Early warning system based on driver face features and lane departure detection

A technology for lane departure and facial features, applied to driver input parameters, vehicle components, transportation and packaging, etc., can solve problems such as increased fatigue driving, large differences in facial images, and poor results, achieving obvious effects and timely alarms Effect

Inactive Publication Date: 2015-12-16
JIAXING ITRUN INFORMATION TECH CO LTD
View PDF5 Cites 34 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

For example, the judgment of fatigue driving is carried out by detecting the posture of the driver's head through hardware equipment. The detection device needs to be in contact with the driver's head, which affects the driver's attention, accelerates the speed of driver fatigue, and increases the occurrence of fatigue driving. chance, reducing the safety of driving
In terms of software, some software judges whether the driver is in a state of fatigue by monitoring whether the facial expression characteristics of the driver change over a period of time, but because the facial expressions are changeable and the facial images vary too much from person to person, the effect is not good. good

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
  • Early warning system based on driver face features and lane departure detection
  • Early warning system based on driver face features and lane departure detection
  • Early warning system based on driver face features and lane departure detection

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0026] PERCLOS is defined as the proportion of time that the eyes are closed per unit time. Practice has proved that the longer the driver's eyes are closed, the more serious the fatigue degree, and the degree of fatigue driving can be determined by measuring the length of the eyes closed.

[0027] The frequency of taking facial images is 40ms, and taking 3 minutes as a time unit, the percentage of the number of "closed eyes" detected within 3 minutes to the total number of detections is counted as the PERCLOS value. The system counts the PERCLOS value of the previous 3 minutes in real time.

[0028] During the driving process, the camera collects the driver's face image and stores it in the image storage module, and the image analysis system analyzes the images in the image storage module (the specific analysis process is as follows: figure 1 As shown), the driver’s head turning state is judged by the facial features of the driver’s face image, and the eye opening and closin...

Embodiment 2

[0032] On the basis of Embodiment 1, the system adds a corresponding information module for obtaining the driving duration and current vehicle speed, and calculates the sensitivity of the current driver according to the data obtained in the information module (such as figure 2 shown), different sensitivities have different sensitivity coefficients, and the sensitivity coefficients are set as follows:

[0033] Medium sensitivity (sensitivity b) sensitivity coefficient Kb is 1, low sensitivity (sensitivity a) Ka=1.18, high sensitivity (sensitivity c) Kc=0.95.

[0034] The sensitivity coefficient is multiplied by the statistical result described in Embodiment 1 and compared with the fatigue threshold to judge the current fatigue state of the driver and issue a corresponding alarm sound.

[0035] Among them, if the driver closes his eyes for as long as 0.5s, the alarm system will immediately send out an alarm sound.

[0036] In addition, when the vehicle speed is higher than 20k...

Embodiment 3

[0038] On the basis of embodiment two, increase the camera two that is used for capturing road image in this system, road image is stored in image storage module, image analysis system analyzes road image and determines lane line, and specific analysis process is as follows image 3 Shown: Determine the trapezoidal region of interest of the road image, based on the assumption of structured roads, segment the road image into near-field and far-field, use low-pass filtering and other image preprocessing methods to denoise, and segment based on gray threshold Carry out edge detection to determine the lane edge feature candidate points, so as to determine the left lane line l1 and the right lane line l2.

[0039] Such as Figure 4 As shown, the image analysis system calculates the angle α between the inner angle bisector of the left lane line and the right lane line and the vertical line of the road image according to the determined left lane line and right lane line, and compares...

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 early warning system based on driver face features and lane departure detection. The early warning system comprises a first camera, a second camera, an image storage module, an image analysis system and an alarm system. The first camera is used for collecting the open and closed states of the eyes of a driver and the head turning state of the driver. The second camera is used for collecting road images. The image storage module is used for storing information collected by the first camera and the second camera. The image analysis system is used for analyzing the information stored in the image storage module. The alarm system makes corresponding alarm prompt sounds according to the judgment result of the image analysis system. According to the early warning system, the fatigue state of the driver can be judged in good time through the face image of the driver and the road images, the corresponding alarm prompt sounds are produced according to the fatigue state, alarming is in time, and the effect is remarkable.

Description

technical field [0001] The invention relates to fatigue driving alarm technology, in particular to an early warning system based on driver's facial features and lane departure detection. Background technique [0002] With the increasing development of traffic and the increasing consumption of automobiles, the problem of driver fatigue driving, especially professional drivers, has begun to attract attention, because fatigue driving is one of the main causes of vicious traffic accidents. According to a survey, 19% of the annual traffic accidents in the world are related to fatigue driving. Especially in the long-distance and high-speed driving process, direct collision accidents caused by fatigue driving account for 25% of the total number of accidents, and the number of deaths caused by it accounts for 41% of catastrophic accidents. [0003] As an important hidden danger of traffic accidents, driver fatigue driving has attracted widespread attention. Many detection devices ...

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): B60W50/14B60W40/08B60W40/105B60W40/06
CPCB60W40/06B60W40/08B60W40/105B60W50/14B60W2040/0827B60W2050/143B60W2520/10B60W2540/00B60W2552/00
Inventor 李德衡王际兰毕国奇迟立明张志鹏
Owner JIAXING ITRUN INFORMATION TECH CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap