KR102551473B1 - System and method for controlling of sterilization gate based on artificial intelligence - Google Patents

Abstract

An artificial intelligence-based sterilization gate control system and method are disclosed. The artificial intelligence-based sterilization gate system according to the present invention includes a smart gate that forms a passage for a target, recognizes the target, and sprays a disinfectant toward the target, and a control unit that controls the smart gate, The smart gate includes a recognition unit for recognizing the target and a spray nozzle for injecting the disinfectant toward the target, and the control unit applies the disinfectant to the target based on a result recognized by the recognition unit. It is possible to control the spray nozzle so as to spray toward.

Description

AI-based sterilization gate control system and method {SYSTEM AND METHOD FOR CONTROLLING OF STERILIZATION GATE BASED ON ARTIFICIAL INTELLIGENCE}

The present invention relates to an artificial intelligence-based sterilization gate control system and method. More specifically, it relates to an artificial intelligence-based sterilization gate control system and method capable of spraying a disinfectant by recognizing a target and controlling a spray nozzle based on the recognized result.

Since COVID-19, an infectious disease (Infection, Infectious Disease) first occurred in 2019, it has spread around the world, causing many confirmed cases and casualties until recently. It is a disease that causes disease, and it is generated through various routes, such as contact with other people.

Due to this, the World Health Organization (WHO) declared Corona 19 a pandemic, the highest warning level of infectious diseases, a pandemic.

Here, Corona 19 is a respiratory infectious disease, the pathogen is SARS-coronavirus-2 (SARS-CoV-2), and mainly spreads by penetrating the respiratory tract or mucous membranes of the eyes, nose, and mouth. That is, it is spread by coughing, sneezing, etc., or by touching a material contaminated with the virus and then touching the eyes, nose, and mouth with hands. Recently, it is known that the possibility of transmission by aerosol is high.

Therefore, conventionally, a thermal imaging camera that detects the fever of an entrant is installed in the immigration facility to monitor the body temperature of the infected person upon entry through thermal imaging, and if the entrant is determined to be infected, the location and movement route of the entrant are identified. Information on suspected infected persons for sterilization or isolation was provided, and post-disinfection work was performed along the movement lines of suspected infected persons to prevent the spread of infectious diseases.

KR 10-2182543B1, which is a prior art, includes a pipe frame including a spray nozzle, but has a problem of causing discomfort to the inspected person by spraying an antiseptic agent on the face of the inspected person.

KR 10-2182543B1 (Title of invention: artificial intelligence quarantine system)

An object of the present invention is to recognize a target and spray a disinfectant to the target based on the recognition result.

In addition, an object of the present invention is to spray a disinfectant to an area other than the face of the target based on the recognition result of the target.

In addition, an object of the present invention is to provide a vision recognition algorithm capable of minimizing the effect of the disinfectant sprayed into the air.

In addition, an object of the present invention is to provide an artificial intelligence-based sterilization gate control system and method including a lens resistant to corrosion even in an environment where a disinfectant is sprayed.

In order to solve the above problems, the present invention includes a smart gate for forming a movement passage of a target, recognizing the target, and spraying a disinfectant toward the target, and a control unit for controlling the smart gate, The gate includes a recognition unit for recognizing the target and a spray nozzle for injecting the disinfectant toward the target, and the controller applies the disinfectant to the target based on a result recognized by the recognition unit. Control the spray nozzle to spray toward the target, and record the recognized result and the usage amount of the disinfectant, wherein the control unit recognizes the face position of the target by the recognition unit, and the disinfectant agent based on the face position can be sprayed.

The recognizing unit may include a depth camera for recognizing the shape of the target and a thermal imaging camera for recognizing the temperature of the target.

The control unit receives a depth image including the target from the depth camera, receives a thermal image including the target from the thermal imaging camera, and receives a height of the target and a body shape of the target from the depth image. , and the facial position of the target and the temperature of the target can be recognized from the thermal image.

In addition, the control unit recognizes the facial position of the target by applying a vision recognition algorithm to the thermal image, and the vision recognition algorithm is a CNN learning algorithm using a plurality of layers according to the CNN learning algorithm. It may contain image filters applied to the image.

In addition, in order to solve the above problems, the present invention includes the steps of receiving a depth image and a thermal image including a target from a recognizing unit, deriving height of the target and body shape information of the target from the depth image; Deriving facial position information and temperature information of the target from the thermal image, controlling a spray nozzle to spray a disinfectant based on the facial position information of the target, deriving the usage amount of the disinfectant and recording the usage amount, height information of the target, body shape information of the target, facial position information of the target, and temperature information of the target.

In addition, in the step of deriving the target's facial position information and the target's temperature information, a vision recognition algorithm is applied to the thermal image to recognize the target's facial position, and a plurality of layers according to the vision recognition algorithm are obtained. A CNN learning algorithm to be used, and the CNN learning algorithm may include an image filter applied to the thermal image.

