Driver Drowsiness Detection Using Eye Open Time Standard Deviation

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing biological body state assessment devices struggle to accurately differentiate between an absentminded state and other driver states, as there is no clear index or feature quantity to definitively assess absentmindedness before drowsiness occurs.

Innovation Solution

A device that calculates the standard deviation of eye open time and face direction variation using face information, where an absentminded state is detected if the eye open time standard deviation exceeds a threshold and the face direction standard deviation is below another threshold, allowing for improved vigilance assessment and prediction of drowsiness occurrence.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If conventional driver state assessment methods are used, then general vigilance can be monitored, but absentminded state cannot be accurately differentiated from other states

Engineering Contradiction:
Improvestate differentiation accuracyVSAvoidabsentminded state information
Core Design Contradiction:
Measurement precisionVSLoss of information

Solution Approach 1:

The patent segments the driver state assessment into multiple independent feature dimensions: eye open time, face direction, and their respective variations. By calculating standard deviation for each feature separately and combining them through logical operations, the system can identify the absentminded state as a distinct category, thereby improving measurement precision and preventing loss of information about specific driver states.

Inventive Principle:
Principle #1Segmentation

2Adaptability or versatility

If multiple feature parameters are monitored simultaneously, then assessment comprehensiveness improves, but system complexity increases

Engineering Contradiction:
Improvestate assessment comprehensivenessVSAvoidcalculation system complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent extracts the essential characteristics of the absentminded state by focusing on two key features: eye open time variation and face direction variation. Instead of processing all possible driver state parameters, the system selectively extracts and monitors only those features that are most indicative of absentmindedness, thereby maintaining assessment comprehensiveness while reducing computational complexity.

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The patent combines multiple monitoring functions into a unified assessment system that integrates eye open time monitoring, face direction monitoring, and their variation calculations. By merging these functions and using logical operations to combine the results, the system achieves comprehensive state assessment without proportionally increasing overall system complexity.

Inventive Principle:
Principle #5Merging (Combining)

Data Source

PatentEP2557549B1Biological body state assessment device
Publication Date: 2022.10.12 TOYOTA JIDOSHA KK
  • EP2557549B1 patent drawingFigure 1
  • EP2557549B1 patent drawingFigure 2
  • EP2557549B1 patent drawingFigure 3

AI summary

Disclosed is a biological body state assessment device capable of accurately assessing an absentminded state of a driver. The biological body state assessment device first acquires face image data of a face image capturing camera, detects an eye open time and a face direction left/right angle of a driver from face image data, calculates variation in the eye open time of the driver and variation in the face direction left/right angle of the driver, and performs threshold processing on the variation in the eye open time and the variation in the face direction left/right angle to detect the absentminded state of the driver. The biological body state assessment device assesses the possibility of the occurrence of drowsiness of the driver in the future using a line fitting method on the basis of an absentminded detection flag and the variation in the eye open time, and when it is assessed that there is the possibility of the occurrence of drowsiness, estimates an expected drowsiness occurrence time of the driver.