KR102341950B1 - Apparatus and method for evaluating aseptic technique based on artificial intelligence using motion analysis - Google Patents

Abstract

The present invention relates to an artificial intelligence-based aseptic manipulation evaluation apparatus and method using motion analysis, wherein the apparatus includes an image receiving unit for receiving an image about a specific person from a monitoring system including a surveillance camera for monitoring a specific space, and from the image A motion data acquisition unit for acquiring digital data on the movement of the specific person, a motion measurement unit for measuring a specific motion among the motions of the specific person by analyzing the digital data, and a sterile operation evaluation based on the measurement result related to the specific motion It includes an evaluation execution unit to perform.

Description

Apparatus and method for evaluating aseptic operation based on artificial intelligence using motion analysis

The present invention relates to aseptic manipulation evaluation technology, and more particularly, artificial intelligence-based sterile manipulation evaluation using motion analysis that can provide feedback to medical personnel by analyzing hand movements and distinguishing desirable and bad behaviors It relates to an apparatus and method.

All aseptic techniques performed in operating rooms in hospitals are based on non-contact techniques to prevent infection. To this end, it is stipulated in the basic manual to always maintain a position in a form that can minimize hand contact in the operating room. In addition, in principle, medical staff in the operating room should maintain their posture with their cleaned hands facing the sky, and it is required to maintain the posture so that their hands do not descend below the joint even after wearing sterile gloves and operating clothes.

On the other hand, with regard to this aseptic posture, that is, movement in the operating room, an experienced staff visually monitors the movement of new personnel and provides continuous feedback on the training. However, there is a disadvantage that the education method performed by monitoring with the human eye is always ineffective due to the limitation of attention.

Various CCTV systems are installed inside medical institutions to protect the safety of internal personnel and to increase security.

Korean Patent Publication No. 10-2009-0085587 (2009.08.07)

An embodiment of the present invention is to provide an apparatus and method for evaluating aseptic manipulation based on artificial intelligence using motion analysis that can provide feedback to medical personnel by analyzing hand movements and classifying desirable and bad behaviors.

An embodiment of the present invention is based on artificial intelligence using motion analysis that can effectively identify whether medical personnel in the operating room are properly implementing the correct aseptic manipulation technique, accurately quantify it, and support improvement through measurement, evaluation and feedback. An object of the present invention is to provide an apparatus and method for evaluating aseptic manipulation.

In embodiments, the apparatus for evaluating aseptic manipulation based on artificial intelligence using motion analysis includes an image receiving unit that receives an image about a specific person from a monitoring system including a surveillance camera for monitoring a specific space, and a movement of the specific person from the image. A motion data acquisition unit for acquiring digital data, a motion measurement unit for measuring a specific motion among the motions of the specific person by analyzing the digital data, and an evaluation performing unit for performing aseptic manipulation evaluation based on the measurement result related to the specific motion do.

The image receiver may decompose the image into a plurality of frames arranged in time order and perform frame compression when a rate of change between successive frames is less than or equal to a preset threshold.

When the number of consecutive frames is three or more, the image receiver may determine any one of the frames as a representative frame in the corresponding time period and perform the frame compression.

The motion data acquisition unit identifies at least one dynamic object for each of the plurality of frames, and determines a dynamic object corresponding to the specific person from the at least one dynamic object based on the association between the plurality of frames, It is possible to obtain digital data about the object.

The motion measurement unit may generate skeletal data corresponding to the movement of the specific person by obtaining characteristic information on each of the face, torso, and arms of the specific person from the digital data.

The evaluation performing unit tracks the movement of the arm in the skeletal data and compares the movement of the arm with a predefined dangerous operation to evaluate the sterile posture of the specific person as the aseptic operation evaluation, and the aseptic operation evaluation is The first rating and the position of the hand calculated according to the time and number of times that the position of the hand related to the movement of the arm is sensed in the first evaluation area defined as an area within a specific radius based on the center of the face It may include a second score calculated according to a distance spaced apart in the ground direction with respect to a horizontal plane including the center of the body.

The sterile operation evaluation apparatus may further include an infection prevention processing unit that provides prevention information for infection prevention according to the aseptic operation evaluation.

