KR102495004B1 - Disinfection system using thermal image and visible image - Google Patents

Abstract

The present invention uses a camera and a thermal imaging camera to double-detect a person with fever and not wearing a mask among visitors, and at the same time, when an event occurs, warning information is displayed to prevent the spread of infectious diseases such as viruses and bacteria from the outside. It can effectively prevent heat dissipation to maximize the effectiveness of heat dissipation, analyze the image acquired by the camera to detect the facial pattern feature of the visitor, but detect the facial pattern feature, which is the pattern feature of the upper area centered on the eyes of the face. After that, it is configured to perform user authentication by comparing it with the previously registered registration DBs, so that the user can authenticate without removing the mask separately to perform user authentication. It is possible to effectively prevent unnecessary authentication time delay due to separation, and since the components such as camera, thermal imaging camera, speaker, and LED light are manufactured in one piece, miniaturization is possible and manufacturing and operating costs can be reduced. It relates to a quarantine system using images and videos.

Description

Disinfection system using thermal image and visible image}

The present invention relates to a quarantine system using thermal imaging and video, and more specifically, detects whether a person has a fever and whether a person is wearing a mask using a camera and a thermal imaging camera, and at the same time performs user authentication by utilizing the facial pattern characteristics of the person In addition, when authentication fails, a person with fever or a person not wearing a mask is detected, warning information is displayed to the outside, enabling double detection and crackdown on persons with fever or not wearing a mask among visitors, effectively preventing the transmission of viruses and bacteria from the outside. It relates to a quarantine system using thermal imaging and video that can maximize quarantine efficiency by doing so.

Recently, various highly contagious infectious diseases such as Corona 19, Middle East Respiratory Syndrome (MERS), Severe Acute Respiratory Syndrome (SARS), and avian influenza (AI) have been As it appears, various studies are being conducted on a quarantine system to prevent the spread of infectious diseases.

These infectious diseases are manifested in the body in various ways, but since they are most commonly accompanied by high fever, thermal imaging cameras are installed at the entrances and exits of airports, various buildings, government offices, hospitals, etc. It is a trend that the introduction of a quarantine system that detects high fever among those entering through the system is increasing.

Typically, since these infectious diseases have a characteristic of rapid transmission through human saliva, breathing, coughing, etc., wearing a mask is being taken as the most basic countermeasure that can significantly reduce the contagiousness and transmission rate of infectious diseases.

However, the conventional quarantine system can detect fever among visitors using a thermal image camera, but has a disadvantage in that the quarantine efficiency is low because the technology and method for detecting whether or not the visitor is wearing a mask are not configured.

On the other hand, as the importance of security has recently emerged along with informatization and the biometric technology and electronic device industry have developed, a user authentication system that permits access to a specific space only for authorized users (User authentication system) this is widely used.

In particular, since facial patterns have not only unique characteristics for each person, but also have inflexible characteristics, various studies are being conducted on facial authentication systems that authenticate users using facial patterns, which are physiological characteristics unique to humans.

However, as the importance of wearing a mask has recently increased, most of the visitors wear a mask, and accordingly, when performing user authentication through the face authentication system, the person takes off the mask separately from the face to take a picture, When the authentication is completed, the task of putting the separated mask back on the face is necessarily performed, which makes the authentication work cumbersome and complicated, as well as delays the authentication time, and causes problems in convenience and efficiency of use.

That is, 1) double detection and crackdown on people with fever and non-wearing masks among visitors, 2) authentication is possible without requiring the user to separately attach and detach the mask during user authentication, and 3) quarantine that can maximize user authentication speed Research on the system is urgently needed.

1 is a diagram showing a construction form of a fever detection system disclosed in Korean Patent Registration No. 10-2091121 (Title of Invention: Arrival Fever Detection System).

The fever detection system (hereinafter referred to as the prior art) 100 of FIG. 1 includes a plurality of thermal cameras C1 to C12 for detecting the body temperature of an entrant moving along an immigration route, and a plurality of thermal cameras C1 to C12. A central control device 110 that collects, processes, and monitors images taken by C12), and a thermal camera test unit for testing whether each thermal camera (C1 to C12) is normal or abnormal and sensor sensitivity ( not shown).

At this time, the prior art 100 assumes a situation in which entrants sporadically move from a plurality of different gates (G1, G2~), and a plurality of thermal cameras (C1 to C12) detect entrants moving along the entry flow path. It has a form of continuous shooting.

The central control device includes an alarm that generates an alarm when the body temperature of the entrant detected by the plurality of thermal cameras C1 to C12 is within a preset reference temperature range.

In the prior art 100 configured as described above, by installing a plurality of thermal cameras (C1 to C12) at a distance along the entry flow path of the entrant, data is collected over the entire length of the entry flow of the entrant to obtain body temperature information for all entrants. It can be easily obtained, and has the advantage of preventing the spread of endemic diseases abroad in advance by detecting the fever of the entrant.

However, when the prior art 100 is applied to entrances and exits of buildings, etc., it is possible to detect a fever among visitors using thermal cameras (C1 to C12), but no technology and method for detecting a person not wearing a mask have been described. Therefore, the prevention rate and quarantine efficiency of infectious diseases are reduced.

Even if a mask recognition system and a face authentication system are applied to the prior art 100, in order to perform mask recognition and face authentication in the prior art 100, authentication must be performed while the person's mask is detached. In addition to being cumbersome and complicated, authentication time is delayed, and problems such as poor usability and efficiency occur.

In addition, since the prior art 100 simply compares facial pattern features detected through facial imaging with pre-registered registration information in a fixed order or randomly, the greater the number of registered registration information, the greater the number. There is a problem that the authentication time increases.

The present invention is to solve this problem, and the problem of the present invention is to double detect a person with a fever and a person not wearing a mask among visitors using a camera and a thermal imaging camera, and at the same time, when an event occurs, warning information is displayed to the outside. It is to provide a quarantine system using thermal imaging and video that can effectively prevent transmission of infectious diseases such as viruses and bacteria from the outside and thereby maximize heat radiation efficiency.

In addition, another problem of the present invention is to analyze the image obtained by the camera to detect the facial pattern feature of the visitor, but after detecting the facial pattern feature, which is the pattern feature of the upper area centered on the eyes of the face, By being configured to perform user authentication by comparing with registered registration DBs, authentication is possible without the person having to take off or attach a mask separately to perform user authentication, increasing the convenience and efficiency of the authentication process and unnecessary unnecessary wear and tear of the mask. It is to provide a quarantine system using thermal images and video that can effectively prevent authentication time delay.

In addition, another problem of the present invention is that components such as a camera, a thermal imaging camera, a speaker, and an LED light are integrally manufactured, so that miniaturization is possible as well as manufacturing and operation costs can be reduced by using thermal images and images. It is to provide a quarantine system.

In addition, another problem of the present invention is configured to compare and contrast registration DBs in response to the access status of users during user authentication, so that the authentication speed can be significantly increased and unnecessary calculation processing can be prevented. It is to provide a quarantine system using thermal imaging and video.

The solution of the present invention for solving the above problems is in the quarantine system including an access detector installed at the entrance of an indoor space to detect people entering and leaving: the access detector includes a bracket; A camera including a photographing device rotatably coupled to the bracket, wherein the photographing device acquires an image by photographing a person's face; A thermal imaging camera that obtains a thermal image by heat-tracking and detecting the face of the person entering the room; Display means for outputting preset warning information to the outside; By analyzing the thermal image obtained by the thermal imaging camera, the body temperature of the visitor is measured to detect whether the visitor has fever, and at the same time, the image obtained by the camera is analyzed to detect whether the visitor is wearing a mask, and the fever of the visitor is detected. When this is detected or the person who is not wearing a mask, the controller further includes a control unit that outputs warning information through the display means, wherein the control unit takes an image as an input value and detects the presence or absence of a mask object of the person as an output value. memory in which algorithms are stored; an object recognition and facial pattern feature detection unit that analyzes the image acquired by the camera using a preset object detection algorithm and outputs object detection data indicating the presence or absence of a mask object; a mask-wearing or non-mask determination unit for determining whether or not the visitor is wearing a mask through the object detection data detected by the object recognition and facial pattern feature detection unit; When it is determined that the person wearing a mask is determined by the mask wearing determination unit, it is determined to allow the person to enter and exit, and when the mask wearing or not wearing judgment unit determines that the person is not wearing a mask, the entry and exit of the person is controlled. The feature detection algorithm takes an image as an input value and outputs not only object detection data indicating the presence or absence of a mask object of the visitor, but also facial pattern feature information, which is the feature information of the person's face. In the memory, registration DBs in which information of users allowed to enter and facial pattern feature information are matched are preset and stored, and the object recognition and facial pattern feature detection unit analyzes the image acquired by the camera using the object detection algorithm. to detect the object detection data indicating the presence or absence of a mask object and the face pattern feature information of the visitor, and the control unit compares the face pattern feature information detected by the object recognition and face pattern feature detection unit with previously registered registration DBs and Further comprising a user authentication unit that compares and determines whether the accessor is an authorized user, and the access determination unit determines that the accessor is a non-heated person and at the same time determines that the accessor is a mask wearer by the mask wearer determination unit, and the user authentication unit When it is authenticated by, it is determined to allow the entry of the visitor, but when the visitor is determined to be a person with fever, or the person is not wearing a mask by the mask determination unit, or the user authentication unit fails authentication, the access of the person In the memory, preset sectors, categories that are sub-components constituting each sector, and authentication sequence information, which is the order of the sectors, are preset and stored in the memory, and the user authentication unit presets a registration DB sorting unit which is executed every second period (T2) and sorts the registration DBs; an authentication processing unit for performing authentication by sequentially comparing and contrasting the facial pattern feature information detected by the object recognition and facial pattern feature detection unit with the registration DB sorted by the registration DB sorting unit; When authentication is successful in the authentication processing unit, authentication information including user information that has been authenticated, time required for authentication processing (t), and category information for each sector corresponding to the time of authentication is generated. , An authentication information generation unit for storing the generated authentication information in the memory, and an update module for substituting the current status information into the category of each sector in the registration DB sorting unit in a preset authentication order; An access status information generation module that generates access status information consisting of the number of authentication times (N) for each sector of pre-registered users by utilizing authentication information; a matching data generation module for generating matching data by matching the access status information generated by the access status information generation module with pre-registered registration DBs based on user information; According to the latest authentication order, which is the authentication order to which the contents of the current state are applied by the update module, a weight proportional to the order is assigned to each sector, and then the latest authentication order for each user is obtained by utilizing the matching data generated by the matching data generation module. The weight of the sector is multiplied by the number of authentications in the same category as the category of each sector in the latest authentication sequence, and the number of authentications in categories that are not the same as the category of each sector in the latest authentication order is multiplied by the weight '1', and then summed up. a weighted score calculation module for calculating a weighted score for each user; and a sorting DB generation module for generating a sorting DB by arranging pre-registered registration oils according to the size of the weighted score calculated by the weighted score calculation module, and then storing the sorted DB in the memory, wherein the user authentication unit An authentication order setting unit that is executed every one cycle (T1) is further included, and the authentication order setting unit includes a determination module and an authentication module for each order combination, wherein the determination module searches for authentication information stored in the memory to transfer from the present A data extraction module extracts authentication information that has been authenticated during the period T-1, and authentication required times t of the authentication information during the previous period T-1 from the present extracted by the data extraction module If the average value calculated by the average value calculation module is greater than or equal to a predetermined threshold value, it is determined that the authentication sequence information does not need to be reset, but if the average value is less than the threshold value, the authentication sequence information and a resetting determining module for determining that resetting is necessary, and the authentication module for each sequence combination is executed when the determining module determines that resetting of the authentication sequence is necessary, and during the previous period (T-1) stored in the memory. A test sample extraction module that searches for biopattern features of authenticated users and randomly extracts n test samples from among them; an authentication order combination module that configures order combinations that can be formed by combining the order of sectors; In the same manner as the update module of the registration DB sorting unit, the access status information generating module, the matching data generating module, the weighted score calculation module, and the sorting DB generating module, sorting DBs are created for each order combination, and at the same time, the test An authentication execution module that compares and compares the test patterns extracted by the sample extraction module with the generated alignment DBs, and the time required for each test pattern to be authenticated using each alignment DB by the authentication execution module. After calculating the authentication time (t), a data calculation module for each order combination that calculates the average value of the authentication time (t) of the test patterns for each sorted DB, and each order combination and an authentication sequence information reset module for resetting an order combination having the highest average value as an authentication order by comparing average values input from the data calculation module, and the update module of the registration DB sorting unit is reset by the authentication order information reset module. It is characterized in that the content of the current state is substituted into the category of each sector according to the established authentication sequence.

In the present invention, the quarantine system further includes gate devices on which the brackets of the access detector are installed, and the control unit 1) opens the access door with the gate device when the person wearing a mask is not a fever person. 2) It is preferable to output a control signal to close the entrance and exit door with the gate device when an intruder has a fever or is not wearing a mask.

In addition, in the present invention, the control unit may include a thermal image analysis unit that analyzes a thermal image obtained by the thermal image camera; After measuring the body temperature (°C) of the visitor through the analysis data detected by the thermal image analyzer, the measured body temperature (°C) is compared with a preset reference value, and if the body temperature (°C) is less than the reference value, the visitor is considered to have no fever. However, if the body temperature (℃) is higher than the reference value, a fever determination unit for determining the visitor as a fever; a control signal generator for generating a control signal according to the data determined by the entry/exit determination unit; The control module further includes a control module that transmits the control signal generated by the control signal generation unit to a corresponding gate device, and the entry/exit determination unit determines whether the person is wearing a mask when the fever determination unit determines that the person has no fever. When the visitor is determined to be wearing a mask, it is determined to allow the person to enter, but when the fever determination unit determines that the person has fever or the mask wearing determination unit determines that the person is not wearing a mask, It is desirable to decide to control the access of.

delete

delete

According to the present invention having the above problems and solutions, a camera and a thermal imaging camera are used to double detect fever and non-mask wearers among visitors, and at the same time, when an event occurs, warning information is displayed to the outside, thereby preventing viruses and viruses from the outside. It is possible to effectively prevent transmission of infectious diseases such as bacteria to maximize heat radiation efficiency.

In addition, according to the present invention, the image obtained by the camera is analyzed to detect the facial pattern feature of the visitor, but after detecting the facial pattern feature, which is the pattern feature of the upper area centered on the eyes of the face, and then registering the previously registered As it is configured to perform user authentication compared to DBs, it is possible to authenticate without having to remove the mask separately for the user authentication to perform user authentication, increasing the convenience and efficiency of the authentication process and at the same time reducing unnecessary authentication time due to wearing and removing the mask. can be effectively prevented.

In addition, according to the present invention, as components such as a camera, a thermal imaging camera, a speaker, and an LED light are integrally manufactured, not only miniaturization is possible, but also manufacturing and operating costs can be reduced.

In addition, according to the present invention, when user authentication is performed, registration DBs are configured to compare and contrast in response to the access status of users, so that the authentication speed can be significantly increased and unnecessary calculation processing can be prevented.

1 is a diagram showing a construction form of a fever detection system disclosed in Korean Patent Registration No. 10-2091121 (Title of Invention: Arrival Fever Detection System).
2 is a configuration diagram showing a quarantine system according to an embodiment of the present invention.
3 is an exemplary view of FIG. 2 .
FIG. 4 is a block diagram illustrating the non-contact type access detector of FIG. 2 .
5 is an exemplary view of FIG. 4 .
6 is another exemplary view of FIG. 4 .
FIG. 7 is a block diagram illustrating a photographing device of FIG. 4 .
8 is an exemplary view of FIG. 7 .
9 is another exemplary view of FIG. 7 .
FIG. 10 is an exemplary diagram illustrating an image acquired by the camera of FIG. 7 .
FIG. 11 is an exemplary diagram illustrating a thermal image obtained by heat-detection and tracking of the thermal imaging camera of FIG. 7 .
12 is a block diagram illustrating a control unit of FIG. 7 .
FIG. 13 is a block diagram illustrating an object recognition and facial pattern feature detection unit of FIG. 12 .
FIG. 14 is a block diagram illustrating a second embodiment of a control unit of FIG. 12 .
FIG. 15 is a block diagram illustrating a second user authentication unit of FIG. 14 .
16 is a block diagram illustrating a registration DB sorting unit of FIG. 15 .
FIG. 17 is a block diagram illustrating an authentication order setting unit of FIG. 15 .

Hereinafter, an embodiment of the present invention will be described with reference to the accompanying drawings.

2 is a configuration diagram showing a quarantine system according to an embodiment of the present invention, and FIG. 3 is an exemplary view of FIG. 2 .

The quarantine system (1), which is an embodiment of the present invention, 1) maximizes the prevention rate of infectious diseases and quarantine efficiency by double detecting and cracking down on those who have a fever and those who do not wear a mask among the entrants, and 2) user authentication using facial recognition When a user is authenticated by adding a function, it is configured so that face authentication is possible without the user separately attaching or detaching the mask, which simplifies unnecessary authentication procedures and increases convenience of use. 3) Used for face authentication at every set cycle (T) This is to maximize the authentication speed by giving priority to pre-registered registration information (registration DB) to be compared, and then performing a matching operation during face authentication according to the assigned priority.

In addition, as shown in FIGS. 2 and 3, the quarantine system 1 of the present invention is installed at each of the entrances 930 of indoor spaces S such as airports, various buildings, government offices, hospitals, etc. It is installed in each of the gate devices 5-1, ..., (5-N) and the gate devices 5-1, ..., (5-N) that open and close the door according to authentication. Non-contact access detectors (3-1), ..., (3 -N) consisting of

At this time, in the present invention, for convenience of description, each of the non-contact type access detectors (3-1), ..., (3-N) analyzes images and thermal images, determines whether fever is present, determines whether a mask is worn, and performs calculations such as user authentication. Although the processing has been described as being performed by itself as an example, it is natural that such calculation processing may be configured to be performed in a controller or local server installed in the corresponding indoor space (S) or in a separate central management server.

The gate devices (5-1), ..., (5-N) are installed in the entrances and exits (930) of the indoor space (S), respectively, and control the access door according to the control of the non-contact type access detector (3) for access control. It opens and closes to control and crack down on the access of visitors.

Since the structures and shapes of these gate devices 5-1, ..., 5-N are already widely used technologies, various structures and shapes of known gate devices can be applied.

4 is a block diagram showing the non-contact type access detector of FIG. 2, FIG. 5 is an example view showing a reduced vertical arm of the housing of FIG. 4, and FIG. 6 is an example showing an expanded vertical arm of FIG. It is also

As shown in Figs. It consists of a photographing device 30 that is installed as possible.

The housing 32 includes a fixing plate 321, vertical arms 323, and brackets 325.

The fixing plate 321 is formed of a disk-shaped plate material, and its lower surface is seated on the ground or a structure.

At this time, a power supply means such as a battery is installed inside the fixing plate 321 .

The vertical arms 323 are installed vertically on the upper surface of the fixing plate 321 and are coupled to be extendable/retractable in the height direction. At this time, since a configuration in which a plurality of pipes or frames are combined to be able to be reduced or extended is a configuration that is already widely used, a detailed description thereof will be omitted.

Also, a bracket 325 is rotatably coupled to an upper end of an upper vertical arm among the vertical arms 323 .

The bracket 325 is rotatably installed on the upper end of the upper vertical arm, and the photographing device 30 is seated thereon.

FIG. 7 is a block diagram illustrating the photographing device of FIG. 4 , FIG. 8 is an example view of FIG. 7 , and FIG. 9 is another example view of FIG. 7 .

The photographing device 30 is installed to enable forward and backward angle adjustment by being seated on the bracket 325 of the housing 32 .

In addition, as shown in FIGS. 7 to 9 , the photographing device 30 includes a case 32 in which a display panel 321 is installed on the front side, and a device installed on the front side of the case 32 to capture an image of a visitor. A camera 31, a Time Of Flight (TOF) sensor 33 installed on the front of the case 32, and a heat sensor 33 installed on the top of the case 32 to heat-detect and track the person entering and exiting the room to obtain a thermal image. An image camera 34, a speaker 35 installed on the lower part of the case 32 to output guidance and warnings, an LED unit 36 installed on the front of the case 32 and turned on, and a case It is installed inside 32 and consists of a controller 300 that manages and controls the operation of these components 31, 33, 34, 35, and 36.

At this time, in the present invention, for convenience of explanation, the structure and shape of the non-contact access detector 3 and the photographing device 30 have been described as being configured as shown in FIGS. 5 and 6 as an example, but the non-contact type access detector 3 and the photographing device The structure and shape of (30) is not limited thereto, and may be configured in various structures and shapes.

FIG. 10 is an exemplary diagram illustrating an image obtained by photographing by the camera of FIG. 7 , and FIG. 11 is an exemplary diagram illustrating a thermal image obtained by thermal detection and tracking of the thermal imaging camera of FIG. 7 .

The camera 31 is installed on the front of the case 32, captures the face of a visitor, obtains an image 910 of FIG. 7, and outputs the obtained image 910 to the controller 300.

At this time, the camera 31 is installed with PTZ (Pan-Tilt-Zoom) set so that the face of the person located at the entrance door of the gate device 5 is photographed.

The thermal imaging camera 34 is installed on the upper part of the case 32 to heat-detect and track the face of the visitor to obtain a thermal image 920, and output the obtained thermal image 920 to the controller 300. .

At this time, the thermal imaging camera 34 is installed with PTZ (Pan-Tilt-Zoom) set so that the face of the person located at the entrance door of the gate device 5 is heat-detected.

The TOF sensor 33 is composed of light transmitters (not shown) that radially emit N optical signals and light receivers (not shown) that receive reflected waves emitted by the light transmitters, and the transmitted and received optical signals. Information is output to the control unit 300 .

That is, since the optical signal information transmitted and received by the TOF sensor 33 of the present invention (hereinafter referred to as TOF information) has different values depending on the size and depth (Length) of the visitor's face, the control unit 300 is configured to use the TOF sensor ( 33), the input TOF information can be analyzed and used for facial pattern feature information.

12 is a block diagram illustrating a control unit of FIG. 7 .

The controller 300 of FIG. 12 is a microprocessor installed inside the case 32 to manage and control the operation of the components 31, 33, 34, 35, and 36.

In addition, as shown in FIG. 12, the control unit 300 includes a control module 301, a memory 302, a communication interface unit 303, an object recognition and facial pattern feature detection unit 304, and a thermal image analysis unit 305. ), fever determination unit 306, mask wearing determination unit 307, user authentication unit 308, access determination unit 309, opening/closing control signal generation unit 310, warning information output unit 311 , a display unit 312, an electronic access list management unit 313, and an untact manager management unit 314.

The control module 301 is an O.S (Operating System) of the control unit 300, and the control target 302, 303, 304, 305, 306, 307, 308, 309 ), (310), (311), (312), (313), (314) to manage and control.

In addition, the control module 301 inputs images and TOF information input from the camera 31 and the TOF sensor 33 to the object recognition and facial pattern feature detection unit 304 through the communication interface unit 303 .

Also, the control module 301 inputs the thermal image input from the thermal image camera 34 to the thermal image analyzer 305 .

In addition, the control module 301 inputs result data detected by the fever determination unit 306 , the mask wearing determination unit 307 , and the user authentication unit 308 to the entry/exit determination unit 309 .

In the memory 302 , images acquired by the camera 31 , the thermal imaging camera 34 , and the TOF sensor 33 , thermal images, and TOF information are temporarily stored.

In addition, a preset feature detection algorithm is stored in the memory 302 .

At this time, the feature detection algorithm is a general machine learning algorithm that can be learned, and in detail, by using the image and TOF information as input values, and analyzing the input values using the learned model, It is an algorithm that detects an object of the detected face object and outputs facial pattern feature information, which is a pattern feature of the upper region centered on the eyes of the detected face object.

Also, pre-registered registration information (registration DB) is stored in the memory 302 . At this time, the registration DB means the facial pattern characteristic information of the person who is allowed to enter.

The communication interface unit 303 inputs and outputs data to and from the camera 31 , the thermal imaging camera 34 , and the TOF sensor 33 .

Also, the communication interface unit 303 transmits and receives data to and from external servers and devices.

FIG. 13 is a block diagram illustrating an object recognition and facial pattern feature detection unit of FIG. 12 .

As shown in FIG. 13, the object recognition and facial pattern feature detection unit 304 includes an image input module 341, a TOF information input module 342, and an analysis module 343.

The image input module 341 receives an image acquired by the camera 31 through the communication interface 303 under the control of the control module 301 .

The TOF information input module 342 receives TOF information input from the TOF sensor 33 through the communication interface unit 303 under the control of the control module 301 .

The analysis module 343 analyzes the input image and TOF information using a preset feature detection algorithm to detect objects such as a face, mask, and glasses, and at the same time detects facial pattern feature information, which is a feature of the detected face object. do.

