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

Abnormal driving detection method and device

A technology for abnormal driving and detection methods, applied in the fields of instruments, character and pattern recognition, computer parts, etc., can solve the problems of little driver abnormality detection, single driving abnormality detection, etc., to achieve accurate acquisition and improve robustness. the effect of improving the safety factor

Inactive Publication Date: 2020-02-07
NAT UNIV OF DEFENSE TECH
View PDF9 Cites 16 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0002] The detection of driving abnormalities in the existing technology is relatively simple, mainly focusing on the detection of abnormal vehicle driving trajectories. There is little mention of abnormal detection of drivers, and there is still room for improvement in the detection algorithm. As an important participant in road traffic, The state of the driver is critical to traffic 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
  • Abnormal driving detection method and device
  • Abnormal driving detection method and device
  • Abnormal driving detection method and device

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0040] as attached Figure 4 As shown, the embodiment of the present invention provides a method for detecting abnormal driving, which specifically includes the following steps:

[0041] Step 1, detect the face image data collected within a predetermined period of time, and extract multiple human eye features; specifically include:

[0042] Using Dlib based on HOG (Histogram of Oriented Gradient, HOG for short) feature and SVM (Support Vector Machine, Support Vector Machine, SVM for short) algorithm to detect face images, obtain several face features; Extract six feature points corresponding to the left eye and right eye from the face features, the six feature points include inner eye corner feature points, outer eye corner feature points, feature points at both ends of the upper eyelid line and feature points at both ends of the lower eyelid line .

[0043] For details, see S100: Human eye detection: This system uses the face detector in the Dlib library. Dlib is a C++ mach...

Embodiment 2

[0134] Based on the first embodiment of the above detection method, the embodiment of the present invention also provides a detection device for abnormal driving, including:

[0135] A camera for collecting face images;

[0136] Sensors, used to collect vehicle driving data; including GPS vehicle speed, acceleration, longitude, latitude;

[0137] The internal detection module is connected with the camera and the alarm, and is used to detect the face image data collected within a predetermined period of time, and extract multiple human eye features; obtain the number of blinks according to the relationship between multiple human eye features and eye opening and closing degrees; The reference value of fatigue is obtained according to the number of blinks and the relationship between eye opening and closing with time during a single blink; the reference value of fatigue is input into the detection model to predict the degree of fatigue to obtain the predicted value of fatigue; when...

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 an abnormal driving detection method and device, and the method comprises the steps: detecting face image data collected in a preset time period, and extracting a plurality ofhuman eye features representing the lengths and widths of eyelids; obtaining the blinking times according to the relationship between the plurality of human eye features and the eye opening degree; obtaining a fatigue reference value according to the blinking times and the change relation of the eye opening degree along with time in the single blinking process; inputting the fatigue reference value into a detection model to predict the fatigue degree so as to obtain a fatigue prediction value; and when the fatigue prediction value is in different fatigue levels, sending an early warning signalcorresponding to the fatigue level. Aiming at the problems of low accuracy, low safety and the like of the existing fatigue driving detection technology, the detection accuracy and the safety coefficient are improved.

Description

technical field [0001] The invention relates to the technical field of intelligent driving, in particular to a method and device for detecting abnormal driving. Background technique [0002] The detection of driving abnormalities in the existing technology is relatively simple, mainly focusing on the detection of abnormal vehicle driving trajectories. There is little mention of abnormal detection of drivers, and there is still room for improvement in the detection algorithm. As an important participant in road traffic, The state of the driver is crucial to traffic safety. Contents of the invention [0003] The present invention provides a detection method and device for abnormal driving, which is used to overcome the defects of robustness and low driving safety factor in the prior art, and improve the robustness of the detection algorithm and the driving safety factor by detecting the abnormal state of the driver . [0004] In order to achieve the above object, the prese...

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): G06K9/00
CPCG06V40/171G06V40/161G06V20/597
Inventor 周鋆杨昊余正飞丁兆云朱先强
Owner NAT UNIV OF DEFENSE 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

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