CN111582183A - Mask identification method and system in public place - Google Patents
Mask identification method and system in public place Download PDFInfo
- Publication number
- CN111582183A CN111582183A CN202010392248.2A CN202010392248A CN111582183A CN 111582183 A CN111582183 A CN 111582183A CN 202010392248 A CN202010392248 A CN 202010392248A CN 111582183 A CN111582183 A CN 111582183A
- Authority
- CN
- China
- Prior art keywords
- mask
- identification
- image data
- pedestrian
- category
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/168—Feature extraction; Face representation
- G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Multimedia (AREA)
- General Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Signal Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a mask identification method and a system in public places, wherein the method comprises the following steps: acquiring video stream data through a camera; tracking a target pedestrian in video stream data to generate pedestrian image data; inputting a pedestrian image into the constructed mask wearing identification model to generate identification categories of pedestrian image data; the identification types comprise a wearing mask type, an unworn mask type and a non-face type. Therefore, the existing view acquisition equipment (camera) in a public place can be utilized to accurately identify the wearing condition of the pedestrian mask in the public place, a powerful judgment basis is provided for prevention and control work, and compared with the mode of simply using artificial field observation and subjective judgment, the method not only reduces the energy loss of workers, but also avoids the functional waste caused by the repeated detection of the same target by different workers, further improves the working efficiency, and reduces the increase of the labor cost caused by the mask wearing rule in the public place.
Description
Technical Field
The invention relates to the technical field of image recognition, in particular to a mask recognition method and system in a public place.
Background
With the improvement of health protection consciousness of social people, the phenomenon of wearing the mask is more and more common. When people go out and enter public places, people need to wear the mask. At the present stage, the identification mode of whether the mask is worn is mostly finished by adopting a subjective judgment means of manual field observation. However, this manual observation is time-consuming, laborious, inefficient and prone to congestion.
Disclosure of Invention
The technical problem to be solved by the invention is to provide a method and a system for identifying a mask in a public place, which can accurately identify the wearing condition of the pedestrian mask in the public place by using the existing view acquisition equipment (camera) in the public place, provide a powerful judgment basis for prevention and control work, and compared with a mode of simply using manual on-site observation and subjective judgment, the method and the system not only reduce the energy loss of workers, but also avoid the functional waste caused by repeatedly detecting the same target by different workers, further improve the working efficiency and reduce the increase of labor cost caused by mask wearing rules in the public place.
In order to solve the technical problem, the invention discloses a public mask identification method in a first aspect, which comprises the following steps: acquiring video stream data through a camera; tracking a target pedestrian in the video stream data to generate pedestrian image data; inputting the pedestrian image into a constructed mask wearing identification model to generate the identification category of the pedestrian image data; wherein the identification categories include a worn mask category, an unworn mask category, and a non-face category.
In some embodiments, tracking a target pedestrian in the video stream data, generating pedestrian image data, comprises: acquiring image data of the same target pedestrian in the video stream data before passing through each camera; storing the image data as a picture in a JPG format; and carrying out duplication elimination calculation on the picture to generate pedestrian image data.
In some embodiments, a method for constructing a mask wearing recognition model includes: carrying out feature extraction on a plurality of groups of pedestrian image data through a depth learning network; classifying data with the same characteristics in the pedestrian image data into one class; learning each type of pedestrian image data to generate a corresponding weight characteristic file; and constructing a mask wearing identification model according to the weight characteristic file.
In some embodiments, the inputting the pedestrian image into the constructed mask wearing recognition model and generating the recognition category of the pedestrian image data includes: intercepting a head region of the pedestrian image by using a detection algorithm to generate identification data; inputting the identification data into the mask wearing identification model, extracting the characteristic value of the identification data according to the mask wearing identification model, and comparing the characteristic value with the weight characteristic file in the mask wearing identification model to generate an identification category.
In some embodiments, further comprising: and outputting and displaying the identification type as the type of the unworn mask.
