EOG Gaze Tracking Drift Noise Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional eye-gaze tracking techniques using Electro-oculography (EOG) face challenges in accurately detecting gaze direction due to low frequency noise and baseline drift, leading to low accuracy in gaze detection.
Innovation Solution
An eye-gaze tracking device that estimates and removes drift noise from observation voltages using a component outside the electro-oculography subspace, allowing for high-accuracy gaze direction estimation by calibrating or dynamically estimating the electro-oculography subspace and using a nonlinear electro-oculography conversion function to separate drift from the electro-oculogram.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If EOG technique is used for eye-gaze tracking, then advantages include not interfering with vision, not being influenced by outside light, not depending on eye shape and opening state, and low power consumption, but low frequency noise and baseline drift cause the observation voltage to exceed the electro-oculography range within approximately one minute, disabling gaze detection
Solution Approach 1:
The patent extracts and removes the drift component from the observation voltage signal. By identifying the drift as a separate entity that can be estimated and subtracted, the system isolates the useful electro-oculogram signal from the harmful baseline drift, enabling continuous gaze detection without the voltage exceeding the measurable range
Solution Approach 2:
The patent implements a feedback mechanism where the drift estimation is continuously updated based on the observation voltage, and this estimated drift is fed back to be subtracted from the original signal. This closed-loop approach allows the system to adapt to changing drift conditions and maintain accurate gaze detection over extended periods
2Reliability
If conventional drift correction methods using battery model or Kalman filter are used, then some drift correction is achieved, but the frequency range overlaps with the electro-oculogram and it is not possible to perform frequency separation, resulting in low accuracy in gaze detection
Solution Approach 1:
The patent moves the drift correction problem from the frequency domain to the time domain by estimating drift as a temporal baseline component. Instead of trying to separate signals by frequency, the method treats drift as a time-varying offset that can be estimated and removed directly from the observation voltage, avoiding the frequency overlap problem entirely
Solution Approach 2:
The patent changes the approach to drift correction by modeling drift as a parameter (baseline voltage) that can be dynamically estimated and adjusted. By treating drift as a separable parameter rather than an inherent signal characteristic, the system can modify the correction method to better match the actual drift behavior, improving both reliability and precision
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
The device achieves high accuracy in gaze direction detection by effectively suppressing drift noise, improving the accuracy of electro-oculography measurement and gaze detection, even in regions with significant crosstalk, and allowing for flexible electrode attachment positions.
Implementation Method 1
The technique is to detect an eye-gaze by measuring eye potential (electro-oculogram) generated by a positive charge in a cornea and a negative charge in a retina
Data Source
AI summary
An eye-gaze tracking device, which detects a gaze direction of a user based on an electro-oculogram, includes: a drift estimating unit which estimates drift noise included in a set of observation voltages among observation voltages that are electro-oculograms generated in a living body and observed at the plurality of electrodes, based on a component outside an electro-oculography subspace that is an assembly of sets of electro-oculograms theoretically observed at a plurality of electrodes; and an eye-gaze tracking unit which detects the gaze direction of the user, based on a signal generated by removing, from the observation voltages, the drift noise estimated by the drift estimating unit.