KR20220071940A - Method for generating guideline to prevent injury and device performing the same - Google Patents

Abstract

Disclosed are a method for generating an injury prevention guideline, which provides a guideline appropriate to an individual's skeleton based on a motion analysis technique using markers attached to the body, and a device for performing the same. The method for generating an injury prevention guideline according to various embodiments comprises the steps of: obtaining a photographed image of a user with markers attached to one or more body parts; generating a skeletal model of the user including multiple point coordinates based on the image; generating a first injury prevention guideline based on a plurality of first coordinates obtained from the user's static posture among the plurality of point coordinates; and generating a second injury prevention guideline based on a plurality of second coordinates obtained from the user's dynamic posture among the plurality of point coordinates. The markers may be first unit patterns formed with a plurality of unit polygons sharing one vertex or second unit patterns in which the first unit patterns are arranged in a row, and the body parts may include the lateral collateral joints of the knees and the anterior superior iliac spine (ASIS).

Description

Method for generating injury prevention guidelines and devices for performing them

Various embodiments of the present invention relate to a method for generating an injury prevention guideline and an apparatus for performing the same.

Recently, as the number of people who have exercise as a hobby increases, the risk of injury due to incorrect exercise posture is also increasing. Since the risk of injury varies depending on the individual's skeleton, sensing and analysis devices for estimating the individual's skeleton and posture are being developed.

As a posture estimation method, the most common method is to use an infrared camera and a retroreflective marker. As another posture estimation method, there is a silhouette-based motion analysis method that obtains information about the position and direction of joints by approximating a model of the human body based on a silhouette obtained by observing from various directions. A deep learning-based posture estimation system can find the position of each joint on a two-dimensional image using a convolutional neural network (CNN). can be estimated.

As a related prior art, there is Korean Patent Publication No. 10-2012-0085064 (title of the invention: wearable gait analysis device and gait analysis system including the same).

The background art described above is possessed or acquired by the inventor in the process of deriving the disclosure of the present application, and cannot necessarily be said to be a known technology disclosed to the general public prior to the present application.

Although there is a method of using an infrared camera and a retro-reflective marker as a posture estimation method, tracking of the marker may be interrupted due to occlusion of the marker, and the price is very high. The motion analysis method based on the silhouette has very low accuracy in the case of movements with little silhouette change, such as rotation, and the deep learning-based posture estimation system has difficulty in not knowing information about rotation. Accordingly, a motion analysis technique that can be recognized from all directions and can perform posture estimation without interruption may be required.

Various embodiments may provide a motion analysis technique that is recognizable in all directions using a marker attached to the body and enables seamless posture estimation.

Various embodiments may provide a technique for generating an injury prevention guideline according to an individual's skeleton based on a motion analysis technique using a marker attached to the body.

However, the technical tasks are not limited to the above-described technical tasks, and other technical tasks may exist.

Injury prevention guideline generation method according to various embodiments includes an operation of acquiring an image of a user with a marker attached to one or more body parts, and generating a skeletal model of the user including a plurality of point coordinates based on the image An operation, an operation of generating a first injury prevention guideline based on a plurality of first coordinates obtained from the user's static posture among the plurality of point coordinates, and the dynamic posture of the user among the plurality of point coordinates and generating a second injury prevention guideline based on a plurality of second coordinates obtained in 1 unit patterns are second unit patterns arranged in a line, and the body part may include a knee lateral collateral joint and an anterior superior iliac spine (ASIS).

The operation of generating the first injury prevention guideline includes an operation of defining a static coordinate system with the plurality of first coordinates, an operation of calculating a first knee angle in the user's static posture in the static coordinate system, and the first It may include the operation of generating the first injury prevention guideline according to the knee angle.

The first injury prevention guideline may be for preventing degenerative arthritis.

The operation of generating the second injury prevention guideline includes an operation of defining a dynamic coordinate system with the plurality of second coordinates, an operation of calculating a second knee angle in the user's dynamic posture in the dynamic coordinate system, and the second It may include the operation of generating the second injury prevention guideline according to the knee angle.

The second injury prevention guideline may be for preventing patellofemoral pain syndrome.

The operation of generating the skeleton model includes an operation of identifying an ID of a pattern included in the marker, an operation of acquiring coordinates of vertices on the pattern based on the ID of the pattern, and an operation of obtaining the coordinates of the vertices on the pattern based on the coordinates of the plurality of vertices on the pattern. and generating the plurality of second coordinates and coordinates associated with the marker among the first coordinates of, wherein the coordinates of the vertices on the pattern are static vertex coordinates obtained from the user's static posture, and the user It may include dynamic vertex coordinates obtained from the dynamic posture of .

The plurality of first coordinates obtained in the static posture include coordinates associated with the marker, and coordinates not associated with the marker, and the coordinates associated with the marker include coordinates of the lateral collateral joint of the knee, coordinates of the anterior superior iliac spine. It may include one or more of coordinates and hip joint coordinates, and the coordinates unrelated to the marker may include coordinates of the ankle joint in the user's static posture.

The plurality of second coordinates obtained in the dynamic posture are coordinates associated with the marker, and the coordinates associated with the marker may include one or more of a knee lateral collateral joint coordinate, a hip joint coordinate, and an ankle joint coordinate. can

The operation of obtaining the coordinates of the vertices on the pattern includes generating three or more dynamic vertex coordinates based on static vertex coordinates that are in a relative relationship with the plurality of first coordinates, and the plurality of coordinates associated with the marker The generating of the second coordinates may include generating a plurality of second coordinates in the relative relationship with the one or more based on the three or more dynamic vertex coordinates.