The invention discloses a mask recognition system in a public place in a second aspect, which comprises: the camera is used for acquiring video stream data; the image acquisition module is used for tracking a target pedestrian in the video stream data and generating pedestrian image data; the identification module is used for inputting the pedestrian image into a constructed mask wearing identification model and generating the identification category of the pedestrian image data; the identification categories comprise a wearing mask category, an unworn mask category and a non-face category.
In some embodiments, the image acquisition module is implemented as: acquiring image data of the same target pedestrian in the video stream data before passing through each camera; storing the image data as a picture in a JPG format; and carrying out duplication elimination calculation on the picture to generate pedestrian image data.
In some embodiments, the system further comprises: and the display module is used for outputting and displaying the identification type as the type of the unworn mask.
The invention discloses a third aspect of another mask recognition device in public places, which comprises:
a memory storing executable program code;
a processor coupled with the memory;
the processor calls the executable program code stored in the memory to execute the mask recognition method for public places according to the first aspect of the present invention.
The fourth aspect of the present invention discloses a computer storage medium, wherein the computer storage medium stores computer instructions, and when the computer instructions are called, the computer storage medium is used for executing the mask identification method in the public places according to any one of the first aspect of the present invention.
Compared with the prior art, the invention has the beneficial effects that:
the implementation of the invention can utilize the existing image acquisition equipment, utilize the existing resources to the maximum extent, and realize the deployment of front-end hardware equipment in part of public places at zero cost; and whether the mask is worn on the head of the pedestrian can be judged through the constructed mask wearing identification model, so that the mask judging accuracy is high, the detection requirements of conventional masks are met, human resources can be liberated, and the maintenance cost of the mask wearing rules of public places is reduced.
Drawings
Fig. 1 is a schematic flow chart of a mask recognition method in a public place according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of another mask identification method in a public place according to an embodiment of the present invention;
fig. 3 is a block diagram of a mask recognition system in a public place according to an embodiment of the present invention;
fig. 4 is a schematic structural view of a mask recognition device in a public place according to an embodiment of the present invention.
Detailed Description
For better understanding and implementation, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be obtained by a person skilled in the art based on the embodiments of the present invention without any inventive step, are within the scope of the present invention.
The terms "comprises," "comprising," and any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or modules is not necessarily limited to those steps or modules explicitly listed, but may include other steps or modules not expressly listed or inherent to such process, method, article, or apparatus.
The embodiment of the invention discloses a mask identification method and system in a public place. . .
Example one
Referring to fig. 1, fig. 1 is a schematic flow chart illustrating a mask recognition method in a public place according to an embodiment of the present invention. The method described in fig. 1 may be applied to a monitoring system in a public place, where the monitoring system may include a plurality of cameras and an algorithm server that are fixedly arranged, and the embodiment of the present invention is not limited to other monitoring systems. As shown in fig. 1, the mask recognition method in public places may include the following operations:
101. and acquiring video stream data through the camera.
In this embodiment, the method can be directly applied to a monitoring system in a public place, so that data can be acquired by using a camera device commonly used in the public place, and the method specifically includes: the camera device fixedly arranged at each corner of the public place directly collects video stream data, so that outdoor equipment does not need to be additionally installed, the time cost and the material resource cost of matched equipment are greatly reduced, and the aim of simply acquiring data is fulfilled.
102. And tracking the target pedestrian in the video stream data to generate pedestrian image data.
The method includes the steps that image data of the same target pedestrian in video stream data before passing through each camera is obtained, illustratively, a certain pedestrian passes through a camera B and a camera c from an A place to a B place successively, the pedestrian is tracked, image data is obtained when the pedestrian passes through the camera a, image data is obtained when the pedestrian passes through the camera B, image data is obtained when the pedestrian passes through the camera c, the obtained image data are sequentially stored as pictures in a JPG format, and then the pictures in the JPG format are subjected to deduplication calculation aiming at pedestrian facial features, so that pedestrian image data are generated.
103. And inputting the pedestrian image into the constructed mask wearing identification model to generate the identification category of the pedestrian image data.
