Fatigue detection method based on face detection and eye state identification

A state recognition and fatigue detection technology, applied in character and pattern recognition, instruments, computer components, etc., can solve problems affecting the accuracy of fatigue detection methods, generalization ability of engineering applications, inaccurate positioning of face and eye areas, facial video Image complexity and other problems, to avoid traffic accidents, good recognition effect, reduce the effect of calculation area

Inactive Publication Date: 2016-12-21
北汽瑞翔汽车有限公司
View PDF3 Cites 23 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] However, under real vehicle conditions, due to frequent illumination changes, facial video images become extremely complex, and the face and eye regions are not accurately positioned during the facial video image processing process, which will inevitably affect the accuracy of the fatigue detection method And the generalization ability of engineering applications

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Fatigue detection method based on face detection and eye state identification
  • Fatigue detection method based on face detection and eye state identification
  • Fatigue detection method based on face detection and eye state identification

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0039] The specific implementation manner and working principle of the present invention will be further described in detail below in conjunction with the accompanying drawings.

[0040] Such as figure 1 As shown, a fatigue detection method based on face detection and human eye state recognition, the steps are as follows:

[0041] First step 1: Sampling the driver’s monitoring video at a sampling rate of k frames / second to obtain the unit time T 0 The face sample set in ;

[0042]Step 2: Use the adaptive enhancement algorithm to train the final classifier G(x) from the collected sample set;

[0043] Face detection is an important step before human eye positioning. AdaBoost is the abbreviation of English "AdaptiveBoosting" (adaptive enhancement), the present invention adopts Adaboost algorithm, utilizes the sample training and detection method provided by OpenCV. First collect samples, and use the haartraining application to train a classifier from the collected samples. Th...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

PUM

No PUM Login to view more

Abstract

The invention discloses a fatigue detection method based on face detection and eye state identification, comprising the following steps: first, sampling a monitoring video of a driver to get a face sample set; then, loading a to-be-detected image frame in the face sample set to a final classifier trained using an adaptive boosting algorithm, scanning image pixels to get a face image set, binarizing precise face areas under different light conditions based on different thresholds through use of an Otsu method, getting the optimal threshold, and precisely positioning the eye area through use of a vertical gray-level projection method to get the best eye shapes in the open state and in the closed state respectively; and finally, judging the fatigue state of the detected person through use of a PERCLOS method. The beneficial effects are as follows: the running speed is high, and the identification effect is good; and effective warning can be issued according to the state of a driver, and thus, effective help is provided for the avoidance of fatigue driving and traffic accidents caused thereby.

Description

technical field [0001] The invention relates to an image processing method for driver fatigue state detection, in particular, a fatigue detection method based on human face detection and human eye state recognition. Background technique [0002] At present, fatigue driving is one of the important hidden dangers of today's traffic safety. When the driver is tired, his ability to perceive the surrounding environment, the ability to judge the situation and the ability to control the vehicle all decline to varying degrees, so traffic accidents are prone to occur. Statistics show that from 2010 to 2011, the number of deaths directly caused by fatigue driving in my country accounted for 11.35% and 12.5% ​​of the total traffic accident deaths of motor vehicle drivers, and about 9,000 people died of fatigue driving every year. Therefore, the research and development of high-performance real-time monitoring and early warning technology for driver fatigue state is of great significan...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to view more

Application Information

Patent Timeline
no application Login to view more
Patent Type & Authority Applications(China)
IPC IPC(8): G06K9/00
CPCG06V40/197G06V20/597
Inventor 姚雷陈美美王国栋梁承东
Owner 北汽瑞翔汽车有限公司
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap