Gaze Tracking via Stereo Disparity Map Compensation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current gaze tracking technologies in three-dimensional spaces face limitations in accurately detecting a watch point due to binocular visual vector errors and match errors, which hinder precise object recognition and human-computer interaction.
Innovation Solution
An electronic apparatus and method that utilize a disparity map to compensate for errors in gaze vector detection by processing binocular images from both eyes and stereo images, minimizing differences between left and right eye watch points through stereo matching and image compensation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If binocular observation is used for gaze tracking, then the system can detect user gaze direction, but measurement accuracy is limited and cannot accurately find the watch point in three-dimensional space at a distance
Solution Approach 1:
The patent introduces a camera as an intermediary device to capture the user's gaze direction. The camera records the actual gaze direction independently, which then serves as a reference to correct the binocular gaze vector. This intermediary measurement allows the system to overcome the limitations of pure binocular observation at distances.
Solution Approach 2:
The patent implements a feedback mechanism where the camera-captured gaze direction is used to compensate for errors in the binocular gaze vector. The system continuously compares the binocular-derived gaze vector with the camera-observed gaze direction and adjusts the watch point detection accordingly, creating a closed-loop correction system.
2Reliability
If a camera is added to capture gaze direction, then tracking performance is improved, but the complexity of the system increases due to the need for precise matching between binocular gaze vector and camera image
Solution Approach 1:
The patent merges the binocular observation system with the camera-based gaze capture system into a unified gaze tracking framework. By combining these two approaches, the system leverages the strengths of both: the binocular system provides depth perception while the camera provides accurate gaze direction, creating a more robust and reliable tracking performance.
Solution Approach 2:
The patent introduces a disparity map as an intermediary computational element that facilitates the matching between binocular and camera data. The disparity map, derived from stereo image processing, serves as a bridge that enables accurate correspondence between the binocular gaze vector and camera gaze direction without requiring complex direct matching algorithms.
3Measurement precision
If stereo matching is performed to obtain disparity map, then watch point compensation accuracy is improved, but processing time and computational complexity increase
Solution Approach 1:
The patent performs preliminary stereo matching to generate the disparity map in advance, before the actual gaze tracking and watch point detection are needed. By pre-computing the disparity map from the stereo images, the system prepares the compensation data structure beforehand, reducing the computational burden during real-time gaze tracking operations.
Data Source
AI summary
An electronic apparatus is disclosed. The electronic apparatus includes an inputter configured to receive a binocular image which is a captured image of both eyes of a user and a stereo image which is an image of a direction corresponding to a gaze of the user captured at locations spaced apart from each other, and a processor configured to detect a watch point of a user in the stereo image by using the binocular image, obtain a disparity map in the input stereo image, and compensate the detected watch point using the obtained disparity map.