Array Camera Eye Tracking via Dynamic Illumination and Sensor Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current eye tracking devices face limitations in light gathering ability, leading to larger imaging sensors and lenses, which hinder integration into mobile devices due to thickness constraints, and struggle with accurate pupil contour determination due to low intensity contrast between the pupil and iris, especially in remote gaze tracking with wide range of motion.
Innovation Solution
The use of an array camera with multiple lenses or image sensors and dynamic illumination control, where multiple IR light sources are used to generate glints, allowing for precise estimation of the pupil center and gaze vector through 3D position calculation and super-resolution image synthesis, while minimizing interference from glints.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If larger imaging sensors and lenses are used to improve light gathering ability, then measurement precision of eye tracking is improved, but device thickness increases making mobile integration difficult
Solution Approach 1:
The patent divides the imaging function into multiple small sensors arranged in an array, each with its own lens element. This segmentation allows the system to achieve sufficient light gathering capability through the collective area of multiple small sensors while maintaining a thin profile, as each individual sensor-lens combination can be made very thin.
Solution Approach 2:
The patent transitions from a single large sensor in the z-dimension (thickness) to multiple small sensors arranged in the x-y plane. This dimensional redistribution allows the total sensing area to be maintained while eliminating the need for large individual lens elements that would increase device thickness.
2Reliability
If multiple light sources are used to generate glint patterns for robust eye detection, then reliability of eye tracking is improved, but glints may interfere with and hide the pupil edge, worsening measurement precision
Solution Approach 1:
The patent divides the detection task into separate functions: some sensors in the array are dedicated to detecting glint patterns from multiple light sources, while other sensors detect the pupil edge. This segmentation allows glints to be detected for robustness without interfering with pupil edge measurement precision, as each sensor type can be optimized for its specific function.
Solution Approach 2:
The patent uses the array of sensors as an intermediary that can simultaneously capture both glint patterns and pupil edges. By distributing detection across multiple sensors with different functions, the system mediates between the need for robust glint detection and precise pupil edge measurement, allowing both to coexist without mutual interference.
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 and robustness of eye tracking by reducing noise and improving pupil detection, enabling effective gaze vector tracking with a wide range of motion and smaller device thickness, thus overcoming the limitations of existing technologies.
Implementation Method 1
Remote eye tracking may be based on detecting reflections of known light sources on the cornea
Data Source
AI summary
Methods and systems for eye tracking are disclosed. One such method obtains a plurality of images of the eye from an array camera and detects glint positions and a pupil edge of the eye in the plurality of the images. A distance from the array camera to the pupil edge may be estimated based on the glint positions. A pupil image may be generated based on selected ones of the plurality of images, the glint positions, and the estimated distance to the pupil edge. A pupil center position may be determined based on the pupil image and the glint positions.