Driver Dozing Detection with Eye Opening and Face Movement

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing driver monitoring systems struggle to accurately differentiate between a driver dozing off and smiling, leading to erroneous detections.

Innovation Solution

A determining device that analyzes the degree of eye opening and the directional movement of a driver's face, using a processor to determine if the face moves in a specific pattern (right and then left, or vice versa) to distinguish between dozing off and smiling.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If the monitoring device determines dozing off based on degree of eye opening and face angle movement, then dozing detection capability is improved, but false detection of smiling faces increases

Engineering Contradiction:

Improvedozing detection accuracyVSAvoidsmiling detection accuracy

Core Design Contradiction:

ReliabilityVSMeasurement precision

Solution Approach 1:

The patent segments the face angle movement detection into multiple independent components: horizontal direction movement (right-left), vertical direction movement (up-down), and temporal duration analysis. By dividing the detection into these separate dimensions, the system can evaluate each aspect independently and combine them to distinguish between dozing and smiling with higher accuracy.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent extends the detection from a single face angle parameter to multiple dimensional parameters including horizontal angle, vertical angle, movement speed, and duration. This multi-dimensional approach allows the system to differentiate between dozing (characterized by specific patterns in multiple dimensions) and smiling (which produces different patterns across the same dimensions).

Inventive Principle:

Principle #17Another dimension (Dimensionality change)

2Device complexity

If the monitoring device uses only degree of eye opening to detect dozing, then detection simplicity is maintained, but detection accuracy decreases when driver is smiling

Engineering Contradiction:

Improvedetection method simplicityVSAvoiddozing detection accuracy

Core Design Contradiction:

Device complexityVSReliability

Solution Approach 1:

The patent merges multiple detection parameters (degree of eye opening, horizontal face angle movement, vertical face angle movement, movement speed, and duration) into a unified dozing detection system. By combining these parameters with logical conditions, the system achieves high detection accuracy while maintaining relatively simple implementation through rule-based evaluation.

Inventive Principle:

Principle #5Merging (Combining)

Data Source

PatentUS20250336217A1Determining device, storage medium storing computer program for determination, and determining method

Publication Date: 2025.10.30 TOYOTA JIDOSHA KK

AI summary

A determining device has a processor configured to determine that a driver has not dozed off when it has been determined that a degree of eye opening of the driver is at or below a reference degree of eye opening and a direction of a driver's face indicates movement in a right direction exceeding a first reference and, in continuation with the movement, the direction of the driver's face indicates movement in a left direction exceeding a second reference, and determine that the driver has dozed off when the degree of eye opening is at or below the reference degree of eye opening and it has not been determined that the direction of the driver's face indicates movement in the right direction exceeding the first reference and, in continuation with the movement, the direction of the driver's face indicates movement in the left direction exceeding the second reference.