3D Object Gaze Point Mapping Without Artificial IR Markers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods are unable to accurately determine the gaze endpoint on arbitrary three-dimensional objects in 3D space, particularly when using natural scenes captured by normal cameras without artificial IR markers.
Innovation Solution
A system utilizing an eye tracking unit, head tracking unit, and 3D scene structure representation to calculate the gaze endpoint by intersecting the gaze direction with a 3D structure representation, allowing determination of the object being gazed at in 3D space.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If artificial IR markers are used for gaze endpoint determination, then measurement precision is improved, but device complexity and ease of operation deteriorate due to requiring special markers and calibration procedures
Solution Approach 1:
The patent extracts and removes the artificial IR markers from the system, enabling gaze endpoint determination to work with natural scenes captured by normal cameras. This eliminates the need for special markers while maintaining measurement capability through 3D structure analysis.
Solution Approach 2:
The system uses the natural 3D structure information already present in the scene to perform gaze endpoint determination, making the system self-sufficient without requiring external artificial markers or specialized calibration procedures.
2Measurement precision
If artificial IR markers are used for gaze endpoint determination, then measurement precision is improved, but ease of operation worsens due to requiring calibration with defined points
Solution Approach 1:
The patent removes the calibration requirement by extracting gaze endpoint information directly from natural scene 3D structure, eliminating the need for users to gaze at defined calibration points or perform complex calibration procedures.
Solution Approach 2:
The system automatically determines gaze endpoints using the inherent 3D structure of the scene, making the operation straightforward without requiring user participation in calibration or special operational procedures.
3Adaptability or versatility
If 3D structure representation is used for gaze endpoint determination, then adaptability to arbitrary 3D objects is improved, but device complexity increases due to requiring 3D scene structure detection
Solution Approach 1:
The patent creates a universal system that can determine gaze endpoints on any arbitrary 3D object by using 3D structure representation, making the system adaptable to diverse scenes without requiring object-specific configurations or markers.
Solution Approach 2:
The 3D structure representation serves as an intermediary that bridges the eye tracker and the arbitrary 3D objects in the scene, enabling gaze endpoint determination through geometric intersection without requiring direct interaction with the objects themselves.
4Measurement precision
If gaze mapping is performed from head-mounted scene camera to reference image, then accuracy is improved, but device complexity increases due to requiring coordinate transformation
Solution Approach 1:
The patent transitions from 2D image plane mapping to 3D space mapping by using 3D structure representation and ray intersection, eliminating the need for complex coordinate transformations between different image planes and reference frames.
Data Source
AI summary
A system for determining the gaze endpoint of a subject, the system comprising: a eye tracking unit adapted to determine the gaze direction of one or more eyes of the subject; a head tracking unit adapted to determine the position comprising location and orientation of the eye tracker with respect to a reference coordinate system; a 3D Structure representation unit, that uses the 3D structure and position of objects of the scene in the reference coordinate system to provide a 3D structure representation of the scene; based on the gaze direction, the eye tracker position and the 3D structure representation, calculating the gaze endpoint on an object of the 3D structure representation of the scene or determining the object itself.