Unlock instant, AI-driven research and patent intelligence for your innovation.

Human eye image processing-based method for judging fatigue of driver

A driver fatigue and image processing technology, applied in character and pattern recognition, instruments, computer components, etc., can solve the problems of unapplicable, complicated process, and high equipment cost, and achieve low cost, high operating efficiency, and simple positioning algorithm Effect

Inactive Publication Date: 2018-01-09
南京栎树交通互联科技有限公司
View PDF4 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method requires two kinds of infrared light sources, the equipment cost is high, and the process is complicated
Yu Pengpeng of Liaocheng University used a classifier algorithm based on Haar-Like features to detect eye closure in a single frame image, which improved the detection speed, but it could not be applied in practice.

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
  • Human eye image processing-based method for judging fatigue of driver
  • Human eye image processing-based method for judging fatigue of driver
  • Human eye image processing-based method for judging fatigue of driver

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0076] Select a video of simulated driving in the cockpit of a vehicle. The frame rate of the video is 25Hz, and the time per frame is 40ms.

[0077] Step 1, select st_train and end_train as 1 and 50 respectively, and select the first 2 seconds for free training. The first frame image as image 3 As shown, the initial face template and human eye template are as follows Figure 4 , 5 shown. Counter=0.

[0078] Step 2, in the free training phase, the gray quantization processing results of the first frame video image are as follows: Figure 6 As shown, the calculated Ao, Ab and At matrices are as follows Figure 7-9 As shown, the value of the white area is 1, and the value of the black area is 0. The white areas in the three matrices respectively represent the face area, background area, and total area of ​​the face and background of the first frame of video.

[0079] For the first frame of video image, the calculated unnormalized likelihood ratio L and normalized likeliho...

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 human eye image processing-based method for judging the fatigue of a driver. Firstly, according to the face condition of a driver, an n initial face template and an initial human eye template are set. Secondly, a previous section of video is processed, and then the free training is carried out. Thirdly, a human eye area in a subsequent frame of a video image is detected,and whether human eyes are closed or not is judged. fourthly, according to the number of consecutive eye closing frames and he current frame number, a perclos value is calculated. Finally, if the perclos value is larger than 0, 15, an alarm is given out by the system and the fatigue of the driver is considered. Otherwise, a subsequent frame is continuously detected.

Description

technical field [0001] The invention belongs to the field of digital image processing, and relates to a method for detecting driver's blink frequency through image processing and judging whether the driver is tired. Background technique [0002] Traffic accidents are the largest public hazard that endangers human life and safety in the world today. At least 500,000 people die in traffic accidents every year. Among them, driver fatigue driving is one of the important causes of traffic fatal accidents. At present, with the rapid development of highways in my country and the general increase of vehicle speeds, driver fatigue detection has become an important part of safe driving. [0003] In the early days, driving fatigue assessment was mainly carried out from a medical point of view with the help of medical devices. This detection method has poor real-time performance and is inconvenient to operate. In 1998, Zhou Peng analyzed the causes of driver fatigue accidents, and pro...

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): G06K9/00
Inventor 华国栋许长勇严加权田学牧
Owner 南京栎树交通互联科技有限公司