Wearable Eye Tracker Power Optimization via Adaptive Frame Rate

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current wearable eye trackers face challenges in power consumption, robustness under varying illumination conditions, and aesthetic design, limiting their effectiveness for continuous, real-time monitoring of eye movements and cognitive states, particularly in outdoor settings and safety-critical applications.

Innovation Solution

A highly optimized low-power wearable eye tracking device that employs a staged processing pipeline with a neural network-based search stage and refine stage, adjusting power consumption and computational blocks based on environmental conditions, using NIR LEDs and a photodiode to manage illumination, and optimizing power usage for indoor and outdoor modes.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If real-time eye tracking is implemented with high frame rates (tens to 100 Hz), then measurement precision and tracking accuracy are improved, but power consumption increases significantly

Engineering Contradiction:
Improveeye tracking accuracyVSAvoidpower consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The system dynamically adjusts its operation mode between continuous high-frame-rate tracking and event-triggered tracking based on scene changes and user needs. The eye tracker operates at high frame rates only when necessary (e.g., during active gaze detection or scene changes), and reduces to lower frame rates or idle states during stable conditions, thereby maintaining tracking accuracy while significantly reducing average power consumption

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system employs periodic sampling at variable intervals rather than continuous high-rate sampling. The frame rate is adjusted periodically based on detected eye movement activity, scene stability, and battery status, allowing the system to achieve sufficient measurement precision for cognitive state detection without sustaining the high power consumption of continuous 100 Hz operation

Inventive Principle:
Principle #19Periodic action

2Adaptability or versatility

If wearable eye tracker components are added to eyeglasses, then functionality is improved, but device complexity and aesthetic design are compromised

Engineering Contradiction:
Improveeye tracking functionalityVSAvoideyeglass structure
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The eyeglass frame is designed to integrate multiple functions: structural support, aesthetic appearance, and housing for eye tracking components. The same frame structure serves both as a fashion accessory and as a functional platform for mounting cameras, LEDs, and sensors, thereby reducing overall device complexity while maintaining eye tracking functionality

Inventive Principle:
Principle #6Universality (Multi-functionality)

Solution Approach 2:

The eye tracking components are strategically positioned in specific locations on the eyeglass frame where they are least obtrusive and most effective. Cameras are placed to optimize eye visibility without blocking the user's field of view, and LEDs are positioned to illuminate the eye without creating glare or aesthetic issues, thereby balancing functionality with design

Inventive Principle:
Principle #3Local quality

3Measurement precision

If NIR LEDs are used for eye illumination, then measurement precision is improved, but power consumption and heat generation increase

Engineering Contradiction:
Improvepupil detection accuracyVSAvoidLED power consumption
Core Design Contradiction:
Measurement precisionVSUse of energy by moving object

Solution Approach 1:

The NIR LEDs are activated in periodic pulses synchronized with the camera frame rate rather than continuously. Each LED pulse provides sufficient illumination for the corresponding frame capture, then the LEDs are turned off during inter-frame periods, reducing average power consumption and heat generation while maintaining adequate illumination for accurate pupil detection during active tracking

Inventive Principle:
Principle #19Periodic action

4Measurement precision

If continuous real-time eye tracking is performed, then detection accuracy for cognitive states is improved, but duration of operation on battery is reduced

Engineering Contradiction:
Improvecognitive state detection accuracyVSAvoidbattery life
Core Design Contradiction:
Measurement precisionVSDuration of action of moving object

Solution Approach 1:

The system dynamically adjusts its monitoring intensity and frame rate based on detected cognitive state changes, user activity levels, and battery status. During periods of stable cognitive state, the system reduces sampling intensity to conserve battery, while automatically increasing resolution and frame rate when changes are detected, thereby extending operational duration while maintaining detection accuracy for critical events

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system performs full-resolution continuous tracking only when necessary for detecting critical cognitive states or anomalies. During normal stable conditions, it uses reduced-resolution or event-triggered sampling that consumes less power, accepting that some intermediate states may be sampled at lower fidelity while ensuring that significant events are captured with high accuracy

Inventive Principle:
Principle #16Partial or excessive action

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

The device achieves accurate eye tracking with reduced power consumption, operating at 7 mW, and maintains robustness across different lighting conditions, enabling continuous monitoring of eye movements and cognitive states with high frame rates, improving detection accuracy and extending battery life.

Implementation Method 1

an NIR illuminator to illuminate the pupil

Methodology Applied
Scientific EffectLight Emitting Diode: Light Emitting Diode

Implementation Method 2

an inward facing camera to capture an image of the pupil

Methodology Applied
Scientific EffectReflection: Reflection

Implementation Method 3

an IR photodiode to detect ambient infrared light levels

Methodology Applied
Scientific EffectPhotoelectric Effect: Photoelectric Effect

Data Source

PatentUS10016130B2Eye tracker system and methods for detecting eye parameters
Publication Date: 2018.07.10 UNIV OF MASSACHUSETTS
  • US10016130B2 patent drawing
  • US10016130B2 patent drawing
  • US10016130B2 patent drawing

AI summary

An improved eye tracker system and methods for detecting eye parameters including eye movement using a pupil center, pupil diameter (i.e., dilation), blink duration, and blink frequency, which may be used to determine a variety of physiological and psychological conditions. The eye tracker system and methods operates at a ten-fold reduction in power usage as compared to current system and methods. Furthermore, eye tracker system and methods allows for a more optimal use in variable light situations such as in the outdoors and does not require active calibration by the user.