Among the embodiments, the method for evaluating aseptic manipulation based on artificial intelligence using motion analysis includes: receiving an image about a specific person from a monitoring system including a surveillance camera for monitoring a specific space; Acquiring data, analyzing the digital data to measure a specific motion among the movements of the specific person, performing aseptic manipulation evaluation based on the measurement result on the specific motion, and preventing infection according to the aseptic manipulation evaluation It includes the step of providing preventive information for

The disclosed technology may have the following effects. However, this does not mean that a specific embodiment should include all of the following effects or only the following effects, so the scope of the disclosed technology should not be understood as being limited thereby.

The apparatus and method for evaluating aseptic manipulation based on artificial intelligence using motion analysis according to an embodiment of the present invention can provide feedback to medical personnel by analyzing hand motion and classifying desirable motion from bad behavior.

The artificial intelligence-based aseptic manipulation evaluation apparatus and method using motion analysis according to an embodiment of the present invention can effectively determine whether medical personnel in the operating room are properly implementing the correct aseptic manipulation technique, and accurately quantify it to measure, evaluate and You can support improvement through feedback.

1 is a view for explaining the aseptic operation evaluation system according to the present invention.
FIG. 2 is a view for explaining the physical configuration of the aseptic operation evaluation device of FIG. 1 .
3 is a view for explaining the functional configuration of the aseptic operation evaluation device of FIG. 1 .
4 is a flowchart illustrating an AI-based aseptic operation evaluation process using motion analysis according to the present invention.

Since the description of the present invention is merely an embodiment for structural or functional description, the scope of the present invention should not be construed as being limited by the embodiment described in the text. That is, since the embodiment may have various changes and may have various forms, it should be understood that the scope of the present invention includes equivalents capable of realizing the technical idea. In addition, since the object or effect presented in the present invention does not mean that a specific embodiment should include all of them or only such effects, it should not be understood that the scope of the present invention is limited thereby.

On the other hand, the meaning of the terms described in the present application should be understood as follows.

Terms such as “first” and “second” are for distinguishing one component from another, and the scope of rights should not be limited by these terms. For example, a first component may be termed a second component, and similarly, a second component may also be termed a first component.

When a component is referred to as being “connected to” another component, it may be directly connected to the other component, but it should be understood that other components may exist in between. On the other hand, when it is mentioned that a certain element is "directly connected" to another element, it should be understood that the other element does not exist in the middle. Meanwhile, other expressions describing the relationship between elements, that is, "between" and "between" or "neighboring to" and "directly adjacent to", etc., should be interpreted similarly.

The singular expression is to be understood as including the plural expression unless the context clearly dictates otherwise, and terms such as "comprises" or "have" refer to the embodied feature, number, step, action, component, part or these It is intended to indicate that a combination exists, and it should be understood that it does not preclude the possibility of the existence or addition of one or more other features or numbers, steps, operations, components, parts, or combinations thereof.

In each step, identification numbers (eg, a, b, c, etc.) are used for convenience of description, and identification numbers do not describe the order of each step, and each step clearly indicates a specific order in context. Unless otherwise specified, it may occur in a different order from the specified order. That is, each step may occur in the same order as specified, may be performed substantially simultaneously, or may be performed in the reverse order.

The present invention can be embodied as computer-readable codes on a computer-readable recording medium, and the computer-readable recording medium includes all types of recording devices in which data readable by a computer system is stored. . Examples of the computer-readable recording medium include ROM, RAM, CD-ROM, magnetic tape, floppy disk, optical data storage device, and the like.

All terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs, unless otherwise defined. Terms defined in the dictionary should be interpreted as being consistent with the meaning of the context of the related art, and cannot be interpreted as having an ideal or excessively formal meaning unless explicitly defined in the present application.

1 is a view for explaining the aseptic operation evaluation system according to the present invention.

Referring to FIG. 1 , the aseptic operation evaluation system 100 may include a user terminal 110 , an aseptic operation evaluation device 130 , and a database 150 .

The user terminal 110 may correspond to a computing device capable of confirming the result of aseptic manipulation evaluation and checking prevention information for infection prevention, and may be implemented as a smartphone, a notebook computer, or a computer, but is not necessarily limited thereto, and a tablet It can also be implemented in various devices such as a PC. The user terminal 110 may be connected to the sterility operation evaluation apparatus 130 through a network, and a plurality of user terminals 110 may be simultaneously connected to the sterility operation evaluation apparatus 130 .

The aseptic manipulation evaluation device 130 may be implemented as a computer or a server corresponding to a program that can provide feedback to medical personnel by tracking the motion of the hand and distinguishing between desirable and bad behaviors. The aseptic operation evaluation device 130 may be wirelessly connected to the user terminal 110 through Bluetooth, WiFi, or the like, and may exchange data with the user terminal 110 through a network.

In one embodiment, the aseptic manipulation evaluation device 130 may perform an artificial intelligence-based sterility manipulation evaluation operation in conjunction with an external system if necessary, and the constructed information is stored in the database 150 corresponding to the physical storage device. can be stored and archived. On the other hand, the sterility evaluation device 130, unlike FIG. 1, may be implemented by including the database 150 therein. In addition, the aseptic operation evaluation device 130 may be implemented as a physical component constituting the system, including a processor, a memory, a user input/output unit, and a network input/output unit, which will be described in more detail with reference to FIG. 2 .

The database 150 may correspond to a storage device for storing various types of information required in the operation process of the aseptic manipulation evaluation device 130 . The database 150 may store image information of medical personnel acquired inside a medical institution such as a hospital, and may store data related to artificial intelligence for motion analysis constructed by the aseptic manipulation evaluation device 130 , and must be limited thereto. Instead, the aseptic manipulation evaluation device 130 may store information collected or processed in various forms in the process of analyzing the movements of medical personnel and providing feedback on the aseptic manipulation evaluation.

The monitoring system 170 may correspond to a device that monitors the movement of users in a medical institution such as a hospital. For example, the monitoring system 170 may correspond to a CCTV system, and may be implemented including a monitoring camera as a configuration for this. The monitoring system 170 may operate independently of the aseptic operation evaluation system 100 , and may be connected to a network to exchange control signals and data signals through interworking.

FIG. 2 is a view for explaining the physical configuration of the aseptic operation evaluation device of FIG. 1 .

Referring to FIG. 2 , the sterility evaluation apparatus 130 may be implemented including a processor 210 , a memory 230 , a user input/output unit 250 , and a network input/output unit 270 .

The processor 210 may execute a procedure for processing each step in the process of the sterility operation evaluation device 130 operating, and manage the memory 230 that is read or written throughout the process, and the memory ( 230) may schedule a synchronization time between the volatile memory and the non-volatile memory. The processor 210 may control the overall operation of the aseptic manipulation evaluation device 130 , and is electrically connected to the memory 230 , the user input/output unit 250 , and the network input/output unit 270 to control data flow between them. can do. The processor 210 may be implemented as a central processing unit (CPU) of the sterility evaluation apparatus 130 .

The memory 230 is implemented as a non-volatile memory, such as a solid state drive (SSD) or a hard disk drive (HDD), and may include an auxiliary storage device used to store overall data required for the aseptic operation evaluation device 130, and , and may include a main memory implemented as a volatile memory such as random access memory (RAM).

The user input/output unit 250 may include an environment for receiving a user input and an environment for outputting specific information to the user. For example, the user input/output unit 250 may include an input device including an adapter such as a touch pad, a touch screen, an on-screen keyboard, or a pointing device, and an output device including an adapter such as a monitor or a touch screen. In an embodiment, the user input/output unit 250 may correspond to a computing device connected through a remote connection, and in such a case, the sterility evaluation device 130 may be implemented as a server.

The network input/output unit 270 includes an environment for connecting with an external device or system through a network, for example, a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), and a VAN (Wide Area Network) (VAN). It may include an adapter for communication such as Value Added Network).

3 is a view for explaining the functional configuration of the aseptic operation evaluation device of FIG. 1 .

Referring to FIG. 3 , the aseptic manipulation evaluation device 130 includes an image receiving unit 310 , a motion data acquiring unit 320 , a motion measuring unit 330 , an evaluation performing unit 340 , an infection prevention processing unit 350 , and a control unit. (360).

The image receiving unit 310 may receive an image about a specific person from the monitoring system 170 including a monitoring camera for monitoring a specific space. Here, the specific space may correspond to a space in which medical treatment is performed, such as a hospital, a public health center, or an operating room. The image receiving unit 310 may be interlocked with the monitoring system 170 to receive images captured by the monitoring camera in real time or at specific time intervals, or may receive limitedly only at a preset specific time. For example, the aseptic operation evaluation device 130 may provide an evaluation result regarding the aseptic operation every week, and for this purpose, the images taken during the previous week are received at once through the image receiving unit 310 to evaluate the aseptic operation. can do.

