Gaze-Holding Event Detection for Intentional XR Interaction

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing user interaction systems fail to accurately differentiate between intentional and unintentional gaze-based interactions, leading to incorrect associations of user activities with user interface elements, particularly in environments involving gaze-holding events and saccadic behaviors.

Innovation Solution

The system identifies gaze-holding events through gaze velocity analysis, distinguishing them from saccadic events and blinks, and associates non-eye-based user activities like hand gestures with gaze-holding events to trigger appropriate user interface responses, ensuring that interactions are only recognized when the user intentionally looks at and interacts with UI elements.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If the system uses gaze-based interaction to trigger user interface responses, then the ease of operation is improved, but the reliability deteriorates due to false positives from unintentional gaze movements

Engineering Contradiction:
Improvegaze-based interactionVSAvoidaccuracy of gaze-based interaction
Core Design Contradiction:
Ease of operationVSReliability

Solution Approach 1:

The patent segments gaze events into distinct types: saccadic events (unintentional quick movements) and gaze-holding events (intentional fixations). By separating these event types and only responding to gaze-holding events, the system maintains ease of gaze-based operation while eliminating false positives from saccadic movements, thus resolving the reliability issue.

Inventive Principle:
Principle #1Segmentation

2Productivity

If the system associates all gaze events with user interface elements, then the productivity is improved through rapid response, but the measurement precision deteriorates due to inability to distinguish intentional from unintentional gaze

Engineering Contradiction:
Improveresponse speedVSAvoidgaze intention detection
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The patent applies dynamics by using temporal characteristics of gaze events to distinguish intention. Gaze-holding events have sustained duration indicating intentional focus, while saccadic events are brief indicating unintentional movement. This dynamic temporal analysis enables precise detection of gaze intention while maintaining rapid system response to legitimate user actions.

Inventive Principle:
Principle #15Dynamics

3Ease of operation

If the system responds to all types of gaze events including saccades, then the ease of operation is improved, but the loss of information increases due to incorrect association with wrong UI elements

Engineering Contradiction:
Improvegaze-based controlVSAvoidincorrect UI element association
Core Design Contradiction:
Ease of operationVSLoss of information

Solution Approach 1:

The patent extracts and isolates gaze-holding events from the overall gaze data stream, specifically separating them from saccadic events. By taking out only the relevant gaze-holding events for UI interaction and excluding saccadic events, the system maintains ease of gaze-based control while preventing incorrect UI element associations that would result from responding to unintentional gaze movements.

Inventive Principle:
Principle #2Taking out (Extraction)

Data Source

PatentUS20240393876A1User interface response based on gaze-holding event assessment
Publication Date: 2024.11.28 APPLE INC
  • US20240393876A1 patent drawing
  • US20240393876A1 patent drawing
  • US20240393876A1 patent drawing

AI summary

Various implementations provide views of 3D environments (e.g., extended reality (XR) environments). Non-eye-based user activity, such as hand gestures, is associated with some types of eye-based activity, such as the user gazing at a particular user interface component displayed within a view of a 3D environment. For example, a user's pinching hand gesture may be associated with the user gazing at a particular user interface component, such as a button, at around the same time as the pinching hand gesture is made. These associated behaviors (e.g., the pinch and gaze at the button) may then be interpreted as user input, e.g., user input selecting or otherwise acting upon that user interface component. In some implementations, non-eye-based user activity is only associated with types of eye-based user activity that are likely to correspond to a user perceiving what they are seeing and/or intentionally looking at something.