Eyeball Tracking Iris Contour Detection via Dynamic Window Adjustment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing eye-tracking technologies face challenges in automatically detecting the starting point of an eyeball and adjusting tracking when errors occur in recognizing the eyeball contour, leading to inaccuracies in pupil positioning and iris contour detection.
Innovation Solution
A method and apparatus for eye-tracking that involves obtaining face grayscale images, detecting the iris contour, determining the central position of the pupil, and adjusting the eyeball window area based on integral projection curves to accurately locate the iris contour, even when errors occur, by preprocessing projection curves to identify key features and thresholds.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional eye-tracking algorithms directly detect iris contour from each frame, then the tracking process is simple, but the accuracy deteriorates when the eyeball is not properly positioned or lighting conditions are poor
Solution Approach 1:
The patent performs preliminary actions by detecting the eyeball position and establishing an eyeball window before attempting iris contour detection. This preliminary positioning ensures that the subsequent contour detection operates on a properly framed region, improving accuracy while managing complexity through staged processing
Solution Approach 2:
The patent segments the face image into multiple regions: face detection region, eyeball detection region, and iris contour detection region. By dividing the image processing into sequential segments with specific focus areas, the system improves measurement precision without overwhelming computational complexity
2Reliability
If the eyeball window size is fixed, then the processing is simple, but the tracking reliability deteriorates when errors occur in contour recognition
Solution Approach 1:
The patent implements dynamic adjustment of the eyeball window size based on detected eyeball position and contour recognition results. The window adapts its dimensions to accommodate varying eyeball positions and sizes, improving tracking reliability while managing complexity through conditional adjustment logic
Solution Approach 2:
The patent employs feedback mechanisms where contour recognition results are used to adjust the eyeball window parameters for subsequent frames. This closed-loop approach improves reliability by continuously adapting to detected features while maintaining manageable complexity through iterative refinement
3Productivity
If manual intervention is required to adjust eyeball position, then the system is easier to control, but the productivity deteriorates due to manual operation requirements
Solution Approach 1:
The patent implements self-service functionality where the system automatically detects the eyeball starting position and configures the initial eyeball window without manual intervention. The algorithm autonomously identifies key features and sets up tracking parameters, improving productivity while managing operational complexity through automated feature detection
Data Source
AI summary
An eyeball tracking method and apparatus, and a device. The method comprises: acquiring a facial grey-scale image set to be detected (101); judging whether the contour of an eyeball iris is determined in an N-th frame facial grey-scale image in the facial grey-scale image set to be detected (102); if not, detecting an eyeball pupil in the N-th frame facial grey-scale image, and determining the central position of the eyeball pupil in the N-th frame facial grey-scale image (103); in the N-th frame facial grey-scale image, taking the central position of the eyeball pupil as a centre to determine a grey-scale image region corresponding to an eyeball window (104); and according to the grey-scale image region corresponding to the eyeball window, determining the contour of the eyeball iris in the N-th frame facial grey-scale image (105). By judging that the contour of an eyeball iris is not determined in a facial grey-scale image, the tracking of the contour of the eyeball iris can be automatically adjusted, and an eyeball pupil is positioned again. By means of the present invention, the accuracy rate of eyeball tracking is improved, and an eyeball can be automatically identified to detect the central position of an eyeball pupil.