Eye Tracking Activity Recognition Without Outward Camera Dependence

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current eye tracking systems rely on outward-facing cameras to estimate gaze vectors, limiting their ability to accurately infer user activities without referencing the external environment.

Innovation Solution

An eye tracking system that includes an inward-facing sensor and controller to analyze eye movements and determine user activities directly, without relying on outward-facing camera images, using features like saccades, fixations, and pupillometry to classify activities.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If an outward-facing camera is used to infer user activities, then the system can capture the user's environment, but the accuracy of eye movement tracking deteriorates

Engineering Contradiction:

Improveenvironment capture capabilityVSAvoideye movement tracking accuracy

Core Design Contradiction:

Adaptability or versatilityVSMeasurement precision

Solution Approach 1:

The patent extracts the eye tracking function from the outward-facing camera system and implements it through dedicated eye tracking sensors positioned near the display. This separation allows the outward-facing camera to continue capturing environmental data while the specialized sensors accurately track eye movements, resolving the contradiction between environment capture and eye tracking precision

Inventive Principle:

Principle #2Taking out (Extraction)

Solution Approach 2:

The patent introduces eye tracking sensors as an intermediary component between the user's eyes and the system's activity recognition. These sensors directly capture eye movement data without relying on outward-facing camera inference, providing accurate eye tracking while the outward-facing camera maintains its environmental capture function

Inventive Principle:

Principle #24Intermediary (Mediator)

2Loss of information

If outward-facing camera images are referenced for activity determination, then context information is available, but the system becomes dependent on external visual context

Engineering Contradiction:

Improvecontext information availabilityVSAvoidcontext independence

Core Design Contradiction:

Loss of informationVSAdaptability or versatility

Solution Approach 1:

The patent segments the activity recognition process into two independent components: eye tracking data collection through dedicated sensors and environmental context capture through outward-facing cameras. This segmentation allows the system to determine activities based on eye movements alone, making it context-independent while still preserving the option to integrate environmental context when available

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The eye tracking sensors serve multiple functions: they can determine user activities independently through eye movement analysis, and they can also work in conjunction with outward-facing camera data when environmental context is needed. This multi-functionality resolves the contradiction by providing context independence while maintaining adaptability to use context information

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS12625544B2Eye tracking system for determining user activity

Publication Date: 2026.05.12 SESAME AI INC

AI summary

Embodiments relate to an eye tracking system. A headset of the system includes an eye tracking sensor that captures eye tracking data indicating positions and movements of a user's eye. A controller (e.g., in the headset) of the tracking system analyzes eye tracking data from the sensors to determine eye tracking feature values of the eye during a time period. The controller determines an activity of the user during the time period based on the eye tracking feature values. The controller updates an activity history of the user with the determined activity.