Eye Gaze Tracking Calibration via External Object Comparison
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Eye gaze tracking systems in vehicles often exhibit errors, particularly a shift or bias in the indicated gaze, which can affect the accuracy of driver monitoring applications such as detecting distraction, drowsiness, and situational awareness.
Innovation Solution
An apparatus and method that estimate errors in eye gaze tracking systems by comparing measured eye gaze information with theoretically determined eye gaze information based on location data from external objects, using forward-looking cameras to capture images at different times and determine relative displacement, depth, and direction of objects, and recalibrating the system accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If eye gaze tracking systems are used to monitor driver state, then driver safety monitoring capability is improved, but measurement precision deteriorates due to systematic errors and bias in gaze indication
Solution Approach 1:
The system uses feedback from multiple sources (head pose sensors, vehicle sensor data, road geometry information) to continuously correct and adjust eye gaze measurements. The measured eye gaze information is compared against expected gaze directions derived from independent measurements, and systematic errors are identified and compensated through this feedback loop, thereby maintaining measurement precision while preserving driver monitoring capability
Solution Approach 2:
The patent introduces intermediary reference systems (head pose sensors, vehicle motion sensors, road geometry models) that serve as mediators between the eye tracker and the actual gaze direction. These intermediaries provide independent measurement channels that help identify and correct errors in the primary eye gaze measurement system, resolving the contradiction between maintaining monitoring capability and improving accuracy
2Measurement precision
If systematic errors in eye gaze tracking are corrected using multiple measurement channels, then measurement precision is improved, but device complexity increases
Solution Approach 1:
The system employs multi-functionality by using vehicle sensors and processing units that serve multiple purposes: they monitor vehicle dynamics for safety, process road geometry data for navigation, and simultaneously provide reference information for correcting eye gaze measurements. This universal use of existing components improves gaze measurement precision without proportionally increasing device complexity
Solution Approach 2:
The system performs self-calibration and self-correction by using its own operational data (vehicle motion, head pose, road geometry) to identify and correct gaze measurement errors. The same sensors and processors used for primary vehicle functions automatically generate correction signals, allowing the system to self-service its calibration needs without requiring external intervention or additional dedicated calibration hardware
Data Source
AI summary
A system and method for error estimation in an eye gaze tracking system in a vehicle may include an operator monitoring system providing measured eye gaze information corresponding to an object outside the vehicle and an external object monitoring system providing theoretical eye gaze information and an error in the measured eye gaze information based upon the measured eye gaze information and the theoretical eye gaze information.