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

Online Perception Method of Driver's Passive Driving State Based on Hierarchical Network Model

A driving state and layered network technology, applied in character and pattern recognition, instruments, calculations, etc., can solve the problems of driver time lag, less research on negative driving state perception, and inability to warn drivers

Active Publication Date: 2020-03-17
HEFEI UNIV OF TECH
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Among them, the research on the mechanism of negative driving state, the behavior performance and adverse effects of negative driving state is relatively mature, but there are few studies on the perception of negative driving state, and the subjective investigation method is mainly used, that is, through interviews, questionnaires and observations. Discriminate the driver's passive driving state in the form of other methods
Although the subjective investigation method is direct and simple, it is easily affected by the driver's subjective factors and has a time lag, and cannot provide timely and effective assistance to the driver and early warning of negative states such as driving safety.

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
  • Online Perception Method of Driver's Passive Driving State Based on Hierarchical Network Model
  • Online Perception Method of Driver's Passive Driving State Based on Hierarchical Network Model
  • Online Perception Method of Driver's Passive Driving State Based on Hierarchical Network Model

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0051] In this embodiment, a method for online perception of driver's passive driving state based on a layered network model: classify the driver's passive driving state, select characteristic parameters that can characterize the driver's passive driving state, and construct a layered network model to perform Training until it meets the system error requirements; by obtaining the driving information, operation information and facial information in the current driving process in real time, extracting the driving characteristic information in the driving information, the operation characteristic information in the operation information and the facial characteristic information in the facial information; Then the extracted feature information is input into the hierarchical network model for calculation, and the current driver's passive driving degree is obtained. Specifically, proceed as follows:

[0052] Step 1, grading the driver's passive driving state;

[0053] According to ...

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 hierarchical network model-based driver passive driving state online sensing method, which comprises the following steps of: grading driver passive driving states, selectingcharacteristic parameters capable of representing the driver passive driving states, and constructing a hierarchical network model for training until the hierarchical network model meets system errorrequirements; acquiring driving information, operation information and face information in the current driving process in real time, and extracting driving characteristic information in the driving information, operation characteristic information in the operation information and face characteristic information in the face information; and inputting the extracted feature information into a hierarchical network model for calculation to obtain the negative driving degree of the current driver. According to the method, the negative driving state of the driver can be identified on line through theextracted features, the negative driving state detection precision can be effectively improved, a foundation is laid for improving the driving safety, and the method has good real-time performance and mobility and has wide application prospects.

Description

technical field [0001] The invention belongs to the field of artificial intelligence, and mainly relates to an online perception method of a driver's passive driving state based on a layered network model. Background technique [0002] With the rapid increase of China's car ownership in recent years, the issue of road traffic safety has become a social focus. According to incomplete statistics, nearly 100,000 people lose their lives due to vehicle traffic accidents in my country every year. Traffic accidents have become the most casualties in various accidents in the country, and traffic safety accidents caused by passive driving state account for a large proportion. Part of it seriously threatens the life and property safety of the broad social groups. Therefore, monitoring and adjusting the driver's negative driving state that affects driving behavior can better reduce dangerous driving behavior and ensure traffic safety. [0003] At present, the domestic and foreign rese...

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 Patents(China)
IPC IPC(8): G06K9/00G06K9/34G06K9/40
Inventor 王跃飞王文康李洋黄飞潘斌刘白隽
Owner HEFEI UNIV OF TECH
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