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

Pedestrian mask wearing real-time detection method based on deep learning

A deep learning and real-time detection technology, applied in the field of Internet of Things and artificial intelligence, can solve the problems of high delay, deep network, detection real-time performance and detection accuracy cannot be satisfied at the same time, and achieve the effect of good engineering practicability.

Inactive Publication Date: 2020-07-10
SOUTHWEST PETROLEUM UNIV
View PDF5 Cites 10 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Most of the networks of deep learning algorithms are deep and complex. Detection is performed on a platform with limited computing power and memory. The delay is high, and real-time detection cannot be achieved, or the real-time detection and detection accuracy cannot be satisfied at the same time.

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
  • Pedestrian mask wearing real-time detection method based on deep learning
  • Pedestrian mask wearing real-time detection method based on deep learning
  • Pedestrian mask wearing real-time detection method based on deep learning

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0047] The specific technical solutions of the present invention are described in conjunction with the examples.

[0048] A real-time detection method for pedestrian mask wearing based on deep learning, the process is as follows figure 1 shown, including the following steps:

[0049] S1. Build a robust backbone network

[0050] The present invention adopts the backbone network Darknet53 as the feature extractor, and the network structure is as follows figure 2 shown. Darknet53 consists of 52 convolutional layers as the main network layer, and the last layer is a fully connected layer composed of 1*1 convolutions. The first layer of the main network layer is convolutional, and then there are 5 sets of repeated resblock_body, each resblock_body_n includes a separate convolutional and a set of res_unit_n, res_unit_n is a convolutional that is repeatedly executed, and the number of executions is n (n=1, 2, 8, 8, 4), the total is 1+(1+1*2)+(1+2*2)+(1+8*2)+(1+8*2)+(1+4*2) = 52...

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 provides a pedestrian mask wearing real-time detection method based on deep learning. The pedestrian mask wearing real-time detection method comprises the following steps: S1, establishing a robust backbone network; S2, carrying out the multi-scale training; S3, performing model compression; S4, performing model optimization. According to the method provided by the invention, more labor overhead cost, and calculation cost and time overhead cost of the small hardware storage device are considered. Whether a pedestrian wears the mask or not can be judged more quickly, and good engineering practicability is achieved.

Description

technical field [0001] The invention belongs to the field of the Internet of Things and artificial intelligence, and specifically relates to a deep learning-based real-time detection method and implementation of pedestrian mask wearing. Background technique [0002] Some large-scale viruses can be transmitted through droplets and other media. When effective antiviral drugs have not been developed, the wearing of masks by the public is very important in reducing the spread of diseases. Masks are necessary protective equipment in special times. There are special personnel at the door to check the wearing conditions of masks in places with large crowds such as residential areas, supermarkets, and stations. Omissions may occur. Therefore, it is of great practical significance to realize real-time detection of pedestrian mask wearing. [0003] Real-time detection of pedestrian mask wearing involves computer vision and embedded hardware devices, requiring cameras and hardware pl...

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): G06K9/00G06N3/04G06N3/08
CPCG06N3/082G06N3/08G06V40/161G06N3/045
Inventor 王兵乐红霞赵春兰肖斌李文璟
Owner SOUTHWEST PETROLEUM UNIV
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