ALBP and SRC algorithm-based fatigue detection method and system

A fatigue detection and algorithm technology, applied in computing, computer parts, instruments, etc., can solve problems such as loss, PERCLOS value failure, error, etc., to achieve accurate judgment, reduce errors, and prevent loss.

Inactive Publication Date: 2014-11-26
WUYI UNIV
View PDF2 Cites 7 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In the past few decades, experts at home and abroad have been actively carrying out research on fatigue detection, while the research and development of fatigue driving monitoring systems in China is still in the initial stage.
From 2006 to 2011, due to the improvement of the safety performance of motor vehicles in our country and the introduction of various traffic regulations, the number of traffic accidents and deaths in our country has decreased to a certain extent during this period, but there are still many traffic accidents that have brought great harm to the people. A great deal of personal injury and property damage
However, due to the rich expression changes of the human face, different local features of the human face can be extracted from the facial images obtained from different angles. The above-mentioned patent only uses the feature value obtained in one way to judge it is easy to cause mistakes, making the calculation The PERCLOS value is invalid; and, the eyes, nose and mouth are some features of the face, and it is easy to make mistakes when extracting and analyzing these features
[0006] Based on the above, considering the rich changes in human facial expressions, the fatigue detection method that judges the driving state through a single or some local features cannot solve the existing problems

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
  • ALBP and SRC algorithm-based fatigue detection method and system
  • ALBP and SRC algorithm-based fatigue detection method and system
  • ALBP and SRC algorithm-based fatigue detection method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0059] refer to Figure 1 to Figure 5 A kind of fatigue detection method based on ALBP and SRC algorithm of the present invention as shown, comprises training sample image bank, and specific flow chart refers to figure 1 Shown:

[0060] Step A, image acquisition.

[0061] In this step, the RGB video stream of the driver's upper body is collected, and the taken RGB video stream is converted into a corresponding grayscale image.

[0062] Step B, using the WLD algorithm for face detection and tracking.

[0063] In this step, use the WLD algorithm to perform face detection and tracking on the grayscale image described in step A to obtain the corresponding face test image. If the face test image is not successfully obtained, return to step A and re-acquire the upper body of the driver. image.

[0064] Step C, calculating the residual using the SRC algorithm.

[0065] Calculate the minimum residual error between the face test image in step B and the training sample image librar...

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 ALBP and SRC algorithm-based fatigue detection method and system. A whole facial expression of a human face is processed to determine whether a driver is in a fatigue state, thereby preventing an error that is caused by only analyzing the single parts like eyes, nose or mouth of the face. According to the invention, a WLD algorithm is used for extracting a human face part, thereby reducing an error of human face extraction to the greatest extent; an ALBP algorithm is used for carrying out feature extraction, thereby completely preventing the loss of the slight facial feature quantity; and an SRC algorithm is used for calculating a residual error and determining a type, thereby precisely realizing determination of the state of the driver.

Description

technical field [0001] The invention relates to the technical field of digital image processing and pattern recognition, in particular to a fatigue detection method and system based on ALBP and SRC algorithms. Background technique [0002] At present, with the development of society and the continuous improvement of people's living standards, automobiles have entered thousands of households, and traffic accidents have also increased thereupon. In many traffic accidents, fatigue driving is an important reason, which has attracted people's attention. Over the past few decades, experts at home and abroad have been actively conducting research on fatigue detection, while the research and development of fatigue driving monitoring systems in China is still in its initial stage. From 2006 to 2011, due to the improvement of the safety performance of motor vehicles in our country and the introduction of various traffic regulations, the number of traffic accidents and deaths in our c...

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 & AuthorityApplications(China)
IPC IPC(8): G06K9/00G06K9/64
Inventor应自炉赵从挺李佳伟甘俊英陈自荣陈盛权
OwnerWUYI UNIV