Machine vision-based eye closure degree calculating method

A computing method and machine vision technology, applied in computing, computer components, instruments, etc., can solve problems such as the inability to accurately estimate the state of the human eye, and achieve the effect of no harm accuracy and low cost

Inactive Publication Date: 2018-09-14
ZHEJIANG UNIV OF TECH
View PDF2 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

When judging the state of the human eye, commonly used methods such as template matching, quadr

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
  • Machine vision-based eye closure degree calculating method
  • Machine vision-based eye closure degree calculating method
  • Machine vision-based eye closure degree calculating method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0035] The present invention will be described in further detail below in conjunction with the accompanying drawings.

[0036] refer to figure 1 , a kind of eye closure calculation method based on machine vision, described method comprises the following steps:

[0037] 1) if figure 1 As shown, take a video and process each frame in the video. The image processing process includes image enhancement technology, threshold segmentation, erosion and expansion technology, and the steps are as follows:

[0038] Step 1.1: Read each frame of picture in the measured video, detect the face from the collected image according to the face classifier in the Viola-Jones algorithm, and mark the face area from the picture;

[0039] Step 1.2: use the eye classifier in machine vision to mark out the eye area (ROI) from the face area, and record its area as A;

[0040] Step 1.3: On the basis of marking the ROI in step 1.2, if the ROI is a color image, grayscale processing is performed on the RO...

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

A machine vision-based eye closure degree calculating method is disclosed and comprises the following steps: 1) a video is collected, and each frame in the video is processed; image processing processes comprise a step of utilizing image enhancement technology as well as threshold value segmentation and corrosion and expansion technology and a step of determining an eye closure degree; 2) according to the closure degree obtained in step 1), an eye state can be determined based on a determining threshold value; 3) statistics are run on the quantity of closed eye frames, the quantity of total frames and the quantity of frames where no eye is detected in the video; the frame quantities are used for obtaining a proportion of eye closing time in the video to be detected; 4) a PERCLOS criterionis used for determining a driver state. The method can be used for effectively calculating the eye closure degree and determining eye closure conditions based on the determining threshold value, and therefore the driver state can be effectively and accurately assessed.

Description

technical field [0001] The invention relates to the technical field of fatigue driving detection, in particular to a computer vision-based eye closure calculation method. This method can effectively solve the misjudgment caused by the different sizes of faces in the picture, and can well adapt to the sampling deviation caused by the distance between the face and the camera in real life. Background technique [0002] Although traffic safety has improved greatly in the past decade, there are still some serious accidents happening all over the world. The vast majority of these accidents are due to human error, especially drowsy or distracted driving. According to a survey on safe driving, 25% to 30% of driving accidents are related to fatigue driving. In the United States, about 13% of major accidents are caused by drivers' fatigue driving each year. At the same time, as many as 20% of road traffic accidents in the United Kingdom are caused by the above reasons. Traffic acci...

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): G06K9/00G06K9/32
CPCG06V40/171G06V40/172G06V10/25
Inventor 钱丽萍吴春旭冯安琪黄玉蘋吴远
Owner ZHEJIANG UNIV OF TECH
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