In addition, in order to solve the above problems, the present invention is a non-transitory computer readable medium storing instructions, and when the instructions are executed by a processor, the processor can perform the above-described method.

The present invention has an effect of significantly reducing the discomfort of target personnel by spraying a disinfectant to an area other than the target's face based on the recognition result of the target.

In addition, the present invention has the effect of providing a vision recognition algorithm capable of overcoming the deterioration of image quality due to the disinfectant floating in the air and deriving accurate recognition results.

In addition, the present invention has an effect of providing an artificial intelligence-based sterilization gate control system and method including a lens resistant to corrosion even in an environment where a disinfectant is sprayed.

Effects obtainable according to the present invention are not limited to the effects mentioned above, and other effects not mentioned can be clearly understood by those skilled in the art from the description below. will be.

1 and 2 are diagrams showing an artificial intelligence-based sterilization gate control system according to the present invention.
3 schematically shows a functional module stored in a memory and driven according to the present invention.
4 to 6 are diagrams showing examples of smart gate driving according to the height of the target and the body shape of the target according to the present invention.
7 is a diagram schematically showing a camera including a lens according to the present invention.
8 is a diagram showing a CNN algorithm according to the present invention.
9 is a diagram showing a CNN filter according to the present invention.
10 is a diagram showing an artificial intelligence-based sterilization gate control method according to the present invention.
The accompanying drawings, which are included as part of the detailed description to aid understanding of the present specification, provide examples of the present specification and describe technical features of the present specification together with the detailed description.

Hereinafter, the embodiments disclosed in this specification will be described in detail with reference to the accompanying drawings, but the same or similar elements are given the same reference numerals regardless of reference numerals, and redundant description thereof will be omitted.

In addition, in describing the embodiments disclosed in this specification, if it is determined that a detailed description of a related known technology may obscure the gist of the embodiment disclosed in this specification, the detailed description thereof will be omitted.

In addition, the accompanying drawings are only for easy understanding of the embodiments disclosed in this specification, the technical idea disclosed in this specification is not limited by the accompanying drawings, and all changes included in the spirit and technical scope of the present invention , it should be understood to include equivalents or substitutes.

Terms including ordinal numbers, such as first and second, may be used to describe various components, but the components are not limited by the terms. These terms are only used for the purpose of distinguishing one component from another.

Singular expressions include plural expressions unless the context clearly dictates otherwise.

In this application, terms such as "comprise" or "have" are intended to designate that there is a feature, number, step, operation, component, part, or combination thereof described in the specification, but one or more other features It should be understood that the presence or addition of numbers, steps, operations, components, parts, or combinations thereof is not precluded.

Hereinafter, based on the above information, the artificial intelligence-based sterilization gate control system according to a preferred embodiment of the present specification will be described in detail as follows.

1 and 2 are diagrams showing an artificial intelligence-based sterilization gate control system according to the present invention.

1 and 2, the artificial intelligence-based sterilization gate control system according to the present invention may include a smart gate 100 and a control unit 200. Hereinafter, a target according to the present invention may mean a person who is a target of recognition and injection of a disinfectant.

The smart gate 100 may form a movement path through which a target can move. The smart gate 100 may include a recognition unit and recognize a target through the recognition unit. In addition, the smart gate 100 may include a spray nozzle 120 and spray a disinfectant through the spray nozzle 120. The smart gate 100 may spray the disinfectant toward the target.

The quarantine agent may refer to all materials for quarantine such as sterilization and antiviral. The quarantine agent is harmless to the human body and may be a quarantine agent against new viruses such as COVID-19.

The control unit 200 is a component for controlling the smart gate 100, and can specifically control the recognition unit and the injection nozzle 120 of the smart gate 100. The control unit 200 may control the spray nozzle 120 to spray the disinfectant toward the target based on the result recognized by the recognition unit.

The recognition unit according to the present invention is a component for recognizing a target and may include a first camera 111 and a second camera 112 . The first camera 111 may be a depth camera for recognizing the shape of the target, and the second camera 112 may be a thermal imaging camera for recognizing the temperature of the target.

In addition, the recognizing unit may further include an optical camera (not shown) for obtaining an optical image including the target, and may further include a temperature sensor (not shown) for recognizing the temperature of the target. In some cases, optical cameras can replace depth cameras, and temperature sensors can replace thermal imaging cameras.

The controller 200 according to the present invention may generate a depth image based on information obtained from a depth camera. Distance information in space is also referred to as a depth image, and methods for extracting such depth information include time of flight (TOF), stereoscopic vision, structured light pattern, and the like.

The TOF (Time of Flight) method analyzes the time it takes for light to reflect off an object and return to form a depth image. Since light travels approximately 300,000 km per second, the sensor measures the very short time for light to return to the distance. Calculate That is, the depth camera may measure the depth of the target by measuring a time of flight (TOF) for the irradiated light to be reflected from the object and return. The depth camera according to the present invention uses a device that is very sensitive to light, such as a SPAD, to detect the moment when the reflected light reaches the light receiver, and uses it to measure the TOF using a direct method, or a photodiode. An indirect method of detecting and calculating the phase difference as an amount of charge can be used when the pulsed light modulated by using is reflected.

