KR102626551B1 - Body analysis device - Google Patents

Abstract

The present invention relates to a body shape analysis device, comprising: an image acquisition unit that captures skeleton images and ROM images (range of motion) of a user through a body code composed of shooting postures; a body shape analysis unit that analyzes the user's joint imbalance, joint movement range, and lateral imbalance by analyzing the skeleton images and the ROM image; and a display unit that displays results analyzed by the body shape analysis unit. Therefore, the present invention can provide a user's body shape analysis result based on the posture index calculated by analyzing the user's image.

Description

Body type analysis device {BODY ANALYSIS DEVICE}

The present invention relates to body shape analysis technology, and more specifically, to a body shape analysis device that can provide a user's body shape analysis result based on the posture index calculated by analyzing the user's image.

The human body is often out of balance in the front, back, left, and right due to bad posture, habits, diseases, etc., resulting in physical imbalance. For example, sitting at a desk for a long time, using a computer, or sitting in an incorrect posture for a long time while driving can cause physical imbalance. In addition, if you have a disease or pain in your right leg and put more force on your left leg for a long time, your left and right body may be out of balance, resulting in physical imbalance.

If this physical imbalance is left unattended for a long period of time, it can have a negative impact on health, so it is necessary to analyze body shape and periodically check body balance and health status.

To this end, equipment that performs body shape analysis is being developed, but it is limited to simply measuring the user's height and weight, measuring body fat through bioimpedance, etc., and then providing the results based on this, providing accurate and detailed information to the user. There is a problem with not being able to provide data.

This application is based on research results conducted under the ‘Seoul City Industry-Academic-Research Cooperation Project’, and specific project information is as follows.

Assignment number: CY201053

Name of local government: Seoul Metropolitan City

Research Project Name: 2020 Post-Corona Specialized Artificial Intelligence Technology Commercialization Support Project

Research project title: Non-face-to-face education service for musculoskeletal treatment/prevention using artificial intelligence

Host organization name: WeHeald Co., Ltd.

Participating organization name: Seja Co., Ltd.

Research period: 2020.12.01. ~ 2021.11.30. (12 months)

Korean Patent Publication No. 10-2016-0035497 (2016.03.31)

One embodiment of the present invention seeks to provide a body shape analysis device that can provide a user's body shape analysis result based on a posture index calculated by analyzing the user's image.

Among the embodiments, the body shape analysis device includes an image acquisition unit that captures skeleton images and ROM images (range of motion) of the user through body codes composed of shooting postures; a body shape analysis unit that analyzes the user's joint imbalance, joint movement range, and lateral imbalance by analyzing the skeleton images and the ROM image; and a display unit that displays results analyzed by the body shape analysis unit.

The image acquisition unit may capture the user's posture and movement process and determine the moment when the movement range is greatest as the ROM image.

The image acquisition unit performs asymmetric measurement by setting a plurality of balance lines for each of the frontal posture and side posture during the shooting process of the skeleton images, and the plurality of balance lines for the movement posture during the shooting process of the ROM image. You can set to perform movement degree measurement.

The body shape analysis unit determines the user's joint imbalance through asymmetric measurement for the frontal posture, determines the user's lateral imbalance through asymmetric measurement for the side posture, and determines the joint imbalance through measurement of the degree of movement for the movement posture. The range of movement can be determined.

The plurality of balance lines may include a central vertical line and a central horizontal line related to the user's body, a vertical line and a horizontal line related to a specific part of the user, a connection line to points of the user's body, and a central point of the user's body. .

The body shape analysis unit detects measurement points corresponding to the lower point of the external auditory canal, the middle point of the upper arm, the front point of the chest, the back point of the scapula, the back point of the lumbar spine, the front point of the navel, the middle point of the thigh, and the point below the pelvic bone in the side posture, Individual distances to the measurement points with respect to a first reference line defined in a vertical direction based on the point below the pectoral bone and a second reference line defined along an image boundary formed behind the user in the skeleton image of the side posture. is measured, and a result value related to the asymmetry measurement can be calculated through a ratio equation related to the individual distance, and an asymmetry ratio between the result value and a preset reference value can be calculated.

