Sight Vector Detection Using Eye Center and Gaze Model
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current sight vector detection methods are limited in accuracy when the user is not positioned centrally in front of the target object, and they may pose a risk to the user's retinal health due to excessive infrared light emission.
Innovation Solution
A method and device that utilize an image capture element and a depth capture element to determine the eye center location, predict the user's sight location based on a gaze model, and calculate the sight vector, eliminating the need for central positioning and reducing retinal exposure to infrared light by using natural light sources.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If image camera and intra-red camera are used to detect user pupil location, then sight target detection is enabled, but the user must stand in front of the center of the target object which limits positioning flexibility
Solution Approach 1:
The patent introduces an eye center location as an intermediary reference point instead of directly detecting pupil location. By calculating the eye center from image data and using it as a mediator, the system can determine sight vectors without requiring the user to be centrally positioned, thus resolving the contradiction between detection accuracy and positioning flexibility
Solution Approach 2:
The patent changes the detection parameter from pupil location to eye center location. This parameter transformation allows the system to work with users at various positions by calculating the eye center relative to the camera, enabling sight vector detection without central positioning requirements while maintaining accuracy
2Reliability
If multiple image cameras and intra-red cameras are used to detect driver sight target, then detection coverage is improved, but device complexity increases
Solution Approach 1:
The patent makes the image capture element perform multiple functions: capturing images for eye center location calculation, obtaining distance information, and enabling sight vector determination. This multi-functionality reduces the need for separate specialized cameras, thereby reducing device complexity while maintaining detection reliability
Solution Approach 2:
The patent combines the functions of image capture and depth/distance capture into a unified processing approach. By merging these functions and processing them together through the eye center calculation and gaze model, the system achieves reliable detection with fewer components, reducing overall device complexity
3Illumination intensity
If IR LEDs emit strong IR rays to user eyes for sight detection, then detection signal strength is improved, but retinal damage risk increases
Solution Approach 1:
The patent extracts and removes the harmful IR LED component from the system. By eliminating the need for active IR illumination and using passive image capture instead, the system maintains detection capability while completely removing the retinal damage risk associated with strong IR light emission
Solution Approach 2:
The patent converts the approach from active illumination (which causes harm) to passive imaging (which is safe). By using natural light reflected from the user's eyes captured by the image camera, the system transforms a potentially harmful active detection method into a safe passive detection method while maintaining functionality
Data Source
AI summary
A sight vector detecting method includes: capturing a user image by an image capture unit and a depth capture unit to obtain a first image and a distance information; based on the first image and the distance information, finding an eye center location of the user; predicting a user sight location by a gaze model to find a target sight location of the user on a target; based on the eye center location of the user, finding a first word coordinate of the eye center location of the user; based on the target sight location of the user, finding a second word coordinate of the target sight location of the user; and based on the first word coordinate of the eye center location of the user and the second word coordinate of the target sight location of the user, calculating a sight vector of the user.