An apparatus according to various embodiments includes a memory including instructions and a processor for executing the instructions, and when the instructions are executed by the processor, the processor takes a picture of a user attaching markers to three or more body parts Acquire an image, generate a skeletal model of the user including a plurality of point coordinates based on the image, and based on a plurality of first coordinates obtained in the static posture of the user among the plurality of point coordinates A first injury prevention guideline is generated, and a second injury prevention guideline is generated based on a plurality of second coordinates obtained from the user's dynamic posture among the plurality of point coordinates, and the marker is a plurality of units The polygons are first unit patterns formed by sharing one vertex, or the first unit patterns are second unit patterns arranged in a line, and the body part is the knee lateral joint and the anterior superior iliac spine ( ASIS)) may be included.

The processor defines a static coordinate system with the plurality of first coordinates, calculates a first knee angle in the static posture of the user in the static coordinate system, and the first injury prevention guideline according to the first knee angle can create

The first injury prevention guideline may be for preventing degenerative arthritis.

The processor defines a dynamic coordinate system with the plurality of second coordinates, calculates a second knee angle in the dynamic posture of the user in the dynamic coordinate system, and the second injury prevention guideline according to the second knee angle can create

The second injury prevention guideline may be for preventing patellofemoral pain syndrome.

The processor identifies the ID of the pattern included in the marker, obtains coordinates of vertices on the pattern based on the ID of the pattern, and among the plurality of first coordinates based on the coordinates of the vertices on the pattern Coordinates associated with a marker and the plurality of second coordinates are generated, and the coordinates of the vertices on the pattern include static vertex coordinates obtained from the user's static posture, and dynamic vertex coordinates obtained from the user's dynamic posture. can do.

The plurality of first coordinates obtained in the static posture include coordinates associated with the marker, and coordinates not associated with the marker, and the coordinates associated with the marker include coordinates of the lateral collateral joint of the knee, coordinates of the anterior superior iliac spine. It may include one or more of coordinates and hip joint coordinates, and the coordinates unrelated to the marker may include coordinates of the ankle joint in the user's static posture.

The plurality of second coordinates obtained in the dynamic posture are coordinates associated with the marker, and the coordinates associated with the marker may include one or more of a knee lateral collateral joint coordinate, a hip joint coordinate, and an ankle joint coordinate. can

The processor generates three or more dynamic vertex coordinates based on static vertex coordinates in a relative relationship with the plurality of first coordinates, and in the relative relationship with the one or more based on the three or more dynamic vertex coordinates. A plurality of second coordinates may be generated.

1 is a diagram for conceptually explaining a method of generating an injury prevention guideline according to various embodiments of the present disclosure;
2 is a schematic block diagram of a guideline generation system according to various embodiments.
FIG. 3 is a view for explaining an operation of generating a first injury prevention guideline in a static posture according to various embodiments of the present disclosure;
4 is a view for explaining an operation of generating a second injury prevention guideline in a dynamic posture according to various embodiments.
5 is a view for explaining in detail the first marker and the second marker shown in FIG. 2 according to various embodiments of the present disclosure;
6A to 6C are diagrams for explaining in detail patterns of the first marker and the second marker shown in FIG. 2 according to various embodiments of the present disclosure;
7A to 7F are diagrams for explaining in detail an operation in which the generating apparatus shown in FIG. 4 identifies IDs of patterns included in a first marker and a second marker according to various embodiments of the present disclosure;
8 illustrates another example of a generating device according to various embodiments.

Specific structural or functional descriptions of the embodiments are disclosed for purposes of illustration only, and may be changed and implemented in various forms. Accordingly, the actual implementation form is not limited to the specific embodiments disclosed, and the scope of the present specification includes changes, equivalents, or substitutes included in the technical spirit described in the embodiments.

Although terms such as first or second may be used to describe various elements, these terms should be interpreted only for the purpose of distinguishing one element from another. 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 or connected to the other component, but it should be understood that another component may exist in between.

The singular expression includes the plural expression unless the context clearly dictates otherwise. In this specification, terms such as "comprise" or "have" are intended to designate that the described feature, number, step, operation, component, part, or combination thereof exists, and includes one or more other features or numbers, It should be understood that the possibility of the presence or addition of steps, operations, components, parts or combinations thereof is not precluded in advance.

Unless defined otherwise, all terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art. Terms such as those defined in a commonly used dictionary should be interpreted as having a meaning consistent with the meaning in the context of the related art, and should not be interpreted in an ideal or excessively formal meaning unless explicitly defined in the present specification. does not

Hereinafter, embodiments will be described in detail with reference to the accompanying drawings. In the description with reference to the accompanying drawings, the same components are assigned the same reference numerals regardless of the reference numerals, and overlapping descriptions thereof will be omitted.

1 is a diagram for conceptually explaining a method for generating an injury prevention guideline according to various embodiments, and FIG. 2 is a schematic block diagram of a guideline generating system according to various embodiments.

Referring to FIG. 1 , according to various embodiments, the guideline generation system 10 may analyze the motion of the user 30 in real time to estimate the displacement of 6 degrees of freedom of each body part of the user 30 in real time. have. Since the guideline generation system 10 can simultaneously estimate the position and orientation of six degrees of freedom of the body part such as the thigh and/or shin of the user 30, data on rotation and/or flexion and/or extension of each joint as well as rotation can be obtained

According to various embodiments, the guideline generating system 10 includes a plurality of point coordinates based on an image captured by the user 30 attaching one or more of the first marker 100 and the second marker 200 . A skeletal model of the user 30 can be created. The guideline generation system 10 generates a skeletal model of the static posture of the user 30 based on the first marker 100 , and sets the first marker 100 and the second marker 200 of the user 30 . You can create a skeletal model in a dynamic pose. The skeleton model includes a plurality of point coordinates, and the plurality of point coordinates are a plurality of first coordinates obtained in the static posture of the user 30 , and a plurality of second coordinates obtained in the dynamic posture of the user 30 . may include

According to various embodiments, the guideline generating system 10 uses the second marker 200 recognizable in all directions even if a part of the second marker 200 is covered, another part of the second marker 200 . By recognizing the skeletal model in the dynamic posture of the user 30 can be generated.

