Drowsiness Estimation Using Recurrence Time to Remove Individual Differences
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing drowsiness estimation systems face challenges in accurately detecting drowsiness due to individual differences in expression values, making it difficult to reliably assess drowsiness levels.
Innovation Solution
A drowsiness estimating apparatus and method that calculates the recurrence required time for drowsiness estimation parameters to return to their initial values after an action is detected, allowing for more accurate drowsiness level estimation by eliminating individual variability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If drowsiness estimation is performed using fixed reference values of expression information, then the estimation process is simple, but accuracy deteriorates due to individual differences between persons
Solution Approach 1:
The system performs preliminary action by detecting actions (eye movements, head movements, blinking) before calculating drowsiness. By detecting these actions first and using them as reference points, the system adapts to individual characteristics without requiring complex pre-calibration procedures, thus resolving the contradiction between simplicity and accuracy.
Solution Approach 2:
The system dynamically adjusts the reference values based on detected actions. Instead of using fixed reference values, the system updates reference expression information based on detected actions like eye movements and blinking, making the estimation adaptive to individual differences while maintaining computational simplicity.
2Measurement precision
If individual-specific reference values are used for each person, then drowsiness estimation accuracy improves, but system complexity increases due to need for individual calibration
Solution Approach 1:
The system employs self-service by automatically detecting actions and generating individual-specific reference values without requiring manual calibration or user intervention. The system serves itself by using its own detection capabilities to establish personalized baselines, achieving high accuracy while keeping the interface simple.
Solution Approach 2:
The system changes parameters dynamically by adjusting reference expression information based on detected actions. Instead of maintaining fixed parameters or requiring manual input, the system automatically modifies reference values based on observed behavior patterns, achieving personalization through parameter adaptation rather than system complexity.
3Measurement precision
If action detection is incorporated to adapt to individual differences, then estimation accuracy improves, but processing time increases
Solution Approach 1:
The system applies partial action by detecting only specific, representative actions (eye movements, head movements, blinking) rather than analyzing all facial expressions. This selective detection approach provides sufficient individual characterization without requiring exhaustive processing, thus balancing accuracy with processing efficiency.
Solution Approach 2:
The system uses preliminary action detection to quickly establish reference values from detected actions, enabling rapid adaptation to individual characteristics. By detecting key actions first and using them to set reference points, the system minimizes processing time while still achieving personalized accuracy.
Data Source
AI summary
A drowsiness-estimating device capable of improving the precision of drowsiness estimation by eliminating the effect of individual differences. In the device, a recurrence required time-calculating part (103) calculates the recurrence required time, which is the time needed, after a detection time when an action is detected, for a drowsiness estimation parameter value acquired after the detection time to return to the value of the drowsiness estimation parameter acquired before the detection time. A drowsiness-estimating part (104) estimates the level of drowsiness of the drowsiness-estimation subject on the basis of the calculated recurrence required time. To be specific, the drowsiness-estimating part (104) maintains a drowsiness level-estimating table in which each of multiple time ranges is correlated with a possible drowsiness level, and specifies a possible drowsiness level that corresponds to the time range, among the multiple time ranges, with which the recurrence required time is associated.