At this time, the feature detection algorithm is a general machine learning algorithm that can be learned, and in detail, by using the image and TOF information as input values, and analyzing the input values using the learned model, It is an algorithm that detects an object of the detected face object and outputs facial pattern feature information, which is a pattern feature of the upper region centered on the eyes of the detected face object.

That is, the present invention is configured to detect the pattern features of the upper region centered on the eyes of the face object, rather than detecting the pattern features of the entire face using the feature detection algorithm, so that the person wearing and removing the mask separately Since user authentication is possible without having to perform user authentication, it is possible to authenticate without having to remove the mask separately to perform user authentication, increasing the convenience and efficiency of the authentication process and effectively preventing unnecessary delay in authentication time due to wearing and removing the mask. has the advantage of being able to

In addition, the control module 301 inputs the object detection data detected by the analysis module 343 to the mask wearing determination unit 307, and the facial pattern feature information detected by the analysis module 343 is input to the user authentication unit ( 308).

The thermal image analysis unit 305 analyzes the thermal image obtained by thermal detection and tracking of the thermal image camera 34 .

At this time, the analysis data detected by the thermal image analyzer 305 is input to the heat determination unit 306 according to the control of the control module 301 .

The fever determination unit 306 measures the body temperature (°C) of the visitor through the analysis data detected by the thermal image analysis unit 305 .

In addition, the fever determination unit 306 compares the measured body temperature (° C.) with a preset reference value, and if the body temperature (° C.) is less than the reference value, the visitor is judged as having no fever, but if the body temperature (° C.) is greater than the reference value, The person entering the room is judged as having a fever.

In addition, the heat determination unit 306 outputs the detected determination data to the access determination unit 309 .

At this time, the control module 301 operates the warning information output unit 311 when it is determined that the visitor is a person with heat by the heat determination unit 306 .

The mask-wearing or non-wearing determination unit 307 utilizes and analyzes the object detection data input from the object recognition and facial pattern feature detection unit 304 to determine whether the entrant is wearing a mask.

In addition, if the mask object is included in the object detection data, the mask wearing determination unit 307 determines that the visitor is wearing a mask, but if the object detection data does not include a mask object, it is determined that the visitor is not wearing a mask. do.

In addition, the mask wearing or non-wearing determination unit 307 outputs the detected determination data to the entry/exit determination unit 309 .

At this time, the control module 301 operates the warning information output unit 311 when it is determined that the visitor is not wearing a mask by the mask wearing determination unit 307 .

The user authentication unit 308 compares and contrasts the facial pattern feature information input from the object recognition and facial pattern feature detection unit 304 with previously registered registration DBs to authenticate whether the person entering the room is an authorized user.

In addition, the user authentication unit 308 determines that user authentication has succeeded if the accessor is an authorized user, but determines that user authentication has failed if the accessor is not an authorized user.

In addition, the user authentication unit 308 outputs the detected authentication result to the access decision unit 309 .

At this time, the control module 301 operates the warning information output unit 311 when it is determined by the user authentication unit 308 that user authentication of the visitor has failed.

The entry/exit determination unit 309 determines whether 1) the person with fever is judged by the fever determination unit 306, 2) the person wearing a mask is judged to be a non-wearing person by the mask determination unit 307, or 3) the user authentication unit 308 ), when the user authentication of the visitor fails, it is determined to control the access of the corresponding visitor, and the detected decision data is output to the opening/closing control signal generator 310.

In addition, the entry/exit determination unit 309 determines that 1) the person with no fever is determined by the fever determination unit 306, 2) the person wearing a mask is determined by the mask wearing determination unit 307, and 3) user authentication When user authentication of the visitor succeeds in the unit 308, it is determined to allow the person to enter and exit, and outputs the detected decision data to the opening/closing control signal generating unit 310.

The opening/closing control signal generation unit 310 generates a control signal for closing the entrance/exit door 51 of the gate device 5 when it is determined by the entrance/exit determination unit 309 to control the entry/exit of the corresponding visitor.

In addition, the opening/closing control signal generation unit 310 generates a control signal for opening the entrance door 51 of the gate device 5 when it is determined in the entrance/exit determination unit 309 that the entrance of the corresponding person is allowed.

At this time, when the control signal is generated by the opening and closing control signal generator 310, the control module 301 controls the communication interface 303 to transmit the generated control signal to the gate device 5, so that the gate device 5 ) is that the access door 51 is opened and closed under the control of the control module 301.

The warning information output unit 311 1) outputs a pre-registered first guide and warning comment to the outside through the speaker 35 when the person who has entered the room is determined to be a person with fever by the heat determination unit 306 .

In addition, the warning information output unit 311 outputs a pre-registered second guide and warning to the outside through the speaker 35 when 2) the mask wearer determination unit 307 determines that the visitor is not wearing a mask. .

In addition, the warning information output unit 311 outputs a pre-registered third guidance and warning to the outside through the speaker 35 when 3) the user authentication by the user authentication unit 308 fails.

The display unit 312 displays images, thermal images, and pre-produced content through the display panel 321 of the case 32 .

The electronic access list management unit 313 generates a list of visitors who have passed through the corresponding gate device 5 and then stores it in an external security server, so that quarantine management and epidemiological investigation can be easily performed.

In addition, the electronic access list management unit 313 includes a QR code reader and is configured to collect visitor information through reading the QR code exposed on the smartphone of the visitor.

The untact manager management unit 314 manages and controls the untact manager, which is an application that provides an editing interface such as adding, updating, and deleting information of a registration DB to an administrator.

At this time, Untack Manager provides the user with a graphical user interface (GUI, Graphic User Interface) that allows the user to add, edit, and delete registration DB data, so that the user can conveniently edit the registration DB through Untack Manager. You will be able to do it.

FIG. 14 is a block diagram illustrating a second embodiment of a control unit of FIG. 12 .

The second control unit 400 of FIG. 14 is a second embodiment of the control unit of the photographing device 30 of the present invention.

In addition, the second control unit 400 includes the communication interface unit 303, the object recognition and facial pattern feature detection unit 304, the thermal image analysis unit 305, and the fever determination unit 306 of the control unit 300 of FIG. 12 described above. ), a mask wearing determination unit 307, an entry/exit determination unit 309, an opening/closing control signal generating unit 310, a warning information output unit 311, and a display unit 312.

In addition, the second control unit 400 further includes a second control module 401, a second memory 402, and a second user authentication unit 408.

The second control module 401 performs the same operation as the control module 301 of FIG. 12 described above, but executes the registration DB sorting unit 45 of FIG. 16 every second predetermined period T2.