According to various embodiments, the guideline generation system 10 generates a first injury prevention guideline based on a plurality of first coordinates, and generates a second injury prevention guideline based on a plurality of second coordinates can do. The first injury prevention guideline may be for preventing degenerative arthritis of the user 30 , and the second injury prevention guideline may be for preventing patellofemoral pain syndrome of the user 30 .

According to various embodiments, the guideline generating system 10 may include a first marker 100 , a second marker 200 , a photographing device 150 , and a generating device 170 . The first marker 100 is a marker attached to some of the body parts of the user 30 (eg, lateral knee, anterior superior iliac spine (ASIS), etc.), and the second The marker 100 may be a marker in the form of a band surrounding a portion (eg, thigh, shin, etc.) of a body part of the user 30 . The first marker 100 and the second marker 200 may include a pattern recognizable by the guideline generating system 10 . For example, the first marker 100 may include a unit pattern, and the second marker 200 may include a pattern in which unit patterns constituting the first marker 100 are arranged in a line.

According to various embodiments, the photographing apparatus 150 may photograph the user 30 to which the first marker 100 and the second marker 200 are attached. The photographing apparatus 150 may be implemented as any type of photographing apparatus capable of acquiring an image in real time, such as a video camera, a camcorder, and a webcam. The generating device 170 may generate a skeletal model of the user 30 based on an image of the user 30 to which the first marker 100 and the second marker 200 are attached. For example, the generating device 170 may generate a skeletal model of the user 30 by recognizing patterns of the first marker 100 and the second marker 200 in the image.

According to various embodiments, although the photographing apparatus 150 is illustrated as being implemented outside the generating apparatus 170 in FIGS. 1 and 2 , the present invention is not limited thereto, and the photographing apparatus 150 according to an embodiment It may be implemented inside the generating device 170 .

FIG. 3 is a view for explaining an operation of generating a first injury prevention guideline in a static posture according to various embodiments of the present disclosure;

Referring to FIG. 3 , according to various embodiments, the generating device 170 processes the image captured in the static posture of the user 30 through the photographing device 150 to identify the pattern of the first marker 100 . can The static posture of the user 30 may mean a posture in which both feet are placed on the ground and stopped. The generating device 170 may identify the ID of the pattern by recognizing the pattern of the first marker 100 . For example, the generating device 170 may identify the ID of the pattern by recognizing the pattern of the first marker 100 using the Douglas-Peucker Algorithm.

According to various embodiments, the generating device 170 may obtain coordinates (eg, static vertex coordinates) of vertices on the first unit pattern 100 based on the ID of the first unit pattern 100 . The static vertex coordinates may be obtained from the static posture of the user 30 . The generating device 170 provides a first marker 100 among a plurality of first coordinates obtained in the static posture of the user 30 based on the coordinates (eg, static vertex coordinates) of the vertices on the first unit pattern 100 . You can create coordinates associated with . The generating device 170 may generate a skeletal model in the static posture of the user 30 based on the plurality of first coordinates. The plurality of first coordinates may include coordinates associated with the first marker 100 and coordinates not associated with the first marker 100 .

According to various embodiments, the coordinates associated with the first marker 100 are coordinates (110-1, 110-2) of the knee lateral joint in the static posture of the user 30, the anterior superior iliac spine ( ASIS)) coordinates (100-3, 100-4) and hip joint coordinates (120-1, 120-2) may include one or more. The coordinates 110-1 and 110-2 of the lateral collateral joint of the knee are coordinates calculated based on the central coordinate of the first marker 100 attached to the surface of the lateral collateral joint of the knee and the half-length of the width of the knee, the anterior superior iliac spine The coordinates (100-3, 100-4) of the (anterior superior iliac spine (ASIS)) may be the central coordinates of the first marker 100 attached to the anterior superior iliac spine. The left hip joint coordinates 120-1 are obtained using [Equation 1] from the coordinates of the anterior superior iliac spines 100-3, 100-4, and the right hip coordinates 120-2 are the anterior superior iliac spines 100 -3, 100-4) may be obtained using [Equation 2].

[Equation 1]

[Equation 2]

는 좌측 고관절 좌표(120-1)이고,

는 우측 고관절좌표(120-2)이고,

는 좌측 전상장골극 좌표(100-3) 및 우측 전상장골극 좌표(100-4)의 중점이며,

는 좌측 전상장골극 좌표(100-3) 및 우측 전상장골극 좌표(100-4) 간의 거리이다.

은 우측 전상장골극 좌표(100-4)에서 좌측 전상장골극 좌표(100-3)로의 단위 벡터이고,

는

로부터 천골(sacrum)의 좌표(130)로의 단위 벡터이며, 천골(sacrum)의 좌표(130)는 [수학식 3]에 의해 획득될 수 있다.

은

과

의 외적값일 수 있다.here,

is the left hip joint coordinates (120-1),

is the right hip joint coordinates (120-2),

is the midpoint of the left anterior superior iliac spine coordinates (100-3) and the right anterior superior iliac spine coordinates (100-4),

is the distance between the left anterior superior iliac spine coordinates (100-3) and the right anterior superior iliac spine coordinates (100-4).

is the unit vector from the right anterior superior iliac spine coordinates (100-4) to the left anterior superior iliac spine coordinates (100-3),

Is

It is a unit vector from to the coordinates 130 of the sacrum, and the coordinates 130 of the sacrum may be obtained by [Equation 3].

silver

class

may be the cross product of

[Equation 3]

은 천골의 좌표(130)이고,

은 촬영 장치(150)의 x축 방향으로의 단위벡터이다.here,

is the coordinates of the sacrum (130),

is a unit vector in the x-axis direction of the photographing apparatus 150 .