The identification categories comprise a wearing mask category, a non-wearing mask category and a non-face category, and the non-face category comprises image categories such as a back head, a non-real face and a fuzzy face.
Further, the construction method of the mask wearing identification model is realized as follows: performing feature extraction on a plurality of groups of pedestrian image data through a deep learning network, wherein the feature extraction is based on identification categories, data with the same features in the pedestrian image data are classified into one category, and specifically, the extracted feature is that the pedestrian image data with a mask are classified into the mask wearing category; classifying the pedestrian image data with the extracted characteristics of not wearing the mask into the class of not wearing the mask; classifying the extracted pedestrian image data with the characteristics of the hindbrain, the fuzzy face and the like into non-face categories. And then, learning each type of pedestrian image data to generate a corresponding weight value feature file, wherein the data learning method can be realized by referring to the machine learning in the prior art. And finally, constructing a mask wearing identification model in an algorithm server according to the weight feature files of each type.
In one embodiment, the pedestrian image is input into the constructed mask wearing identification model, and the identification category of the pedestrian image data is generated and realized as follows:
and receiving the pictures in the JPG format transmitted through the network in the algorithm server. In order to make the identification process simple and quick and eliminate unnecessary interference, a detection algorithm is used for intercepting the head area of the pedestrian image to generate identification data, the interception method can carry out head feature interception according to the configured algorithm, then the identification data is input into the mask wearing identification model, the mask wearing identification model can automatically extract the feature value of the identification data, and the feature value is compared with the weight feature file in the mask wearing identification model to generate the identification category. Therefore, the identification type of a certain pedestrian can be directly obtained, and whether the pedestrian wears the mask in a public place can be judged.
According to the method provided by the embodiment, the existing image acquisition equipment can be utilized, the existing resources are utilized to the maximum extent, and the front-end hardware equipment deployment can be realized in partial public places at zero cost; and whether the mask is worn on the head of the pedestrian can be judged through the constructed mask wearing identification model, so that the mask judging accuracy is high, the detection requirements of conventional masks are met, human resources can be liberated, and the maintenance cost of the mask wearing rule in public places is reduced.
Example two
Referring to fig. 2, the method described in fig. 2 may be applied to a monitoring system in a public place, where the monitoring system may include a plurality of cameras and an algorithm server, and the embodiment of the present invention is not limited to other monitoring systems. As shown in fig. 2, the mask recognition method in public places may include the following operations:
201. and acquiring video stream data through the camera.
In this embodiment, the method can be directly applied to a monitoring system in a public place, so that data can be acquired by using a camera device commonly used in the public place, and the method specifically includes: the camera device fixedly arranged at each corner of the public place directly collects video stream data, so that outdoor equipment does not need to be additionally installed, the time cost and the material resource cost of matched equipment are greatly reduced, and the aim of simply acquiring data is fulfilled.
202. And tracking the target pedestrian in the video stream data to generate pedestrian image data.
The method includes the steps that image data of the same target pedestrian in video stream data before passing through each camera is obtained, illustratively, a certain pedestrian passes through a camera B and a camera c from an A place to a B place successively, the pedestrian is tracked, image data is obtained when the pedestrian passes through the camera a, image data is obtained when the pedestrian passes through the camera B, image data is obtained when the pedestrian passes through the camera c, the obtained image data are sequentially stored as pictures in a JPG format, and then the pictures in the JPG format are subjected to deduplication calculation aiming at pedestrian facial features, so that pedestrian image data are generated.
203. And inputting the pedestrian image into the constructed mask wearing identification model to generate the identification category of the pedestrian image data.
The identification categories comprise a wearing mask category, a non-wearing mask category and a non-face category, and the non-face category comprises image categories such as a back head, a non-real face and a fuzzy face.
