Hybrid Eye Tracking for Power-Aware Pupil Feature Calculation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing head-mounted systems face challenges in achieving efficient eye tracking while maintaining a lightweight and non-overbearing form factor, as cameras used for accurate tracking result in excessive power consumption and limited trackable eye position ranges.
Innovation Solution
A hybrid eye tracking system combining a head-mounted camera and another device, such as a photosensor-oculography device, where eye positions outside a certain range trigger reduced power consumption modes and higher rate calculations, while within the range, accurate image-based calculations are performed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If cameras are used for eye tracking to achieve accurate tracking results, then measurement precision is improved, but use of energy increases excessively
Solution Approach 1:
The system dynamically switches between camera-based eye tracking and alternative device-based measurements depending on eye position. When the eye is within the narrower trackable range of the camera, the camera is activated for high-precision tracking. When the eye moves outside this range, the system transitions to using other eye tracking devices that have broader tracking ranges, thereby avoiding excessive power consumption while maintaining acceptable tracking accuracy across all eye positions.
Solution Approach 2:
The system changes the operational parameters of the eye tracking system by adjusting which device is active based on eye position parameters. The computer determines eye position and selectively activates the camera only when the eye position falls within the camera's optimal tracking range, otherwise relying on alternative devices. This parameter-based selection optimizes the balance between measurement precision and power consumption.
2Weight of moving object
If cameras are positioned on the sides of the eyes to achieve desirable form factor, then weight and form factor are improved, but the range of trackable eye positions is limited
Solution Approach 1:
The system achieves multi-functionality by combining multiple eye tracking devices with different tracking characteristics. The camera provides high-precision tracking for a limited range of eye positions, while alternative eye tracking devices provide broader coverage. Together, they create a universal eye tracking system that maintains both desirable form factor and extended tracking range, allowing the system to adapt to various eye positions without compromising weight or form factor.
3Adaptability or versatility
If cameras are positioned in front of the eye to capture clearer images and cover wide range of eye positions, then range of trackable eye positions is improved, but form factor becomes undesirable
Solution Approach 1:
The eye tracking function is segmented across multiple devices with different positioning and capabilities. Instead of relying on a single camera positioned in front of the eye, the system divides the tracking task between a camera (positioned for optimal form factor) and alternative eye tracking devices. Each device handles specific portions of the tracking range, collectively achieving wide coverage without requiring any single device to be positioned suboptimally.
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 optimizes power usage and extends the range of trackable eye positions, making it suitable for untethered devices like augmented reality smartglasses for all-day use.
Implementation Method 1
a head-mounted device that takes measurements indicative of positions of an eye of a user... a photosensor-oculography device, which may be less accurate
Data Source
AI summary
Systems, methods, and computer programs for eye tracking. In one embodiment, a system includes a head-mounted device that takes measurements indicative of positions of an eye of a user (“eye positions”). The system also includes a head-mounted camera that captures images of the eye. A computer calculates the eye positions based on the measurements. The head-mounted camera is better positioned to capture images of the user's pupil when the eye positions fall within a certain range compared to when the eye positions fall outside the certain range. The computer calculates, at a first average rate, pupil features based on images captured when the eye positions fall within the certain range. The computer refrains from calculating pupil features, or calculates pupil features at a second average rate, which is less than half the first average rate, based on images captured when the eye positions fall outside the certain range.