Wearable Gaze Mapping for Model-Free Feature Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing eye tracking systems require pre-existing information about the environment to identify areas of interest, limiting their functionality without a predetermined image or model.
Innovation Solution
A method and system using a wearable device with an eye tracking arrangement and an outward-facing image sensor to determine gaze points and identify areas of interest based on attention criteria, such as fixation time and object classification, without requiring prior knowledge of the environment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If pre-existing environment information (predetermined image or model) is used to identify areas of interest, then the accuracy of gaze association with environment features is improved, but the system cannot function in dynamic environments without such pre-defined models
Solution Approach 1:
The system performs preliminary actions by capturing scene images and detecting features before gaze association occurs. The outward-facing image sensor captures the environment, and feature detection algorithms identify keypoints, edges, and corners in advance, creating a foundation for subsequent real-time gaze mapping without requiring pre-existing environment models.
Solution Approach 2:
The patent introduces an intermediary approach by using detected environment features from captured images as a mediator between the gaze data and the physical environment. Instead of directly mapping gaze to pre-defined models, the system uses dynamically detected features as an intermediate representation that bridges eye tracking data with environmental context.
2Adaptability or versatility
If real-time gaze point determination is performed without pre-defined environment models, then the system's versatility in dynamic environments is improved, but the ability to accurately associate gaze with specific environment features deteriorates
Solution Approach 1:
The system employs self-service by autonomously detecting and identifying environment features directly from captured images without external pre-processing or pre-defined models. The feature detection algorithms automatically extract keypoints, edges, and corners from the scene, enabling the system to adapt to any environment it encounters while maintaining functional capability.
Solution Approach 2:
The patent applies parameter changes by dynamically adjusting the feature detection and image processing parameters based on the captured scene characteristics. The system modifies detection sensitivity, feature selection criteria, and image processing parameters in real-time to optimize performance for different environmental conditions and lighting scenarios.
3Loss of information
If multiple gaze points are processed with attention criteria (fixation time, viewing instances), then the identification of meaningful areas of interest is improved, but the computational complexity and processing time increase
Solution Approach 1:
The system applies partial action by selectively processing only those gaze points that meet specific attention criteria, such as minimum fixation duration or repeated viewing instances. Instead of analyzing every single gaze point, the system filters and focuses computational resources on gaze patterns that indicate genuine user interest, thereby reducing processing overhead while preserving meaningful behavioral information.
Solution Approach 2:
The patent implements feedback mechanisms by using attention criteria results to refine and adjust processing parameters. The system monitors fixation patterns and viewing instances, using this feedback to dynamically adjust which gaze points require detailed analysis and how computational resources are allocated across different processing stages.
4Loss of information
If scene images are captured and processed to identify areas of interest, then the analysis of user behavior in the environment is improved, but the device complexity and processing requirements increase
Solution Approach 1:
The patent applies universality by designing the wearable device with multi-functional components. The outward-facing image sensor serves multiple purposes: capturing scene images for feature detection, providing environmental context for gaze association, and enabling various analysis applications. This multi-functionality reduces the need for separate dedicated components for each function, thereby managing device complexity.
Solution Approach 2:
The system replaces complex mechanical or manual analysis methods with automated image processing and computer vision algorithms. Instead of requiring manual environment modeling or complex mechanical tracking systems, the patent uses software-based feature detection and image analysis to achieve user behavior analysis, reducing mechanical complexity while enhancing analytical capability.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
According to an aspect of the disclosure, there is provided a method for identifying at least one area of interest in an environment around a wearable device, wherein the wearable device comprises an eye tracking arrangement and an outward-facing image sensor, the method comprising determining a plurality of gaze points of a user of the wearable device and corresponding timestamps using at least the eye tracking arrangement, selecting at least one gaze point from the plurality of determined gaze points based on one or more attention criteria, receiving, at least one scene image from the outward-facing image sensor at a time corresponding to the timestamp of the at least one selected gaze point, and identifying one or more areas of interest (AOIs) in the scene image based on the at least one selected gaze point.