In an embodiment, the image receiving unit 310 may decompose an image into a plurality of frames arranged in time order and perform frame compression when a rate of change between successive frames is less than or equal to a preset threshold. The rate of change between frames may be calculated based on the color difference between pixels, and the aseptic manipulation evaluation apparatus 130 may set and utilize a threshold value in advance. For example, an image can be divided into 30 frames per second, and when the rate of change between frames is less than 1% because there is no motion to be evaluated or there is little motion even if there is, the same image is displayed in all divided frames. can be created

Accordingly, the image receiving unit 310 may increase evaluation efficiency through pre-processing of the image acquired in the step before performing the aseptic manipulation evaluation. In this case, the frame compression performed by the image receiving unit 310 may correspond to an operation of selecting a frame usable for evaluation from among a plurality of frames.

In an embodiment, when the number of consecutive frames is three or more, the image receiving unit 310 may determine one of the corresponding frames as a representative frame in the corresponding time period and perform frame compression. When three or more frames with little change are consecutive, the image receiver 310 may determine any one of them as a representative frame in the corresponding section. In addition, the image receiving unit 310 may repeatedly perform frame compression according to the rate of change even between consecutive representative frames, and the number of repetitions regarding frame compression may be preset by the aseptic manipulation evaluation device 130 .

The motion data acquisition unit 320 may acquire digital data related to the movement of a specific person from the image. The motion data acquisition unit 320 may perform image analysis for each frame constituting the image by using artificial intelligence. That is, it is possible to identify a specific person and obtain data related to the movement as digital data.

In an embodiment, the motion data acquisition unit 320 identifies at least one dynamic object for each of a plurality of frames, and selects a dynamic object corresponding to a specific person from at least one dynamic object based on the association between the plurality of frames. and can acquire digital data about the corresponding dynamic object. Here, the dynamic object may correspond to a moving object in the image, and may include a person, an animal, and the like.

That is, the motion data acquisition unit 320 may identify a dynamic object existing in an image for each frame, and may generate and utilize an identification model for dynamic object identification. The identification model is a learning model generated through artificial intelligence learning, and may use a two-dimensional image as an input and provide information about identifiable objects existing in the image as an output. In this case, the output information may include minimum bounding rectangle (MBR) information about the dynamic object and the identified object information in the form of a feature vector. For example, when three dynamic objects exist in one frame image, three feature vectors corresponding to the dynamic objects may be included in the output information.

The motion measurement unit 330 may measure a specific motion among motions of a specific person by analyzing the digital data. That is, the motion measurement unit 330 may detect a specific motion or detect a motion within a specific range by tracking the motion of the corresponding dynamic object for each frame when it corresponds to a person among the dynamic objects identified in the image. The motion measurement unit 330 may perform motion measurement using only the image related to the dynamic object identified by the motion data acquisition unit 320 , and a learning model for motion measurement may be used. Through this, the motion measurement unit 330 may generate evaluation data regarding whether the medical personnel maintains an aseptic posture.

In an embodiment, the motion measurement unit 330 may generate skeletal data corresponding to the movement of the specific person by acquiring characteristic information on each of the face, torso, and arms of the specific person from the digital data. Here, the skeleton data may correspond to skeleton data corresponding to the user's movement, and may include parameter information for each part of the human body. That is, the skeletal data may be expressed as a set of parameter information for each part of the human body, and the motion measurement unit 330 may generate skeletal data for the face, torso, and both arms as a body part used for aseptic manipulation evaluation. can

The evaluation performing unit 340 may perform sterile operation evaluation based on the measurement result related to a specific operation. The evaluation performing unit 340 may extract correct motions and dangerous motions from a specific person's motions based on a desirable aseptic posture, respectively, and may perform aseptic manipulation evaluation according to the number of times, time, and motion patterns of the corresponding motions. . Therefore, the evaluation of aseptic manipulation can give a relatively low score when dangerous motions, for example, touching the face or mouth, or lowering the hand below the elbow, are frequently detected or maintained for a long time. . In addition, the aseptic manipulation assessment can give relatively high scores if correct behavior is detected frequently or maintained for a long time.

On the other hand, the evaluation performing unit 340 may generate an evaluation report for the evaluation of aseptic manipulation, and the evaluation report includes a rating graph according to the passage of time, a detection time of a dangerous action or detailed evaluation thereof and a comprehensive evaluation result, etc. Thus, it can be implemented with various visual expressions.

