High-precision mask wearing identification method and system

An identification method and high-precision technology, applied in the field of high-precision mask-wearing identification methods and systems, can solve problems such as low reliability, missing targets, and labor, to reduce time costs, improve reliability, and improve daily work efficiency. Effect

Inactive Publication Date: 2020-10-30
广东邦鑫数据科技股份有限公司 +1
View PDF11 Cites 3 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] However, these methods are time-consuming, laborious, and inefficient, especially in scenes with a large flow of people, and it is easy to miss the target when the observer is tired.
For the use of image recognition technology to identify pedestrians wearing masks, it is easily affected by the external lighting environment and has low reliability.

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
  • High-precision mask wearing identification method and system
  • High-precision mask wearing identification method and system
  • High-precision mask wearing identification method and system

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0032] see figure 1 , figure 1 It is a schematic flow chart of a high-precision mask-wearing identification method disclosed in the embodiment of the present invention. in, figure 1 The described method can be applied to a public place monitoring system, and the public place monitoring system includes a plurality of cameras and an algorithm server, and other monitoring systems also belong to the protection scope of the present invention, and the embodiments of the present invention are not limited. Such as figure 1 As shown, the high-precision mask wearing recognition method may include the following operations:

[0033] Step S101: Obtain video stream data through multiple cameras.

[0034] In this application, the camera device in a common public place can be directly used to collect video stream data through the camera device. Therefore, there is no need to install additional outdoor equipment, which greatly reduces the time and material costs required for supporting equ...

Embodiment 2

[0048] see figure 2 , figure 2 It is a schematic flow chart of another high-precision mask wearing identification method disclosed in the embodiment of the present invention. in, figure 2 The described method can be applied to a public place monitoring system, and the public place monitoring system includes a plurality of cameras and an algorithm server, and other monitoring systems also belong to the protection scope of the present invention, and the embodiments of the present invention are not limited. Such as figure 2 As shown, the high-precision mask wearing recognition method may include the following operations:

[0049] Step S201: Obtain video stream data through multiple cameras.

[0050] In this application, the camera device in a common public place can be directly used to collect video stream data through the camera device. Therefore, there is no need to install additional outdoor equipment, which greatly reduces the time and material costs required for supp...

Embodiment 3

[0067] see image 3 , image 3 Described is a high-precision wearing mask recognition system, and the system includes:

[0068] A plurality of cameras 1 acquire video stream data.

[0069] The algorithm server 2 is used to extract feature data according to the video stream data.

[0070] The calculation module 3 is used to input the characteristic data into the constructed mask recognition model to perform confidence calculation and generate a confidence value.

[0071] Judgment module 4 is used to judge whether the feature data wears a mask according to the preset confidence threshold and confidence value, if the confidence value is greater than the preset confidence value, then it is judged that the feature data does not wear a mask, and an alarm message is output.

[0072] The decoding module 5 is used to carry out the image decoding operation to the video stream data, and generates the image data in the RGB format and transmits it to the algorithm server 2.

[0073] In...

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 high-precision mask wearing identification method and system, the method is applied to a public place monitoring system, the public place monitoring system comprises a plurality of cameras and an algorithm server, and the method comprises the following steps: obtaining video stream data through the plurality of cameras; extracting feature data according to the video stream data; inputting the feature data into a constructed mask recognition model for confidence calculation, and generating a confidence value; and judging whether the feature data wears the mask or not according to a preset confidence threshold value and the confidence value, if the confidence value is greater than the preset confidence value, judging that the feature data does not wear the mask, andgenerating alarm information to be output. Therefore, the pedestrian position can be more accurately positioned through the deep learning technology, the reliability and anti-interference performanceof identification are greatly improved, manpower and material resources are saved, and the improvement of the labor efficiency is facilitated.

Description

technical field [0001] The invention relates to the technical field of image recognition, in particular to a high-precision mask-wearing recognition method and system. Background technique [0002] At present, whether people entering and exiting wear masks is more subjectively judged by manual on-site observation, observing multiple scenes in the monitoring room, and using simple image recognition technology to assist the monitoring of staff. [0003] However, these methods are time-consuming, labor-intensive, and inefficient, especially in scenes with a large flow of people, and it is easy to miss the target when the observer is tired. For the use of image recognition technology to identify pedestrians wearing masks, it is easily affected by the external lighting environment, and the reliability is low. Contents of the invention [0004] The technical problem to be solved by the present invention is to provide a high-precision mask wearing recognition method and system, ...

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
CPCG06V40/161G06V40/172G06V20/40G06F18/22G06F18/214
Inventor 曾强汤坚范亮舒煜昌秦若涵许思捷李刚领王秋媚曹梓峰
Owner 广东邦鑫数据科技股份有限公司
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