Also, the depth camera may measure the depth of the target through a stereo camera. This may mean an optical method, and in this case, the depth camera may be a 3D camera using structured light. In this way, equipment for measuring the three-dimensional shape of an object using an optical method is commonly referred to as a 3D scanner. Such a 3D scanner may be composed of an image acquisition unit composed of a lens and a camera, a scan line light projection unit that projects scan line light, and a computer that analyzes and processes an image acquired through the scan line light projection unit.

A thermal imaging camera is a device that converts the temperature change of a target object or scene into a visible image. . A lens in a thermal imaging camera is not a generally used glass lens, but an opaque lens coated with magnesium-aluminum, and a sensor in which a detector detecting infrared rays is arranged on a focal plane may be used.

The controller 200 according to the present invention may receive a depth image including a target from a depth camera, apply a vision recognition algorithm to the depth image, and recognize the height of the target and the body shape of the target. Also, the control unit 200 according to the present invention may classify the height of the target and the body shape of the target using classification during machine learning. Details of the vision recognition algorithm will be described later.

In addition, the control unit 200 according to the present invention may acquire information about the target by vision recognition of the target photographed by the optical camera.

According to FIG. 2 , the smart gate 100 according to the present invention may include a pillar portion 101 formed on both sides of the movement passage and a body portion 102 formed on the upper portion of the movement passage. In the present invention, the direction toward the moving passage is defined as the inner side, and the opposite direction is defined as the outer side. A recognition unit 110 may be installed in the body unit 102 .

According to FIG. 2, a plurality of injection nozzles 120 according to the present invention may be installed in the smart gate 100. The spray nozzle 120 may be installed to face the inside of the movement passage along the movement passage formed in the smart gate 100 . The injection nozzle 120 sprays the disinfectant toward the inside of the moving passage, but the angle may be adjusted by a preset range. The spray nozzle 120 may change the angle at which the disinfectant is sprayed under the control of the control unit 200 .

A plurality of spray nozzles 120 according to the present invention may be installed inside the pillar portion 101 . The pillar part 101 may include a first pillar part 101a and a second pillar part 101b. The plurality of injection nozzles 120 may be installed inside the pillar part 101 along the direction in which the pillar part 101 extends. The plurality of injection nozzles 120 may be driven in response to the elongation of the target.

In addition, the plurality of spray nozzles 120 according to the present invention can be rotated within a predetermined standard to adjust the spray angle of the disinfectant. Although not shown in the drawing, each of the plurality of injection nozzles according to the present invention may include a driving device (not shown) for reciprocating the tip of each nozzle at an angle in a predetermined direction. An example in which the injection nozzle is driven to move at an angle in a predetermined direction by the driving device may be supported by FIGS. 4 and 5 to be described later.

According to FIG. 2 , the controller 200 may include a processor 210, a memory 220 and a communication module 230.

The processor 210 may execute commands stored in the memory 220 to control other components. The processor 210 may execute instructions stored in the memory 220 .

The processor 210 is a component capable of performing calculations and controlling other devices. Mainly, it may mean a central processing unit (CPU), an application processor (AP), a graphics processing unit (GPU), and the like. Also, the CPU, AP, or GPU may include one or more cores therein, and the CPU, AP, or GPU may operate using an operating voltage and a clock signal. However, while a CPU or AP consists of a few cores optimized for serial processing, a GPU may consist of thousands of smaller and more efficient cores designed for parallel processing.

The processor 210 may provide or process appropriate information or functions to a user by processing signals, data, information, etc. input or output through the components described above or by running an application program stored in the memory 220.

The memory 220 stores data supporting various functions of the control unit 200 . The memory 220 may store a plurality of application programs (application programs or applications) driven by the control unit 200, data for operation of the control unit 200, and commands. At least some of these application programs may be downloaded from an external server through wireless communication. In addition, the application program may be stored in the memory 220, installed in the control unit 200, and driven by the processor 210 to perform the operation (or function) of the control unit 200.

The memory 220 may be a flash memory type, a hard disk type, a solid state disk type, a silicon disk drive type, or a multimedia card micro type. ), card-type memory (eg SD or XD memory, etc.), RAM (random access memory; RAM), SRAM (static random access memory), ROM (read-only memory; ROM), EEPROM (electrically erasable programmable read -only memory), a programmable read-only memory (PROM), a magnetic memory, a magnetic disk, and an optical disk. Also, the memory 220 may include a web storage performing a storage function on the Internet.

The communication module 230 transmits and receives information with a base station or a camera having a communication function through an antenna. The communication module 230 may include a modulation unit, a demodulation unit, a signal processing unit, and the like. Also, the communication module 230 may perform a wired communication function.

Wireless communication may refer to communication using a wireless communication network using a communication facility previously installed by telecommunication companies and a frequency of the communication facility. At this time, the communication module 230 is CDMA (code division multiple access), FDMA (frequency division multiple access), TDMA (time division multiple access), OFDMA (orthogonal frequency division multiple access), SC-FDMA (single carrier frequency division multiple access), and the like, as well as the communication module 230 can also be used for 3rd generation partnership project (3GPP) long term evolution (LTE). In addition, not only 5G communication, which is currently being commercialized, but also 6G, which is scheduled to be commercialized later, can be used. However, the present specification may utilize a pre-installed communication network without being bound by such a wireless communication method.

In addition, as a short range communication technology, Bluetooth, BLE (Bluetooth Low Energy), Beacon, RFID (Radio Frequency Identification), NFC (Near Field Communication), infrared communication (Infrared Data Association; IrDA) ), UWB (Ultra Wideband), ZigBee, etc. may be used.

The communication module 230 may connect the computing device and an external server through wireless communication and/or wired communication. Also, the communication module 230 may receive data generated by the recognition unit and transmit commands generated by the processor 210 to other components.

3 schematically shows a functional module stored in a memory and driven according to the present invention.

According to FIG. 3 , the memory according to the present invention may store a depth image analysis module 221, a thermal image analysis module 222, a result recording module 223, and a disinfectant usage estimation module 224.

The depth image analysis module 221 may derive height information of the target and body shape information of the target from the depth image. Specifically, the depth image analysis module 221 may perform a vision recognition algorithm on the depth image in order to recognize the approximate height and body shape of the target. The corresponding process may be as follows.

(1) Recognize target and reference objects

(2) Recognize the height and body shape of the target based on the reference object

However, since the height and width of the reference object are known in advance, the depth image analysis module 221 may retrieve previously stored height and width information of the reference object from the memory. The height of the target may be derived based on the height of the reference object, and the body shape of the target may be derived based on the width of the reference object.

The thermal image analysis module 222 may derive the facial position of the target and the temperature of the target from the thermal image. Specifically, the thermal image analysis module 222 may perform a vision recognition algorithm on the thermal image in order to recognize the face of the target and derive its location. The corresponding process may be as follows.

(1) Load an algorithm that has previously learned an existing thermal image including a person's face from the DB

(2) Receiving a thermal image including a target from a thermal imaging camera

(3) Recognize the target's face from the received thermal image

(4) Extracting temperature information about the face of the recognized target

(5) Deriving the positional information of the target's face based on the height of the reference object

However, the height and width of the reference object are known in advance, and may be controlled to maintain a predetermined temperature. The thermal image analysis module 222 may recognize a reference object by recognizing the outline of an object having a predetermined temperature. The thermal image analysis module 222 may retrieve previously stored height and width information of a reference object from a memory.

The result recording module 223 may record the result analyzed by the depth image analysis module 221 and/or the thermal image analysis module 222 in a memory. The result recording module 223 may transmit the recorded result data to the disinfectant usage estimation module 224 .

The disinfectant usage prediction module 224 may use a regression algorithm. The disinfectant usage prediction module 224 may use at least one of linear regression, Gaussian process regression, and Kalman filter. The disinfectant usage prediction module 224 may predict the disinfectant usage based on the recorded result data.

4 to 6 are diagrams showing examples of smart gate driving according to the height of the target and the body shape of the target according to the present invention.

4 to 6, the spray nozzle 120 according to the present invention may include a first spray nozzle 120a to a third spray nozzle 120c. The first spray nozzle 120a to the third spray nozzle 120c may be installed inside the first pillar portion. A plurality of spray nozzles 120 may also be installed on the second pillar part, and may operate correspondingly to the first spray nozzles 120a to third spray nozzles 120c installed on the first pillar part.

According to FIG. 4, the head position of the first target 11 is located near the reference line. Accordingly, the controller (200 in FIG. 1 ) may drive only the second spray nozzle 120b and the third spray nozzle 120c without driving the first spray nozzle 120a. In addition, the controller (200 in FIG. 1 ) may control the second injection nozzle 120b to face downward than the reference line. This is to avoid spraying the disinfectant to the face of the first target 11.

According to FIG. 5, the head of the second target 12 is positioned away from the reference line by a first distance. Accordingly, the controller (200 in FIG. 1 ) may drive only the second spray nozzle 120b and the third spray nozzle 120c without driving the first spray nozzle 120a. The controller (200 in FIG. 1 ) may control the second spray nozzle 120b so that the disinfectant reaches a height higher than the reference line. This is to spray the disinfectant to as many areas as possible without spraying the second target 12 to the face.

According to FIG. 6, the head of the third target 13 is located away from the reference line by a second distance. Accordingly, the controller (200 in FIG. 1 ) may drive all of the first spray nozzles 120a to the second spray nozzles 120b. In addition, the controller (200 in FIG. 1 ) may control the first injection nozzle 120a to face downward than the reference line. This is to avoid spraying the disinfectant to the face of the first target 11.

The reference line according to the present invention may be set at a predetermined position. In addition, the first reference line according to the present invention may be set at a predetermined position, and the second reference line may be set based on the position of the face of the third target 13 . The second reference line may be set based on the position of the head of the third target 13 recognized through vision recognition.

7 is a diagram schematically showing a camera including a lens according to the present invention.

According to FIG. 7 , the first camera 111 and/or the third camera (thermal image camera and/or optical camera) according to the present invention may include a camera module 1320 . The camera module 1320 according to the present invention may generate a thermal image or an optical image according to the type of image sensor. The camera module 1320 may include a housing 1324 including a through hole on a side wall, a lens 1321 installed in the through hole, and a driving unit 1323 that drives the lens 1321 . The through hole may have a size corresponding to the diameter of the lens 1321 . The lens 1321 may be inserted into the through hole.

The driving unit 1323 may be configured to control the lens 1321 to move forward or backward. The lens 1321 and the driving unit 1323 are connected in a conventionally known manner, and the lens 1321 may be controlled by the driving unit 1323 in a conventionally known manner.

In order to obtain various video images, the lens 1321 needs to be exposed to the outside of the camera module 1320 or the housing 1324 .

In particular, since it should be installed around the moving path of the target through which the disinfectant according to the present invention is sprayed, a lens with strong fouling resistance is required. Accordingly, the present invention proposes a coating layer for coating the lens 1321 to solve this problem.

Preferably, the lens 1321 may include an acrylic compound represented by Formula 1 below on its surface; It may be coated with a coating composition containing an organic solvent, inorganic particles and a dispersant.

[Formula 1]

here,

n and m are the same as or different from each other, each independently represent an integer of 1 to 100, and L ₁ is a biphenylene group.

When the lens 1321 is coated with the coating composition, it can exhibit excellent water repellency and stain resistance, so even if the lens 1321 installed around the moving passage is exposed to a polluted environment and salt for a long time, it is possible to collect clean and clear external images. can

The inorganic particles may be selected from the group consisting of silica, alumina, and mixtures thereof. The average diameter of the inorganic particles is 70 to 100 μm, but is not limited to the above example. After forming the coating layer 1322 on the surface of the lens 1321, the inorganic particles may improve physical strength and maintain viscosity within a certain range to increase moldability.

The organic solvent is selected from the group consisting of methyl ethyl ketone (MEK), toluene, and mixtures thereof, and preferably methyl ethyl ketone may be used, but is not limited to the above examples.

As the dispersing agent, a polyester-based dispersing agent may be used, and specifically, TEGO-Disperse 670 (manufacturer : EVONIK) can be used, but it is not limited to the above examples, and all dispersants obvious to those skilled in the art can be used without limitation.

The coating composition may further include a stabilizer as other additives, and the stabilizer may include an antioxidant and the like, but is not limited to the above examples and may be used without limitation.

The coating composition for forming the coating layer 1322 may more specifically include an acrylic compound represented by Chemical Formula 1; organic solvents, inorganic particles and dispersants.

The coating composition may include 40 to 60 parts by weight of the acrylic compound represented by Formula 1, 20 to 40 parts by weight of inorganic particles, and 5 to 15 parts by weight of a dispersant, based on 100 parts by weight of the organic solvent. In the case of the above range, a synergistic effect is expressed to the extent that the water repellency effect due to the interaction of each component is of critical significance, and when it is out of the above range, the synergistic effect is rapidly reduced or almost nonexistent.

More preferably, the viscosity of the coating composition is 1500 to 1800 cP, and when the viscosity is less than 1500 cP, when applied to the surface of the lens 1321, there is a problem that it is not easy to form the coating layer 1322 because it flows down, and 1800 cP If it exceeds, there is a problem that it is not easy to form a uniform coating layer 1322 .

[Preparation Example 1: Preparation of coating layer]

1. Preparation of coating composition

A coating composition was prepared by mixing methyl ethyl ketone with an acrylic compound represented by Formula 1, inorganic particles, and a dispersant:

[Formula 1]

here,

n and m are the same as or different from each other, each independently represent an integer of 1 to 100, and L ₁ is a biphenylene group.

A more specific composition of the antistatic composition is shown in Table 1 below.

TX1 TX2 TX3 TX4 TX5 organic solvent 100 100 100 100 100 acrylic compound 30 40 50 60 70 inorganic particles 10 20 30 40 50 dispersant One 5 10 15 20

(unit weight parts)

2. Preparation of coating layer

A coating layer 1322 was formed by applying the coating composition of DX1 to DX5 on one surface of the lens 1321 and then curing the coating composition.