In addition, the second control module 401 executes the authentication sequence setting unit 46 of FIG. 15 to be described later for every preset first cycle T1. At this time, the authentication sequence information refers to the preset authentication sequence of each sector, and the authentication sequence information set by the authentication sequence setting unit 46 is used by the registration DB sorting unit 45 . At this time, the sector means a type that can classify the authentication result, and each sector includes a plurality of categories that are sub-components of the corresponding sector.

For example, the sector can be set to 'time zone', 'day of the week', and 'date', and the category of the 'time zone' sector is '0:00 ~ 02:00', ..., '22:00 ~ 24:00'. The category of the 'day of the week' sector may be composed of 'Mon', 'Tue', 'Wed', 'Thu', 'Fri', 'Sat', and 'Sun', and the 'date' sector The category may be composed of '1 day', '2 days', ..., '30 days', '31 days'.

In the second memory 402, registration DB (registration information) of pre-registered users is preset and stored like the memory 302 of FIG. 12 described above. At this time, the registration DB is stored in the second memory 402 by converting the user information of the previously registered user and the facial pattern feature information of the corresponding user into a DB.

In addition, authentication information generated by the authentication information generator 44 of FIG. 15 to be described later is stored in the second memory 402 . At this time, the access status information includes user information that has been authenticated, required time for authentication, and category content of each sector where authentication has been performed.

In addition, the second memory 402 stores a sorting DB, which is a registration DB sorted by the registration DB sorting unit 45 of FIG. 16 to be described later.

In addition, the second memory 402 stores authentication sequence information set by the authentication sequence setting unit 46 of FIG. 15 to be described later.

15 is a block diagram illustrating a second user authentication unit of FIG. 14 .

As shown in FIG. 15, the second user authentication unit 408 includes an authentication processing unit 43, an authentication information generating unit 44, a registration DB sorting unit 45, and an authentication order setting unit 46.

The authentication processing unit 43 is a processor that performs user authentication.

In addition, the authentication processing unit 43 sequentially compares and contrasts the facial pattern feature information input from the object recognition and facial pattern feature detection unit 304 and the sorted DBs sorted by the registration DB sorting unit 45 to detect similarities. do. At this time, since the technology and method for detecting the similarity of the specific pattern of the subject is a technology commonly used in a biometric authentication system, a detailed description thereof will be omitted.

In addition, the authentication processing unit 43 1) determines that the two data do not match if the similarity between the two data is less than a preset threshold, 2) determines that the two data match if the similarity of the two data exceeds the threshold, When a sorted DB having a similarity equal to or greater than the threshold value is detected, it is determined that authentication has succeeded, and authentication is terminated.

In addition, the authentication result (authentication success or authentication failure) information detected by the authentication processing unit 43 is input to the authentication information generation unit 44 .

When authentication is successful by the authentication processing unit 43, the authentication information generation unit 44 displays the user information of the corresponding person, the time required for authentication (t), and the category for each sector where authentication was performed (date of authentication, day of the week of authentication, authentication time) content is matched to generate authentication information.

The registration DB sorting unit 45 is executed according to the control of the second control module 401 at every second predetermined period T2 .

16 is a block diagram illustrating a registration DB sorting unit of FIG. 15 .

As shown in FIG. 16, the registration DB sorting unit 45 includes an update module 451, an entry/exit status information generating module 452, a matching data generating module 453, a weighted score calculation module 454, and a sorting DB. It consists of a generating module 455.

The update module 451 substitutes the current state (current time, today's day, today's date) into the category of each sector in the authentication order set by the authentication order setting unit 46. At this time, the authentication sequence to which the current state is substituted will be referred to as the latest authentication sequence. For example, assuming that the authentication sequence of authentication sequence information is 1) time, 2) day of the week, and 3) date, and the current status is '10~11:00', 'Saturday', '14th', update module (451) substitutes the current status for the authentication sequence information and updates it in the latest authentication sequence of 1) 10 to 11 o'clock, 2) Saturday, and 3) the 14th.

The access status information generation module 452 utilizes the authentication information stored in the second memory 402 to generate access status information consisting of the number of authentication times (N) for each category of each sector of pre-registered users.

For example, access status information includes user information (A), time range (13 to 14 o'clock: 5 times, 23 to 24 o'clock 12 times), day of the week (Monday: 9 times, Wednesday: 1 time, Friday: 7 times) .

The matching data generation module 453 generates matching data by matching the access status information generated by the access status information generation module 452 with pre-registered registration DBs on a user basis.

The weighted score calculation module 454 assigns a weight to each sector according to the latest authentication order updated by the update module 451, but only to the category of each sector in the current state. In this case, the weight has a higher value when the authentication order is higher, and a lower value when the authentication order is lower.

For example, assuming that the latest authentication order information is 1) 10 to 11 o'clock, 2) Saturday, and 3) the 14th, the weighted score calculation module 454 determines that the current state of the 'time' sector, which is the highest priority, is The applied category '10~11:00' is given the highest weight 'A', and the next highest weighted 'B' (B < A ), and the lowest weight, 'C' (C<B<A), is assigned to '14 days', which is the category to which the current state of the 'date' sector, which is the last order, is applied.

In addition, the weighted score calculation module 454 uses the matching data generated by the matching data generation module 453 to multiply the number of authentication times of the same category as the category content of each sector in the latest authentication order for each user by a weight, and then add them up In this way, a weighted score is calculated for each user. At this time, the category content of each sector in the latest authentication sequence and the number of authentication times in other categories are multiplied by the integer ‘1’ (1<C<B<A).

The sorting DB generation module 455 sorts the previously registered registration DBs according to the size of the weighted score calculated by the weighted score calculation module 454 to create a sorting DB. At this time, the generated sorting DBs are stored in the second memory 402 and used for authentication of the authentication processing unit 43 .

The authentication sequence setting unit 46 is executed according to the control of the second control module 402 for each preset first cycle T1.

FIG. 17 is a block diagram illustrating an authentication order setting unit of FIG. 15 .

As shown in FIG. 17, the authentication order setting unit 46 includes a determination module 461 and an authentication module 463 for each order combination.

The decision module 461 determines whether resetting of the authentication sequence is necessary.

In addition, the determination module 461 includes a data extraction module 4611, an average value calculation module 4612, and a reset determination module 4613.