The disclosed technology can have the following effects. However, since it does not mean that a specific embodiment must include all of the following effects or only the following effects, the scope of rights of the disclosed technology should not be understood as being limited thereby.

The body shape analysis device according to an embodiment of the present invention can provide a user's body shape analysis result based on the posture index calculated by analyzing the user's image.

The body shape analysis device according to an embodiment of the present invention provides a ROM measurement function capable of body shape analysis in video units, making it possible to more easily and intuitively analyze the range of motion of moving joints and left and right body imbalance.

1 is a diagram illustrating a body shape analysis system according to the present invention.
FIG. 2 is a diagram explaining the system configuration of the body shape analysis device of FIG. 1.
FIG. 3 is a diagram explaining the functional configuration of the body shape analysis device of FIG. 1.
Figure 4 is a flowchart explaining the body shape analysis method according to the present invention.
Figure 5 is a diagram illustrating an embodiment of the frontal body shape analysis process according to the present invention.
Figures 6 and 7 are diagrams illustrating an embodiment of the lateral body shape analysis process according to the present invention.

Since the description of the present invention is only an example for structural or functional explanation, the scope of the present invention should not be construed as limited by the examples described in the text. In other words, since the embodiments can be modified in various ways and can have various forms, the scope of rights of the present invention should be understood to include equivalents that can realize the technical idea. In addition, the purpose or effect presented in the present invention does not mean that a specific embodiment must include all or only such effects, so the scope of the present invention should not be understood as limited thereby.

Meanwhile, the meaning of the terms described in this application should be understood as follows.

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

When a component is referred to as being “connected” to another component, it should be understood that it may be directly connected to the other component, but that other components may exist in between. On the other hand, when a component is referred to as being “directly connected” to another component, it should be understood that there are no other components in between. Meanwhile, other expressions that describe the relationship between components, such as "between" and "immediately between" or "neighboring" and "directly neighboring" should be interpreted similarly.

Singular expressions should be understood to include plural expressions unless the context clearly indicates otherwise, and terms such as “comprise” or “have” refer to implemented features, numbers, steps, operations, components, parts, or them. It is intended to specify the existence of a combination, and should be understood as not excluding in advance the possibility of the presence or addition of one or more other features, numbers, steps, operations, components, parts, or combinations thereof.

For each step, identification codes (e.g., a, b, c, etc.) are used for convenience of explanation. The identification codes do not explain the order of each step, and each step clearly follows a specific order in context. Unless specified, events may occur differently 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 opposite order.

All terms used herein, unless otherwise defined, have the same meaning as commonly understood by a person of ordinary skill in the field to which the present invention pertains. Terms defined in commonly used dictionaries should be interpreted as consistent with the meaning they have in the context of the related technology, and cannot be interpreted as having an ideal or excessively formal meaning unless clearly defined in the present application.

1 is a diagram illustrating a body shape analysis system according to the present invention.

Referring to FIG. 1, the body shape analysis system 100 may include a user terminal 110, a body shape analysis device 130, and a database 150.

The user terminal 110 may correspond to a terminal device operated by a user. Additionally, the user terminal 110 is a device constituting the body shape analysis system 100 and may correspond to a computing device that operates in conjunction with the body shape analysis device 130. For example, the user terminal 110 may be implemented as a smartphone, laptop, or computer that can be operated by being connected to the body shape analysis device 130, but is not necessarily limited thereto, and may also be implemented as a variety of devices, including tablet PCs, etc. You can. Additionally, the user terminal 110 may install and execute a dedicated program or application (or app) for linking with the body shape analysis device 130.

In one embodiment, the user terminal 110 may be implemented to include a camera for capturing user images used for body shape analysis. In other words, the video or image captured through the user terminal 110 can be transmitted to the body shape analysis device 130 through the network, and the body shape analysis device 130 analyzes the received video or image to generate a body shape analysis result. can do.

