A method for detecting a sleeping behavior of a person on duty based on a convolutional neural network

A convolutional neural network, technology for on-duty personnel, applied in instruments, character and pattern recognition, computer parts and other directions, can solve the problems of human waste, time-consuming and laborious, low efficiency, etc., achieve strong persuasion, small moving range, long lasting effect

Active Publication Date: 2019-05-07
HANGZHOU XUJIAN SCI & TECH CO LTD
View PDF8 Cites 19 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

This method is time-consuming and labor-intensive, which not only causes a waste of manpower, but also is very inefficient, and cannot completely eliminate accidents

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 method for detecting a sleeping behavior of a person on duty based on a convolutional neural network
  • A method for detecting a sleeping behavior of a person on duty based on a convolutional neural network
  • A method for detecting a sleeping behavior of a person on duty based on a convolutional neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0026] The technical solutions in the embodiments of the present invention are clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. The flow chart of the convolutional neural network detecting the sleeping behavior of the personnel on duty provided in the embodiment of the present invention. Such as Figure 1~3 As shown, a method based on convolutional neural network to detect the sleeping behavior of duty personnel mainly includes the following steps:

[0027] Step (1): Collect 3,000 pictures of people in different sleeping positions from the top view angle as positive sample pictures. Collect pictures of people who are not sleeping from the top view angle, including people in different postures such as walking, standing, and sitting. The number is 6000, as a set of negative sample pictures.

[0028] Step (2): Preprocess the positive and negative sample image sets, cut out the regions that only include people, ...

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 convolutional neural network-based method for detecting the sleep behavior of a person on duty, and the method comprises the steps: 1, collecting a sleep figure picture as apositive sample picture set; And collecting character pictures which do not sleep as a negative sample picture set. 2, using a YOLO v3 algorithm to facilitate positive and negative sample picture sets, obtaining a character area, and forming positive and negative sample data sets; 3, dividing the positive and negative sample data sets into a training data set and a test data set; And 4, constructing the convolutional neural network based on the ShuffleNet v2 model. And 5, training the convolutional neural network model by using the training data set. And 6, deploying the trained convolutionalneural network model in a visual analysis system, analyzing video stream data acquired by video monitoring equipment, and detecting the duty condition of a person on duty. According to the technical scheme, the target detection technology and the behavior recognition technology based on the convolutional neural network are fused according to the characteristics of the sleep behavior, and the analysis result is accurate and effective.

Description

technical field [0001] The invention relates to the technical field of personnel behavior analysis, in particular to a method for detecting sleeping behavior of personnel on duty based on a convolutional neural network. Background technique [0002] In the petrochemical industry, safe production is directly related to the life and property of every employee, as well as the survival and development of the enterprise. At present, all relevant enterprises have achieved all-round coverage of video surveillance in the factory area. At the same time, they have set up duty rooms and equipped corresponding duty personnel, trying to establish an effective safety production mechanism through the combination of human defense and technical defense. In a large factory area, due to the large area, the on-duty personnel are responsible for a large number of video surveillance equipment, which increases the work intensity. Especially at night, it is difficult for the on-duty personnel to e...

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): G06K9/00G06K9/62
Inventor 邱彦林李华松胡松涛卢锡芹倪仰鲁立虹张慧娟张秀飞邬奇龙
Owner HANGZHOU XUJIAN SCI & TECH CO LTD
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

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap