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

On-duty personnel fatigue state detection method based on face multi-feature point recognition

A technology for on-duty staff and fatigue status, which is applied in the fields of attitude estimation and face detection, which can solve problems such as fluctuations in accuracy, inability to evaluate the fatigue status of on-duty staff, and affect the accuracy and stability of fatigue status detection, achieving the effect of improving accuracy

Active Publication Date: 2021-09-03
HUNAN UNIV OF SCI & TECH
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

However, in the complex environment of the duty room, only relying on a single facial feature point positioning detection cannot comprehensively evaluate the fatigue state of the duty personnel, and the accuracy rate will fluctuate greatly, seriously affecting the accuracy and stability of fatigue state detection

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
  • On-duty personnel fatigue state detection method based on face multi-feature point recognition
  • On-duty personnel fatigue state detection method based on face multi-feature point recognition
  • On-duty personnel fatigue state detection method based on face multi-feature point recognition

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0022] Such as figure 1 As shown, the method for detecting fatigue state of duty personnel based on facial multi-feature point recognition provided by the embodiment of the present invention includes the following steps.

[0023] Step A: Image processing. The image data of the on-duty personnel is collected every once in a while and processed in gray scale to eliminate the interference of irrelevant variables, and the image is divided into several 2*2 pixel areas. The manner of grayscale processing may be: gray=0.39*R+0.5*G+0.11*B, wherein: R, G, and B respectively represent pixel values ​​of red, green, and blue.

[0024] Calculate its horizontal gradient and vertical gradient values:

[0025]

[0026] Among them: G x (x, y) is the horizontal direction gradient of the pixel point (x, y), G y (x, y) is the (x, y) vertical direction gradient of the pixel, and the H(x, y) function is a two-dimensional column vector.

[0027] Then the gradient magnitude of the (x, y) pixe...

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

An on-duty personnel fatigue state detection method based on face multi-feature point recognition is characterized by comprising the steps: selecting a plurality of face key points of the operator on duty as face feature points, wherein the face feature points comprise eye region feature points, mouth region feature points and head region feature points; collecting image data of the facial feature points of the operator on duty at set intervals, and calculating and obtaining a blink detection parameter, a yawn detection parameter and a head posture parameter; and averaging the blink detection parameters, the yawn detection parameters and the head posture parameters in the plurality of time periods, performing weighted addition to obtain a fatigue state feature value of the operator on duty, comparing the feature value with a fatigue threshold value, and judging the fatigue state of the operator on duty. The degree of the blinking state, the yawn state and the head correcting state of the operator on duty is judged from the three feature areas of the eyes, the mouth and the head, the fatigue value of the operator on duty is comprehensively evaluated, and the accuracy of fatigue state judgment of the operator on duty is effectively improved.

Description

technical field [0001] The invention relates to the fields of face detection, posture estimation and the like, in particular to a method for detecting the fatigue state of a person on duty. Background technique [0002] On-duty personnel in platforms such as airport control consoles, railway operation rooms, and hospital intensive care units need to stare at video images 24 hours a day, and night-time personnel are prone to fatigue, causing fatigue states such as distraction and dozing off. It is extremely easy to cause a major impact. If there is an emergency message to be processed, and the person on duty at this time is dozing off, he cannot handle the emergency fault message in time, which will easily lead to major consequences. Therefore, it is very important to propose a fatigue state detection method for duty personnel. [0003] The fatigue state detection method of night duty personnel based on facial feature point recognition is suitable for evaluating the fatigue...

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): G06K9/00G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06N3/045G06F18/2411
Inventor 刘述钢陈磊
Owner HUNAN UNIV OF SCI & TECH