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

Driver distracted driving monitoring method using key point attention

A key point, attention technology, applied in the field of image processing and pattern recognition, to achieve the effect of improving the accuracy

Pending Publication Date: 2022-03-25
SOUTHEAST UNIV
View PDF0 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This makes distracted driver detection an important part of the car and could lead to the development of new ADAS systems

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 distracted driving monitoring method using key point attention
  • Driver distracted driving monitoring method using key point attention
  • Driver distracted driving monitoring method using key point attention

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0023] The present invention will be further explained below in conjunction with the accompanying drawings and specific embodiments. It should be understood that the following specific embodiments are only used to illustrate the present invention and are not intended to limit the scope of the present invention.

[0024] A kind of driver's distracted driving monitoring method utilizing key point attention of the present invention, concrete implementation steps are as follows:

[0025] Step 1: Select the existing StateFarm dataset for the distracted driving image dataset;

[0026] Step 2: Build an attention network based on keypoint projections, image 3 It is a schematic diagram of the structure of the model; ResNet-50 combined with the channel-space conversion block is used as the backbone to extract global features and input them into all subsequent branches; at the same time, Lightweight OpenPose is used to generate key point heat maps containing rich spatial information ;F...

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 distracted driving monitoring method using key point attention. According to the method, discriminative key point features of a driver are utilized to distinguish distracted driving behaviors with similar appearances. According to the method, the feature transformation process is improved through channel-space transformation convolution, so that the representation capability of convolution features is enhanced. Meanwhile, a light OpenPose is used to generate a key point heat map as an attention map of global features, and a key point projection strategy is proposed to fuse key point information and convolution features, that is, point multiplication is carried out on the heat map of each key point and the global feature map to generate local refined features. The projection of the key point information to the global features improves the discrimination degree of final classification representation, and the distraction driving monitoring accuracy of the driver can be further improved. The method has important application value in the field of traffic safety.

Description

technical field [0001] The invention belongs to the field of image processing and pattern recognition, and in particular relates to a driver distraction driving monitoring method utilizing key point attention. Background technique [0002] Today, more and more modern vehicles are equipped with advanced driver assistance systems (ADAS). These systems are developed to prevent accidents by warning the driver of possible problems and in the event of an accident, enabling the driver and passengers to use safe techniques. But even today's latest self-driving cars aren't fully autonomous, requiring drivers to be cautious and ready to take control of the wheel in an emergency. There are five levels of autonomy, and most self-driving cars fall into the Level 2 or Level 3 category, meaning the driver must be ready to intervene when requested and cannot be distracted. An example of a system under development that falls into the Level 4 category is the Waymo self-driving cab service. ...

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): G06V20/59G06V40/20G06V10/77G06V10/80G06V10/764G06V10/774G06V10/82G06N3/04G06N3/08G06K9/62
CPCG06N3/08G06N3/045G06F18/213G06F18/24G06F18/253G06F18/214
Inventor 路小波陆明琦胡耀聪
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