Method for acquiring motion analysis data and motion analysis data acquisition system

Abstract

To provide a motion analysis data acquisition method and a motion analysis data acquisition system capable of acquiring data that appropriately reflects the motion of a subject so that direct and detailed analysis of the motion of the subject can be performed for evaluation of human body functions, etc.SOLUTION: A motion analysis data acquisition method comprises imaging a subject during the following test with a camera of a mobile terminal, and generating data indicating the coordinates of a plurality of feature points on the subject's body on the basis of the imaging result. The subject is made to stand up from sitting on a chair 41 at a position P1, and is moved along markers 42 to 44 to a position P2 separated to the right side from the position P1. Consequently, for the imaged right half of the subject, data indicating the coordinates of the feature points and how the feature points are connected is acquired during the motion of standing up from the chair at the position P1 and during the motion from the position P1 to the position P2.SELECTED DRAWING: Figure 5

Description

Technical Field

[0001] The present invention relates to a motion analysis data acquisition method and a motion analysis data acquisition system for acquiring data for analyzing the motion of a person during movement.

Background Art

[0002] Conventionally, for the purpose of medical evaluation of human body functions, etc., a person may be made to perform an action such as walking and this may be verified. The "Timed Up and Go (TUG) test" of Non-Patent Document 1 is an example of this. The subject is made to stand up from a sitting state on a chair, walk 3 m, then change direction and walk back to the original chair and sit on the chair again. In Non-Patent Document 1, the correlation between the time taken for this series of actions and the balance, walking speed and functional ability of the subject is discussed.

Prior Art Documents

Non-Patent Documents

[0003]

Non-Patent Document 1

Summary of the Invention

Problems to be Solved by the Invention

[0004] In the TUG test of Non-Patent Document 1, only the time taken for the series of actions to be performed on the subject ​is used as an evaluation index. On the other hand, the present inventors considered that important information for medical evaluation of human body functions and the like could be obtained if a series of movements of a subject could be analyzed more directly and in detail. Therefore, in order to enable direct and detailed analysis of the subject's movements, it was decided to aim at obtaining data for motion analysis that appropriately reflects a series of movements of the subject. The object of the present invention is to provide a motion analysis data acquisition method and a motion analysis data acquisition system capable of acquiring data that appropriately reflects the movements of a subject so that direct and detailed analysis of the subject's movements can be performed for evaluation of human body functions and the like.

Means for Solving the Problems

[0005] The motion analysis data acquisition method of the present invention uses imaging means for converting a subject image into data and outputting it, and feature point derivation means for generating data indicating the coordinates of a plurality of feature points in the human body included in the subject indicated by the data based on the data output from the imaging means, and is a method for acquiring data for analyzing the motion of a person when moving. The subject is made to stand up from a state of sitting on an object at a first position, and is made to walk or run to a second position spaced apart from the first position in a direction intersecting the optical axis of the imaging means and parallel to the horizontal direction. A subject motion step, an imaging step of continuously imaging at least one of the left and right halves of the subject during the motion in the subject motion step by the imaging means, and based on the data output from the imaging means regarding the imaging performed in the imaging step, during the motion of standing up from the object and during each timing of the subject during the motion from the first position to the second position. analysis can be performed, and data that appropriately reflects the movements of the subject can be obtained. The present invention aims to provide a motion analysis data acquisition method and a motion analysis data acquisition system that can acquire data that appropriately reflects the movements of a subject so that direct and detailed analysis of the subject's movements can be performed for the evaluation of human body functions and the like.