According to various embodiments, the coordinates unrelated to the first marker 100 include coordinates 150-1 and 150-2 of the ankle joint in the static posture of the user 30, and the coordinates of the ankle joint in the static posture The coordinates may be fixed values independent of the user 30 .

According to various embodiments, the generating device 170 may include a plurality of first coordinates among a plurality of point coordinates (eg, coordinates 110-1 and 110-2 of the lateral joint of the knee in a static posture, anterior superior iliac spine) static as coordinates of (anterior superior iliac spine (ASIS)) (100-3, 100-4), hip coordinates (120-1, 120-2), and ankle joint coordinates (150-1, 150-2)) Coordinate systems 160-1 to 160-4 can be defined. The y-axis vector of the static coordinate systems 160-1 to 160-4 may be a cross product of the z-axis vector of the static coordinate systems 160-1 to 160-4 and the z-axis vector of the photographing apparatus 150 . The z-axis vector of the photographing apparatus 150 may be a vector perpendicular to the sagittal plane of the user 30 . The x-axis vector of the static coordinate system (160-1~160-4) is the cross product of the y-axis vector of the static coordinate system (160-1~160-4) and the z-axis vector of the static coordinate system (160-1~160-4) can

3도가 벗어나면 총점 100점을 기준으로 16 점의 위험도 점수를 부여할 수 있다. 생성 장치(170)는 제1 무릎 각도가 정상 범위로부터

6도가 벗어나면 총점 100점을 기준으로 33 점의 위험도 점수를 부여할 수 있다. 생성 장치(170)는 제1 무릎 각도가 정상 범위로부터

9도가 벗어나면 총점 100점을 기준으로 50점의 위험도 점수를 부여할 수 있다.According to various embodiments, the static coordinate system (160-1, 160-2) is defined between the coordinates (110-1, 110-2) of the lateral joint of the knee and the coordinates (150-1, 150-2) of the ankle joint In this case, the z-axis vector of the static coordinate system (160-1, 160-2) is from the coordinates (150-1, 150-2) of the ankle joint to the coordinates (110-1, 110-2) of the lateral joint of the knee. It can be a vector. When the static coordinate system (160-3, 160-4) is defined between the coordinates (110-1, 110-2) of the knee lateral joint and the coordinates of the hip joint (120-1, 120-2), the static coordinate system (160 The z-axis vector of -3 and 160-4) may be a vector from the coordinates 110-1 and 110-2 of the lateral joint of the knee to the coordinates of the hip joint (120-1, 120-2). According to various embodiments, , the generating device 170 may calculate the first knee angle in the static posture of the user 30 in the static coordinate systems 160 - 1 to 160 - 4 . The generating device 170 calculates the first knee angle based on the static coordinate systems 160 - 1 and 160 - 3 on the left lower body of the user 30 , and the static coordinate system 160 on the right lower body of the user 30 . -2, 160-4), the first knee angle may be calculated. For example, on the left lower body of the user 30 , the generating device 170 generates a static coordinate system 160 - 1 defined between the coordinates 110 - 1 of the lateral collateral joint of the knee and the coordinates 150 - 1 of the ankle joint. ), and the first knee angle by calculating the y-axis rotation angle among the xyz Euler angles between the coordinates 110-1 of the lateral joint of the knee and the static coordinate system 160-3 defined between the coordinates of the hip joint 120-1 can be obtained. The generating device 170 may generate a first injury prevention guideline for preventing osteoarthritis according to the first knee angle. For example, when the first knee angle is in the range of -1.5 degrees to 4.5 degrees, the generating device 170 may determine that the first knee angle is in the normal range and thus is safe from degenerative arthritis. The generating device 170 determines that the first knee angle is from the normal range.

If the 3 degree deviates, a risk score of 16 points can be given based on a total score of 100 points. The generating device 170 determines that the first knee angle is from the normal range.

If it deviates from 6 degrees, a risk score of 33 points can be given based on a total score of 100 points. The generating device 170 determines that the first knee angle is from the normal range.

If it deviates from 9 degrees, a risk score of 50 points can be given based on a total score of 100 points.

4 is a view for explaining an operation of generating a second injury prevention guideline in a dynamic posture according to various embodiments.

Referring to FIG. 4 , according to various embodiments, the generating device 170 identifies the pattern of the second marker 200 by processing the image captured in the dynamic posture of the user 30 through the photographing device 150 . can The user's dynamic posture may refer to a posture after performing at least one of a single leg squat and a drop vertical jump 5 times or more. The generating device 170 may identify the ID of the pattern by recognizing the pattern of the second marker 200 robustly against image distortion caused by the inclination or bending of the second marker 200 . For example, the generating device 170 may identify the ID of the pattern by recognizing the pattern of the second marker 200 using the Douglas-Peucker Algorithm. For example, the generating device 170 recognizes the second unit pattern 300 included in the second marker 200 , thereby disposing the first unit pattern 100 arranged in a line on the second unit pattern 300 . can be obtained.

According to various embodiments, the generating device 170 may obtain coordinates (eg, dynamic vertex coordinates) of vertices on the first unit pattern 100 based on the arrangement of the first unit pattern 100 and the ID of the pattern. have. The dynamic vertex coordinates may be obtained from the dynamic posture of the user 30 . For example, the generating device 170 may generate three or more dynamic vertex coordinates corresponding to the static vertex coordinates by identifying the arrangement of the first unit pattern 100 and the ID of the pattern. The generating device 170 may generate a plurality of second coordinates obtained from the dynamic posture of the user 30 based on three or more dynamic vertex coordinates. For example, the generating device 170 may apply the least-square-method to three or more dynamic vertex coordinates to generate a plurality of second coordinates having a relative relationship with the three or more dynamic vertex coordinates. The relative relationship between the three or more dynamic vertex coordinates and the plurality of second coordinates may be the same as the relative relationship between the static vertex coordinates and the plurality of first coordinates. The generating device 170 may generate a skeletal model in the dynamic posture of the user 30 based on the plurality of second coordinates. The plurality of second coordinates may include coordinates associated with the second marker 200 .