[Experimental example]

1. Evaluation of surface appearance

Due to the difference in viscosity of the coating composition, after the coating layer 1322 was prepared, a sensory evaluation was performed on whether a uniform surface was formed. Evaluation was conducted on whether or not a uniform coating layer 1322 was formed, and the evaluation was conducted according to the following criteria.

○: uniform coating layer formation

×: Formation of non-uniform coating layer

TX1 TX2 TX3 TX4 TX5 sensory evaluation Х ○ ○ ○ Х

When forming the coating layer 1322, if the viscosity is less than a certain amount, flow occurs on the surface of the lens 1321, and it is difficult to form a uniform coating layer 1322 after the curing process in many cases. Accordingly, a problem of lowering the production yield may occur. In addition, even when the viscosity is too high, it is difficult to uniformly apply the composition and it is impossible to form a uniform coating layer 1322 .

2. Measurement of water repellency angle

After forming the coating layer 1322 on the surface of the lens 1321, the results of measuring the water repellency angle are shown in Table 3 below.

Advancing contact angle (“) Static contact angle (“) receding contact angle (“) TX1 117.1±2.9 112.1±4.1 < 10 TX2 132.4±1.5 131.5±2.7 141.7±3.4 TX3 138.9±3.0 138.9±2.7 139.8±3.7 TX4 136.9±2.0 135.6±2.6 140.4±3.4 TX5 116.9±0.7 115.4±3.0 < 10

As shown in Table 3, after the coating layer 1322 was formed using the coating compositions of TX1 to TX5, the result of measuring the contact angle was confirmed. TX1 and TX5 measured receding contact angles less than 10 degrees. That is, it was confirmed that a phenomenon in which water droplets are pinned occurs when the coating composition is out of the optimal range for preparing the coating composition. On the other hand, it was confirmed that the pinning phenomenon did not occur in TX2 to 4, indicating that excellent waterproofing effect could be exhibited.

3. Fouling resistance evaluation

A lens 1321 having a coating layer 1322 according to the above embodiment formed around the road was attached to a model camera, and exposed to a moving passage environment sprayed with a disinfectant for 40 days. As the comparative example (Con), the same lens 1321 without the coating layer 1322 was used, and in each example, the model camera was installed at the same location of the moving passage.

After that, the degree of contamination and corrosion of the lens 1321 before and after the experiment was evaluated as related, and for objective comparison, the result was compared with a comparative example in which the coating layer 1322 was not formed, and the result was evaluated by an index of 1 to 10, and the following Table 4 shows. In the index below, the lower the number, the better the stain resistance.

Con TX1 TX2 TX3 TX4 TX5 stain resistance 10 7 3 3 3 8

(Unit: index)

Referring to Table 4, in the case of forming the coating layer 1322 on the lens 1321, even if the lens 1321 is exposed to the outside while installing the camera in the external environment, high fouling resistance can be easily analyzed for a long period of time. It can be seen that image data can be collected. In particular, in the case of TX2 to TX4, it can be confirmed that the contamination resistance by the coating layer 1322 is very excellent.

8 is a diagram showing a CNN algorithm according to the present invention, and FIG. 9 is a diagram showing a CNN filter according to the present invention.

Referring to FIG. 8 , a Convolutional Neural Network (CNN) algorithm is a technique widely used in the field of image processing and can support automatic learning so that each element of a filter represented by a matrix is suitable for data processing. Also, according to FIG. 9, types and functions of filters are shown.

That is, the CNN algorithm may be a learning algorithm using a plurality of layers. In addition, the CNN algorithm can automatically learn a filter that maximizes image classification accuracy, and by adding a new layer called a convolutional layer and a polling layer before the fully connected layer, after applying the filtering technique to the original image, the filtered image A classification operation can be performed on .

According to FIG. 8, the CNN algorithm applies a filtering technique to an original image by adding a new layer called a convolutional layer and a pooling layer before the fully-connected layer, and then performs classification operation on the filtered image. It can be configured to do this.

At this time, the operation expression for the image filter using the CNN algorithm is as shown in Equation 1 below.

[Equation 1]

(step,

: 행렬로 표현된 필터링된 이미지의 i번째 행, j번째 열의 픽셀,

: pixels in the i-th row and j-th column of the filtered image expressed as a matrix,

F: filter,

X: image,

F _H : height of filter (number of rows),

F _W : The width of the filter (number of columns). )

Preferably, the operation expression for the image filter using the CNN algorithm is as shown in Equation 2 below.

[Equation 2]

(step,

: 행렬로 표현된 필터링된 이미지의 i번째 행, j번째 열의 픽셀,

: pixels in the i-th row and j-th column of the filtered image expressed as a matrix,

: 응용 필터

: Application filter

X: image,

_F'H : height of application filter (number of rows),

F' _W : The width (number of columns) of the application filter.)