Further, the construction method of the mask wearing identification model is realized as follows: performing feature extraction on a plurality of groups of pedestrian image data through a deep learning network, wherein the feature extraction is based on identification categories, data with the same features in the pedestrian image data are classified into one category, and specifically, the extracted feature is that the pedestrian image data with a mask are classified into the mask wearing category; classifying the pedestrian image data with the extracted characteristics of not wearing the mask into the class of not wearing the mask; classifying the extracted pedestrian image data with the characteristics of the hindbrain, the fuzzy face and the like into non-face categories. And then, learning each type of pedestrian image data to generate a corresponding weight value feature file, wherein the data learning method can be realized by referring to the machine learning in the prior art. And finally, constructing a mask wearing identification model in an algorithm server according to the weight feature files of each type.
In one embodiment, the pedestrian image is input into the constructed mask wearing identification model, and the identification category of the pedestrian image data is generated and realized as follows:
and receiving the pictures in the JPG format transmitted through the network in the algorithm server. In order to make the identification process simple and quick and eliminate unnecessary interference, a detection algorithm is used for intercepting the head area of the pedestrian image to generate identification data, the interception method can carry out head feature interception according to the configured algorithm, then the identification data is input into the mask wearing identification model, the mask wearing identification model can automatically extract the feature value of the identification data, and the feature value is compared with the weight feature file in the mask wearing identification model to generate the identification category. Therefore, the identification type of a certain pedestrian can be directly obtained, and whether the pedestrian wears the mask in a public place can be judged.
204. And outputting and displaying the identification type as the type of the unworn mask.
In order to purify the main information and improve the processing efficiency, only the identification result of the type of the unworn mask is fed back. The feedback method can be realized by directly sending the result to the monitoring background by the algorithm server, namely, transmitting the result of whether the target person wears the mask to the monitoring background in a network transmission mode. In other implementation manners, alarm information can be generated during transmission to remind workers in the field of the behavior that the workers do not wear the mask.
According to the method of the embodiment, a large amount of human resources are prevented from being consumed in the wearing ring of the visual mask, the existing view acquisition equipment in public places is used, the detection work is realized through an intelligent background server, and the human resources are liberated. And after sending the police that does not wear the gauze mask, manpower resources will concentrate on dissuading work, on keeping original personnel configuration basis, the work load that the at utmost alleviates special period increases, improves work efficiency.
EXAMPLE III
Referring to fig. 3, fig. 3 illustrates a mask recognition system for public places, which includes:
and the camera 1 is used for acquiring video stream data.
And the image acquisition module 2 is used for tracking the target pedestrian in the video stream data and generating pedestrian image data.
And the identification module 3 is used for inputting the pedestrian image into the constructed mask wearing identification model and generating the identification category of the pedestrian image data.
Wherein the identification categories include a worn mask category, an unworn mask category, and a non-face category.
Since the present embodiment can be directly applied to a monitoring system in a public place, the data acquisition can be realized by using a camera 1 device commonly used in the public place, which is specifically realized as follows: the camera device fixedly arranged at each corner of the public place directly collects video stream data, so that outdoor equipment does not need to be additionally installed, the time cost and the material resource cost of matched equipment are greatly reduced, and the purpose of simply acquiring data is achieved.
The image acquisition module 2 may be implemented as: acquiring image data of the same target pedestrian in video stream data before passing through each camera, illustratively, a certain pedestrian passes through a camera B and a camera c successively from a ground to a ground, so tracking the pedestrian realizes acquiring one piece of image data when the pedestrian passes through the camera a, acquiring one piece of image data when the pedestrian passes through the camera B, acquiring one piece of image data when the pedestrian passes through the camera c, sequentially storing the acquired image data into pictures in a JPG format, and performing deduplication calculation on the pictures in the JPG format aiming at the facial features of the pedestrian so as to generate image data of the pedestrian.
The identification categories comprise a wearing mask category, a non-wearing mask category and a non-face category, and the non-face category comprises image categories such as a back head, a non-real face and a fuzzy face.
