Eye Gaze Tracking Using Web Camera and Adaptive Head Pose Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing eye gaze tracking systems face challenges in accurately tracking gaze under varying illumination conditions and require expensive infrared cameras, which are intrusive and sensitive to infrared sources, glasses, and head movements, limiting their practicality and accuracy.
Innovation Solution
A generic camera-based eye gaze tracking system using a weighted adaptive algorithm for head pose estimation, combining local sensitive histograms and active shape models to detect eye regions and iris centers, and a multi-scale eye corner detector to form an eye vector, which is then calibrated to estimate gaze points robustly across different lighting conditions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If infrared cameras are used for eye gaze tracking, then gaze tracking accuracy is improved, but device cost increases and system complexity increases
Solution Approach 1:
The patent replaces expensive infrared cameras with a standard web camera, using a low-cost imaging device to achieve the same gaze tracking function. This substitution maintains measurement precision while dramatically reducing device cost and complexity.
Solution Approach 2:
The patent replaces the optical-mechanical infrared camera system with a software-based processing system that uses standard camera images. By substituting mechanical/optical components with computational algorithms (eye region detection, iris center detection, head pose estimation), the system achieves comparable accuracy with simpler hardware.
2Measurement precision
If infrared cameras are used for eye gaze tracking, then gaze tracking accuracy is improved, but the system becomes more sensitive to infrared sources and glasses
Solution Approach 1:
By using a standard web camera instead of an infrared camera, the system eliminates sensitivity to infrared sources and glasses. The web camera captures visible light images that are not affected by these interfering factors, providing more reliable gaze tracking in diverse environments.
Solution Approach 2:
The patent changes the operating parameter from infrared wavelength to visible light wavelength. This parameter change fundamentally alters the system's interaction with the environment, making it immune to infrared source interference and glass reflections that plague infrared-based systems.
3Measurement precision
If infrared cameras are used for eye gaze tracking, then gaze tracking accuracy is improved, but the system becomes more sensitive to head movements
Solution Approach 1:
The patent replaces the infrared camera system with a web camera system that uses computational algorithms to estimate head pose and compensate for head movements. This substitution reduces sensitivity to head movements by using multiple facial feature points and geometric relationships that remain stable despite head position changes.
Solution Approach 2:
The patent implements feedback mechanisms through continuous head pose estimation and compensation. By detecting head movement and dynamically adjusting the gaze calculation, the system maintains accuracy despite head movements, using real-time feedback from facial feature tracking to correct gaze estimates.
4Device complexity
If standard web cameras are used for eye gaze tracking, then device cost is reduced, but robustness to illumination changes deteriorates
Solution Approach 1:
The patent changes the image processing parameters by using illumination-invariant features such as eye reflection patterns and geometric relationships between facial features. These parameters are designed to remain stable across different lighting conditions, enabling the low-cost web camera system to achieve robustness comparable to expensive infrared systems.
Solution Approach 2:
The patent focuses on local features in the eye region, such as the iris reflection pattern and eye corner geometry, which are locally illuminated and less affected by global illumination changes. By concentrating on these localized, illumination-resistant features, the system maintains reliability across varying lighting conditions despite using a low-cost camera.
Data Source
AI summary
The invention relates to method and apparatus of an eye gaze tracking system. In particular, the present invention relates to method and apparatus of an eye gaze tracking system using a generic camera under normal environment, featuring low cost and simple operation. The present invention also relates to method and apparatus of an accurate eye gaze tracking system that can tolerate large illumination changes.