In one embodiment, the evaluation performing unit 340 tracks the movement of the arm in the skeletal data and compares the movement of the arm with a predefined dangerous operation to perform the evaluation of the sterile posture of a specific person as the aseptic operation evaluation. have. In this case, the evaluation of aseptic manipulation includes a first rating calculated according to the time and number of times that the position of the hand related to the movement of the arm is sensed within a first evaluation area defined as an area within a specific radius based on the center of the face; A second rating may be included in which the position of the hand is calculated according to a distance spaced apart from the horizontal plane including the center of the body in the ground direction.

That is, since the position and direction of the hand can be very important evaluation factors for the aseptic posture, the evaluation performing unit 340 performs sterility focusing on the movement of the arm that is closely related to the position of the hand among the body parts of a specific person. Operational evaluation can be performed. To this end, the evaluation performing unit 340 may utilize the reference data on the aseptic posture stored in the database 150, and the reference data may include information on the exemplary behavior of the aseptic posture.

More specifically, the evaluation performing unit 340 may acquire the position information of the hand according to the movement of the arm, and perform aseptic manipulation evaluation based on whether the position of the hand is similar to the position of the hand required in the aseptic posture. can An evaluation area regarding the position of the hand required in the aseptic posture may be set in advance and reflected in the evaluation, for example, an area within 30 cm of the center of the face may be set as the evaluation area. In addition, a distance spaced apart in the ground direction with respect to a horizontal plane including the center of the body (or the height of the elbow) may be set as an evaluation criterion, and accordingly, evaluation of aseptic manipulation may be made based on the separation distance.

In one embodiment, the evaluation performing unit 340 includes a third rating calculated according to the distance and time in which the position of the hand is spaced apart in the ground direction based on the horizontal plane (or the height of the elbow) including the center of the body Aseptic handling evaluation can be performed. In another embodiment, the evaluation performing unit 340 may perform aseptic manipulation evaluation including a fourth rating calculated according to the number and time of contact with an object in which the position of the hand is in contact with another object.

Meanwhile, the evaluation performing unit 340 may calculate a comprehensive rating by integrating various ratings, and may determine an infection risk level for the corresponding operation based on the overall rating for the user's operation. That is, the evaluation performing unit 340 may track the position of the user's hand and calculate the risk of infection, and the aseptic manipulation evaluation device 130 may provide feedback on the corresponding operation in real time based on the risk of infection. .

The infection prevention processing unit 350 may provide prevention information for infection prevention according to the aseptic operation evaluation. When the aseptic operation evaluation is expressed numerically, the infection prevention processing unit 350 may grade the evaluation result based on the numerical value, and may provide infection prevention information according to the evaluation grade. The infection prevention information is prevention information for infection prevention and may include code of conduct (manual) information for maintaining an aseptic posture of medical personnel.

In one embodiment, the infection prevention processing unit 350 may provide aseptic posture learning in conjunction with the evaluation of aseptic manipulation. More specifically, the aseptic operation evaluation device 130 may perform the sterile operation evaluation in real time and provide the result, and the infection prevention processing unit 350 notifies the user in real time through the corresponding user terminal 110 based on the real-time rating. You can draw the user's attention by providing a method. At this time, the real-time notification may be implemented in the form of vibration, alarm, push message, etc. and displayed through the user terminal 110 .

To this end, a dedicated program or a dedicated app may be installed and executed in the user terminal 110 . A dedicated program or dedicated app may provide a menu related to aseptic posture learning, and the user may freely control the start and end of aseptic posture learning through activation of the menu.

The control unit 360 controls the overall operation of the aseptic manipulation evaluation device 130 , and the image receiving unit 310 , the motion data obtaining unit 320 , the motion measuring unit 330 , the evaluation performing unit 340 , and the infection prevention processing unit Control flow or data flow between 350 may be managed.

4 is a flowchart illustrating an AI-based aseptic operation evaluation process using motion analysis according to the present invention.

Referring to FIG. 4 , the aseptic manipulation evaluation device 130 may receive an image about a specific person from the monitoring system 170 including a monitoring camera for monitoring a specific space through the image receiving unit 310 (step S410). . The aseptic manipulation evaluation device 130 may acquire digital data regarding the movement of a specific person from the image through the motion data acquisition unit 320 (step S430).

