Driver fatigue driving real-time detection method and system based on deep learning

A driver fatigue, real-time detection technology, applied in the field of computer vision and deep learning, can solve the problems of inability to meet the real-time requirements of fatigue driving detection, few data sets for fatigue driving detection, and many deep neural network parameters, etc., to improve reliability. performance and practicability, avoiding repeated extraction, and reducing the amount of computation

Active Publication Date: 2021-09-07
UNIV OF SCI & TECH OF CHINA
View PDF10 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in practical applications, high-precision deep neural networks have many parameters and slow calculations, which cannot meet the real-time requirements of fatigue driving detection. On the other hand, deep neural networks are highly dependent on training data sets, and there are still few data sets for fatigue driving detection.

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
  • Driver fatigue driving real-time detection method and system based on deep learning
  • Driver fatigue driving real-time detection method and system based on deep learning
  • Driver fatigue driving real-time detection method and system based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] Such as figure 1 As shown, a kind of driver's fatigue driving real-time detection method based on deep learning that the embodiment of the present invention provides, comprises the following steps:

[0027] Step S1: Collect the real-time image of the driver's cab, use the three-level cascaded neural network to detect the position of the face, and use the face position of the previous frame in the subsequent frame to use the third level of the three-level cascaded neural network. Face tracking to obtain face images;

[0028] Step S2: Normalize the size, mean and variance of the face image to obtain the face input feature map, input the face key point detection deep neural network, and obtain the face key points;

[0029] Step S3: Select part of the key points of the face and match them with the key points of the 3D standard face to obtain the 3D posture of the head, and identify the behavior of nodding and not looking straight ahead according to the multi-frame results;...

Embodiment 2

[0072] Such as Figure 6 As shown, the embodiment of the present invention provides a real-time detection system for driver fatigue driving based on deep learning, including the following modules:

[0073] Obtaining face image module 61, used to collect real-time images of the driver's cab, using a three-level cascaded neural network to detect the position of the face, and in subsequent frames, using the face position of the previous frame, using a three-level cascaded neural network The third stage in the process carries out face tracking to obtain a face image;

[0074] Obtaining the human face key point module 62 is used to normalize the size, mean and variance of the human face image to obtain the input feature map of the human face, input the human face key point detection depth neural network, and obtain the human face key point;

[0075] Identifying nodding and not looking straight ahead module 63, used to select some key points of the face and match them with 3D stand...

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 relates to a driver fatigue driving real-time detection method and system based on deep learning, and the method comprises the steps: S1, collecting a real-time image of a cab, and obtaining a face image through a neural network; sS, normalizing the face image to obtain a face input feature map, and inputting the face input feature map into a face key point detection deep neural network to obtain face key points; S3, selecting a part of face key points to be matched with 3D standard face key points, and identifying nodding and non-front-looking behaviors; S4, extracting an eye region according to the face key points, detecting the opening and closing state of eyes, and calculating the eye fatigue state; S5, calculating the mouth opening and closing degree according to the mouth key points, and recognizing yawning behaviors; and S6, calculating the fatigue value of the driver according to the steps S3, S4 and S5. Rich face feature information can be recognized, different behavior features of the head, the eyes and the mouth are detected respectively, multiple fatigue behaviors are detected, and the reliability and practicability of the method are improved.

Description

technical field [0001] The invention relates to the field of computer vision and deep learning, in particular to a method and system for real-time detection of driver fatigue driving based on deep learning. Background technique [0002] With the wide popularization of automobiles, driving safety issues are getting more and more attention. Fatigue driving is one of the common causes of traffic accidents. However, drivers are often unable to assess their fatigue state during driving. Therefore, using external equipment to detect the driver's fatigue state in real time and reminding the abnormal state can effectively prevent The occurrence of traffic accidents reduces traffic safety hazards. [0003] According to the measurement method of data, fatigue driving detection methods can be divided into three categories: methods based on vehicle driving state, methods based on driver's physiological characteristics, and methods based on computer vision. [0004] The method based on...

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): G06K9/00G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045Y02T10/40
Inventor 凌强代淇源李峰许永华
Owner UNIV OF SCI & TECH OF CHINA
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