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

Slim-YOLOv3-based mask wearing condition detection method

A detection method and mask technology, which is applied in the field of deep learning target detection and computer vision, can solve the problems that the detector cannot achieve high precision and expensive computing resources, and achieve the effect of increasing network detection speed, improving detection accuracy, and achieving accurate and fast results

Active Publication Date: 2021-06-11
CHONGQING UNIV OF POSTS & TELECOMM
View PDF5 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0007] At present, although many devices for video detection of mask wearing have appeared in practical applications, the computing resources consumed by high detection accuracy devices are often expensive, and cheap detectors cannot achieve high accuracy.

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
  • Slim-YOLOv3-based mask wearing condition detection method
  • Slim-YOLOv3-based mask wearing condition detection method
  • Slim-YOLOv3-based mask wearing condition detection method

Examples

Experimental program
Comparison scheme
Effect test

specific Embodiment approach

[0064] A specific embodiment of a training improvement Slim-YOLOV3 model, including:

[0065] S1: Get the original data set, and classify the original data set, the results of the classification include: specification wearing hood map, not standardizing wearing mask, not wearing mask Figure three class;

[0066] S2: Divide the classified data set to obtain the training sample set and test sample set; data enhancement processing is performed on the training sample.

[0067] S3: Enter the image of the enhanced training sample into the YOLOV3 network model of the backbone network DarkNet-53, extracts multi-scale classification features and positioning features;

[0068] S4: Two feature layers need to be output, and the two feature layers are located at different locations of the trunk portion Darknet 53, located in the middle lower layer, the underlayer, and the two feature layers are (26, 26, 512) and (13, 13, 1024), respectively. Then, two feature layers are subjected to 5 convolut...

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 belongs to the technical field of deep learning target detection and computer vision, and particularly relates to a Slim-YOLOv3-based mask wearing condition detection method, which comprises the following steps: acquiring face video data in real time, and preprocessing the face video data; and inputting the preprocessed face image into the trained Slim-YOLOv3 model, and judging whether the user correctly wears the mask or not. According to the invention, through adoption of the Slim-YOLOv3-based mask wearing condition video detection method and an improved unsupervised self-classification method, sub-class division is carried out on data of non-standard mask wearing, so that a mask wearing video detection task can be realized more accurately and rapidly. The proposed network is more concise, so that the application cost is further reduced.

Description

Technical field [0001] The present invention belongs to depth learning objective detection and computer visual technology, and in particular, the present invention relates to the detection method of mask wearing sites based on Slim-Yolov3. Background technique [0002] Due to harmful gases, odors, foams, viruses, all virus, through air, to effectively prevent the material invading the human body by standardizing the wearing mask. The role of the standard wearing mask is not only to prevent viruses from spreading from the invisible person to others, reducing the probability of secondary communication to protect others, but also protect the wearer, reduce the amount of virus in contact with the wearer, make the virus The risk of infection is lower. [0003] In recent years, deep learning has made great progress in the fields of target testing, image classification, semantic segmentation. Combined with various algorithms of convolutional neural networks, both precision or computatio...

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): G06K9/00G06N3/04G06N3/08
CPCG06N3/08G06V40/165G06V40/171G06V40/172G06N3/048G06N3/045
Inventor 姜小明向富贵张中华吕明鸿王添赖春红王伟李章勇
Owner CHONGQING UNIV OF POSTS & TELECOMM
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

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

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com