On-Axis Eye Gaze Tracking with Dynamic Illumination
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing eye-tracking systems require multiple illumination sources and complex setups, limiting their size, modularity, and usability, particularly in handheld devices, and struggle with variability in user parameters and false positive detection.
Innovation Solution
A single on-axis imaging system with dynamic illumination and eye candidate filtering techniques, allowing for reliable eye tracking with a single camera and coaxial illumination source, which optimizes image quality and reduces false positives.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If multiple illumination sources and imaging systems are used to determine user's point of gaze, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The patent extracts and eliminates the off-axis illumination source from the traditional eye-tracking system, retaining only the on-axis illumination source. This simplification reduces device complexity while the patent compensates by optimizing the on-axis illumination parameters and using advanced image processing algorithms to maintain gaze estimation accuracy.
Solution Approach 2:
The single on-axis imaging system performs multiple functions: it captures eye images for gaze tracking, detects pupil position, identifies corneal reflections, and filters false positives all through one imaging apparatus. This multi-functionality reduces the need for multiple separate components while maintaining measurement precision.
2Reliability
If multiple illumination sources are used, then reliability of eye detection is improved, but ease of manufacture deteriorates
Solution Approach 1:
The patent removes the off-axis illumination source from the system, simplifying the manufacturing process. The single on-axis illumination source is easier to align and integrate into devices, particularly handheld devices, while the patent maintains detection reliability through optimized illumination intensity and advanced image processing techniques that filter false positives.
Solution Approach 2:
The patent optimizes parameters of the single on-axis illumination source, such as intensity, wavelength, and timing, to maximize eye detection reliability. By carefully controlling these parameters, the system achieves reliable performance without requiring multiple illumination sources, thereby simplifying manufacturing.
3Measurement precision
If on-axis and off-axis illumination sources are used with image differencing, then false positive detection is reduced, but device complexity increases
Solution Approach 1:
The patent extracts and removes the off-axis illumination source, relying solely on the on-axis illumination source. To compensate for the loss of image differencing capability, the patent implements sophisticated false positive filtering algorithms that analyze image features, pupil geometry, and corneal reflection patterns to distinguish true eye detections from false positives.
Solution Approach 2:
The patent replaces the mechanical/optical approach of using multiple illumination sources with a computational approach. Advanced image processing and machine learning algorithms substitute for the physical image differencing method, achieving false positive reduction through software rather than hardware complexity.
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
Enables smaller, more modular eye-tracking systems that can accommodate a wider range of users and environments, improving reliability and reducing false positive detection rates, while maintaining accurate gaze estimation.
Implementation Method 1
capturing an image using the single on-axis imaging apparatus
Data Source
Figure 1
Figure 2~3
Figure 4
AI summary
A system and method are provided for performing eye gaze tracking. The system is configured for and the method comprises optimizing illumination of a scene for a single on-axis imaging apparatus, capturing an image using the single on-axis imaging apparatus under the optimized illumination, and processing the captured image to perform a gaze estimation. Dynamic illumination control, eye candidate detection and filtering, and gaze estimation techniques are also provided.