Camera-Based Oculometric Extraction for High-Resolution Eye Tracking

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing technologies for measuring minute eye movements are costly, time-consuming to set up, and lack the necessary resolution, often requiring controlled lab settings and standardized stimuli, while neural networks fail to achieve the required resolution for oculometric parameter measurements.

Innovation Solution

A system utilizing standard cameras and machine learning models to capture and process video streams from devices like smartphones, enabling high-resolution oculometric parameter extraction without controlled settings, employing preprocessing, prediction models, and deconvolution techniques to enhance accuracy.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If dedicated eye tracking devices are used in controlled lab settings, then measurement precision is improved, but device complexity and setup time increase

Engineering Contradiction:
Improveeye movement measurement precisionVSAvoidcontrolled setup complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The patent uses standard cameras to capture eye images instead of dedicated eye tracking devices. The system copies the function of expensive specialized equipment using ordinary camera hardware, combined with advanced image processing algorithms to achieve similar measurement precision without the complexity of dedicated lab setups

Inventive Principle:
Principle #26Copying

Solution Approach 2:

The patent replaces complex mechanical eye tracking systems with standard camera-based image capture and computational algorithms. Instead of using specialized optical and mechanical components for eye tracking, the system uses general-purpose camera hardware combined with software processing to achieve the same measurements

Inventive Principle:
Principle #28Mechanics substitution (Replace mechanical system)

2Ease of operation

If neural networks are used to obtain eye movements, then ease of operation is improved, but measurement precision deteriorates

Engineering Contradiction:
Improveease of eye movement measurementVSAvoideye movement resolution
Core Design Contradiction:
Ease of operationVSMeasurement precision

Solution Approach 1:

The patent employs feedback mechanisms where the system continuously processes camera images, adjusts its analysis based on detected eye characteristics, and refines its measurements. The feedback loop allows the system to adapt to different lighting conditions, eye colors, and individual anatomical variations while maintaining high measurement precision

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system dynamically changes processing parameters based on detected eye characteristics and environmental conditions. The image processing algorithms adjust parameters such as contrast enhancement, edge detection sensitivity, and feature extraction thresholds to optimize measurement precision for each specific imaging condition

Inventive Principle:
Principle #35Parameter changes

3Measurement precision

If standardized stimuli and controlled ambient conditions are used, then measurement precision is improved, but adaptability deteriorates

Engineering Contradiction:
Improveoculometric parameter accuracyVSAvoidenvironmental adaptability
Core Design Contradiction:
Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent implements dynamic adaptation to varying environmental conditions. The image processing system continuously adjusts its parameters and algorithms based on real-time detection of lighting conditions, ambient factors, and individual user characteristics, allowing it to maintain measurement precision across diverse environments without requiring controlled settings

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The system performs preliminary characterization of the user's eye anatomy and environmental conditions before measurement. By pre-processing to identify individual eye characteristics, iris patterns, and ambient lighting conditions, the system can optimize its measurement parameters in advance and maintain accuracy across different environments

Inventive Principle:
Principle #10Preliminary action

4Device complexity

If standard cameras are used in uncontrolled environments, then device complexity is reduced, but measurement precision deteriorates

Engineering Contradiction:
Improvesetup simplicityVSAvoidoculometric parameter resolution
Core Design Contradiction:
Device complexityVSMeasurement precision

Solution Approach 1:

The patent applies advanced image processing parameter transformations and algorithmic adjustments to compensate for the lower quality input from standard cameras. By dynamically changing processing parameters such as image enhancement, noise reduction thresholds, and feature detection sensitivity, the system recovers high measurement precision from standard camera images

Inventive Principle:
Principle #35Parameter changes

Solution Approach 2:

The system introduces intermediary processing layers between the standard camera and the final measurement output. Advanced image processing algorithms act as intermediaries that enhance, clean, and transform the raw camera images into high-precision oculometric measurements, bridging the gap between simple hardware and precise measurements

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP4333686B1Obtaining high-resolution oculometric parameters
Publication Date: 2026.03.18 NEUROLIGHT LTD
  • EP4333686B1 patent drawingFigure 1A
  • EP4333686B1 patent drawingFigure 1B
  • EP4333686B1 patent drawingFigure 2

AI summary

Disclosed are systems and methods for extracting high resolution oculometric parameters. A video stream having a video of a face of a user is processed to obtain a set of oculometric parameters, such as eyelid data, iris data (e.g., iris translation, iris radius and iris rotation), and pupil data (e.g., pupil center and pupil radius) at a first resolution. A deconvolution process is performed on the video stream to improve accuracy or resolution of the oculometric parameters, based on stimulus information of a video stimulus displayed on a client device associated with the user, environment data of an environment in which the user is located, device data of the client device, etc. The oculometric parameters are then processed using a prediction model that is trained based on high resolution oculometric parameters obtained using eye tracking devices to predict oculometric parameters at a resolution greater than the first resolution.