Further, the method for constructing the mask wearing identification model in the identification module 3 is realized as follows: performing feature extraction on a plurality of groups of pedestrian image data through a deep learning network, wherein the feature extraction is based on identification categories, data with the same features in the pedestrian image data are classified into one category, and specifically, the extracted feature is the category of wearing the mask; classifying the pedestrian image data with the extracted characteristics of not wearing the mask into the class of not wearing the mask; classifying the extracted pedestrian image data with the characteristics of the hindbrain, the blurred face and the like into non-face categories. And then, learning each type of pedestrian image data to generate a corresponding weight characteristic file, wherein the data learning method can be realized by referring to the machine learning in the prior art. And finally, constructing a mask wearing identification model in an algorithm server according to the weight feature files of each type.
In one embodiment, the pedestrian image is input into the constructed mask wearing identification model, and the identification category of the pedestrian image data is generated and realized as follows:
the recognition module 3 may be implemented as: and receiving the pictures in the JPG format transmitted through the network in the algorithm server. In order to enable the identification process to be simple and quick and eliminate unnecessary interference, the head area of the pedestrian image is intercepted by using a detection algorithm to generate identification data, the head feature interception can be carried out according to the configured algorithm by the interception method, then the identification data is input into the mask wearing identification model, the mask wearing identification model can automatically extract the feature value of the identification data, and the feature value is compared with the weight value feature file in the mask wearing identification model to generate the identification category. Therefore, the identification type of a certain pedestrian can be directly obtained, and whether the pedestrian wears the mask in a public place can be judged.
In a preferred embodiment, the system further comprises:
and the display module 4 is used for outputting and displaying the identification type as the type of the unworn mask.
In order to purify the main information and improve the processing efficiency, the identification result of the type of the unworn mask is fed back only through the display module 4. The feedback method can be realized by directly sending the algorithm server to the monitoring background, namely, transmitting the result of whether the target person wears the mask to the monitoring background in a network transmission mode. In other embodiments, alarm information may be generated during transmission to remind workers in the field of the behavior of not wearing the mask.
Example four
Referring to fig. 4, fig. 4 is a schematic structural diagram of a mask recognition device in a public place according to an embodiment of the present invention. As shown in fig. 4, the system may include:
a memory 401 storing executable program code;
a processor 402 coupled with the memory 401;
the processor 402 calls the executable program code stored in the memory 401 for executing the mask recognition method for public places described in the first embodiment or the second embodiment.
EXAMPLE five
The embodiment of the invention discloses a computer-readable storage medium which stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute the mask identification method of a public place described in the first embodiment or the second embodiment.
EXAMPLE six
An embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to cause a computer to execute the mask recognition method for public places described in the first embodiment or the second embodiment.
The above-described embodiments are only illustrative, and the modules described as separate parts may or may not be physically separate, and the parts displayed as modules may or may not be physical modules, may be located in one place, or may be distributed on a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above detailed description of the embodiments, those skilled in the art will clearly understand that the embodiments may be implemented by software plus a necessary general hardware platform, and may also be implemented by hardware. Based on such understanding, the above technical solutions may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, where the storage medium includes a Read-Only Memory (ROM), a Random Access Memory (RAM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), a One-time Programmable Read-Only Memory (OTPROM), an Electrically Erasable Programmable Read-Only Memory (EEPROM), a Read-Only optical disk (Compact Disc-Read-Only Memory, CD-ROM), or other memories, CD-ROM, or other magnetic disks, and the storage medium includes a Read-Only Memory (ROM), a Random Access Memory (RAM), a Programmable Read-Only Memory (PROM), an Erasable Programmable Read-Only Memory (EPROM), an EEPROM), a Read-Only optical disk (CD-ROM), or other memories, A tape memory, or any other medium readable by a computer that can be used to carry or store data.
Finally, it should be noted that: the mask identification method and system in public places disclosed in the embodiments of the present invention are only preferred embodiments of the present invention, and are only used for illustrating the technical solutions of the present invention, not for limiting the same; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those skilled in the art; the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and the modifications or the substitutions do not make the essence of the corresponding technical solutions depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (10)
1. A method for identifying a mask in a public place, the method comprising:
acquiring video stream data through a camera;
tracking a target pedestrian in the video stream data to generate pedestrian image data;
inputting the pedestrian image into a constructed mask wearing identification model to generate the identification category of the pedestrian image data;
wherein the identification categories include a worn mask category, an unworn mask category, and a non-face category.
