Gaze Tracking Calibration Without Corneal Reflection Dependence
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing camera-based eye tracking methods require corneal reflections for accurate tridimensional gaze estimation, which are unreliable in varying environmental conditions and increase system complexity, limiting their use to controlled indoor environments.
Innovation Solution
A method and system for gaze tracking that determines the pupil centre and optical axis without relying on corneal reflections by computing the eye centre of rotation, using head pose estimation and user-specific parameters to calculate gaze direction in a world coordinate system.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If geometrical eye model-based methods use corneal reflections for accurate tridimensional gaze estimation, then measurement precision is improved, but device complexity and noise sensitivity increase
Solution Approach 1:
The patent extracts and eliminates the dependency on corneal reflections from the gaze tracking system. By formulating a method that computes the optical axis directly from the pupil center and head pose without requiring corneal reflection detection, the invention removes the complex hardware and processing requirements associated with corneal reflection tracking while maintaining accurate tridimensional gaze estimation.
Solution Approach 2:
The patent introduces head pose estimation as an intermediary element that bridges the gap between simple pupil center detection and accurate tridimensional gaze tracking. By combining pupil center coordinates with head pose information (rotation and translation), the system can compute the optical axis in the world coordinate system without directly observing corneal reflections.
2Measurement precision
If geometrical eye model-based methods use corneal reflections for gaze tracking, then measurement precision is improved, but reliability deteriorates in varying environmental conditions
Solution Approach 1:
The patent removes the system's vulnerability to environmental lighting changes by eliminating corneal reflection dependency. The new method relies on the pupil center and head pose, which are more stable features that do not disappear or vary intensity with changing illumination conditions, thereby improving reliability in both indoor and outdoor environments.
Solution Approach 2:
The patent changes the fundamental parameters used for gaze estimation from corneal reflection coordinates to pupil center coordinates combined with head pose parameters. This parameter transformation fundamentally alters the system's sensitivity to environmental conditions, making it robust to lighting variations while maintaining measurement precision.
3Measurement precision
If corneal reflection detection is implemented for accurate gaze tracking, then measurement precision is improved, but ease of operation deteriorates due to limited environmental applicability
Solution Approach 1:
The patent creates a universal gaze tracking method that functions across diverse environments without requiring controlled indoor conditions. By using pupil center and head pose as basis for computation, the system achieves multi-environment applicability including outdoor settings with natural lighting, making the technology more versatile and easier to deploy in real-world scenarios.
Data Source
AI summary
The present disclosure allows for accurate and computationally efficient gaze tracking without requiring a corneal reflection. Eye tracking systems and methods are provided. They include obtaining images of the user's face, detecting a head pose, and locating the centre eye rotation, the pupil centre, the optical axis, the cornea centre and finally the visual axis corresponding to the gaze direction using user-specific parameters. Calibration systems and methods are also provided for acquiring the user-specific parameters. They include at least twice displaying a target point for the user to glaze at, directing light to obtain a corneal reflection, obtaining an image of the user's face, detecting the head pose, inferring a transformation to convert coordinates between the world coordinate system and a head coordinate system, and locating the corneal reflection, the cornea centre, the pupil centres and the optical axes. The data acquired thereby is used to compute the parameters.