Multi-User Eye Tracking via Sequential Image Capture
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing multi-user eye tracking systems are inefficient as they typically require multiple cameras to track multiple users simultaneously, leading to inferior image quality and increased complexity, making it difficult to track multiple users at the same time without a significant loss in frame rate.
Innovation Solution
A method for operating an eye tracking device that captures images in a predeterminable time sequence using a single camera with a wide opening angle, allowing for simultaneous tracking of multiple users by processing images in different states (user search, eye tracking, and combined states) to determine user presence and gaze direction, and adjusting settings like illumination and image processing based on the current state.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If multiple cameras are used to track multiple users simultaneously, then the ability to track multiple users is improved, but the device complexity and cost increase
Solution Approach 1:
A single camera system is designed to perform multiple functions: it can track multiple users simultaneously, switch between users, and adapt to different tracking scenarios. The camera acts as a universal tracking device that replaces what would traditionally require multiple specialized cameras, thereby reducing system complexity while maintaining multi-user capability
Solution Approach 2:
The camera system dynamically adjusts its orientation and focus to track different users. Instead of having static multiple cameras fixed on different users, a single camera dynamically repositions itself to follow eye movements and switch between users in real-time, enabling multi-user tracking with a single device
2Measurement precision
If multiple active camera orientation systems are used for each user, then the tracking precision for each user is improved, but the frame rate decreases due to reorientation time
Solution Approach 1:
The system performs preliminary actions by continuously monitoring and predicting user eye movements before a switch is needed. The camera system maintains readiness to track any user by pre-positioning and pre-focusing, reducing the reorientation time when switching between users and maintaining high frame rates
Solution Approach 2:
The camera system uses periodic scanning and sampling to monitor multiple users' eye positions. By periodically updating the positions of all users and using predictive algorithms, the system can quickly switch between users without significant reorientation time, maintaining both precision and frame rate
3Device complexity
If a single camera is used to track multiple users, then the device complexity is reduced, but the image quality and tracking accuracy deteriorate
Solution Approach 1:
The camera system captures images at high resolution and then applies local quality processing by focusing computational resources on specific regions of interest (user eyes) within the image. This allows the single camera to maintain high tracking accuracy for multiple users by optimizing image processing for eye detection and tracking in different spatial locations
Solution Approach 2:
The system performs preliminary image processing and analysis to identify and locate user eyes before detailed tracking begins. By pre-processing images to detect eye positions and characteristics, the system compensates for the single camera's limitations and maintains high tracking accuracy through advanced image analysis algorithms
4Productivity
If images are captured successively in a predeterminable time sequence, then the processing load is reduced, but the ability to capture simultaneous user actions is limited
Solution Approach 1:
The image processing is segmented into different states and priorities. The system divides processing into user detection, eye tracking, and action recognition stages, processing images in a time sequence but maintaining the ability to reconstruct simultaneous user actions by correlating data across multiple processed frames using predictive models
Data Source
AI summary
The invention relates to a method for operating an eye tracking device (10) for multi¬user eye tracking, wherein images (24) of a predefined capturing area (14) of the eye tracking device (10) are captured by means of an imaging device (12) of the eye tracking device (10) and the captured images (24) are processed by means of a processing unit (16) of the eye tracking device (10). If a first user (26a) and a second user (26b) are present in the predefined capturing area (14) of the eye tracking device (10), a first information relating to the first user (26a) and a second information relating to the second user (26b) are determined on the basis of the captured images (24) by processing the images (24). Furthermore the images (24) are captured successively in a predeterminable time sequence.