Drowsiness Detection via Eye Movement Interpolation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing camera-based systems for drowsiness detection face challenges in providing reliable early predictions due to low sampling rates, which limits their effectiveness in predicting drowsiness onset.
Innovation Solution
A method that receives eye movement data at sampling rates greater than 20 Hz but less than 250 Hz, interpolates the data to achieve rates greater than 250 Hz, calculates amplitude and velocity ratios of eyelid movements, and uses these values in an algorithm to determine drowsiness, allowing for reliable predictions without the need for high sampling rates.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If camera-based systems are used for drowsiness detection, then the system is less intrusive and does not require spectacles, but the sampling rate is low which reduces measurement precision
Solution Approach 1:
The patent introduces an intermediary processing step (interpolation algorithm) between the low sampling rate camera data and the drowsiness detection algorithm. This intermediary process generates intermediate data points that effectively increase the sampling rate without requiring faster camera hardware, thus resolving the contradiction between using intrusive spectacles-mounted sensors and using less intrusive camera-based systems.
2Measurement precision
If high sampling rates are used for eye movement data collection, then measurement precision improves, but device complexity and cost increase
Solution Approach 1:
The patent creates a virtual copy of the high sampling rate data stream through interpolation, generating synthetic data points that mimic what a high-speed sensor would capture. This allows the drowsiness detection algorithm to operate as if receiving high-rate data without actually requiring high-speed hardware, thereby reducing device complexity while maintaining measurement precision.
3Measurement precision
If data interpolation is performed to increase sampling rate, then measurement precision improves, but processing time increases
Solution Approach 1:
The patent performs data interpolation in advance, before the actual drowsiness detection algorithm is applied. By pre-processing the low sampling rate camera data into a high sampling rate format ahead of time, the system eliminates the need for real-time interpolation during critical detection phases, thus reducing processing time delays while maintaining measurement precision.
Data Source
Figure 1A~1B
Figure 2
Figure 3
AI summary
Lower sampling rates have been found to provide sufficient data for use in the method of USA patents 7071831, 7616125 and 779149. The method of determining drowsiness includes the steps of receiving eye movement data collected at sampling rates as low as 20Hz. The data is preferentially interpolated to provide a data set at a higher sampling rates in the order of 500Hz. For each data point values of amplitude and velocity of eye movement and whether the measures relate to eyelid opening or closing are derived. An algorithm is then used to obtain values of the amplitude to velocity ratios of eyelid opening and closing and using these values in an algorithm for providing a measure of drowsiness. With this method eyelid and eye movement may be monitored using any suitable technology or sensor including video or digital camera technology to identify and measure the appropriate ocular movements.