According to various embodiments, the coordinates associated with the second marker 200 are coordinates (110-5, 110-6) of the knee lateral joint in the dynamic posture of the user 30, coordinates of the hip joint (120-5, 120-6), and coordinates of the ankle joint (150-5, 150-6). The relative relationship between the three or more dynamic vertex coordinates and the coordinates associated with the second marker 200 may be the same as the relative relationship between the static vertex coordinates and the plurality of first coordinates.

According to various embodiments, the generating device 170 may include a plurality of second coordinates among a plurality of point coordinates (eg, coordinates (110-5, 110-6) of the lateral joint of the knee in a static posture, anterior superior iliac spine Dynamically with coordinates of (anterior superior iliac spine (ASIS)) (100-7, 100-8), hip coordinates (120-5, 120-6), and ankle joint coordinates (150-5, 150-6)) A coordinate system (160-5 to 160-8) can be defined.

6.75도를 벗어나면 총점 100점을 기준으로 16 점의 위험도 점수를 부여할 수 있다. 생성 장치(170)는 변화각이 정상 범위로부터

13도가 벗어나면 총점 100점을 기준으로 33 점의 위험도 점수를 부여할 수 있다. 생성 장치(170)는 변화각이 정상 범위로부터

19.75도가 벗어나면 총점 100점을 기준으로 50점의 위험도 점수를 부여할 수 있다.According to various embodiments, the generating device 170 may calculate the second knee angle in the dynamic posture of the user 30 in the dynamic coordinate system 160 - 5 to 160 - 8 . The generating device 170 calculates the second knee angle based on the dynamic coordinate systems 160-5 and 160-7 on the left lower body of the user 30, and the dynamic coordinate system 160 on the right lower body of the user 30 -6, 160-8), the second knee angle may be calculated. For example, on the left lower body of the user 30 , the generating device 170 is located between the coordinates 110-1 and 110-2 of the lateral collateral joint of the knee and the coordinates 150-1 and 150-2 of the ankle joint. The defined dynamic coordinate system 160-5, and the y-axis rotation among xyz Euler angles between the knee lateral collateral joint coordinates 110-5 and the hip joint coordinate system 160-7 defined between the hip coordinates 120-5 A second knee angle may be obtained by calculating the angle. The generating device 170 may generate a second injury prevention guideline for preventing patellofemoral pain syndrome according to the magnitude of the change angle from the first knee angle to the second knee angle. For example, when the magnitude of the angle of change is in the range of -6.25 to 6.75 degrees, the generating device 170 may determine that the user 30 is safe from patellofemoral pain syndrome because the magnitude of the angle of change is in the normal range. The generating device 170 determines that the angle of change is from the normal range.

If it deviates from 6.75 degrees, a risk score of 16 points can be given based on a total score of 100 points. The generating device 170 determines that the angle of change is from the normal range.

If 13 degrees is deviating, a risk score of 33 points can be given based on a total score of 100 points. The generating device 170 determines that the angle of change is from the normal range.

If it deviates from 19.75 degrees, a risk score of 50 points can be given based on a total score of 100 points.

5 is a view for explaining in detail the first marker and the second marker shown in FIG. 2 according to various embodiments, and FIGS. 6A to 6C are the first and second markers shown in FIG. 2 according to various embodiments. It is a drawing for explaining in detail the pattern of a marker.

5 and 6A to 6C , according to various embodiments, the first marker 100 is a part of the body part of the user 30 (eg, the lateral knee of the knee, the anterior superior iliac spine ( anterior superior iliac spine (ASIS), etc.), and the second marker 200 is implemented in the form of a band including a pattern, so that some of the body parts of the user 30 (eg, thigh, shin, etc.) It can be attached around. The first marker 100 and the second marker 200 may include a pattern recognizable by the guideline generating system 10 . For example, the first marker 100 may include a first unit pattern, and the second marker 200 may include a second unit pattern in which the first unit patterns are arranged in a line.

According to various embodiments, the first unit patterns 100 may be a pattern in which a plurality of unit polygons share one vertex. For example, the first unit patterns may be hexagonal patterns formed by gathering six triangles having one point as one of three vertices.

According to various embodiments, the guideline generating system 10 may minimize the possibility of not recognizing the vertices of the pattern due to image distortion by using an equilateral triangle having the smallest interior angle as a unit polygon. In addition, the guideline generating system 10 determines the area of a unit polygon in consideration of resolution, focal length, a range required for motion analysis, and/or a pixel area required for recognition of each unit polygon. can be decided For example, the guideline generating system 10 may calculate the width of a triangle that is a unit polygon based on [Equation 4].

[Equation 4]

Here, A is the area of the unit polygon, Apixel is the area of the image formed by the unit polygon, T is the distance between the unit polygon and the focal point, and fx and fy are the distance between the image and the focal point.

According to various embodiments, the first unit patterns 100 may share at least one unit polygon with an adjacent first unit pattern to generate the second unit pattern 300 . For example, the first unit patterns 100 that are hexagonal patterns may be arranged to overlap adjacent hexagonal patterns and two triangles, thereby generating the second unit pattern 300 . The unit polygons may or may not include the identification mark 190 therein. The first unit pattern 100 may be divided into different types according to the arrangement of unit polygons including the identification mark 190 . For example, the first unit pattern 100, which is a hexagonal pattern, may be divided into a total of nine types (hexagonal 0 to hexagonal 8) except for the radially symmetrical pattern as shown in FIG. 6B .

