Electronic Device Gaze-Line Mapping for Alertness Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems struggle to accurately infer a driver's alertness level based on gaze lines, particularly in varying driving conditions, leading to potential safety risks.
Innovation Solution
An electronic device equipped with an imaging unit, gaze-line detector, and controller that utilizes machine learning to create a gaze-line prediction map and estimate alertness levels by analyzing gaze lines and biological information, improving accuracy through learning from various driving scenarios.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional methods are used to infer driver alertness based on gaze lines, then the system is simpler to implement, but the accuracy of alertness estimation deteriorates in varying driving conditions
Solution Approach 1:
The system performs preliminary actions by collecting gaze line data and image data during normal driving conditions and using machine learning to train inference units in advance. This pre-training allows the system to accurately estimate alertness levels in varying driving conditions without requiring complex real-time adjustments, thus improving measurement precision while managing device complexity.
Solution Approach 2:
The patent introduces an image recognition unit and machine learning-based inference units as intermediaries between the gaze line detection and alertness estimation. These intermediaries process visual information and contextual data to enhance the accuracy of alertness estimation, resolving the contradiction by adding functional layers that improve precision without proportionally increasing overall system complexity.
2Measurement precision
If machine learning-based inference units are added to improve gaze line prediction accuracy, then the measurement precision improves, but the device complexity increases
Solution Approach 1:
The system segments the alertness estimation function into multiple specialized inference units: a gaze line prediction map inference unit that processes visual information, and a biological information inference unit that estimates alertness levels. This segmentation allows each unit to be optimized for its specific task, improving overall measurement precision while managing complexity through functional decomposition.
Solution Approach 2:
The patent uses machine learning to create copied models (inference units) that replicate the relationship between gaze lines, images, and alertness levels based on training data. These copied models enable accurate real-time predictions without requiring complex real-time processing, thus improving measurement precision while keeping the operational system relatively simple.
Data Source
AI summary
An electronic device 10 includes an imaging unit 11, a gaze-line detector 12, and a controller 14. The imaging unit 11 is configured to create at least one image corresponding to a view by image capturing. The gaze-line detector is configured to detect a gaze line of a subject, the gaze line being directed to the view. The controller 14 is configured to serve as a first inference unit 15 and a second inference unit 16. The first inference unit 15 is capable of inferring a gaze-line prediction map based on the at least one image. The second inference unit 16 is capable of inferring biological information regarding an alertness level of the subject based on the gaze-line prediction map and the gaze line of the subject.