Dual Camera Gaze Tracking via Segmented Field of View
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing gaze tracking systems face challenges in accurately tracking user gaze direction from a distance, leading to lower-quality tracking and increased processing resources required for improved resolution, which can introduce latency and processing burdens.
Innovation Solution
A dual-tracking method using a pair of cameras, where the first camera captures a wider field of view to identify the user and reposition the second camera with a smaller field of view for precise eye tracking, enabling more accurate and efficient gaze direction identification.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If a single camera with wide field of view is used to track user gaze from a distance, then the user can be located within the environment, but the tracking precision of eye direction deteriorates
Solution Approach 1:
The system divides the tracking task into two segments: a first camera captures a wide field of view to locate the user's head and eyes, then a second camera with narrower field of view is positioned to capture detailed images of the eyes for precise gaze direction measurement. This segmentation allows each camera to be optimized for its specific function, resolving the contradiction between wide coverage and precision.
Solution Approach 2:
The first camera acts as an intermediary that facilitates the operation of the second camera. By detecting the user's eye location with the wide-field first camera, the system can automatically position the second camera to capture the eyes, enabling the second camera to achieve high precision without requiring manual positioning or a fixed installation location.
2Measurement precision
If a single camera with narrow field of view is used to improve eye tracking precision, then measurement precision improves, but the ability to locate and target the user's eyes deteriorates
Solution Approach 1:
The first camera performs preliminary action by capturing the user's eyes within the wide field of view before the second camera begins detailed tracking. This preliminary detection of eye location enables the system to position the second camera correctly, allowing the narrow-field camera to focus on precision measurement without worrying about acquiring or locating the eyes.
3Measurement precision
If a single high-resolution camera is used to capture eye details from a distance, then measurement precision may improve, but processing resources and latency increase
Solution Approach 1:
Instead of using a single high-resolution camera to capture the entire scene, the system applies local quality by using the first camera to identify the user's eye location in a wide field of view, then directing the second camera to capture high-resolution images only of the eye region. This approach concentrates processing resources on the relevant local area, reducing overall processing burden while maintaining high measurement precision for gaze direction.
Data Source
AI summary
A gaze tracking system comprising a first camera operable to capture images of a user within an environment, a second camera, having a smaller field of view than the first camera, operable to capture images of at least one of the user's eyes, an eye identification unit operable to identify a location of at least one of the user's eyes from images captured by the first camera, a camera control unit operable to modify the position and/or orientation of the second camera in dependence upon the detected location of the at least one of the user's eyes, so as to cause the second camera to be able to capture images of at least one of the user's eyes, and a gaze direction identification unit operable to identify a gaze direction of the user from images captured by the second camera.