The body shape analysis device 130 may be implemented as a server corresponding to a computer or program that performs the body shape analysis method according to the present invention. Additionally, the body shape analysis device 130 may be connected to the user terminal 110 through a wired network or a wireless network such as Bluetooth, WiFi, or LTE, and may transmit and receive data with the user terminal 110 through the network.

Additionally, the body shape analysis device 130 may be implemented to operate in connection with an independent external system (not shown in FIG. 1) to provide related services. For example, the body shape analysis device 130 may be implemented to provide various services in conjunction with a payment system, authentication system, machine learning system, blockchain system, etc. In one embodiment, the body shape analysis device 130 may be implemented as a cloud server and may perform operations that provide big data analysis and user-customized information through cloud services.

The database 150 may correspond to a storage device that stores various information required during the operation of the body shape analysis device 130. For example, the database 150 may store information about a video or image taken of a user, and may store information about body shape analysis results, but is not necessarily limited thereto, and the body shape analysis device 130 may be used according to the present invention. In the process of performing the body shape analysis method, information collected or processed can be stored in various forms.

In addition, in FIG. 1, the database 150 is shown as a device independent of the body shape analysis device 130, but is not necessarily limited thereto, and may be implemented as a logical storage device included in the body shape analysis device 130. Of course.

FIG. 2 is a diagram explaining the system configuration of the body shape analysis device of FIG. 1.

Referring to FIG. 2 , the body shape analysis device 130 may include a processor 210, a memory 230, a user input/output unit 250, and a network input/output unit 270.

The processor 210 can execute a body shape analysis procedure according to an embodiment of the present invention, and manage the memory 230 that is read or written in this process, and the volatile memory and non-volatile memory in the memory 230. You can schedule the synchronization time between The processor 210 can control the overall operation of the body shape analysis 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 the data flow between them. You can. The processor 210 may be implemented as a CPU (Central Processing Unit) of the body shape analysis device 130.

The memory 230 may be implemented as a non-volatile memory such as a solid state disk (SSD) or a hard disk drive (HDD) and may include an auxiliary memory device used to store all data required for the body shape analysis device 130, It may include a main memory implemented as volatile memory such as RAM (Random Access Memory). Additionally, the memory 230 can store a set of instructions for executing the body shape analysis method according to the present invention by being executed by the electrically connected processor 210.

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

The network input/output unit 270 provides a communication environment for connection to the user terminal 110 through a network, for example, a local area network (LAN), a metropolitan area network (MAN), a wide area network (WAN), and It may include an adapter for communication such as VAN (Value Added Network). Additionally, the network input/output unit 270 may be implemented to provide short-range communication functions such as WiFi and Bluetooth or wireless communication functions of 4G or higher for wireless transmission of data.

FIG. 3 is a diagram explaining the functional configuration of the body shape analysis device of FIG. 1.

Referring to FIG. 3, the body shape analysis device 130 may include an image acquisition unit 310, a body shape analysis unit 330, a display unit 350, and a control unit 370.

The image acquisition unit 310 can capture the user's skeleton images and ROM images (range of motion) through body codes composed of shooting postures. Here, the body code may correspond to the user's posture information that needs to be photographed for body shape analysis. For example, body shape analysis may require images of the user's frontal posture, knee posture, and side posture, or images of the user's movements. The body code can be defined including frontal posture, knee posture, and side posture or standard movements related to the user's movements. The image acquisition unit 310 may acquire a video or image by photographing a user in a shooting posture corresponding to the body code.

To this end, the image acquisition unit 310 may operate in conjunction with the user terminal 110 and receive a video or image captured through the camera of the user terminal 110 from the user terminal 110.

At this time, the camera operated under the control of the user terminal 110 may include not only cameras included in smartphones, laptops, tablets, etc., but also a 3D depth sensor. Additionally, the image acquisition unit 310 may simultaneously receive videos or images taken at various angles from a plurality of user terminals 110.