2. The mask recognition method for public places according to claim 1, wherein the tracking of the target pedestrian in the video stream data to generate pedestrian image data includes:
acquiring image data of the same target pedestrian in the video stream data before passing through each camera;
storing the image data as a picture in a JPG format;
and carrying out duplication elimination calculation on the picture to generate pedestrian image data.
3. The mask recognition method for public use according to claim 1, wherein the method for constructing the mask wearing recognition model includes:
carrying out feature extraction on a plurality of groups of pedestrian image data through a deep learning network;
classifying data with the same characteristics in the pedestrian image data into one class;
learning each type of pedestrian image data to generate a corresponding weight value feature file;
and constructing a mask wearing identification model according to the weight characteristic file.
4. The mask recognition method for public places according to any one of claims 1 to 3, wherein the step of inputting the pedestrian image into the constructed mask wearing recognition model to generate the recognition category of the pedestrian image data comprises the steps of:
intercepting a head region of the pedestrian image by using a detection algorithm to generate identification data;
inputting the identification data into the mask wearing identification model, extracting a characteristic value of the identification data according to the mask wearing identification model, and comparing the characteristic value with a weight characteristic file in the mask wearing identification model to generate an identification category.
5. The method for recognizing a mask in a public place according to claim 4, further comprising: and outputting and displaying the identification type as the type of the unworn mask.
6. A mask recognition system for public use, the system comprising:
the camera is used for acquiring video stream data;
the image acquisition module is used for tracking a target pedestrian in the video stream data and generating pedestrian image data;
the identification module is used for inputting the pedestrian image into a constructed mask wearing identification model and generating the identification category of the pedestrian image data;
wherein the identification categories include a worn mask category, an unworn mask category, and a non-face category.
7. The mask recognition system for public use according to claim 6, wherein the image acquisition module is implemented as:
acquiring image data of the same target pedestrian passing through each camera in the video stream data;
storing the image data as a picture in a JPG format;
and carrying out duplication elimination calculation on the picture to generate pedestrian image data.
8. The mask recognition system for public use according to claim 6, further comprising:
and the display module is used for outputting and displaying the identification type as the type of the unworn mask.
9. Gauze mask recognition device of public place, its characterized in that, the device includes:
a memory storing executable program code;
a processor coupled with the memory;
the processor calls the executable program code stored in the memory to execute the mask recognition method for public places according to any one of claims 1 to 5.
10. A computer storage medium storing computer instructions for performing the method of mask recognition in public places according to any one of claims 1 to 5 when the computer instructions are invoked.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010392248.2A CN111582183A (en) | 2020-05-11 | 2020-05-11 | Mask identification method and system in public place |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010392248.2A CN111582183A (en) | 2020-05-11 | 2020-05-11 | Mask identification method and system in public place |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111582183A true CN111582183A (en) | 2020-08-25 |
Family
ID=72112163
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010392248.2A Pending CN111582183A (en) | 2020-05-11 | 2020-05-11 | Mask identification method and system in public place |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111582183A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113723308A (en) * | 2021-08-31 | 2021-11-30 | 上海西井信息科技有限公司 | Detection method, system, equipment and storage medium of epidemic prevention suite based on image |
| CN114257790A (en) * | 2021-12-21 | 2022-03-29 | 北京睿芯高通量科技有限公司 | Mask early warning method and device in intelligent security system, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106570467A (en) * | 2016-10-25 | 2017-04-19 | 南京南瑞集团公司 | Convolutional neutral network-based worker absence-from-post detection method |