According to various embodiments, the second unit pattern 300 may include two adjacent first unit patterns 200 - 1 and 200 - 2 . For example, the second unit pattern 300 may be a pattern in which adjacent hexagonal patterns 200 - 1 and 200 - 2 share two triangles and overlap each other. The second unit pattern 300 may be identified by a unique ID according to the types of the first unit patterns 100 - 1 and 100 - 2 included therein. In this case, even when the second unit pattern 300 includes the first unit patterns 100-1 and 100-2 of the same type, the included first unit patterns 100-1 and 100-2 are rotated. In the case of overlapping with each other, they can be identified by different IDs.

According to various embodiments, in FIG. 6C , second unit patterns 300-1 and 300-2 including a first unit pattern 100-1 having a hexagonal 0 and a first unit pattern 100-2 having a hexagonal 1 are shown in FIG. ), the second unit pattern including the first unit pattern 200-1 having hexagonal 0 and the first unit pattern 100-2 having hexagonal 1 is two second units illustrated in FIG. 6C . It is not limited to the patterns 300 - 1 and 300 - 2 , and more mutually identifiable second unit patterns 300 may exist. A total of 394 IDs of the second unit patterns 300 identifiable from each other may exist.

According to various embodiments, the generating device 170 may identify the unique IDs of the first unit patterns 100 to distinguish them from the different first unit patterns 100 , and the unique IDs of the second unit patterns 300 . can be identified and distinguished from the different second unit patterns 300 . The generating device 170 may identify IDs of the first unit patterns 100 included in the first marker 100 to obtain coordinates on the first unit patterns 100 , and the second unit pattern 300 ) to obtain the arrangement of the first unit patterns 100 by identifying the coordinates on the second unit patterns 300 may be obtained.

7A to 7F are diagrams for explaining in detail an operation in which the generating device shown in FIG. 4 identifies IDs of patterns included in a first marker and a second marker according to various embodiments of the present disclosure;

Referring to FIGS. 7A to 7F , according to various embodiments, the generating device 170 processes an image captured by the user 30 who has attached the first marker 100 and the second marker 200 to obtain a first Patterns included in the marker 100 and the second marker 200 may be identified.

According to various embodiments, the generating device 170 may threshold the pattern of a part of the second marker 200 as shown in FIG. 7A as shown in FIG. 7B . For example, the generating device 170 generates a kernel of a predetermined size centered on a pixel for each pixel included in the image, sets an average intensity of pixels in the kernel as a threshold, and each The image can be binarized by giving 1 if the pixel intensity is greater than the threshold and 0 if it is less.

According to various embodiments, the generating apparatus 170 may recognize the outline of the pattern in the binarized image as shown in FIG. 7C and recognize the vertices of each triangle as shown in FIG. 7D . The generating device 170 individually recognizes the vertices of each triangle, so that even if the vertices of the plurality of triangles are overlapping vertices, they may be recognized as vertices included in each triangle. The generating device 170 may recognize the identification mark 190 included in the second marker 200 .

According to various embodiments, the generating device 170 may recognize the first unit pattern. For example, the generating device 170 uses a square having as the length of one side the average of the lengths of the sides of a triangle including the vertices with respect to all recognized vertices as a region of interest (ROI). The inspection may be performed, and when a total of six vertices are included in the square, the generating device 170 may recognize the corresponding vertex as the center of the first unit pattern 100 .

According to various embodiments, when the center point of the first unit pattern 100 is recognized, the generating device 170 starts with a triangle including a vertex that is a reference point for the ROI test, and clockwise the identification mark inside the triangle. can be read. For example, the generating device 170 may obtain a binary code by reading a triangle including the identification mark as 1 and a triangle not including the identification mark as 0. In the example of FIG. 7E , since the region of interest inspection is performed based on the vertex of the triangle indicated by number 3 , the generating device 170 may obtain a binary code 101100 for the first unit pattern 100 . As another example, when the region of interest inspection is performed based on the vertex of the triangle indicated by number 1, the generating device 170 may obtain the binary code 001011 .

According to various embodiments, the generating device 170 may have a binary code library for each type of the first unit pattern 100 . After obtaining the binary code of each first unit pattern 100 , the generating device 170 identifies the type of each first unit pattern 100 and a reference triangle of the first unit pattern based on the binary code library can do.

According to various embodiments, in the example of FIG. 7E , the generating device 170 obtained a binary code that is 101100, and 01100 is included in 100101, 001011, 010110, 101100, 011001, 110010, which are binary code libraries for hexagon 5, so , the generating device 170 may identify the first unit pattern 100 as a hexagon 5 .

According to various embodiments, the binary code library includes information identifying a reference triangle for each binary code to obtain a binary code that is 101100 in the example of FIG. 7E , and the generating device 170 starts reading the binary code The third triangle, counterclockwise from the triangle, can be identified as the reference triangle.

According to various embodiments, the generating apparatus 170 may identify a triangle included in the first unit pattern 100 based on a reference triangle for each of the first unit patterns 100 . For example, the generating device 170 may assign numbers from 0 to 5 in a clockwise direction from the reference triangle.

According to various embodiments, the generating device 170 recognizes the second unit patterns 300 , the type of the first unit pattern 100 included in the second unit patterns 300 , and the two first unit patterns ( IDs of the second unit patterns 300 may be identified based on the overlapping positions of the second unit patterns 300 .

According to various embodiments, the generating device 170 determines the type of the first first unit pattern 100 included in the second unit pattern 300 , the type of the second second unit pattern 300 , and the number of overlapping triangles. Based on the ID, the ID of the second unit pattern 300 may be determined. In the example of FIG. 7F , the type of the first first unit pattern 100 is hexagonal 5, the type of the second first unit pattern 100 is hexagonal 0, and the numbers of the overlapping triangles are 3, 0, 4, and Since it is 5, the generating device 170 may determine the ID of the second unit pattern 300 as [5, 0, 3, 0, 4, 5].

