A method for establishing a neural network model for real-time detection of mask wearing and an implementation system

A neural network model, real-time detection technology, applied in biological neural network models, neural learning methods, neural architectures, etc., to achieve great practical value, reduce labor, and reduce detection costs.

Pending Publication Date: 2020-11-24
XI'AN UNIVERSITY OF ARCHITECTURE AND TECHNOLOGY
View PDF0 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

In order to do a good job in the prevention and control of infectious viruses, effectively cut off the transmission of the virus, resolutely curb the spread of the epidemic, and ensure the safety and health of the people, it is necessary to set up a large number of public places such as communi

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 establishing a neural network model for real-time detection of mask wearing and an implementation system
  • A method for establishing a neural network model for real-time detection of mask wearing and an implementation system
  • A method for establishing a neural network model for real-time detection of mask wearing and an implementation system

Examples

Experimental program
Comparison scheme
Effect test

Example Embodiment

[0075] Embodiment:

[0076] The system according to the present embodiment includes a camera, raspberry sent 4b boards, NCS2 neural computation rods, a mask detect pre-trained model, body temperature infrared probe, voice broadcast module, a display screen; camera capture detection region Facial images, body temperature infrared probe detected before the camera person's body temperature, raspberry pie were acquired temperature information of the image information and image of persons captured by the camera, to import pre-training model mask testing to NCS2 neural computation stick, after nerve stick acceleration reasoning, real-time the regional staff to detect whether taken with a mask image recognition analysis and processing, and the corresponding screen display and the picture on the screen wearing masks and body temperature value is correct text prompts.

[0077] Facial capture camera for image detection region;

[0078] Camera with the official launch of Raspberry Pi camera ...

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 method for establishing a neural network model for real-time detection of mask wearing and an implementation system. According to the system of the invention, the neural network model for real-time detection of mask wearing is built in the neural calculation rod; accelerated reasoning can be carried out through a nerve calculation rod; the real-time processing capabilityof the control panel is combined; therefore, the system can analyze and process whether a person in a shot detection area wears a mask or not in real time and carry out image recognition, and output aresult to the display; according to the invention, real-time mask detection can be realized, the calculated amount of image data processing is completely migrated to the edge of a network, no serveris used any more, the detection cost can be reduced, the identification precision is high, the labor force is reduced, and the invention has great practical value.

Description

technical field [0001] The invention belongs to the field of target detection of edge computing, and in particular relates to a method for building a neural network model and an implementation system for real-time detection of mask wearing. Background technique [0002] Infectious viruses are currently mainly transmitted through droplets and contact, and aerosol transmission may only occur under certain special conditions. Under normal working and living conditions, wearing a mask correctly is sufficient to meet daily protection needs. During the epidemic, it is particularly important for the general public to wear masks correctly when they go out. In order to do a good job in the prevention and control of infectious viruses, effectively cut off the transmission of the virus, resolutely curb the spread of the epidemic, and ensure the safety and health of the people, it is necessary to set up a large number of public places such as communities, schools, units, canteens, and s...

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): G06N3/04G06N3/08G06K9/00
CPCG06N3/08G06V40/161G06N3/045
Inventor 陈登峰陈鹏文王帅举肖海燕李明海陈章政刘磊
Owner XI'AN UNIVERSITY OF ARCHITECTURE AND TECHNOLOGY
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