Eye Closure Detection via Luminance Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing eye closure detection devices are prone to errors due to the presence of edges other than eyelid-eyeball boundaries in eye region images, leading to incorrect determination of eye openness or closure.
Innovation Solution
A state determination device that calculates the luminance values of pixels in eye region images over time intervals, determining the eye-closed state by identifying specific luminance thresholds and calculating the duration of eye closure to accurately assess the person's state without relying on edge detection.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If edge detection is used to identify eyelid-eyeball boundaries in eye region images, then the device can detect eye closure state, but the presence of other edges (such as eyelashes) causes erroneous detection of boundaries
Solution Approach 1:
The patent extracts only the luminance information from eye region images and eliminates edge detection processing. By taking out the problematic edge detection step and replacing it with luminance value analysis, the system avoids erroneous detection caused by eyelashes and other edges while maintaining the ability to determine eye closure state accurately
Solution Approach 2:
The patent changes the detection parameter from spatial features (edges and boundaries) to temporal-luminance features. By monitoring changes in luminance values over time rather than detecting spatial boundaries, the system achieves reliable eye closure detection without being affected by interfering edges such as eyelashes
2Adaptability or versatility
If edge detection methods are used to determine eye state, then the system can identify eyelid boundaries, but the detection is easily affected by illumination conditions and individual facial structure differences
Solution Approach 1:
The patent changes the detection approach from spatial boundary detection to temporal luminance analysis. This parameter change makes the system adaptable to different illumination conditions and individual facial structures, as luminance value changes over time provide reliable eye closure information regardless of these varying factors
Solution Approach 2:
The luminance-based detection method serves multiple functions: it works across different illumination conditions, adapts to various facial structures, and reliably determines eye closure state. This universal approach replaces the specialized edge detection method that fails under diverse conditions
Data Source
AI summary
A state determination device includes a calculator that receives multiple eye region images captured at different timings in a time interval from when a person opening eyes closes the eyes to when the person opens the eyes next and calculates a luminance value relating to multiple pixels included in each of the eye region images and a determiner, wherein the determiner calculates a time interval from a first time point when the luminance value relating to the pixels reaches a predetermined first luminance value for the first time to a second time point when the luminance value relating to the pixels reaches a second luminance value after the first time point; if a time interval from the first time point to the second time point is a first time interval, the determiner determines that the person is in a first state; if the time interval from the first time point to the second time point is a second time interval which is shorter than the first time interval, the determiner determines that the person is in a second state which differs from the first state; and the determiner outputs a determination result.