| CN109598186A (en) * | 2018-10-12 | 2019-04-09 | 高新兴科技集团股份有限公司 | A kind of pedestrian's attribute recognition approach based on multitask deep learning |
| CN109815851A (en) * | 2019-01-03 | 2019-05-28 | 深圳壹账通智能科技有限公司 | Kitchen hygiene detection method, device, computer equipment and storage medium |
| CN111062429A (en) * | 2019-12-12 | 2020-04-24 | 上海点泽智能科技有限公司 | Chef cap and mask wearing detection method based on deep learning |
-
2020
- 2020-05-11 CN CN202010392248.2A patent/CN111582183A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106570467A (en) * | 2016-10-25 | 2017-04-19 | 南京南瑞集团公司 | Convolutional neutral network-based worker absence-from-post detection method |
| CN109598186A (en) * | 2018-10-12 | 2019-04-09 | 高新兴科技集团股份有限公司 | A kind of pedestrian's attribute recognition approach based on multitask deep learning |
| CN109815851A (en) * | 2019-01-03 | 2019-05-28 | 深圳壹账通智能科技有限公司 | Kitchen hygiene detection method, device, computer equipment and storage medium |
| CN111062429A (en) * | 2019-12-12 | 2020-04-24 | 上海点泽智能科技有限公司 | Chef cap and mask wearing detection method based on deep learning |
Non-Patent Citations (1)
| Title |
|---|
| 谢征宇 等: "基于视频的轨道交通车站乘客口罩佩戴检测及测温技术", 《专栏 安全与视频》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113723308A (en) * | 2021-08-31 | 2021-11-30 | 上海西井信息科技有限公司 | Detection method, system, equipment and storage medium of epidemic prevention suite based on image |
| CN113723308B (en) * | 2021-08-31 | 2023-08-22 | 上海西井科技股份有限公司 | Image-based epidemic prevention kit detection method, system, equipment and storage medium |
| CN114257790A (en) * | 2021-12-21 | 2022-03-29 | 北京睿芯高通量科技有限公司 | Mask early warning method and device in intelligent security system, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108319926A (en) | A kind of the safety cap wearing detecting system and detection method of building-site | |
| CN111199200A (en) | Wearing detection method and device based on electric protection equipment and computer equipment | |
| CN108053427A (en) | A kind of modified multi-object tracking method, system and device based on KCF and Kalman | |
| CN111353338B (en) | Energy efficiency improvement method based on business hall video monitoring | |
| CN113052107B (en) | Method for detecting wearing condition of safety helmet, computer equipment and storage medium | |
| CN111860187A (en) | High-precision worn mask identification method and system | |
| CN111062281A (en) | Abnormal event monitoring method and device, storage medium and electronic equipment | |
| CN111582183A (en) | Mask identification method and system in public place | |
| CN110751125A (en) | Wearing detection method and device | |
| CN113283369A (en) | Port wharf operating personnel safety protection measure monitoring system and method | |
| CN111325133A (en) | Image processing system based on artificial intelligence recognition | |
| CN115099724A (en) | Monitoring and early warning method, device and equipment for construction scene and storage medium | |
| CN112464850A (en) | Image processing method, image processing apparatus, computer device, and medium | |
| CN115190277A (en) | Safety monitoring method, device and equipment for construction area and storage medium | |
| CN117893779A (en) | Method and system for realizing abnormality identification under building construction based on machine vision | |
| CN113627321A (en) | Image identification method and device based on artificial intelligence and computer equipment | |
| CN114092875A (en) | Operation site safety supervision method and device based on machine learning | |
| CN113628172A (en) | Intelligent detection algorithm for personnel handheld weapons and smart city security system | |
| CN112992372A (en) | Epidemic situation risk monitoring method, device, equipment, storage medium and program product | |
| JPWO2018173947A1 (en) | Image retrieval device | |
| CN112347989A (en) | Reflective garment identification method and device, computer equipment and readable storage medium | |
| CN116682162A (en) | Robot detection algorithm based on real-time video stream | |
| CN114973080A (en) | Method, device, equipment and storage medium for detecting wearing of safety helmet | |
| CN112949606B (en) | Method and device for detecting wearing state of work clothes, storage medium and electronic device | |
| CN115829324A (en) | Personnel safety risk silent monitoring method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200825 |
|
| RJ01 | Rejection of invention patent application after publication |