In addition, the aseptic manipulation evaluation apparatus 130 may measure a specific motion among the motions of a specific person by analyzing the digital data through the motion measurement unit 330 (step S450). The sterility operation evaluation apparatus 130 may perform the sterility operation evaluation based on the measurement result related to a specific operation through the evaluation performing unit 340 (step S470). The aseptic operation evaluation apparatus 130 may provide prevention information for infection prevention according to the aseptic operation evaluation through the infection prevention processing unit 350 (step S490).

Although the above has been described with reference to preferred embodiments of the present invention, those skilled in the art can variously modify and change the present invention within the scope without departing from the spirit and scope of the present invention as set forth in the claims below. You will understand that it can be done.

100: aseptic operation evaluation system
110: user terminal 130: aseptic operation evaluation device
150: database 170: surveillance system
210: processor 230: memory
250: user input/output unit 270: network input/output unit
310: image receiving unit 320: motion data obtaining unit
330: motion measuring unit 340: evaluation performing unit
350: infection prevention processing unit 360: control unit

Claims (8)

an image receiving unit for receiving an image about a specific person from a monitoring system including a monitoring camera for monitoring a specific space;
a motion data acquisition unit configured to acquire digital data related to the movement of the specific person from the image;
a motion measurement unit that analyzes the digital data to measure a specific motion among the motions of the specific person; and
Comprising an evaluation performing unit for performing aseptic operation evaluation based on the measurement result related to the specific operation,
The motion measurement unit generates skeletal data corresponding to the movement of the specific person by obtaining characteristic information for each of the face, torso, and arms of the specific person from the digital data,
The evaluation performing unit tracks the movement of the arm in the skeletal data and compares the movement of the arm with a predefined dangerous operation to evaluate the sterile posture of the specific person as the aseptic operation evaluation,
The evaluation of the aseptic manipulation includes a first rating calculated according to the time and number of times the position of the hand related to the movement of the arm is sensed within a first evaluation area defined as an area within a specific radius based on the center of the face; Artificial intelligence-based aseptic manipulation evaluation apparatus using motion analysis, characterized in that the position of the hand includes a second rating calculated according to a distance in the ground direction based on a horizontal plane including the center of the torso.
According to claim 1, wherein the image receiving unit
Artificial intelligence-based aseptic manipulation evaluation apparatus using motion analysis, characterized in that the image is decomposed into a plurality of frames arranged in time sequence and frame compression is performed when the rate of change between successive frames is less than or equal to a preset threshold value .
The method of claim 2, wherein the image receiving unit
Artificial intelligence-based aseptic manipulation evaluation apparatus using motion analysis, characterized in that when the number of the consecutive frames is three or more, any one of the frames is determined as a representative frame in the corresponding time period and the frame compression is performed .
The method of claim 2, wherein the motion data acquisition unit
Identifying at least one dynamic object for each of the plurality of frames, determining a dynamic object corresponding to the specific person from the at least one dynamic object based on the association between the plurality of frames, and digital data on the dynamic object Artificial intelligence-based aseptic operation evaluation device using motion analysis, characterized in that it acquires.
delete delete According to claim 1,
Artificial intelligence-based aseptic operation evaluation apparatus using motion analysis, characterized in that it further comprises an infection prevention processing unit that provides prevention information for infection prevention according to the aseptic operation evaluation.
Receiving an image about a specific person from a monitoring system including a monitoring camera for monitoring a specific space;
obtaining digital data about the movement of the specific person from the image;
measuring a specific motion among the motions of the specific person by analyzing the digital data;
performing aseptic operation evaluation based on the measurement result regarding the specific operation; and
Comprising the step of providing prevention information for preventing infection according to the aseptic manipulation evaluation,
Measuring the specific motion includes generating skeletal data corresponding to the motion of the specific person by acquiring feature information on each of the face, torso, and arms of the specific person from the digital data,
The step of performing the aseptic manipulation evaluation includes: tracking the movement of the arm in the skeletal data and comparing the motion of the arm with a predefined dangerous motion to evaluate the aseptic posture of the specific person as the aseptic manipulation evaluation including,
The evaluation of the aseptic manipulation includes a first rating calculated according to the time and number of times the position of the hand related to the movement of the arm is sensed within a first evaluation area defined as an area within a specific radius based on the center of the face; An artificial intelligence-based aseptic manipulation evaluation method using motion analysis, characterized in that the position of the hand includes a second rating calculated according to a distance in the ground direction based on a horizontal plane including the center of the torso.

Images