Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Driver fatigue state rapid detection method based on deep learning

A driver fatigue and deep learning technology, which is applied in the field of rapid detection of driver fatigue status based on deep learning, can solve the problems of affecting the fatigue detection effect and high cost of promotion and application, so as to avoid no longer learning, alleviate degradation problems, and improve The effect of compression ratio

Inactive Publication Date: 2020-01-10
SOUTHEAST UNIV
View PDF4 Cites 15 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Facial key point detection technology is of great significance for fatigue driving detection. Wrong key point positioning results will seriously affect the effect of fatigue detection.
The fatigue recognition method based on physiological signals cannot be popularized and applied because of its high cost and the need for direct contact with the driver's limbs, while the fatigue recognition method based on video images is non-contact, low cost, and easy to implement. It has become a hot research direction in the field of fatigue recognition

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 state rapid detection method based on deep learning
  • Driver fatigue state rapid detection method based on deep learning
  • Driver fatigue state rapid detection method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0043] The detailed process of the present invention will be clearly and completely described below in conjunction with the accompanying drawings and embodiments.

[0044] Face fatigue state detection algorithm of the present invention, its flow process is as follows Figure 1 to Figure 4 As shown, the specific steps are as follows:

[0045] Step 1: Collect a color image of the driving state, use a three-level cascaded deep neural network to detect the face part in the image, and use the regression frame to mark the face part. The specific process is as follows:

[0046] Step 1.1: Input the entire image into the first-level face candidate frame generation network, process each 12×12 window in the image, and obtain a two-dimensional face classification vector and a four-dimensional face classification vector through network output layer mapping The bounding box regression offset of , the offset is used for the correction of the face regression box.

[0047] Step 1.2: Scale 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 driver fatigue state rapid detection method based on deep learning, and the method comprises the following steps: (1), collecting a color image of a driver during driving, detecting a face part of the driver in the image through a deep learning method, and marking the face part through a regression frame; (2) taking the face boundary regression frame as input, inputting the face boundary regression frame into a multi-task learning network, and finally detecting to obtain a face key point of a face and an attitude angle of a head; and (3) establishing a space-time fatigue feature sequence by using the face key points and the head attitude angle, inputting the feature sequence into a fatigue recognition deep learning network as input, and finally outputting a fatigue state recognition result. Real-time performance and accuracy requirements of driver fatigue state detection are fully considered, a corresponding optimization method is designed by optimizing compression and fatigue characteristics of a deep learning network model on the premise of ensuring accuracy, the volume of the network is compressed to the maximum extent, and the operation speed of the algorithm is increased.

Description

technical field [0001] The invention belongs to the field of pattern recognition, and relates to a method for quickly detecting driver fatigue state based on deep learning. Background technique [0002] Studies have shown that fatigue driving is one of the main causes of road traffic accidents, and research on fatigue detection algorithms is of great significance for improving road traffic safety. In recent years, due to the continuous attention to road safety issues, driver fatigue detection technology has become a hot research topic in related fields, and different companies and research institutes have also developed many different detection schemes. Due to the poor real-time performance, the traditional fatigue detection method needs to be in contact with the driver's body, and the shortcomings of low robustness often cannot be popularized and applied. In recent years, with the emergence of high-performance GPUs and the development of artificial intelligence chips, deep...

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
IPC IPC(8): G06K9/00G06N3/04
CPCG06V40/161G06V40/168G06V40/172G06V20/597G06N3/045
Inventor 路小波张晨
Owner SOUTHEAST UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com