Smart Glass Gaze Selection Dual Camera Segmentation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing smart glass systems face limitations in accurately discerning objects selected by user gaze and providing relevant information due to reliance on front-facing cameras, which can obstruct the user's view and fail to accurately interpret eye movements.
Innovation Solution
Incorporating a first camera for capturing front images and a second camera for capturing images of the user's eyes, with a controller analyzing both to determine object selection based on gaze and execute functions corresponding to eye gestures, while maintaining an unobstructed view and utilizing a transparent display for information provision.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a front-facing camera is used to capture images for object selection, then object recognition functionality is provided, but the user's view is obstructed and eye movement tracking accuracy deteriorates
Solution Approach 1:
The patent divides the imaging function into two separate cameras: a first camera for capturing front images and a second camera for capturing eye images. This segmentation allows each camera to be optimized for its specific function and positioned without interfering with the other, resolving the contradiction between providing object recognition and maintaining clear view/tracking accuracy
Solution Approach 2:
The patent introduces a controller as an intermediary that receives and processes images from both cameras, analyzes eye movements relative to front objects, and determines object selection. This intermediary coordinates the data from both cameras to achieve accurate object selection without requiring the front camera to directly track eye movements, thus avoiding view obstruction while maintaining tracking accuracy
2Device complexity
If a single camera is used for both front imaging and eye tracking, then device complexity is reduced, but measurement precision of eye movements and object selection deteriorates
Solution Approach 1:
The patent segments the imaging system into two specialized cameras: one optimized for capturing front scenes and objects, and another optimized for capturing eye movements. This segmentation enables each camera to be positioned and configured for its specific function, achieving high measurement precision for both front object recognition and eye tracking without the compromises required by a single-camera system
3Adaptability or versatility
If the front camera is positioned to capture a wide field of view, then object detection capability is improved, but eye movement tracking precision deteriorates
Solution Approach 1:
The patent assigns different imaging tasks to separate cameras: the first camera is positioned and configured to capture a wide field of view for comprehensive object detection, while the second camera is positioned to specifically capture eye movements with the precision needed for accurate tracking. This segmentation allows each camera to be optimized for its specific function without compromise
Solution Approach 2:
The controller acts as an intermediary that integrates data from both cameras, using the wide-field first camera for object detection and the precision-focused second camera for eye tracking, then combining this information to achieve both wide object detection capability and precise eye movement tracking
Data Source
AI summary
A smart glass may include a glass having a transparent display function, a first camera obtaining a front image, a second camera obtaining an image of a user's eyes, and a controller which analyzes the front image and the image of the user's eyes, determines a specific object selected by the user's gaze from a plurality of objects included in the front image based on the result of an analysis, obtains information about the specific object, and displays the information about the specific object on a transparent display area of the glass. The smart glass may provide information about the specific object selected by the user's gaze, and/or may execute a specific function corresponding to user's eye gesture.