Eye Tracking Calibration Using Visible Targets
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing eye gaze tracking systems face challenges in accurately calibrating geometric parameters, particularly when the eye tracking device and display are separate, leading to inefficient calibration processes that are either restrictive or time-consuming and unreliable.
Innovation Solution
The implementation of a method using visible calibration targets, including both display targets and sensor targets, to gather eye tracking data and determine geometric parameters, allowing for flexible setup configurations and improved accuracy by correlating gaze points defined by these targets.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If a fixed geometric relationship between display screen, light source, and sensor is utilized for calibration, then calibration accuracy is improved, but device flexibility and adaptability deteriorate
Solution Approach 1:
The patent applies preliminary action by pre-defining multiple possible geometric configurations and their corresponding calibration parameters. The system determines the actual configuration through detection before calibration, allowing it to select the appropriate pre-prepared calibration data, thus achieving both accuracy and flexibility.
Solution Approach 2:
The patent implements dynamics by making the calibration process adaptive rather than static. The system dynamically detects the actual geometric relationship between components and automatically selects or adjusts calibration parameters accordingly, enabling the calibration system to adapt to different device configurations.
2Adaptability or versatility
If manual input of calibration parameters is required, then adaptability to different setups is improved, but calibration time and reliability deteriorate
Solution Approach 1:
The patent applies self-service by enabling the system to automatically detect its own geometric configuration and determine appropriate calibration parameters without user intervention. The eye tracking device autonomously identifies component positions and selects calibration data, eliminating manual input requirements while maintaining adaptability.
Solution Approach 2:
The patent implements feedback through an automated detection mechanism that gathers information about the actual geometric relationship between the display, light source, and sensor, then uses this feedback to automatically select appropriate calibration parameters, replacing manual input with intelligent automated adjustment.
3Measurement precision
If the eye tracking device is integrated with the display device, then calibration accuracy is improved, but system versatility and upgradability deteriorate
Solution Approach 1:
The patent applies segmentation by separating the eye tracking device from the display device into independent units. Each device can be upgraded or replaced independently while the system automatically detects and adapts to the new configuration, maintaining calibration accuracy without requiring integrated fixed relationships.
Solution Approach 2:
The patent implements universality by creating a calibration system that works across multiple device configurations and combinations. The automated detection and parameter selection mechanism allows the same eye tracking device to accurately calibrate with different display devices, enabling universal compatibility and independent upgradability.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enables accurate and flexible calibration of eye tracking systems, enhancing the accuracy of gaze tracking by determining geometric parameters that fit the specific setup of the eye tracking device and display, improving user experience and system performance.
Implementation Method 1
Some known eye gaze tracking techniques involve illuminating the eyes by emitting light from one or more light sources and detecting reflections of the emitted light off of the eyes with a sensor
Implementation Method 2
detecting reflections of the emitted light off of the eyes with a sensor
Data Source
AI summary
Implementations of the present disclosure may include calibration techniques for systems which include eye tracking devices and display devices. The calibration techniques may involve a calibration process which utilizes a plurality of visible calibration targets that each defines a gaze point for a user. The calibration targets may include both targets output to the display device, as well as gaze points located on the eye tracking device itself. The calibration techniques may also include additional sensors on the eye tracking device to gather additional calibration information, such as a back-facing camera which captures images of the display device from the eye tracking device. Increased information regarding system setup that is useful in calibrating the eye tracking system may be obtained from the calibration process.