3D Gazing Point Detection via Binocular Homography Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional gazing point detection methods face challenges in precision and consistency due to variations in eye parameters and external environmental factors, requiring complex calibration and geometric measurements, which can be inconvenient and error-prone, especially when the user's gaze is outside the display screen.
Innovation Solution
A method and system using a wearable device with external and internal cameras to detect a gazing point in 3D space by generating mapping relationships and determining pupillary distance, allowing for accurate detection on a virtual screen, simplifying the calibration and detection processes without sacrificing precision.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional gazing point detection methods use corneal reflections and require precise geometric measurements of eye parameters, light source locations, and camera positions, then detection precision can be maintained, but device complexity and calibration difficulty increase significantly
Solution Approach 1:
The patent extracts and eliminates the requirement for complex geometric measurements of eye parameters (pupil center, cornea curvature center, cornea radius) by using a different detection approach that relies on mapping relationships between calibration points and gazing points, thereby simplifying the system while maintaining detection precision
Solution Approach 2:
The patent changes the detection parameters from requiring precise eye geometric parameters to using mapping relationships established through calibration with known points, transforming the problem from one requiring complex biological measurements to one using geometric mapping that can be determined through simpler calibration procedures
2Measurement precision
If conventional methods require detailed geometric measurements and controlled environments, then detection accuracy is improved, but ease of operation and user convenience deteriorate
Solution Approach 1:
The patent performs preliminary calibration by establishing mapping relationships between known calibration points and their corresponding gazing points before actual use. This preliminary action creates a reference framework that simplifies subsequent detection operations, allowing users to obtain accurate gazing point measurements without performing complex measurements during operation
Solution Approach 2:
The patent creates a virtual screen as a copy or representation of the physical calibration screen in 3D space. This virtual screen contains the mapping relationships that allow gazing points to be detected accurately without requiring the physical screen to be present or visible, thereby improving ease of operation while maintaining precision
3Measurement precision
If detection methods rely on a physical display screen, then gazing point detection within screen boundaries is accurate, but adaptability to gaze outside the screen is limited
Solution Approach 1:
The patent extends the detection capability from the 2D physical screen plane to 3D space by creating a virtual screen that represents the calibration plane in three-dimensional coordinates. This dimensional extension allows the system to accurately detect gazing points anywhere in 3D space, not just those falling within the physical screen boundaries, thereby improving adaptability while maintaining precision through the established mapping relationships
Data Source
AI summary
A system for detecting a gazing point of a user in a three-dimensional (3D) space based on a virtual screen is provided. The system includes at least a processor and a wearable device, the wearable device further comprising an external camera arranged for capturing images of the user's field of view, and two internal cameras arranged for capturing binocular images of the user's left and right eyes. The processor is designed to determine the gazing point of the user based on a virtual screen. The coordinates of the pupil center as determined according to the images from the internal cameras are mapped to the images from the external camera based on a left and a right mapping relationships, which further mapped to the virtual screen as an intermediate screen for calculating the 3D coordinates of the gazing point.