil shape variations and gazing vectors, creating a calibration dataset that improves subsequent measurement accuracy.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system creates a digital copy or model of the user's specific eye geometry based on calibration images. This eye model includes parameters such as corneal curvature, pupil size, and iris patterns, which are then used to simulate and compare against real-time pupil shapes, enabling more accurate gazing vector determination without requiring complex physical measurements.

Inventive Principle:
Principle #26Copying

2Measurement precision

If multiple pupil shape information data are collected and analyzed, then the accuracy of eye tracking is improved, but the computational complexity and processing time increase

Engineering Contradiction:
Improveeye tracking accuracyVSAvoidprocessing circuit complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The system extracts only the most relevant features from captured eye images, such as pupil center position, pupil radius, and iris boundary points, rather than processing entire image datasets. This feature extraction approach maintains measurement precision while significantly reducing the computational burden on the processing circuit.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The system transforms raw image data into simplified geometric parameters (e.g., converting pixel coordinates to angular measurements, representing pupil shapes as ellipses with specific parameters). This parameter transformation reduces data dimensionality and complexity while preserving the essential information needed for accurate eye tracking calculations.

Inventive Principle:
Principle #35Parameter changes

Data Source

PatentEP3540574B1Eye tracking method, electronic device, and non-transitory computer readable storage medium
Publication Date: 2021.08.11 HTC CORP
  • EP3540574B1 patent drawingFigure 1
  • EP3540574B1 patent drawingFigure 2
  • EP3540574B1 patent drawingFigure 3

AI summary

An eye tracking method includes: constructing, by a processing circuit, an eye model; analyzing, by the processing circuit, a first head center position, according to a plurality of first pupil shape information and the eye model, wherein the plurality of first pupil shape information correspond to a plurality of first gazing vectors; capturing, by a camera circuit, a first image of the eye; analyzing, by the processing circuit, a determined gazing vector, according to the eye model and the first image; and adjusting, by the processing circuit, the first head center position according to an actual pupil shape information group and a plurality of simulated pupil shape information groups.