In one embodiment, the image acquisition unit 310 performs asymmetric measurement by setting a plurality of balance lines for each of the frontal and side postures in the process of shooting skeleton images, and performs asymmetric measurement in the process of shooting ROM images. It is possible to measure the degree of movement by setting a plurality of balance lines. The image acquisition unit 310 can collect video or images for body shape analysis in conjunction with the user terminal 110, and, if necessary, capture images in the skeleton image or ROM image through a dedicated program running on the user terminal 110. Information can be collected through tracking.

More specifically, the image acquisition unit 310 may collect information about a plurality of balance lines used for body shape analysis through user input. For example, the image acquisition unit 310 may request user input regarding the balance line for the skeleton image or ROM image through a dedicated program of the user terminal 110. That is, the user can check his/her video or image on the user terminal 110 and directly input the balance line corresponding to the video or image using a predetermined interface. The image acquisition unit 310 may receive information directly input by the user along with the video or image and transmit it to the body shape analysis step.

In one embodiment, the plurality of balance lines may include a central vertical line and a central horizontal line related to the user's body, vertical and horizontal lines related to a specific part of the user, connection lines to points of the user's body, and a central point of the user's body. . The central vertical line may correspond to the vertical center line, and when the user inputs a pair of both end points in a horizontal position corresponding to the waist or pelvis of the body, the center line between the points may be derived.

Additionally, the central horizontal line may correspond to the horizontal center line, and when the user inputs points about the ends of the head and soles in the vertical direction, the center line between the corresponding points may be derived. Vertical and horizontal lines related to a specific part of the user may correspond to vertical and horizontal lines defined based on a specific location on the body when a specific location on the body is input by the user.

Additionally, the connecting line for points on the user's body may correspond to a straight line defined by connecting the points when two or more points on the body are input by the user. For example, if there are two points, it can be defined as a connecting line connecting the points. If there are three points, two connecting lines can be defined between the other points (i.e., reference points) based on the first point (i.e., center point), and the angle between the two connecting lines is defined. It can be.

Additionally, the central point of the user's body may correspond to the central point of the body, and vertical and horizontal cross lines may be defined based on the central point of the body according to the user's selection. In the process of collecting an image related to the user's posture, the image acquisition unit 310 may collect at least one of a plurality of balance lines along with the image, and for this purpose, a predetermined number of balance lines may be collected through a dedicated program running on the user terminal 110. An interface can be provided.

In addition, the image acquisition unit 310 can collect information about a plurality of balance lines by providing an independent interface according to the skeleton image and the ROM image. That is, in the case of skeleton images, input functions of the vertical center line, dR0, dL0, dR1, dL1, horizontal center line, aR0 and aL0 for asymmetry measurement can be provided along with the angle measurement function for frontal posture or knee posture. there is. In the case of side posture, input functions of the vertical center line, dE, dS, dH, dB, dA, dK, and dL for asymmetry measurement can be provided.

Additionally, in the case of ROM video, a balance line input function may be provided to select a specific frame during video playback and measure the angle on the specific frame. At this time, information about the balance line input in a specific frame may be sequentially generated and stored together with the corresponding ROM image.

In one embodiment, the image acquisition unit 310 may capture the user's posture movement process and determine the moment when the movement range is the greatest as the ROM image. The image acquisition unit 310 can start or stop recording the ROM video according to the user's selection on the user terminal 110, and basically generates the captured video from the start point to the end point as a ROM video. In addition, the image acquisition unit 310 can determine the moment when the movement range is the greatest by tracking the user's posture movement process among the captured images, and selectively apply the time range section based on that point in time to the corresponding time range section. Only ROM videos can be created.

The body shape analysis unit 330 may analyze the user's joint imbalance, joint movement range, and lateral imbalance by analyzing skeleton images and ROM images. In one embodiment, the body shape analysis unit 330 determines the user's joint imbalance through asymmetric measurement for the frontal posture, determines the user's lateral imbalance through asymmetric measurement for the side posture, and measures the degree of movement for the movement posture. Through this, the range of joint movement can be determined. The analysis process of joint imbalance will be explained in more detail with reference to FIG. 5 , and the analysis process for lateral imbalance will be explained in more detail with reference to FIG. 6 .

