Dual Imaging Eye Tracking Actuator Mechanism
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional eye tracking systems in large environments, such as vehicle passenger compartments, face challenges in accurately detecting and tracking user gaze directions due to the need for wide-angle lenses, which results in high processing loads, increased latency, and power consumption.
Innovation Solution
The use of multiple imaging devices, where a first imaging device with a wide field of view generates initial image data for face detection, and a second imaging device with a smaller field of view, directed by an actuator, captures high-resolution images of the user's face, reducing power consumption and heat generation.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Area of stationary object
If a wide-angle lens is used to capture images in large environments, then the field of view is improved, but the measurement precision of eye detection deteriorates
Solution Approach 1:
The system divides the imaging task into two segments: a first imaging device with a wide-angle lens captures the entire passenger compartment to locate the user's face, while a second imaging device with a narrow-angle lens captures high-resolution images of the eyes. This segmentation allows each device to be optimized for its specific function, resolving the contradiction between wide field of view and precise eye detection.
2Measurement precision
If a high-resolution camera is used to improve eye tracking accuracy, then the measurement precision is improved, but the processing load increases
Solution Approach 1:
The system extracts only the necessary portion of the scene (the user's eyes) using face location information from the first imaging device, and directs the second high-resolution imaging device to capture only that region. This extraction approach allows high measurement precision for eye tracking while minimizing the processing load by not requiring the entire wide field of view to be processed at high resolution.
3Measurement precision
If a high-resolution camera is used to improve eye tracking accuracy, then the measurement precision is improved, but the power consumption increases
Solution Approach 1:
The system uses the first imaging device to periodically locate the user's face and determine when eye tracking is needed. The second high-resolution imaging device is activated only when necessary, based on the face location information. This periodic activation pattern maintains high measurement precision when needed while significantly reducing overall power consumption compared to continuous operation of a high-resolution camera.
4Area of stationary object
If a wide-angle lens is used to capture large environments, then the area coverage is improved, but the measurement precision of eye detection deteriorates
Solution Approach 1:
The first imaging device with the wide-angle lens acts as an intermediary that locates the user's face within the large passenger compartment. This face location information serves as a mediator to guide the second imaging device with the narrow-angle lens to the precise location of the eyes. This two-stage approach allows the system to cover large areas while maintaining high measurement precision for eye detection.
Data Source
AI summary
This disclosure describes, in part, systems and techniques for performing eye tracking. For instance, a system may include a first imaging device that generates first image data. The system may then analyze the first image data to determine a location of a face of a user. Using the location, the system may cause an actuator to move from a first position to a second position in order to direct a second imaging device towards the face of the user. While in the second position, the second imaging device may generate second image data representing at least the face of the user. The system may then analyze the second image data to determine a gaze direction of the user. In some instances, the first imaging device may include a first field of view (FOV) that is greater than a second FOV of the second imaging device.