The data extraction module 4611 searches for authentication information stored in the second memory 402 and extracts authentication information that has been authenticated during the previous period (T-1) from the present.

The average value calculation module 4612 extracts authentication required times (t) of authentication information for a period (T-1) from the present extracted by the data extraction module 4611 and calculates an average value thereof.

The resetting determination module 4613 determines that if the average value calculated by the average value calculation module 4612 is greater than or equal to a preset threshold value, resetting the authentication sequence information is not necessary, but if the average value is less than the threshold value, resetting the authentication sequence information is performed. judge it necessary At this time, the threshold is defined as the minimum value of the authentication time required to determine that priority information needs to be reset.

In addition, if the second control module 401 determines that the resetting of the authentication sequence is not necessary by the determination module 461, a separate operation is not performed and the authentication sequence of the previous cycle (T-1) is used as it is, but resetting If it is determined that this is necessary, the authentication module 463 for each sequence combination is executed.

The authentication module 463 for each sequence combination is driven when the determination module 461 determines that the authentication sequence needs to be reset.

The authentication module 463 for each sequence combination includes a test sample extraction module 4631, an authentication sequence combination module 4632, an authentication execution module 4633, a data calculation module for each sequence combination 4634, and an authentication sequence information resetting module 4635. ) is made up of

The test sample extraction module 4631 searches for facial pattern features of authenticated users during the previous period T-1 stored in the second memory 402 and randomly extracts n test samples from among them. That is, the test sample extraction module 4631 randomly extracts facial pattern features of those who have performed user authentication during the previous period (T-1).

The authentication sequence combination module 4632 configures sequence combinations that can be formed by combining the sequence of sectors. For example, assuming that the sectors are 'day of the week', 'time zone', and 'date', the authentication sequence combination module 4632 performs a) time-day-date, b) time-date-day, c) day- Six order combinations such as time-date, d) day-date-time, e) date-time-day, and f) date-day-time can be configured.

The authentication execution module 4633 includes the update module 451 of the registration DB sorting unit 45, the access status information generation module 452, the matching data generation module 453, the weighted score calculation module 454, and the alignment In the same manner as the DB creation module 455, sorted DBs are created for each order combination. At this time, the current state causes the same value to be applied.

For example, assuming that the sectors are 'day of the week', 'time zone', and 'date', as described above, the order combination is composed of 6, and accordingly, the authentication module 4633 arranges DBs for each order combination. be able to create

In addition, the authentication execution module 4633 compares and compares the test patterns extracted by the test sample extraction module 4631 with the generated alignment DBs. In other words, the authentication execution module 4633 performs authentication by comparing each test pattern with 6 alignment DBs.

The data calculation module 4634 for each order combination calculates the certification required time (t), which is the time required for each test pattern to be authenticated using each sort DB by the authentication execution module 4633, and then tests for each sort DB. The average value of authentication required times (t) of the patterns is calculated.

For example, when 2 test patterns are extracted and 6 sorted DBs are generated for each order combination, the data calculation module 4634 for each order combination can calculate a total of 12 certification required times (t) and sort them. A total of 6 average values can be calculated based on the DBs.

At this time, the average values calculated by the data calculation module 4634 for each sequence combination are input to the authentication sequence information resetting module 4635.

The authentication sequence information resetting module 4635 compares the average values input from the data calculation module 4634 for each sequence combination and resets the sequence combination having the highest average value as the authentication sequence. At this time, the priority information reset by the authentication sequence information resetting module 4635 is stored in the second memory 402 under the control of the second control module 401 .

In this way, the quarantine system 1, which is an embodiment of the present invention, uses the camera 31 and the thermal imaging camera 34 to double detect a person with fever and a person not wearing a mask among the visitors, and at the same time, when an event occurs, warns By exposing it to the outside, it is possible to effectively prevent transmission of infectious diseases such as viruses and bacteria from the outside, thereby maximizing heat radiation efficiency.

In addition, the quarantine system 1 of the present invention analyzes the image obtained by the camera 31 to detect the facial pattern feature of the visitor, but the facial pattern feature, which is the pattern feature of the upper area centered on the eyes of the face After detection, it is configured to perform user authentication by comparing it with previously registered registration DBs, so that the user can authenticate without removing the mask separately to perform user authentication, increasing the convenience and efficiency of the authentication process and wearing a mask at the same time. and unnecessary authentication time delay due to separation can be effectively prevented.

In addition, in the quarantine system 1 of the present invention, as components such as the camera 31, the thermal imaging camera 34, the speaker 35, and the LED light 36 are integrally manufactured, not only can miniaturization be produced, but also manufacturing and It can reduce operating cost.

In addition, the quarantine system 1 of the present invention is configured to compare and contrast registration DBs in response to the access status of users during user authentication, so that the authentication speed can be significantly increased and unnecessary calculation processing can be prevented. there is.

1: quarantine system 3-1, ..., 3-N: access detector
5-1, ..., 5-N: gate device 30: photographing device 31: camera
32: bracket 33: TOF sensor 34: thermal imaging camera
35: speaker 36: LED unit 37: control unit
300: control unit 301: control module 302: memory
303: communication interface unit 304: object recognition and facial pattern feature detection unit
305: thermal image analysis unit 306: heat determination unit
307: Mask wear or not determination unit 308: User authentication unit 309: Access or not determination unit
310: open/close control signal generation unit 311: warning information output unit 312: display unit
321: fixed plate 322: caster 323: vertical arm
325: hinge coupling part 341: image input module 342: TOF information input module
343: analysis module

Claims (5)

