Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

A fatigue detection method for personnel in fixed positions based on information fusion

A fatigue detection and fusion algorithm technology, applied in the field of image processing, can solve problems such as poor robustness, failure to meet actual product requirements, and large impact of light

Active Publication Date: 2019-06-25
NANJING LES ELECTRONICS EQUIP CO LTD
View PDF6 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Although these algorithms are simple to calculate, they are greatly affected by light and have poor robustness.
Therefore, the false alarm rate of the final fatigue detection result is too high, which cannot meet the actual product demand

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
  • A fatigue detection method for personnel in fixed positions based on information fusion
  • A fatigue detection method for personnel in fixed positions based on information fusion
  • A fatigue detection method for personnel in fixed positions based on information fusion

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0057] The present invention will be further described below in conjunction with the accompanying drawings and embodiments.

[0058] The invention discloses a fatigue detection method for personnel in fixed positions based on information fusion, such as figure 1 shown, including the following steps:

[0059] S1: Image preprocessing:

[0060] Image size is one of the important factors affecting image processing speed. By scaling the input image, the efficiency and accuracy of face detection in the video image can be effectively improved; secondly, the image is enhanced by histogram equalization and the image is denoised by Gaussian filtering, which is convenient for future Extract the feature points of the image.

[0061] S2: Face detection:

[0062] Face detection is realized by using HOG feature + cascade classifier. The extraction of HOG features firstly grayscales the input image, and uses the Gamma correction method to normalize the image to reduce the interference ca...

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 information fusion-based fatigue detection method for fixed-post personnel, which solves the problems of fatigue feature detection and decision-level information fusion under single-channel video. First, the regression tree method is used to calibrate the face of the input image to achieve high-precision face detection; then, the detected face is detected using the eye feature point positioning technology based on the cascaded convolutional neural network to realize the eye and mouth. The precise detection of feature points, by analyzing the feature points of multi-frame images of the video, calculates the PERCLOS parameters, blink frequency and yawn frequency respectively. Then, the method based on ASM local positioning and face feature triangle is used to realize the head pose estimation, so as to calculate the nodding frequency. Finally, an information fusion algorithm based on rough set theory is used to realize the fatigue detection of personnel in fixed positions.

Description

technical field [0001] The invention belongs to the technical field of image processing, and in particular relates to an information fusion-based fatigue detection method for fixed-post personnel. Background technique [0002] With the development of computer and artificial intelligence technology, more and more people are engaged in more mental work, such as IT industry workers, drivers, intelligence personnel and so on. When faced with boring, stressful or heavy responsibility work, it is easy to cause distraction, mental fatigue, reduced work efficiency and even operational errors leading to safety hazards. Fatigue detection technology can effectively warn the fatigue status of this type of operators, so as to improve work efficiency and reduce potential safety hazards. [0003] At present, most fatigue detection algorithms, especially eye fatigue feature detection algorithms, use edge detection or threshold segmentation to calculate eye closure. Although these algorith...

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 Patents(China)
IPC IPC(8): G06K9/00G06K9/62
CPCG06V40/165G06V40/171G06V40/172G06V20/46G06F18/241G06F18/25
Inventor 朱伟贺超李嘉琦杜瀚宇王寿峰马浩白俊奇苗锋刘文张瑞全王扬红张禹
Owner NANJING LES ELECTRONICS EQUIP CO LTD
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products