Eye Tracking Using Resting Position Calibration
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Eye-based user interfaces face challenges with imprecision in determining user gaze, leading to frustration and inefficiency, as users struggle to control interfaces using gaze-based methods due to the lack of precision, requiring significant interface modifications and high error tolerance.
Innovation Solution
A system that maps eye gestures to commands by establishing a resting position for the eyes, using eye boxes to determine horizontal and vertical positions, and interpreting movements as directional gestures within defined regions, allowing for more precise and efficient control without the need for fine-tuned gaze alignment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If gaze-based tracking methods are used to determine user focus, then user interface interaction is enabled, but precision in determining where the user is looking deteriorates
Solution Approach 1:
The patent divides the eye into multiple detectable features (pupils, irises, sclera, eyelids, eyelashes) and tracks their relative positions and movements. By segmenting the eye into distinct anatomical features and analyzing their spatial relationships, the system achieves more precise gaze determination than traditional pupil-only tracking methods
Solution Approach 2:
The patent introduces intermediate computational steps that analyze the relative positions and movements of multiple eye features before determining gaze direction. This intermediary analysis of feature relationships acts as a mediator between raw eye images and final gaze determination, improving precision through multi-feature correlation
2Ease of operation
If error tolerance is increased to accommodate imprecise gaze control, then user interface usability is maintained, but the selectable buttons must be made larger
Solution Approach 1:
The patent replaces traditional mechanical cursor control systems with gesture-based eye movement recognition. By detecting specific gesture patterns (saccades, smooth pursuits, blinks) and mapping them to interface commands, the system eliminates the need for precise pixel-level gaze alignment, allowing standard-sized buttons to remain usable
3Ease of operation
If traditional gaze-based control is used, then user interface interaction is possible, but time consumption increases due to imprecise control
Solution Approach 1:
The patent utilizes periodic eye movements (natural blinking patterns, regular saccades during reading) as the basis for gesture recognition. By detecting these periodic eye behaviors and mapping them to interface commands, the system enables efficient interaction without requiring continuous, precise gaze stabilization, reducing the time needed to control the interface
Data Source
AI summary
In some embodiments, a method receives images of eyes of a user. The method computes a vertical resting position of the eyes and computes a horizontal resting position of the eyes based on an average horizontal position of both of the eyes. An image of the eyes of the user is received. Then, the method calculates when an offset for a direction and a magnitude of the eyes is within a region in a plurality of regions and determines a command for the region. A call for the command is generated to a device to cause the command to be performed on a user interface.