Web Camera Gaze Calibration Using Corneal Reflection Geometry
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing web cameras used for gaze tracking lack known focal length and field of view properties, making it difficult to translate eye direction into screen location accurately.
Innovation Solution
A method and system for determining calibration information using digital image processing to locate features in the eye, such as the limbus and corneal reflection, to estimate the focal length and field of view of the camera, allowing for gaze point detection without requiring specific user orientation or prior knowledge of camera properties.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If web cameras with unknown properties are used for gaze tracking, then device versatility is improved, but measurement precision deteriorates due to unknown focal length and field of view
Solution Approach 1:
The system performs preliminary calibration by capturing images of a calibration pattern before actual gaze tracking. This preliminary action determines the camera's focal length and field of view, enabling subsequent precise gaze point measurements without requiring prior knowledge of camera properties.
Solution Approach 2:
The calibration process uses the camera itself to capture images of a calibration pattern, and the system automatically processes these images to determine the camera's optical parameters. This self-calibration approach eliminates the need for external measurement equipment or manual parameter input.
2Measurement precision
If calibration information is determined for each camera, then measurement precision is improved, but device complexity increases due to individual calibration requirements
Solution Approach 1:
The system uses a standardized calibration pattern with known geometric properties as a reference copy. By comparing the captured calibration pattern against its known original dimensions, the system automatically calculates camera parameters, simplifying the calibration process while maintaining precision.
Solution Approach 2:
The calibration process determines specific camera parameters (focal length, field of view) by analyzing the transformation between the known calibration pattern dimensions and their captured appearance. This parameter determination automates the calibration process, reducing complexity while improving measurement precision.
3Ease of operation
If facial features are used to deduce user geometry, then ease of operation is improved, but measurement precision deteriorates due to varying camera fields of view
Solution Approach 1:
The calibration pattern serves as an intermediary reference object with known dimensions. By measuring how this known pattern appears in the camera image, the system can accurately determine camera parameters, which then enable precise distance and geometry calculations from facial features without being affected by varying camera fields of view.
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
Enables accurate gaze point calibration of web cameras for eye-tracking on electronic displays, applicable to various users and conditions, without needing precise user positioning or camera property information.
Implementation Method 1
detecting bright spots in the image that derive from the pupil and cornea of the eye. This approach exploits the bright-eye or 'red-eye' effect known to photographers, whereby light enters the eye and is reflected or absorbed and re-emitted through the pupil
Data Source
AI summary
Method for determining calibration information in relation to a digital camera used to depict a user in a system for determining a user gaze point in relation to an entity, the method comprising: receiving from the camera at least one image of a user; performing digital image processing on the image to determine an in-image feature size dimension of a feature of the entity as reflected in an eye of the user; and to determine an in-image limbus size dimension of a limbus of the eye; determining a current distance between the eye and the entity based on said in-image size dimensions, a curvature of the eye cornea, a physical limbus size and a physical feature size; and determining said calibration information in the form of a focal length and/or a field of view of the camera based on said current distance and said physical limbus size dimension.