Occupant Eye Detection Using Proximity-Based Target Selection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing occupant observation devices face high processing loads and increased erroneous detection frequencies due to the complexity of eye detection in images, making real-time vehicle control challenging.
Innovation Solution
An occupant observation device is configured with an imager capturing the occupant's head and an eye detector that prioritizes the eye closer to the imager for detection, reducing processing load and improving accuracy by deriving the eye opening rate based on feature points and switching detection targets based on detection quality.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If eye detection is performed on both eyes in the image, then detection completeness is improved, but processing load increases
Solution Approach 1:
The patent extracts and focuses detection resources on only one eye (the closer eye) rather than processing both eyes. The eye detector is configured to identify and detect features of the closer eye to the imager, eliminating the need to process the farther eye. This extraction principle reduces the amount of data to be processed while maintaining essential detection functionality for determining eye opening rate.
Solution Approach 2:
The patent applies partial action by performing detection on only one eye instead of both eyes. Since the closer eye provides sufficient information for eye opening rate calculation, detecting both eyes would be excessive. This partial detection approach reduces processing load while maintaining adequate detection accuracy for the intended application.
2Measurement precision
If comprehensive eye detection is performed, then detection accuracy is improved, but processing time increases
Solution Approach 1:
The patent extracts the essential detection target (the closer eye) from the complete set of detection targets (both eyes). By focusing computational resources on detecting only the closer eye's features, the system achieves adequate detection accuracy for eye opening rate calculation while significantly reducing the time required to process image data.
Solution Approach 2:
The patent implements partial detection by analyzing only one eye instead of both eyes. This partial action provides sufficient measurement precision for determining eye opening rate and occupant state, while reducing processing time to enable more frequent or real-time monitoring.
3Reliability
If detection is performed on the eye farther from the imager, then detection coverage is improved, but detection accuracy decreases
Solution Approach 1:
The patent applies local quality by selecting the closer eye as the detection target based on its superior image quality characteristics. The closer eye provides higher resolution, better contrast, and more reliable feature detection compared to the farther eye. This local optimization principle ensures that detection is performed on the eye with the most favorable local conditions for accurate measurement.
Data Source
AI summary
Provided is an occupant observation device including an imager configured to capture an image of a head of an occupant of a vehicle; and an eye detector configured to detect at least a part of eyes of the occupant in the image captured by the imager, in which the eye detector sets an eye closer to the imager among the eyes of the occupant as a detection target.