Additionally, in the analysis process of the range of joint movement, the range of joint movement can be determined by determining the user's movement posture from the ROM image and measuring the degree of movement for the corresponding movement posture. For example, if the user's movement posture in the ROM video is determined to be 'lifting left leg', the range of movement for the left knee joint can be determined by measuring the degree of movement relative to the height of the left knee. At this time, the user's moving posture may include lifting legs, walking, spreading legs, waving hands, opening hands, bending knees, jumping, etc.

The display unit 350 may display the results analyzed by the body shape analysis unit 330. To this end, the display unit 350 may be implemented including a display panel that outputs various image information. Meanwhile, the display unit 350 may display analysis results in conjunction with the user terminal 110. That is, the display unit 350 can transmit the analysis result to the user terminal 110, and the analysis result can be provided through a dedicated program running on the user terminal 110. For this purpose, the dedicated program can graphically visualize and output the analysis results using various visualization tools.

In one embodiment, the display unit 350 may provide customized information to the user based on body shape analysis results. For example, user-customized information may include posture information, exercise information, and food information. In other words, the display unit 350 can provide integrated management information on the body shape analysis results, and if it is determined that there is a problem with a specific joint as a result of the body shape analysis, information on posture, exercise, and food that is good for the joint is customized to the user. It can be provided as.

The control unit 370 can control the overall operation of the body shape analysis device 130 and manage the control flow or data flow between the image acquisition unit 310, the body shape analysis unit 330, and the display unit 350.

Figure 4 is a flowchart explaining the body shape analysis method according to the present invention.

Referring to FIG. 4, the body shape analysis device 130 analyzes the user's skeleton images and ROM images (ROM images, range of motion) through body codes composed of shooting postures through the image acquisition unit 310. ) can be photographed (step S410).

Additionally, the body shape analysis device 130 may analyze the skeleton images and ROM images through the body shape analysis unit 330 to analyze the user's joint imbalance, joint movement range, and lateral imbalance (step S430).

Additionally, the body shape analysis device 130 may display the results analyzed by the body shape analysis unit through the display unit 350 (step S450).

Figure 5 is a diagram illustrating an embodiment of the frontal body shape analysis process according to the present invention.

Referring to FIG. 5, the body shape analysis device 130 may perform asymmetry measurement by analyzing an image related to the frontal posture among the user's skeleton images. The body shape analysis device 130 can set the center line of the user's body in a frontal posture. At this time, the center line may be defined around a specific point directly input by the user, and if necessary, the body shape analysis device 130 may derive it through image analysis.

For example, the body shape analysis device 130 may detect a bounding box containing the user's body from an image of the frontal posture by applying an object detection algorithm, and determine the center point of the bounding box. The center line defined in the vertical direction can be determined based on .

Thereafter, the body shape analysis device 130 may perform asymmetric measurement on parts selected by the user or set in advance based on the center line. In figure (a) of FIG. 5, the body shape analysis device 130 can perform asymmetric measurements of the head, shoulders, pelvis, and knees based on the center line. For example, the body shape analysis device 130 may measure the asymmetry degree dR ₁ /DL ₁ using measurement points, dR ₁ and dL ₁ , set at the shoulder area on the center line. Additionally, the body shape analysis device 130 can measure the asymmetry degree dR ₂ /DL ₂ using measurement points, dR ₂ and dL ₂ , set in the pelvic region from the center line. The body shape analysis device 130 can calculate the degree of left and right asymmetry in parts such as the head, shoulders, pelvis, and knees and numerically express it as a + or - value depending on the direction of leaning to the left or right.

