Driver Vigilance Detection via Head Kinematics

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing driver vigilance monitoring systems are ineffective in determining driver drowsiness or distraction when the driver is wearing sunglasses or caps, or in high ambient light conditions, as they struggle to measure eye openness and pupil movements.

Innovation Solution

A method using a camera and computer to analyze head movements, including speed, amplitude, and duration, to determine driver vigilance levels, which can detect drowsiness or distraction even with partial face masking or high ambient light, by identifying dynamic and static periods and comparing these parameters with predetermined thresholds.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If direct measurements of face characteristics (eyes, pupils) are used to determine driver vigilance, then the system can detect drowsiness and distraction, but the system becomes ineffective when the driver wears sunglasses or caps or when ambient light is high

Engineering Contradiction:

Improvedriver vigilance detection reliabilityVSAvoidsystem effectiveness under various environmental conditions

Core Design Contradiction:

ReliabilityVSAdaptability or versatility

Solution Approach 1:

The patent uses head movements as an intermediary indicator to infer driver vigilance state. Instead of directly measuring eye characteristics that become obscured by sunglasses or poor lighting, the system measures head position, orientation, and movement patterns as indirect proxies for alertness level.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces the optical measurement system (camera analyzing eye characteristics) with a mechanical measurement approach (detecting head movements and positions). This substitution allows the system to function effectively regardless of lighting conditions or facial obstructions.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If the system uses camera-based eye analysis to monitor driver vigilance, then it can provide warning for drowsiness, but it fails to detect vigilance levels when face portions are difficult to see or differentiate

Engineering Contradiction:

Improveeye openness and pupil movement measurement precisionVSAvoidvisibility of face portions under various conditions

Core Design Contradiction:

Measurement precisionVSDifficulty of detecting and measuring

Solution Approach 1:

The patent inverts the measurement approach by not trying to see the eyes directly, but rather by observing the movements of the head that contains the eyes. This indirect measurement through head kinematics bypasses the visibility problem entirely.

Inventive Principle:

Principle #13The other way round (Inversion)

Solution Approach 2:

Head movements serve as an intermediary measurement that correlates with eye state without requiring direct visualization of the eyes. The system measures head position, velocity, and acceleration as proxy indicators of driver alertness.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS11893807B2Method for determining a level of alertness of a driver

Publication Date: 2024.02.06 CONTINENTAL AUTOMOTIVE TECHNOLOGIES GMBH

AI summary

A method for determining a state of vigilance of a driver in a vehicle using a predetermined image-analyzing algorithm. The method especially includes a step of executing the predetermined algorithm on the generated sequence of images in order to detect a series comprising at least one movement of the head of the driver, a step of determining the speed and/or the amplitude of each identified movement and of the dynamic and static periods of the head of the driver, a step of detecting dynamic and static periods of the head of the driver and of measuring the frequency and duration of each period, and a step of determining a state of vigilance of the driver from the speed and/or the amplitude determined for each identified movement and from the frequency and duration of each detected period.