Eye Pose Tracking Using Iris and Sclera Features in Wearable HMDs
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing eye tracking technologies face challenges in accurately determining eye pose, particularly with wearable head-mounted displays, due to user morphology dependence and poor resolution from distant cameras, and fail to effectively utilize iris and sclera features for biometric identification and gaze direction estimation.
Innovation Solution
Utilizing cameras mounted close to the eye in a wearable HMD to capture high-resolution iris and sclera features, employing feature-based and code-based tracking techniques to compute the three-dimensional eye pose, including yaw, pitch, and roll angles, and integrating this with a wearable display system for biometric authentication and gaze tracking.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If cameras are mounted at a distance to capture eye images, then the field of view is larger, but the image resolution and quality of iris/sclera features deteriorate
Solution Approach 1:
The patent introduces an intermediary optical system consisting of magnifying lenses or telescopic optics positioned between the distant camera and the eye. This intermediary magnifies the eye features optically before they reach the camera sensor, thereby maintaining high resolution images of iris and sclera features while keeping the camera at a comfortable distance for adequate field of view.
2Device complexity
If traditional eye tracking methods are used that rely on corner/tail position measurement, then the system is simpler to implement, but the accuracy deteriorates due to user morphology dependence
Solution Approach 1:
The patent replaces the mechanical/geometric measurement approach (tracking eye corners and tails) with a pattern recognition and feature matching approach. By substituting simple geometric point tracking with sophisticated iris and sclera feature analysis, the system achieves morphology-independent accuracy while maintaining reasonable system complexity through algorithmic processing.
Solution Approach 2:
The patent changes the measurement parameters from simple geometric coordinates (corner positions) to complex biometric features (iris patterns, sclera vessels). This parameter transformation enables morphology-independent tracking by using invariant features that remain consistent across different users, thereby improving accuracy without excessive complexity increase.
3Measurement precision
If high-resolution eye imaging is achieved by placing cameras close to the eye, then feature quality improves, but the device complexity and integration difficulty increase
Solution Approach 1:
The patent designs the wearable HMD camera system to serve multiple functions: capturing high-resolution eye images for biometric authentication, tracking eye movements for gaze estimation, and providing general visual feedback to the user. By making the camera system multi-functional, the patent justifies the increased integration complexity through multiple benefits, particularly the ability to use the same hardware for both authentication and tracking purposes.
4Measurement precision
If biometric authentication using iris features is implemented, then identification accuracy improves, but the processing time and computational requirements increase
Solution Approach 1:
The patent implements preliminary action by pre-processing and storing iris code templates during enrollment, and by continuously capturing and pre-processing eye images during normal operation. When authentication is needed, the system compares live iris codes against pre-stored templates, significantly reducing authentication time. The system also continuously tracks eye features, so gaze estimation data is already prepared when needed.
Data Source
Figure 1~1A
Figure 2A
Figure 2B
AI summary
Systems and methods for eye pose identification using features of an eye are described. Embodiments of the systems and methods can include segmenting an iris of an eye in the eye image to obtain pupillary and limbic boundaries of the eye, determining two angular coordinates (e.g., pitch and yaw) of an eye pose using the pupillary and limbic boundaries of the eye, identifying an eye feature of the eye (e.g., an iris feature or a scleral feature), determining a third angular coordinate (e.g., roll) of the eye pose using the identified eye feature, and utilizing the eye pose measurement for display of an image or a biometric application. In some implementations, iris segmentation may not be performed, and the two angular coordinates are determined from eye features.