Eye-Status Detection Using Dynamic Eye-Contour Standard Deviations
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing eye status detection systems are inaccurate due to variations in distance and unique facial characteristics, affecting the reliability of drowsiness detection in drivers.
Innovation Solution
A method and device that utilize standard deviations of eye contour heights to accurately detect changes in eye status by analyzing eye contour areas, employing grayscale conversion, binarization, dilation, and erosion processes to enhance contour detection, and using smoothing windows to determine eye-open and eye-closed statuses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If conventional threshold-based detection methods are used, then the detection process is simple, but the accuracy deteriorates due to distance changes and unique facial characteristics
Solution Approach 1:
The patent changes the detection parameter from fixed thresholds to dynamic standard deviations calculated from eye contour height variations. By computing standard deviations across multiple frames and using these dynamic values for status determination, the system adapts to different facial characteristics and distances, resolving the contradiction between simple detection process and accurate measurement.
2Ease of manufacture
If fixed thresholds are used for eye contour area and height, then the detection method is straightforward, but reliability deteriorates due to variations in distance and facial characteristics
Solution Approach 1:
The patent transforms the static fixed thresholds into dynamic adaptive thresholds based on standard deviations calculated from sequential eye contour measurements. The system continuously updates the standard deviation values from multiple frames, creating a dynamic detection mechanism that adapts to changing conditions such as distance variations and individual facial characteristics, thereby improving reliability while maintaining ease of implementation.
3Measurement precision
If standard deviations of eye contour heights are used, then detection accuracy improves, but the computational complexity increases
Solution Approach 1:
The patent performs preliminary calculations by pre-processing the eye contour extraction and preparing the height difference arrays before computing standard deviations. By organizing the data structure in advance and pre-calculating intermediate values from sequential frames, the system reduces the computational burden during the actual detection phase, thereby achieving high accuracy without excessive computational complexity.
Data Source
AI summary
A method for detecting changes in eye status is provided. The method includes receiving multiple consecutive facial images generated by a photography device photographing a person's face, wherein each facial image includes an eye region. The method includes obtaining a partial image including the eye region from each of the facial images. The method includes obtaining an eye contour area based on the partial image. The method includes obtaining standard deviations of eye contour heights based on the eye contour area. The method includes determining a change in the eye status of eyes within a time interval based on the standard deviations of all eye contour heights within the time interval, wherein the eye status includes an eye-open status and an eye-closed status.