Implicit Gaze Calibration Using Screen Content and Neural Networks
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing gaze tracking systems require time-consuming and resource-intensive personalized calibration, which is not optimal for various devices and user constraints, leading to inaccurate gaze detection.
Innovation Solution
An implicit calibration method using spatiotemporal information and a neural network to generate a personalized gaze function based on screen content and uncalibrated gaze information, without explicit calibration steps, enabling real-time calibration on diverse devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If explicit personalized calibration with research-grade eye tracker is used, then measurement precision is improved, but loss of time and resource intensity increase
Solution Approach 1:
The system performs self-calibration by automatically analyzing screen content and uncalibrated gaze trajectories to generate a personalized calibration function without requiring explicit user participation in calibration tasks. The neural network processes the user's natural viewing behavior to derive calibration parameters autonomously.
Solution Approach 2:
The patent replaces the mechanical research-grade eye tracker calibration process with a computational approach using neural networks that process screen content and gaze data to generate calibration functions, eliminating the need for physical calibration equipment and procedures.
2Measurement precision
If explicit personalized calibration with research-grade eye tracker is used, then measurement precision is improved, but use of energy and resource intensity increase
Solution Approach 1:
The system uses partial information (screen content and uncalibrated gaze trajectories) rather than requiring complete calibration datasets, performing sufficient calibration action to achieve acceptable accuracy without exhaustive processing. The neural network processes only the necessary minimal dataset for calibration.
3Adaptability or versatility
If device-specific information is used for uncalibrated gaze tracking, then adaptability is improved, but measurement precision deteriorates
Solution Approach 1:
The system applies local calibration by generating device-specific calibration functions tailored to each individual user's viewing behavior patterns. The calibration function is customized for each user-device combination while maintaining compatibility across different device types through the universal neural network approach.
Data Source
AI summary
The technology relates to methods and systems for implicit calibration for gaze tracking. This can include receiving, by a neural network module, display content that is associated with presentation on a display screen. The neural network module may also receive uncalibrated gaze information, in which the uncalibrated gaze information includes an uncalibrated gaze trajectory that is associated with a viewer gaze of the display content on the display screen. A selected function is applied by the neural network module to the uncalibrated gaze information and the display content to generate a user-specific gaze function. The user-specific gaze function has one or more personalized parameters. And the neural network module can then apply the user-specific gaze function to the uncalibrated gaze information to generate calibrated gaze information associated with the display content on the display screen. Training and testing information may alternatively be created for implicit gaze calibration.