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

Mask state reminding method and device and mobile terminal

A state and mask technology, applied in the field of mask recognition, to achieve the effects of less memory usage, reduced number of false alarms, and accurate mask status

Active Publication Date: 2020-12-22
UBTECH ROBOTICS CORP LTD
View PDF10 Cites 0 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] The embodiment of the present application provides a mask state reminder method, which can solve the problems existing in the existing methods

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
  • Mask state reminding method and device and mobile terminal
  • Mask state reminding method and device and mobile terminal
  • Mask state reminding method and device and mobile terminal

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0036] If there is an epidemic, public places usually remind people to wear masks to reduce the probability of cross-infection. However, the existing methods can only judge whether people wear masks or not. In fact, if the user only hangs the mask near the mouth (without covering the mouth and nose), there is also the possibility of germs spreading or being infected. The risk of germ infection, in addition, the existing method also has the situation that the deployment of mobile terminals (such as mobile phones or robots) is difficult and there are many false positives. In order to solve these problems, this application proposes a mask status reminder method .

[0037] figure 1 It shows a flow chart of a mask status reminder method provided in Embodiment 1 of the present application, which is described in detail as follows:

[0038] Step S11 , face detection is performed on the image frame, and a face area is determined, wherein the face area is an area where a face exists. ...

Embodiment 2

[0098] Corresponding to the mask status reminder method described in the above embodiment, Figure 9 It shows a structural block diagram of the mask status reminding device provided by the embodiment of the present application. For the convenience of description, only the parts related to the embodiment of the present application are shown.

[0099] refer to Figure 9 , the mask state reminding device 9 includes: a face area determination unit 91, a mask state acquiring unit 92, a face calibration unit 93, and a mask state reminding unit 94. in:

[0100] A human face area determining unit 91, configured to perform face detection on the image frame, and determine a human face area, wherein the human face area is an area where a human face exists;

[0101] In some embodiments, the determined human face can be selected by a graphic frame, and the area surrounded by the graphic frame is the human face area. After the human face is framed, an image frame with the graphic frame is...

Embodiment 3

[0126] Figure 10 It is a schematic structural diagram of a mobile terminal provided by an embodiment of the present application. like Figure 10 As shown, the mobile terminal 10 of this embodiment includes: at least one processor 100 ( Figure 10 Only one processor is shown in ), a memory 101, and a computer program 102 stored in the memory 101 and operable on the at least one processor 100, when the processor 100 executes the computer program 102, the above-mentioned Steps in any of the various method embodiments:

[0127] Performing face detection on the image frame, and determining a face area, wherein the face area is an area where a face exists;

[0128] Obtain the mask state of the face in the face area, wherein the mask state includes: the state of not wearing a mask, the state of not wearing a mask, and the state of wearing a mask;

[0129] If the state of the mask is the state of not wearing a mask or the state of not wearing a mask, then the trained face calibra...

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 is suitable for the technical field of mask recognition, and provides a mask state reminding method and device and a mobile terminal, and the method comprises the steps: carrying out theface detection of an image frame, and determining a face region which is a region with a face; obtaining mask states of a human face in the human face area, the mask states including a non-mask-wornstate, a non-mask-worn state and a mask-worn state; if the mask state is a non-worn mask state or a non-worn mask state, adopting a trained face calibration model to calibrate a first target face so as to filter features, which are mistakenly detected as faces, in the first target face, wherein the trained face calibration model is a lightweight dichotomy model, and the first target face is a facecorresponding to an unworn state or a mask-unworn state; and performing mask state reminding on the face obtained after the first target face is calibrated. By means of the method, the determined state of the mask can be more accurate.

Description

technical field [0001] The present application belongs to the technical field of mask identification, and in particular relates to a mask status reminder method, device, mobile terminal and computer-readable storage medium. Background technique [0002] When an epidemic occurs, public places usually remind people in public places to wear masks to reduce the probability of cross-infection. [0003] Some face detection and mask recognition algorithms that currently exist have some problems in the application process. For example, the face detection algorithm, in order to be able to be deployed on mobile terminals, its corresponding face detection model is generally relatively light, prone to false detection, if not processed, it will bring many false positives. For the mask recognition algorithm, it can only recognize the state of wearing a mask and the state of not wearing a mask, and the corresponding mask recognition model will be relatively heavy, which in turn leads to g...

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): G06K9/00G06K9/32G06K9/46G06K9/62G06N3/04G06N3/08
CPCG06N3/08G06V40/161G06V40/168G06V40/172G06V10/25G06V10/443G06N3/045G06F18/241G06V40/165G08B21/245G06T7/70G06T2207/30201G08B21/18
Inventor 曾钰胜刘业鹏程骏庞建新熊友军
Owner UBTECH ROBOTICS CORP LTD
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