Wearable Gaze Mapping via Eye Tracking and Scene Capture
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems fail to accurately and efficiently determine a user's gaze direction in their environment without manual processing, especially in dynamic settings, and struggle to map this information effectively.
Innovation Solution
A method using a wearable device equipped with an eye tracking device and an outward-facing image sensor, which captures scene images and determines gaze directions, and calculates confidence and quality values for gaze points, allowing for efficient mapping of user attention in various environments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual processing is used to determine gaze direction, then accuracy can be maintained, but processing time increases significantly
Solution Approach 1:
The system performs preliminary actions by capturing scene images and determining gaze directions simultaneously at the point in time the scene image is captured, rather than processing manually after the fact. This preliminary automated capture and determination of gaze data eliminates subsequent manual processing time while maintaining accuracy through the integrated sensor system.
Solution Approach 2:
The patent replaces manual mechanical processing with an automated optical and computational system. The outward facing image sensor captures scene images, while the eye tracking device determines gaze directions automatically, substituting human manual analysis with electronic sensing and computational algorithms that process data in real-time.
2Loss of time
If automated gaze tracking is implemented, then processing time is reduced, but reliability of gaze detection decreases
Solution Approach 1:
The system merges multiple independent components into a unified automated gaze tracking system. The outward facing image sensor and the eye tracking device are combined and synchronized to operate together, with the image sensor capturing scene images while the eye tracking device simultaneously determines gaze directions. This integration of multiple sensing modalities enhances reliability through cross-validation while maintaining real-time automated processing.
Solution Approach 2:
The system implements feedback mechanisms where the determined gaze directions are continuously monitored and adjusted based on the captured scene images and eye tracking data. This feedback loop ensures that automated gaze detection maintains high reliability by validating results against multiple data sources and correcting deviations in real-time.
3Device complexity
If simple gaze detection is used, then system complexity is reduced, but mapping accuracy in dynamic environments deteriorates
Solution Approach 1:
The system employs universal multi-functional components that serve multiple purposes. The outward facing image sensor not only captures scene images for visual recording but also provides contextual information for gaze mapping. The eye tracking device simultaneously performs gaze direction determination and contributes to confidence/quality value calculations. This multi-functionality maintains relatively simple device architecture while achieving accurate gaze mapping in dynamic environments through the versatile use of each component.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
A method for determining correspondence between a gaze direction and an environment around a wearable device is disclosed. The wearable device may include an eye tracking device and an outward facing image sensor. The method may include receiving an input parameter and at least one scene image from the outward facing image sensor. The method may further include determining, with at least the eye tracking device, at least one gaze direction of a wearer of the wearable device at a point in time corresponding to when the scene image was captured by the outward facing image sensor. The method may additionally include determining, based at least in part on the input parameter, that a particular scene image includes at least a portion of a predefined image. The method may moreover include determining, based on the at least one gaze direction, at least one gaze point on the particular scene image.