Eye Tracking Display Control via Deep Learning Gaze Mapping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing eye tracking technologies require expensive equipment and are inconvenient for users, with difficulties in precise measurement and accurate calculation of gaze points, limiting their application to simple display control and window operation.
Innovation Solution
A display control method using Deep Learning-based gaze mapping that tracks user gaze through AI algorithms, learning from user image data to control display elements such as brightness and window operations without the need for complex equipment or precise gaze angle calculations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional eye tracking equipment (corneal reflection measurement) is used, then measurement precision is improved, but device complexity and cost increase
Solution Approach 1:
The patent uses a camera to capture images of the user's eyes and creates a digital model of the eye structure. Instead of using complex corneal reflection measurement equipment, the system copies the essential functional information (eye position and gaze direction) through image processing and deep learning algorithms, achieving accurate gaze tracking with simpler imaging devices
Solution Approach 2:
The patent replaces complex optical measurement systems (corneal reflection apparatus) with a camera-based imaging system combined with deep learning algorithms. The mechanical/optical measurement process is substituted with computational image analysis, using neural networks to directly predict gaze points from eye images, thereby simplifying the hardware while maintaining or improving measurement accuracy
2Ease of operation
If manual control methods are used for eye tracking operations, then ease of operation is improved, but productivity decreases
Solution Approach 1:
The system performs eye tracking operations automatically without requiring manual intervention. The deep learning model autonomously processes eye images, detects gaze points, and determines user intent, enabling the system to serve itself in the eye tracking task. This eliminates the need for manual control while maintaining ease of use and significantly improving productivity through automation
Solution Approach 2:
The system continuously captures eye images, processes them through the deep learning model, and adjusts its gaze point predictions in real-time based on the detected eye movements. This closed-loop feedback mechanism enables automatic adaptation to user gaze changes, allowing productive automation while maintaining natural and easy interaction
3Ease of manufacture
If simple display control is implemented, then ease of manufacture is improved, but adaptability decreases
Solution Approach 1:
The patent implements a universal eye tracking system that can control multiple types of display elements and perform various operations (brightness adjustment, window management, application switching). The deep learning-based gaze detection core is designed to be function-agnostic, allowing the same system to adapt to different control scenarios and display devices, thereby achieving both ease of manufacture and high versatility
Data Source
AI summary
The present disclosure discloses a display control method and control apparatus using eye tracking. The display control method includes matching the image on which the user's face is displayed with the image on which its gaze is displayed, respectively, detecting the gaze information of the user by using the matched image with respect to the input of the user's face image, and controlling a display by manipulating a control element related to the gaze information among the control elements included in display information. According to the present disclosure, it is possible to control the display by using Artificial Intelligence (AI), a Deep Learning-based gaze mapping technology, and a 5G network without complicated calculation for a gaze angle.