According to various embodiments, the generating apparatus 170 may identify the arrangement of the first unit patterns 100 included in the second unit pattern 300 based on the ID of the second unit pattern 300 . For example, the generating device 170 may obtain the position of the second unit pattern 300 based on the ID of the second unit pattern 300 , and based on the position of the second unit pattern 300 , The arrangement of the entire first unit pattern 100 may be identified by obtaining the position of the first unit pattern 100 included in the second unit pattern 300 .

According to various embodiments, the generating device 170 may obtain coordinates of vertices on the pattern included in the first marker 100 and the second marker 200 based on the ID of the pattern. For example, when the same ID of a pattern is identified in two or more images, the generating device 170 may calculate 3D coordinates of triangular vertices on the pattern through triangulation.

8 illustrates another example of a generating device according to various embodiments.

Referring to FIG. 8 , according to various embodiments, the generating device 170 may include a memory 173 and a processor 177 .

According to various embodiments, the memory 173 may store instructions (eg, a program) executable by the processor 177 . For example, the instructions may include instructions for executing an operation of the processor 177 and/or an operation of each component of the processor 177 .

According to various embodiments, the memory 173 may be implemented as a volatile memory device or a nonvolatile memory device. The volatile memory device may be implemented as dynamic random access memory (DRAM), static random access memory (SRAM), thyristor RAM (T-RAM), zero capacitor RAM (Z-RAM), or twin transistor RAM (TTRAM). Nonvolatile memory devices include EEPROM (Electrically Erasable Programmable Read-Only Memory), Flash memory, MRAM (Magnetic RAM), Spin-Transfer Torque (STT)-MRAM (Spin-Transfer Torque (STT)-MRAM), Conductive Bridging RAM (CBRAM) , FeRAM(Ferroelectric RAM), PRAM(Phase change RAM), Resistive RAM(RRAM), Nanotube RRAM(Nanotube RRAM), Polymer RAM(Polymer RAM(PoRAM)), Nano Floating Gate Memory (NFGM)), a holographic memory, a Molecular Electronic Memory Device, and/or an Insulator Resistance Change Memory.

According to various embodiments, the processor 177 may execute computer-readable code (eg, software) stored in the memory 173 and instructions induced by the processor 177 . The processor 177 may be a hardware-implemented data processing device having a circuit having a physical structure for executing desired operations. Target operations may include, for example, code or instructions included in a program. A data processing device implemented as hardware includes, for example, a microprocessor, a central processing unit, a processor core, a multi-core processor, and a multiprocessor. , an Application-Specific Integrated Circuit (ASIC), and a Field Programmable Gate Array (FPGA).

According to various embodiments, the generating device 170 may be implemented in a computing device, a machine-type communication device, an IoT device, or a portable electronic device. Portable electronic devices include laptop computers, mobile phones, smart phones, tablet PCs, mobile internet devices (MIDs), personal digital assistants (PDAs), and enterprise digital assistants (EDAs). ), digital still camera, digital video camera, PMP (portable multimedia player), PND (personal navigation device or portable navigation device), handheld game console, e-book (e-book), may include a smart device (smart device). For example, the smart device may include a smart watch or a smart band.

According to various embodiments, the operation performed by the processor 177 may be substantially the same as the operation of the generating device 170 described with reference to FIGS. 1 to 7F . Accordingly, detailed description will be omitted.

The embodiments described above may be implemented by a hardware component, a software component, and/or a combination of a hardware component and a software component. For example, the apparatus, methods, and components described in the embodiments may include, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate (FPGA) array), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing and responding to instructions, may be implemented using a general purpose computer or special purpose computer. The processing device may execute an operating system (OS) and a software application running on the operating system. A processing device may also access, store, manipulate, process, and generate data in response to execution of the software. For convenience of understanding, although one processing device is sometimes described as being used, one of ordinary skill in the art will recognize that the processing device includes a plurality of processing elements and/or a plurality of types of processing elements. It can be seen that can include For example, the processing device may include a plurality of processors or one processor and one controller. Other processing configurations are also possible, such as parallel processors.

Software may comprise a computer program, code, instructions, or a combination of one or more thereof, which configures a processing device to operate as desired or is independently or collectively processed You can command the device. The software and/or data may be any kind of machine, component, physical device, virtual equipment, computer storage medium or apparatus, to be interpreted by or to provide instructions or data to the processing device. , or may be permanently or temporarily embody in a transmitted signal wave. The software may be distributed over networked computer systems and stored or executed in a distributed manner. Software and data may be stored in a computer-readable recording medium.

The method according to the embodiment may be implemented in the form of program instructions that can be executed through various computer means and recorded in a computer-readable medium. The computer readable medium may store program instructions, data files, data structures, etc. alone or in combination, and the program instructions recorded on the medium may be specially designed and configured for the embodiment, or may be known and available to those skilled in the art of computer software. have. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks and magnetic tapes, optical media such as CD-ROMs and DVDs, and magnetic media such as floppy disks. - includes magneto-optical media, and hardware devices specially configured to store and execute program instructions, such as ROM, RAM, flash memory, and the like. Examples of program instructions include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter or the like.

The hardware devices described above may be configured to operate as one or a plurality of software modules to perform the operations of the embodiments, and vice versa.

As described above, although the embodiments have been described with reference to the limited drawings, those of ordinary skill in the art may apply various technical modifications and variations based thereon. For example, the described techniques are performed in an order different from the described method, and/or the described components of the system, structure, apparatus, circuit, etc. are combined or combined in a different form than the described method, or other components Or substituted or substituted by equivalents may achieve an appropriate result.

Therefore, other implementations, other embodiments, and equivalents to the claims are also within the scope of the following claims.

