Gaze Tracking Using Virtual Grid Mapping on Mobile Terminals
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing gaze position tracking systems for mobile terminals face errors due to the assumption of fixed user motion and the need for infrared light, which is not suitable for portable devices where the user's distance and motion vary, leading to inaccuracies in determining the actual gaze position.
Innovation Solution
A method and apparatus using a camera-mounted mobile terminal to detect the eye area, generate virtual grids, and map the pupil position within these grids, allowing for real-time tracking and adjustment of the gaze point based on eye movement, without requiring additional equipment like infrared light.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If infrared ray light is used for gaze position tracking, then measurement precision is improved, but device complexity and cost increase due to additional hardware requirements
Solution Approach 1:
The patent extracts and removes the infrared light source and corresponding optical components from the gaze tracking system. By using only the mobile terminal's existing camera to capture eye images and analyze pupil position through image processing, the system eliminates the need for separate infrared hardware while maintaining gaze tracking functionality
Solution Approach 2:
The patent creates a virtual representation of the eye and pupil using image processing techniques. By capturing images with the camera and generating virtual eye models and pupil positions through algorithmic analysis, the system replicates the functionality of complex optical infrared systems using simpler digital processing
2Measurement precision
If the user's motion is assumed to be fixed, then measurement precision is improved, but adaptability deteriorates when users move or change distance from the device
Solution Approach 1:
The patent implements dynamic adaptation by continuously adjusting the virtual eye model and pupil position calculations based on real-time detection of eye movement, head position, and distance changes. The system updates its parameters as the user moves, maintaining accurate gaze tracking without requiring fixed user behavior
Solution Approach 2:
The patent employs feedback mechanisms where the system continuously monitors eye position, head orientation, and distance from the device, then adjusts the gaze calculation accordingly. This closed-loop approach allows the system to compensate for user motion and maintain measurement accuracy under varying conditions
3Measurement precision
If the camera captures the entire face area, then measurement precision is improved, but the system becomes less suitable for portable terminals where users are close to the device
Solution Approach 1:
The patent focuses the image processing on the specific local area of the eye rather than requiring the entire face to be captured. By detecting and analyzing only the eye region and surrounding areas, the system maintains high measurement precision while being adaptable to close-up portable device usage where the entire face may not be visible
Data Source
AI summary
A method for tracking a user's gaze point using a mobile terminal is provided. The method includes detecting the user's eye area from a camera that is mounted in the mobile terminal and selecting reference points of the eye area, detecting a pupil corresponding to an interest area that is obtained from the reference points, generating a first virtual grid of the eye area using a pickup image of a gaze point of the pupil corresponding to each corner of the display and generating a second virtual grid having the same division areas as those of the first virtual grid in the display, and mapping a position of the pupil within the second virtual grid area corresponding to a position of the pupil within the first virtual grid.