는 응용 필터로서 광 이미지로부터 타겟을 인식하고, 타겟의 얼굴 영역을 인식하기 위한 필터일 수 있다. 특히, 방역제가 분사되는 중에 이동 통로를 이동하는 타겟을 인식하기 위해서는, 보다 효과적인 응용 필터가 필요할 수 있다. 이러한 필요성을 충족하기 위하여 응용 필터

는 아래의 수학식 3에 의하여 연산될 수 있다.Preferably,

is an applied filter, and may be a filter for recognizing a target from an optical image and recognizing a face region of the target. In particular, a more effective application filter may be required to recognize a target moving along a moving path while the disinfectant is being sprayed. Application filters to meet these needs

Can be calculated by Equation 3 below.

[Equation 3]

: 필터,

: 계수,

: 응용 필터)(step,

: filter,

: Coefficient,

: application filter)

에 따른 필터는 도 9에 따른 엣지 인식 필터(Edge detection), 샤픈 필터(sharpen) 및 박스 블러 필터(Box blur) 중 어느 하나의 행렬일 수 있다. Preferably, each according to the present invention

The filter according to may be a matrix of any one of an edge detection filter according to FIG. 9, a sharpen filter, and a box blur filter.

를 구하는 연산식은 아래의 수학식 4와 같다. 이때,

는 필터의 효율을 높이기 위하여 사용되는 하나의 변수로서 해석될 수 있으며, 그 단위는 무시될 수 있다. Preferably,

The operation expression for obtaining is as shown in Equation 4 below. At this time,

can be interpreted as a variable used to increase the efficiency of the filter, and its unit can be ignored.

[Equation 4]

However, the diameter (diameter) of the lens of the camera used to take the image is in mm, the amount of disinfectant spray is in spray volume (L) / second (s), and the disinfectant concentration is in sprayed quarantine ingredient weight (g) / It can be a mass concentration value that is a solution volume (L).

[Experimental example]

Regarding the thermal image according to the present invention, when the application filter F' of the present invention is applied, the result of recognizing the position of the face of the target is as follows. The table below shows the accuracy of the recognition result as a numerical value, depending on whether a filter is applied or not, requested by a person in the relevant technical field. However, it is assumed that the type of disinfectant does not affect the result.

no filter applied

적용filter

apply filter

apply Match (score) 49 62 87

Table 5 shows the scores for concordance evaluated by experts for each case. In this experimental example, the degree of agreement between the result of recognizing the target's face position and the actual target's face position based on 100 samples is measured out of 100 points.

As can be seen in Table 5, when the filter is not applied, the degree of coincidence is evaluated relatively low due to factors that interfere with target recognition, such as spraying of a disinfectant. In contrast, when the general CNN filter F was applied, the consistency was somewhat high, but when the applied filter F' was applied, the agreement was significantly improved.

Hereinafter, an artificial intelligence-based sterilization gate control method according to another preferred embodiment of the present specification will be described in detail based on the above information.

At this time, the subject performing the artificial intelligence-based sterilization gate control method according to the present invention may be a controller (200 in FIG. 1) or a processor according to the present invention.

10 is a diagram showing an artificial intelligence-based sterilization gate control method according to the present invention.

According to FIG. 10, the artificial intelligence-based sterilization gate control method according to the present invention includes receiving a depth image including a target and a thermal image from a recognition unit (S1100), elongation of the target from the depth image, and Deriving body shape information (S1200), deriving facial location information and temperature information of the target from the thermal image (S1300), spraying a disinfectant based on the facial location information of the target Controlling the nozzle (S1400), deriving the amount of the disinfectant agent (S1500), and the amount, height information of the target, body shape information of the target, facial position information of the target, and temperature information of the target A recording step (S1600) may be included.

Receiving a depth image and a thermal image including a target from the recognizing unit ( S1100 ) may be a step of receiving a depth image and a thermal image from a depth camera and a thermal image camera.

In the step of deriving the height of the target and the body shape information of the target ( S1200 ), the target may be recognized from the depth image, a reference object may be recognized, and the height of the target may be derived based on a predetermined height of the reference object. In addition, in the step of deriving the height of the target and the body shape information of the target (S1200), the body shape of the target may be derived based on the predetermined width of the reference object. The body shape of the target is recognized approximately and can be defined based on the width of the body of the target relative to the width of the reference object.

In the step of deriving the target's facial location information and the target's temperature information (S1300), a vision recognition algorithm is applied to the thermal image to recognize the target's facial location, and a plurality of layers according to the vision recognition algorithm are generated. A CNN learning algorithm to be used, and the CNN learning algorithm may include an image filter applied to the thermal image.

In the step of controlling the spray nozzle to spray the disinfectant based on the facial location information of the target (S1400), the disinfectant is sprayed only to the remaining area except for the position of the target's face so that the disinfectant is not sprayed on the target's face. It may be a step of controlling the spray nozzle to do so.

