Eye Tracking Illumination Control for Reflection Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Remote eye tracking systems face challenges in maintaining robustness due to issues like occlusions from spectacles, head movement, and extreme tracking angles, which reduce the quality and quantity of usable images for eye tracking.
Innovation Solution
The method involves categorizing reflections based on their position and other criteria to control light sources, adjusting their intensity to remove disruptive reflections and enhance useful ones, thereby improving image quality and tracking robustness.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Illumination intensity
If light sources are constantly on during image acquisition, then illumination intensity is sufficient, but disruptive reflections from spectacles increase
Solution Approach 1:
The patent applies periodic action by pulsing light sources during the exposure time window of the image sensor rather than keeping them constantly on. This temporal modulation ensures sufficient illumination for image capture while reducing the duration and intensity of reflective artifacts from spectacles, thereby resolving the contradiction between maintaining illumination and minimizing disruptive reflections.
Solution Approach 2:
The patent implements dynamics by actively adjusting the intensity of individual light sources based on real-time detection of reflection patterns. The system dynamically modifies which light sources are active and at what intensity levels, adapting to the user's head position, eye position, and spectacle configuration to minimize disruptive reflections while maintaining adequate illumination.
2Reliability
If multiple light sources are used to improve tracking quality, then illumination coverage increases, but the complexity of controlling light intensity separately for each source increases
Solution Approach 1:
The patent applies feedback by using image analysis to detect reflection patterns and feed this information back to the control system. Based on the detected reflections and their characteristics, the system automatically adjusts the intensity of individual light sources, eliminating the need for complex manual control while maintaining high tracking quality through adaptive optimization.
Solution Approach 2:
The system implements self-service by automatically determining the optimal intensity configuration for each light source based on real-time image analysis. The processing unit autonomously evaluates reflection patterns and adjusts light source intensities without external intervention, simplifying the control interface while maintaining reliable tracking performance.
3Manufacturing precision
If light source intensity is adjusted to remove disruptive reflections, then image quality improves, but the time required for adjustment and re-capture increases
Solution Approach 1:
The patent maintains continuity of useful action by performing light source intensity adjustments within the same image acquisition sequence rather than requiring separate adjustment and capture phases. The system continuously monitors reflection patterns and modifies light source intensities on-the-fly during ongoing image capture, eliminating idle adjustment time and maintaining uninterrupted eye tracking operation.
Solution Approach 2:
The patent applies preliminary action by pre-configuring multiple light sources in different spatial positions before image capture begins. This allows the system to quickly switch between different light source combinations and intensity levels during capture based on detected reflection patterns, rather than requiring time-consuming physical repositioning or manual adjustment during the capture process.
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 significantly increases the number of usable images for eye tracking, enhancing the system's robustness and accuracy even in challenging situations like occlusions and extreme angles.
Implementation Method 1
a plurality of light sources capable of illuminating the eye of the user
Implementation Method 2
determines whether reflections are detected in the first image
Data Source
Figure 1~3
Figure 4
Figure 5
AI summary
The invention relates to an eye tracking device and a method for operating an eye tracking device (30) comprising an imaging device (32), a plurality of light sources (34), a processing unit and a control unit. The imaging device (32) captures a first image (36a) while at least one of the light sources (34) emits light. If at least one first reflection (14; 16; 16a - 16f) is detected, a position in the first image (36a) of the at least one first reflection (14; 16; 16a - 16f) is determined, the first reflection (14; 1 6; 16a - 16f) is categorized on the basis of the position in the first image (36a) and if the first image (36a) does not fulfil a predefined quality criterion, the plurality of light sources (34) is controlled in dependence of the categorization by changing the light intensity of at least one light source (34).