Additionally, the body shape analysis device 130 can set a horizontal line regarding the user's ankle point in the frontal posture. At this time, the user's ankle point may correspond to the point below the pelvic bone or the sole of the foot. In figure (b) of FIG. 5, the body shape analysis device 130 can perform asymmetric measurement of the head, shoulders, pelvis, and knees based on the ankle point. For example, the body shape analysis device 130 may measure the degree of asymmetry aR/aL using measurement points, aR and aL, set in the shoulder area based on the ankle point. The body shape analysis device 130 can calculate the degree of height asymmetry in parts such as the head, shoulders, pelvis, and knees and numerically express it as a + or - value depending on the left or right tilt. Additionally, the body shape analysis device 130 can express + or - values related to tilt as upper left, upper right, lower left, and lower right. Meanwhile, the asymmetry degree calculated from the frontal posture can be analyzed as a normal range between 1±0.3.

Figures 6 and 7 are diagrams illustrating an embodiment of the lateral body shape analysis process according to the present invention.

Referring to FIGS. 6 and 7, the body shape analysis device 130 may perform asymmetry measurement by analyzing an image related to the side posture among the user's skeleton images. First, in the side posture, the body shape analysis device 130 measures the point below the external auditory canal (ear) 610, the midpoint of the upper arm (620), the rear point of the scapula (back) (630), and the front point of the thorax (chest) (640). , the measurement points corresponding to the rear point of the lumbar spine (650), the front point of the navel (660), the midpoint of the thigh (thigh) (670), and the point below the ankle bone (680) can be detected, respectively. .

Afterwards, the body shape analysis device 130 uses a first reference line 690 defined in the vertical direction based on the point below the pectoral bone 680 and an image boundary 730 formed behind the user in the skeleton image 710 of the side posture. ) The individual distances to the measurement points can be measured with respect to the second reference line 720 defined along. For example, in FIG. 6, the body shape analysis device 130 measures the distance dK of the rear point 630 of the scapula (back) and the distance dB of the front point 640 of the chest (chest) based on the first reference line 690. , the distance dL to the rear point of the lumbar spine (650) and the distance dA to the front point of the navel (660) can be measured, respectively.

In addition, in FIG. 7, the body shape analysis device 130 measures the distance dE to the point 610 below the external auditory canal (ear), the distance dS to the midpoint 620 of the upper arm (upper arm), and the thigh based on the second reference line 720. (Thigh) The distance dH to the midpoint (670) can be measured respectively. That is, in the case of dE, dS, and dH in asymmetric measurement, the distance measured based on the second reference line 720 may be used instead of the distance measured based on the first reference line 690. Because dE, dS, and dH can be measured in units of 10 mm and 1 mm, respectively, so while they are normal to the naked eye, the value related to the asymmetry ratio can be calculated as a very large value, such as 10. Therefore, dE, dS, and dH can be measured based on the border of the screen formed behind the measuring person based on the shooting screen. In the case of a camera linked to the body shape analysis device 130, the user's posture is always measured with the same pixel at the same location and distance, so the asymmetry rate regarding the user's posture can be effectively measured by applying the above method. .

Thereafter, the body shape analysis device 130 may calculate a result value related to asymmetry measurement through a ratio equation regarding individual distances and calculate an asymmetry ratio between the result value and a preset reference value (for example, '1'). More specifically, the rate equation for the asymmetry rate can be defined as follows. (1)(dK+dA)/(dB+dL), (2)(dE)/(dS), (3)(dE)/(dH), (4)(dS)/(dH).

Meanwhile, the body shape analysis device 130 is operated between the center line defined in the vertical direction based on the midpoint of the thigh (thigh) 670 and the midpoint of the thigh (thigh) 670 and the rear point of the scapula (back) 630. The angle TI between the connecting lines can be measured. In addition, the body shape analysis device 130 connects the connection line between the midpoint of the thigh (thigh) 670 and the rear point of the scapula (back) 630, the rear point of the scapula (back) 630, and the rear point of the lumbar spine (back) ( 650), the angle BT between the connecting lines can be measured. The body shape analysis device 130 can calculate a ratio equation for (5) TI/BT.

As a result, the body shape analysis device 130 can derive the asymmetry degree rate by calculating the ratio equations for (1) to (5) above for the side posture. At this time, the asymmetry degree can be analyzed as a normal range between 1±0.3. For example, if the (dE)/(dS) value is greater than 1, it can be analyzed as a turtle neck, and if it is less than 1, it can be analyzed as a straight neck, etc., and the body shape analysis device 130 is based on the asymmetry degree rate. The degree can be quantified and provided.

