Eye Tracking Glint Identification via Pixel Intensity Thresholding
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing eye tracking systems face difficulties in accurately determining gaze direction due to reflections from parts of the eye other than the cornea, which can lead to errors in identifying pupil direction and gaze direction.
Innovation Solution
The method involves identifying scleral reflections by determining the pixel intensity of a glint and its neighboring pixels, with a threshold value to differentiate between corneal and scleral reflections, thereby reducing errors in eye tracking algorithms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If glints are identified in images for eye tracking, then gaze direction can be determined, but reflections from sclera may be mistakenly identified as corneal reflections introducing errors
Solution Approach 1:
The patent applies local quality by analyzing the specific characteristics of pixel intensity at the glint location versus its neighborhood. By examining the local intensity distribution pattern (sharp peak for corneal reflections vs. more uniform for scleral reflections), the system can distinguish between different reflection types based on their unique local properties, thereby improving identification reliability while maintaining measurement precision
Solution Approach 2:
The patent utilizes parameter changes by comparing the pixel intensity parameter between the glint and its neighboring pixels. The ratio or difference in intensity values serves as a discriminative parameter that changes differently for corneal versus scleral reflections, enabling the system to differentiate reflection types and improve both accuracy and reliability of gaze determination
2Illumination intensity
If additional light sources are used to illuminate the eyes, then image quality improves, but reflections from other parts of the eye increase causing identification difficulties
Solution Approach 1:
The patent converts the harmful effect of scleral reflections into a beneficial discrimination feature. By analyzing the intensity characteristics of these reflections, the system can identify and filter out scleral reflections from corneal reflections. The additional illumination that causes multiple reflections also provides the intensity contrast needed to distinguish between them, turning a potential harm into a useful diagnostic feature
Solution Approach 2:
The patent introduces an intermediary analysis step between image capture and gaze determination. The pixel intensity comparison acts as an intermediary filter that processes the raw image data, identifying and eliminating false reflections before they can affect the final gaze calculation. This intermediary layer resolves the conflict between needing sufficient illumination and avoiding harmful reflections
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 eye tracking by correctly distinguishing between corneal and scleral reflections, reducing the risk of mistaken identification and improving the reliability of gaze direction determination.
Implementation Method 1
The image is a result of the image sensor detecting light from one or more illuminators reflected from the eye of the user
Data Source
AI summary
A method of identifying scleral reflections in an eye tracking system is disclosed. A glint is identified in an image from an image sensor, wherein the glint is a representation in the image of a reflection of light from a cornea of the eye of the user or from a sclera of the eye of the user. A first pixel intensity of the glint is determined, a second pixel intensity of neighbor pixels of the glint is determined, and an absolute value of the difference between the first pixel intensity of the glint and the second pixel intensity of the neighbor pixels of the glint is determined. The glint is identified as a representation of a reflection from the sclera of the eye of the user on condition that the determined absolute value of the difference is below a predetermine threshold value.