Multimodal Eye Tracking with Dynamic Sensor Fusion

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Eye tracking systems face challenges in accurately capturing eye positions and movements under dynamic conditions while minimizing power consumption, as high resolution optical scanning is power-intensive and low refresh rates fail to accurately capture high-frequency eye movements.

Innovation Solution

The integration of multimodal sensors, such as optical sensors and electro-ocular voltage sensors, in a wearable computing system, which adjusts sensor measurement rates in real-time to balance accuracy and power consumption, leveraging the strengths of both sensor types to enhance eye tracking accuracy and efficiency.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If high resolution optical scanning is used to improve eye tracking accuracy, then measurement precision is improved, but power consumption increases

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

Solution Approach 1:

The patent combines multiple sensor types (optical sensors and electro-ocular voltage sensors) into a hybrid eye tracking system. The optical sensors capture eye position and movement, while electro-ocular voltage sensors detect electrical potentials associated with eye movements. By merging these complementary sensing modalities, the system achieves high measurement precision through sensor fusion while managing power consumption by leveraging the lower-power electro-ocular sensors for certain measurements.

Inventive Principle:
Principle #5Merging (Combining)

Solution Approach 2:

The system dynamically adjusts sensor measurement rates based on detected eye behavior. When rapid eye movements are detected, the system increases the measurement frequency of optical sensors to capture high-frequency movements accurately. During periods of stable gaze, the system reduces measurement rates to conserve power. This dynamic adaptation allows the system to maintain high accuracy when needed while minimizing power consumption during normal operation.

Inventive Principle:
Principle #15Dynamics

2Use of energy by moving object

If sensor data is updated at low refresh rate to conserve power, then power consumption is reduced, but ability to capture high frequency eye movements deteriorates

Engineering Contradiction:
Improvepower consumptionVSAvoideye movement capture frequency
Core Design Contradiction:
Use of energy by moving objectVSSpeed

Solution Approach 1:

The system implements dynamic refresh rate adjustment based on detected eye movement characteristics. The processor monitors eye behavior patterns and automatically increases the sensor measurement rate when rapid or high-frequency eye movements are detected, ensuring accurate capture of saccades and other fast movements. When eye movements are slow or stationary, the system reduces the refresh rate to minimize power consumption. This dynamic approach resolves the contradiction by adapting the refresh rate to actual operational needs rather than using a fixed rate.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system incorporates feedback mechanisms where the detected eye behavior informs subsequent sensor operation parameters. The processor analyzes sensor data in real-time to detect patterns indicating high-frequency eye movements, and this feedback triggers adjustments in measurement rates. The feedback loop ensures that the system responds appropriately to actual eye movement demands, maintaining high-speed capture capability when needed while conserving power during normal operation.

Inventive Principle:
Principle #23Feedback

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 enables accurate and efficient eye tracking, even in unpredictable lighting conditions, by optimizing sensor data updates based on eye behavior, thereby improving power management and computational efficiency.

Implementation Method 1

electro-ocular voltage sensors, which output a signal corresponding to a position and/or movement of the eye based on detected electrical potential

Methodology Applied
Scientific EffectElectro-ocular voltage:

Data Source

PatentEP3610359B1Multimodal eye tracking
Publication Date: 2023.09.20 MAGIC LEAP INC
  • EP3610359B1 patent drawingFigure 1
  • EP3610359B1 patent drawingFigure 2A
  • EP3610359B1 patent drawingFigure 2B

AI summary

A method is disclosed, the method comprising the steps of receiving, at a first time interval from a first sensor configured to output data indicative of a first position of an eye, first data; receiving, at a second time interval from a second sensor configured to output data indicative of a delta position of the eye, second data; determining, based on the first data, a first position of the eye; determining, based on the second data, a delta position of the eye; determining, using the first position of the eye and the delta position of the eye, a second absolute position of the eye; and in response to determining the second position of the eye, generating an output signal indicative of the second position of the eye.