In the quarantine system including an access detector installed at the entrance of an indoor space to detect visitors:
The entrance detector
Brackets;
Including a photographing device rotatably coupled to the bracket,
The photographic device is
A camera that acquires an image by photographing a person's face;
A thermal imaging camera that obtains a thermal image by heat-tracking and detecting the face of the person entering the room;
Display means for outputting preset warning information to the outside;
By analyzing the thermal image obtained by the thermal imaging camera, the body temperature of the visitor is measured to detect whether the visitor has fever, and at the same time, the image obtained by the camera is analyzed to detect whether the visitor is wearing a mask, and the fever of the visitor is detected. Further comprising a control unit for outputting warning information through the display means when this is detected or the person who is not wearing a mask,
The control unit
a memory storing a feature detection algorithm that takes an image as an input value and uses the presence or absence of a mask object as an output value;
an object recognition and facial pattern feature detection unit that analyzes the image acquired by the camera using a preset object detection algorithm and outputs object detection data indicating the presence or absence of a mask object;
a mask-wearing or non-mask determination unit for determining whether or not the visitor is wearing a mask through the object detection data detected by the object recognition and facial pattern feature detection unit;
When it is determined that the person wearing a mask is determined by the mask wearing determination unit, it is determined to allow the person to enter and exit, and when the mask wearing or not wearing judgment unit determines that the person is not wearing a mask, the entry and exit of the person is controlled. Including an entry or exit decision unit that determines,
The feature detection algorithm takes an image as an input value and outputs not only object detection data indicating the presence or absence of a mask object of the visitor, but also facial pattern feature information, which is feature information of the visitor's face,
In the memory, registration DBs in which information of users allowed to enter and facial pattern feature information are matched are set and stored in advance,
The object recognition and facial pattern feature detection unit
Analyzing the image acquired by the camera using the object detection algorithm to detect object detection data indicating the presence or absence of a mask object and facial pattern feature information of the person entering and leaving,
The control unit
Further comprising a user authentication unit for determining whether an entrant is an authorized user by collating and comparing the facial pattern feature information detected by the object recognition and facial pattern feature detection unit with previously registered registration DBs,
The entry/exit determination unit
When the entrant is judged to be a person with no fever and at the same time the entrant is judged to be wearing a mask by the mask wearer and authenticated by the user authentication unit, it is determined to allow the entrant to enter, but if the entrant is determined to be feverish or the mask is worn When the entrant is judged to be not wearing a mask by the wear/abuse determination unit or when the user authentication unit fails authentication, it is determined to control the access of the entrant,
In the memory, preset sectors, categories, which are sub-components constituting each sector, and authentication sequence information, which is the order of the sectors, are preset and stored;
The user authentication unit
a registration DB sorting unit that is executed every second period (T2) and sorts the registration DBs;
an authentication processing unit for performing authentication by sequentially comparing and contrasting the facial pattern feature information detected by the object recognition and facial pattern feature detection unit with the registration DB sorted by the registration DB sorting unit;
When authentication is successful in the authentication processing unit, authentication information including user information that has been authenticated, time required for authentication processing (t), and category information for each sector corresponding to the time of authentication is generated. , Includes an authentication information generator for storing the generated authentication information in the memory,
The registration DB sorting unit
an update module for substituting the contents of a current state into categories of each sector in a preset authentication sequence;
An access status information generation module that generates access status information consisting of the number of authentication times (N) for each sector of pre-registered users by utilizing authentication information;
a matching data generation module for generating matching data by matching the access status information generated by the access status information generation module with pre-registered registration DBs based on user information;
According to the latest authentication order, which is the authentication order to which the contents of the current state are applied by the update module, a weight proportional to the order is assigned to each sector, and then the latest authentication order for each user is obtained by utilizing the matching data generated by the matching data generation module. The weight of the sector is multiplied by the number of authentications in the same category as the category of each sector in the latest authentication sequence, and the number of authentications in categories that are not the same as the category of each sector in the latest authentication order is multiplied by the weight '1', and then summed up. a weighted score calculation module for calculating a weighted score for each user;
A sorting DB generating module for generating a sorting DB by arranging pre-registered registration oils according to the size of the weighted score calculated by the weighted score calculation module, and then storing the sorted DB in the memory;
The user authentication unit
Further comprising an authentication sequence setting unit that is executed every preset first period (T1),
The authentication sequence setting unit
Including a judgment module and an authentication module for each order combination,
The judgment module
A data extraction module that searches for authentication information stored in the memory and extracts authentication information that has been authenticated during a period (T-1) from the present to the previous period; and during a period (T-1) from the present extracted by the data extraction module. An average value calculation module that extracts authentication required times (t) of authentication information and calculates an average value thereof, and if the average value calculated by the average value calculation module is greater than a preset threshold value, it is determined that authentication sequence information does not need to be reset However, if the average value is less than the threshold value, a reset determination module for determining that authentication sequence information needs to be reset is included;
The authentication module for each order combination
Executed when the determination module determines that it is necessary to reset the authentication sequence,
A test sample extraction module for searching for biopattern features of authenticated users during the previous period (T-1) stored in the memory and randomly extracting n test samples from among them, and a combination of the order of sectors. In the same way as the authentication order combination module constituting order combinations, the update module of the registration DB sorting unit, the access status information generation module, the matching data generation module, the weighted score calculation module, and the sorting DB generation module, the order An authentication execution module that creates sorting DBs for each combination and at the same time compares and compares the test patterns extracted by the test sample extraction module with the generated sorting DBs; After calculating the time required for authentication (t), which is the time required for authentication using each sort DB, a data calculation module for each order combination that calculates the average value of the time required for authentication (t) of test patterns for each sort DB; An authentication sequence information reset module for resetting the sequence combination having the highest average value as an authentication sequence by comparing average values input from the data calculation module for each sequence combination,
The update module of the registration DB sorting unit
The quarantine system, characterized in that, according to the authentication sequence reset by the authentication sequence information resetting module, the contents of the current state are substituted into the category of each sector. The method of claim 1, wherein the quarantine system further comprises gate devices installed on the upper surface of the bracket of the access detector,
The control unit
1) When the entrant is not a fever but wears a mask, the gate device outputs a control signal to open the access door, 2) Control to close the access door with the gate device when the entrant is a fever or not wearing a mask A quarantine system characterized in that it outputs a signal. The method of claim 2, wherein the control unit
a thermal image analysis unit analyzing the thermal image acquired by the thermal image camera;
After measuring the body temperature (°C) of the visitor through the analysis data detected by the thermal image analyzer, the measured body temperature (°C) is compared with a preset reference value, and if the body temperature (°C) is less than the reference value, the visitor is considered to have no fever. However, if the body temperature (℃) is higher than the reference value, a fever determination unit for determining the visitor as a fever;
a control signal generator for generating a control signal according to the data determined by the entry/exit determination unit;
Further comprising a control module for transmitting the control signal generated by the control signal generator to the corresponding gate device,
The entry/exit determination unit
When the fever determination unit determines that the visitor has no fever and the mask wearing determination unit determines that the visitor is wearing a mask, it is determined to allow the person to enter and exit, but the fever determination unit determines that the visitor has fever. or when the entrant is judged to be a non-wearing mask by the mask wearing determination unit, it is characterized in that it is determined to control the entry and exit of the entrant. delete delete

Images