In one embodiment, the body shape analysis device 130 may provide a function to automatically track each skeletal point using a depth camera, etc. In this case, the body shape analysis device 130 can effectively analyze the frontal posture, side posture, and movement posture with just a simple photograph, including turtle neck, straight neck, pelvic anteroposterior displacement, upper and lower spine imbalance, whole body left-right deviation, shoulder imbalance, OX legs, etc. can be automatically measured and provided as analysis results.

The body shape analysis device 130 according to the present invention can immediately identify joint imbalance. In other words, the body shape analysis device 130 displays angles for each joint point so that the degree can be intuitively confirmed and provides a function for determining imbalance tendencies. In addition, the body shape analysis device 130 can provide a posture index for measuring lateral body shapes such as turtle neck and straight neck, and has zoom-in and zoom-out functions for specifying 8 measurement points and 8 measurement point standards. Can provide objective analysis values. In addition, the body type analysis device 130 provides ROM (Range of Motion) measurement and analysis functions, allows the range of motion of human joints to be freely measured in various movements, and provides a dynamic analysis function for each frame through video recording. can be provided.

The body shape analysis device 130 according to the present invention can collect data on body shape measurement by analyzing videos or images taken with a smartphone, etc., and learns body shape measurement-related data photographed and collected by an unspecified number of people to determine body shape. You can also build a learning model for analysis. In other words, the body shape analysis device 130 can contribute to building a body shape analysis system by easily providing body shape analysis results on personal devices such as smartphones through the constructed learning model.

Although the present invention has been described above with reference to preferred embodiments, those skilled in the art may make various modifications and changes to the present invention without departing from the spirit and scope of the present invention as set forth in the claims below. You will understand that you can do it.

100: Body type analysis system
110: User terminal 130: Body shape analysis device
150: database
210: Processor 230: Memory
250: user input/output unit 270: network input/output unit
310: Image acquisition unit 330: Body shape analysis unit
350: display unit 370: control unit

Claims (4)

The user's skeleton images (skeleton images) and ROM images (ROM images, range of motion) are captured through a body code composed of shooting postures, and in the process of shooting the skeleton images, the front posture and side posture are recorded respectively. an image acquisition unit that sets a plurality of balance lines to perform asymmetric measurement, and performs movement degree measurement by setting the plurality of balance lines with respect to the movement posture during the capturing of the ROM image;
By analyzing the skeleton images and the ROM image, the user's joint imbalance, joint movement range, and lateral imbalance are analyzed, the user's joint imbalance is determined through asymmetry measurement for the frontal posture, and the lateral posture is determined. a body shape analysis unit that determines the user's lateral imbalance by measuring asymmetry and determines a range of joint movement by measuring the degree of movement for the movement posture; and
It includes a display unit that displays the results analyzed by the body shape analysis unit,
The body shape analysis unit
In the side posture, measurement points corresponding to the point below the external auditory canal, the middle point of the upper arm, the front point of the chest, the back point of the scapula, the back point of the lumbar spine, the front point of the navel, the middle point of the thigh, and the point below the pelvic bone are detected,
Individual distances to the measurement points with respect to a first reference line defined in a vertical direction based on the point below the pectoral bone and a second reference line defined along an image boundary formed behind the user in the skeleton image of the side posture. Measure,
A body shape analysis device characterized in that it calculates a result value related to the asymmetry measurement through a ratio equation regarding the individual distance and calculates an asymmetry ratio between the result value and a preset reference value.
The method of claim 1, wherein the plurality of balance lines are
A body shape analysis device comprising a central vertical line and a central horizontal line for the user's body, a vertical line and a horizontal line for a specific part of the user, a connecting line for points on the user's body, and a central point for the user's body.
The method of claim 1, wherein the image acquisition unit
A body shape analysis device characterized in that the user's posture movement process is filmed and the moment when the movement range is the greatest is determined using the ROM image.
delete