The step of deriving the usage amount of the disinfectant (S1500) may be a step of deriving the usage amount of the disinfectant sprayed through the spray nozzle per standard time. Specifically, the present invention can additionally recognize the target number of people and derive the usage amount of the disinfectant based on the target number of people. For example, in the case of spraying 10L of the disinfectant per standard time, the present invention can derive the disinfectant sprayed per person according to the target number of people.

In the step of recording the usage amount, height information of the target, body shape information of the target, facial position information of the target, and temperature information of the target (S1600), the corresponding data is recorded in a memory, and the machine is based on the recorded data. It is possible to predict the usage amount of the disinfectant by performing running.

To predict, the artificial intelligence-based sterilization gate control method according to the present invention may further include predicting the amount of disinfectant used through a regression algorithm based on the recorded data (S1700).

In the step of predicting the disinfectant usage amount (S1700), the disinfectant usage amount may be predicted based on the recorded result data using at least one of linear regression, Gaussian process regression, and Kalman filter.

In addition, the artificial intelligence-based sterilization gate control method according to the present invention may have the same features as those described for the artificial intelligence-based sterilization gate control system according to an embodiment of the present invention, so that redundant information may be omitted. there is.

The above-described present invention can be modeled as a computer readable code on a medium on which a program is recorded. The computer-readable medium includes all types of recording devices in which data readable by a computer system is stored. Examples of computer-readable media include Hard Disk Drive (HDD), Solid State Disk (SSD), Silicon Disk Drive (SDD), ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, etc. there is Accordingly, the above detailed description should not be construed as limiting in all respects and should be considered illustrative. The scope of this specification should be determined by reasonable interpretation of the appended claims, and all changes within the equivalent scope of this specification are included in the scope of this specification.

Any or other embodiments of the present invention described above are not mutually exclusive or distinct. Certain or other embodiments of the present invention described above may be used in combination or combination of respective configurations or functions.

The above detailed description should not be construed as limiting in all respects and should be considered illustrative. The scope of the present invention should be determined by reasonable interpretation of the appended claims, and all changes within the equivalent scope of the present invention are included in the scope of the present invention.

100: smart gate
110: recognition unit
120: injection nozzle
200: control unit

Claims (7)

A smart gate that forms a passage for a target, recognizes the target, and injects a disinfectant toward the target; and
Including; a control unit for controlling the smart gate;
The smart gate,
a recognition unit for recognizing the target; and
Including; spray nozzle for spraying the disinfectant toward the target,
The recognition unit,
a depth camera for recognizing the shape of the target; and
Including; a thermal imaging camera for recognizing the temperature of the target,
The control unit,
Based on the result recognized by the recognition unit, control the spray nozzle to spray the disinfectant toward the target, record the recognized result and the amount of the disinfectant,
Recognizing the face position of the target by the recognition unit, spraying the disinfectant based on the face position,
Receiving a depth image including the target from the depth camera, receiving a thermal image including the target from the thermal imaging camera, recognizing the height of the target and the body shape of the target from the depth image, recognizing the facial position of the target and the temperature of the target from the thermal image;
Recognizing the facial position of the target by applying a vision recognition algorithm to the thermal image;
The vision recognition algorithm is a CNN learning algorithm using a plurality of layers according to, and the CNN learning algorithm includes an image filter according to Equation 2 below applied to the thermal image.
AI-based sterilization gate system.
[Equation 2]

(step,

: pixels in the i-th row and j-th column of the filtered image expressed as a matrix,

: As an applied filter, Equation 3 below is applied.

: image,

: height of application filter (number of rows),

: The width (number of columns) of the application filter.)
[Equation 3]

(step,

: filter,

: Coefficient derived according to Equation 4 below,

: application filter)
[Equation 4]

delete delete delete receiving, by a control unit, a depth image and a thermal image including a target from a recognizing unit;
deriving height and body shape information of the target from the depth image by a controller;
deriving facial location information of the target and temperature information of the target from the thermal image by a controller;
Controlling a spray nozzle to spray a disinfectant based on facial position information of the target by a controller;
Deriving the amount of the disinfectant used by the control unit; and
Recording, by a controller, the amount of use, height information of the target, body shape information of the target, facial position information of the target, and temperature information of the target;
The step of deriving the target's face location information and the target's temperature information,
Recognizing the facial position of the target by applying a vision recognition algorithm to the thermal image;
The vision recognition algorithm is a CNN learning algorithm using a plurality of layers according to, and the CNN learning algorithm includes an image filter according to Equation 2 below applied to the thermal image,
AI-based sterilization gate control method.
[Equation 2]

(step,

: pixels in the i-th row and j-th column of the filtered image expressed as a matrix,

: As an applied filter, Equation 3 below is applied.

: image,

: height of application filter (number of rows),

: The width (number of columns) of the application filter.)
[Equation 3]

(step,

: filter,

: Coefficient derived according to Equation 4 below,

: application filter)
[Equation 4]

delete A non-transitory computer readable medium storing instructions,
The instructions, when executed by a processor, cause the processor to perform the method of claim 5.

Images