Vehicle Drowsiness Detection Eye Closure Classification

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current drowsiness detection systems in vehicles often misinterpret eye closures caused by factors like changing lighting conditions or external stimuli as driver drowsiness, leading to false warnings.

Innovation Solution

A method that compares physiological data from an image sensor with predetermined rules related to lighting conditions within the vehicle compartment to accurately classify eye and head movements, distinguishing between actual drowsiness and other causes of eye closure, such as reaction to bright lights or head movements.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If eye closure detection is used to determine driver drowsiness, then drowsiness detection capability is improved, but false positive rate increases due to misinterpretation of eye closures caused by lighting conditions or external stimuli

Engineering Contradiction:
Improvedrowsiness detection reliabilityVSAvoideye closure classification accuracy
Core Design Contradiction:
ReliabilityVSMeasurement precision

Solution Approach 1:

The patent segments the eye closure detection process into multiple classification stages: detecting eye closure events, categorizing them by duration and frequency, analyzing head position context, and evaluating lighting conditions. This multi-stage segmentation allows the system to distinguish between drowsiness-related closures and those caused by external factors like sunlight or headlights.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent introduces intermediary analysis parameters including head position detection, lighting condition sensing, and eye closure pattern analysis as mediators between raw eye closure detection and final drowsiness determination. These intermediaries help filter out false positives by providing contextual information about the cause of eye closures.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If the system monitors multiple physiological parameters (eye, face, head, arms, body motion), then detection comprehensiveness is improved, but system complexity increases

Engineering Contradiction:
Improvedetection comprehensivenessVSAvoidsystem complexity
Core Design Contradiction:
Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The patent employs a single image sensor that performs multiple functions: detecting eye closure events, determining head position, analyzing facial expressions, and monitoring body motion. This multi-functional approach achieves comprehensive detection without proportionally increasing system complexity, as one sensor replaces what would otherwise require multiple specialized sensors.

Inventive Principle:
Principle #6Universality (Multi-functionality)

3Reliability

If the system provides warnings for detected eye closures, then driver safety is improved, but false warnings increase when driver is not actually drowsy

Engineering Contradiction:
Improvesafety warning reliabilityVSAvoidfalse warning alerts
Core Design Contradiction:
ReliabilityVSObject-generated harmful factors

Solution Approach 1:

The patent implements feedback mechanisms where the system continuously monitors eye closure patterns, head position, and lighting conditions, then adjusts warning generation based on this feedback. The classification algorithm learns from patterns and provides feedback to the warning system, enabling it to distinguish between genuine drowsiness requiring intervention and transient eye closures that do not indicate safety risks.

Inventive Principle:
Principle #23Feedback

Data Source

PatentEP2564777B1Method for classification of eye closures
Publication Date: 2017.06.07 VOLVO CAR CORP
  • EP2564777B1 patent drawingFigure 1~2
  • EP2564777B1 patent drawingFigure 3

AI summary

The present invention relates to a method for improving the reliability of a portion of physiological data from an image sensor (302) monitoring an operator (202) positioned in an operator compartment (114) of a vehicle (100), the method comprising receiving, from the image sensor (302), physiological data comprising information relating to at least one of eye, face, head, arms and body motion of the operator (202), identifying an indication of at least an eyelid closure, eye movement or head movement of the operator (202) based on the physiological data, comparing at least one of the physiological data and a lighting condition within the operator compartment with a predetermined set of rules for a current operator status, and classifying the type of eyelid closure, eye movement and/or head movement by correlating the identified eyelid closure, eye movement and/or head movement and a result of the comparison.