Gaze-Based Device Control via Iris Tracking and Image Segmentation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current telecommunications devices face challenges in modifying images within video streams during communication sessions and require physical manipulation for operations, limiting accessibility and efficiency in video communications.

Innovation Solution

An image segmentation system that identifies and tracks facial features, such as irises, within video streams to perform biometric identification, modify images, and control device operations based on gaze direction, enabling interactive communication without physical manipulation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If physical manipulation of the device is used to perform operations, then the device can be operated reliably, but accessibility and ease of operation are limited for users who cannot physically manipulate the device

Engineering Contradiction:
ImproveaccessibilityVSAvoidoperation method
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The patent replaces physical mechanical interaction with optical field interaction by using gaze detection systems. Instead of requiring users to physically touch or manipulate device components, the system detects eye gaze direction through cameras and image processing to determine user intent and control device operations. This substitution of mechanical control with optical-based gaze tracking enables accessibility for users with physical limitations while maintaining reliable operation control.

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

2Adaptability or versatility

If traditional video streaming is used during communication sessions, then video communication can be maintained, but images within the video stream cannot be modified

Engineering Contradiction:
Improveimage modification capabilityVSAvoidvideo stream stability
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The patent segments the video stream processing into separate functional components: the original video communication stream remains stable and unchanged, while a parallel image modification system operates independently by detecting gaze direction and applying modifications to specific regions of interest within the video frames. This segmentation allows the system to maintain video stream reliability for communication purposes while simultaneously enabling adaptive image modification capabilities for enhanced user interaction.

Inventive Principle:
Principle #1Segmentation

3Ease of operation

If gaze-based control is implemented, then accessibility and interaction are improved, but the system complexity increases due to image segmentation and tracking requirements

Engineering Contradiction:
Improveinteraction capabilityVSAvoidsystem architecture
Core Design Contradiction:
Ease of operationVSDevice complexity

Solution Approach 1:

The patent implements a universal gaze detection system that serves multiple functions simultaneously: it detects user attention for accessibility control, identifies areas of interest for image modification, tracks facial features for communication analytics, and provides input for device operation control. By designing the image segmentation and tracking system to fulfill multiple purposes, the patent reduces the need for separate specialized systems, thereby managing complexity while enhancing interaction capabilities across different use cases.

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

Data Source

PatentUS20240420336A1Gaze-based control of device operations
Publication Date: 2024.12.19 SNAP INC
  • US20240420336A1 patent drawing
  • US20240420336A1 patent drawing
  • US20240420336A1 patent drawing

AI summary

Systems, devices, media, and methods are presented for gaze-based control of device operations. One method includes receiving a video stream from an imaging device, the video stream depicting one or more eyes, determining a gaze direction for the one or more eyes depicted in the video stream, detecting a change in the gaze direction of the one or more eyes, and triggering an operation in a client device based on the change in the gaze direction.