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

Vision-based driving behavior detecting method

A detection method and behavior technology, applied in the field of vision-based driving behavior detection, can solve the problems of poor consistency of driver warning and single fatigue behavior, and achieve good effectiveness, low false alarm rate of warning and wide application range of warning Effect

Active Publication Date: 2018-12-07
ZHEJIANG LEAPMOTOR TECH CO LTD
View PDF9 Cites 43 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

The fatigue behavior that this type of system can warn of is relatively simple, and the consistency of warnings for different drivers is relatively poor

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
  • Vision-based driving behavior detecting method
  • Vision-based driving behavior detecting method
  • Vision-based driving behavior detecting method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0036] The technical solutions of the present invention will be further specifically described below through specific embodiments and in conjunction with the accompanying drawings.

[0037] A vision-based driving behavior detection method, the processing flow is as follows figure 1 As shown, the cab image is collected, face information is extracted, face detection and identity verification are performed using a deep convolutional neural network, and the position of key points of the face and the feature map of the face are output; the position of the key points of the face and the face Feature map, for fatigue driving application detection and distracted driving application detection; based on the fatigue driving and distracted driving application detection results, judge the driver's fatigue state and distracted state, issue fatigue warning and distraction early warning signals, and warn driving fatigue behavior and Driving distraction behavior, judge and display driving fati...

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 provides a vision-based driving behavior detecting method. The method comprises: collecting a cab image, extracting face information, carrying out face detection and identity verification by using a deep convolutional neural network, and outputting a face key point position and a face feature map; on the basis of the outputted face key point position and face feature map, carrying out fatigue driving application detection and distracting driving application detection; and determining a fatigue state and distraction state of a driver based on fatigue driving and distracting driving application detection results, sending out fatigue early-warning and distracting early-warning signals, warning a driving fatigue behavior and driving distraction behavior early, and determining anddisplaying a driving fatigue level and a driving concentration level. According to the invention, the driver behavior monitoring system is perfected; the fatigue driving behaviors like drowsiness, yawning, and head lowering and distracting driving behaviors like call receiving and calling and smoking during the driving process are analyzed intelligently; and behavior prompting is carried out.

Description

technical field [0001] The invention relates to the technical field of safe driving, in particular to a vision-based driving behavior detection method. Background technique [0002] There are 500,000 traffic accidents in China every year, and the death toll due to traffic accidents exceeds 100,000. According to the statistics of road traffic accidents, more than half of the traffic accidents are caused by the driver's danger or wrong vehicle operation. However, most of these man-made accidents are caused by fatigue driving, so the intelligent analysis and early warning system of driving behavior has important application value. The active safety systems of existing passenger cars and commercial vehicles rarely have functions involving driver behavior analysis and reminders, especially for commercial transport vehicles, where long-term and long-distance driving leads to a higher probability of the above-mentioned fatigue driving. Most existing commercial vehicles do not hav...

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): G06K9/00B60W40/08
CPCB60W40/08B60W2040/0827G06V40/172G06V40/197G06V20/597
Inventor 缪其恒陈淑君苏志杰郑皓洲王江明许炜
Owner ZHEJIANG LEAPMOTOR TECH CO LTD
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