Claims (19)

acquiring an image of a user with a marker attached to one or more body parts;
generating a skeletal model of the user including a plurality of point coordinates based on the image;
generating a first injury prevention guideline based on a plurality of first coordinates obtained from the user's static posture among the plurality of point coordinates; and
An operation of generating a second injury prevention guideline based on a plurality of second coordinates obtained from the user's dynamic posture among the plurality of point coordinates
including,
The marker is
First unit patterns formed by a plurality of unit polygons sharing one vertex, or
The first unit patterns are second unit patterns arranged in a line,
The body part is
How to create injury prevention guidelines, including the lateral collateral joint of the knee and the anterior superior iliac spine (ASIS).
According to claim 1,
The operation of generating the first injury prevention guideline is,
defining a static coordinate system with the plurality of first coordinates;
calculating a first knee angle in the static posture of the user in the static coordinate system; and
Creating the first injury prevention guideline according to the first knee angle
Including, injury prevention guidelines creation method.
According to claim 1,
The first injury prevention guidelines are for preventing osteoarthritis, injury prevention guidelines generating method.
According to claim 1,
The operation of generating the second injury prevention guideline is,
defining a dynamic coordinate system with the plurality of second coordinates;
calculating a second knee angle in the user's dynamic posture in the dynamic coordinate system; and
Creating the second injury prevention guideline according to the second knee angle
Including, injury prevention guidelines creation method.
According to claim 1,
The second injury prevention guideline is to prevent patellar femoral pain syndrome, injury prevention guideline generation method.
According to claim 1,
The operation of generating the skeletal model is,
identifying the ID of the pattern included in the marker;
obtaining coordinates of vertices on the pattern based on the ID of the pattern; and
generating the plurality of second coordinates and the coordinates associated with the marker among the plurality of first coordinates based on the coordinates of the vertices on the pattern
includes,
The coordinates of the vertices on the pattern are,
Including static vertex coordinates obtained from the user's static posture, and dynamic vertex coordinates obtained from the user's dynamic posture, injury prevention guideline generation method.
7. The method of claim 6,
The plurality of first coordinates obtained in the static posture are,
coordinates associated with the marker, and coordinates unrelated to the marker.
including,
The coordinates associated with the marker are
It includes at least one of the coordinates of the lateral joint of the knee, the coordinates of the anterior superior iliac spine, and the coordinates of the hip joint,
The coordinates unrelated to the marker are,
Coordinates of the ankle joint in the user's static posture
Including, injury prevention guidelines generation method.
7. The method of claim 6,
The plurality of second coordinates obtained in the dynamic posture are coordinates associated with the marker,
The coordinates associated with the marker are
Including one or more of the coordinates of the lateral joint of the knee, the coordinates of the hip joint, and the coordinates of the ankle joint, the method of generating an injury prevention guideline.
7. The method of claim 6,
The operation of obtaining the coordinates of the vertices on the pattern is,
generating three or more dynamic vertex coordinates based on the static vertex coordinates in a relative relationship with the plurality of first coordinates
including,
The operation of generating the plurality of second coordinates associated with the marker comprises:
generating a plurality of second coordinates in the relative relationship with the one or more based on the three or more dynamic vertex coordinates
Including, injury prevention guidelines creation method.
A computer program stored in a computer-readable recording medium in combination with hardware to execute the method of any one of claims 1 to 9.
a memory containing instructions; and
a processor for executing the instructions
including,
When the instructions are executed by the processor, the processor
Obtaining an image of a user attaching a marker to one or more body parts,
Create a user's skeleton model including a plurality of point coordinates based on the image,
Generates a first injury prevention guideline based on a plurality of first coordinates obtained in the user's static posture among the plurality of point coordinates,
Generate a second injury prevention guideline based on a plurality of second coordinates obtained from the user's dynamic posture among the plurality of point coordinates,
The marker is
First unit patterns formed by a plurality of unit polygons sharing one vertex, or
The first unit patterns are second unit patterns arranged in a line,
The body part is
A device comprising the lateral collateral joint of the knee and the anterior superior iliac spine (ASIS).
12. The method of claim 11,
The processor is
defining a static coordinate system with the plurality of first coordinates,
Calculate the first knee angle in the static posture of the user in the static coordinate system,
generating the first injury prevention guidelines according to the first knee angle.
12. The method of claim 11,
The first injury prevention guideline is for preventing osteoarthritis.
12. The method of claim 11,
The processor is
defining a dynamic coordinate system with the plurality of second coordinates,
Calculate a second knee angle in the user's dynamic posture in the dynamic coordinate system,
generating the second injury prevention guidelines according to the second knee angle.
12. The method of claim 11,
The second injury prevention guidelines are for preventing patellofemoral pain syndrome, the device.
12. The method of claim 11,
The processor is
Identifies the ID of the pattern included in the marker,
To obtain the coordinates of the vertices on the pattern based on the ID of the pattern,
generating coordinates and a plurality of second coordinates associated with the marker among the plurality of first coordinates based on the coordinates of the vertices on the pattern;
The coordinates of the vertices on the pattern are,
and static vertex coordinates obtained from the user's static posture, and dynamic vertex coordinates obtained from the user's dynamic posture.
17. The method of claim 16,
The plurality of first coordinates obtained in the static posture are,
coordinates associated with the marker, and coordinates unrelated to the marker.
including,
The coordinates associated with the marker are
It includes at least one of the coordinates of the lateral joint of the knee, the coordinates of the anterior superior iliac spine, and the coordinates of the hip joint,
The coordinates unrelated to the marker are,
and the coordinates of the ankle joint in the static posture of the user.
17. The method of claim 16,
The plurality of second coordinates obtained in the dynamic posture are coordinates associated with the marker,
The coordinates associated with the marker are
A device comprising one or more of the coordinates of the lateral collateral joint of the knee, the coordinates of the hip joint, and the coordinates of the ankle joint.
17. The method of claim 16,
The processor is
generating three or more dynamic vertex coordinates based on the static vertex coordinates in a relative relationship with the plurality of first coordinates;
and generate a plurality of second coordinates in the relative relationship with the one or more based on the three or more dynamic vertex coordinates.

Images