Means for Solving the Problems

[0006] The motion analysis data acquisition method of the present invention uses imaging means for converting a subject image into data and outputting it, and feature point derivation means for generating data indicating the coordinates of a plurality of feature points in the human body included in the subject indicated by the data based on the data output from the imaging means, and is a method for acquiring data for analyzing the motion of a person when moving. The subject is made to stand up from a state of sitting on an object at a first position, and is made to walk or run to a second position spaced apart from the first position in a direction intersecting the optical axis of the imaging means and parallel to the horizontal direction. A subject motion step, an imaging step of continuously imaging at least one of the left and right halves of the subject during the motion in the subject motion step by the imaging means, and based on the data output from the imaging means regarding the imaging performed in the imaging step, during the motion of standing up from the object and during each timing of the subject during the motion from the first position to the second position. and, based on the data output from the imaging means, data indicating the coordinates of a plurality of feature points in the human body included in the subject indicated by the data is generated. It is a method for acquiring data for analyzing the motion of a person when moving. The subject is made to stand up from a state of sitting on an object at a first position, and is made to walk or run to a second position spaced apart from the first position in a direction intersecting the optical axis of the imaging means and parallel to the horizontal direction. A subject motion step, an imaging step of continuously imaging at least one of the left and right halves of the subject during the motion in the subject motion step by the imaging means, and based on the data output from the imaging means regarding the imaging performed in the imaging step, during the motion of standing up from the object and during each timing of the subject during the motion from the first position to the second position. using, to obtain data for analyzing the motion of a person when moving. The subject is made to stand up from a state of sitting on an object at a first position, and is made to walk or run to a second position spaced apart from the first position in a direction intersecting the optical axis of the imaging means and parallel to the horizontal direction. While making the subject stand up from a sitting state on an object at the first position, and walking or running the subject to a second position spaced apart from the first position in a direction intersecting the optical axis of the imaging means and parallel to the horizontal direction. and walking or running to a second position spaced apart from the first position in a direction intersecting the optical axis of the imaging means and parallel to the horizontal direction. A subject motion step, an imaging step of continuously imaging at least one of the left and right halves of the subject during the motion in the subject motion step by the imaging means, and based on the data output from the imaging means regarding the imaging performed in the imaging step, during the motion of standing up from the object and during each timing of the subject during the motion from the first position to the second position. During the motion in the subject motion step, at least one of the left and right halves of the subject is continuously imaged by the imaging means. An imaging step, and based on the data output from the imaging means regarding the imaging performed in the imaging step, during the motion of standing up from the object and during each timing of the subject during the motion from the first position to the second position. and, based on the data output from the imaging means regarding the imaging performed in the imaging step, during the motion of standing up from the object and during each timing of the subject during the motion from the first position to the second position. each timing of the subject during the motion from the first position to the second position. A feature point generation step for causing the feature point derivation means to generate first analysis data indicating the coordinates of a plurality of feature points. And a generation step.

[0007] According to the method for acquiring motion analysis data of the present invention, the subject is moved from a first position to a second position along a direction intersecting the optical axis of the imaging means. Then, at least one of the right half and the left half of the subject is continuously imaged by the imaging means. For this reason, a subject image in which the walking or running posture of the subject is continuously captured from the side with respect to the traveling direction can be obtained. And based on the subject image, data indicating the coordinates of a plurality of feature points on the human body is acquired. For this reason, such data can appropriately reflect the situation of the motion seen from the side of the subject, for example, the degree of the forward leaning posture, the speed of kicking off the foot, the speed of waving the hand, the degree of raising the knee, etc. The strength or weakness of the human body function often appears in these elements. For example, a subject in a weak physical condition tends to have a forward leaning posture or a weak hand wave. Thus, the situation of the motion seen from the side of the subject can be an important judgment factor for evaluating the human body function and the like. In the present invention, information indicating such an important judgment factor can be numerically acquired as the coordinates of the feature points on the body. For this reason, by analyzing the numerical values, it is possible to directly and in detail evaluate the body function and the like. As described above, according to the present invention, it is possible to acquire data that enables a direct and detailed analysis of the motion of the subject for evaluating the human body function and the like. Also, in the present invention, in the subject motion step, at the second position, the imaging... ... ... ... ... ... ... ... ... ... ... ... ...

[0008] Also, in the present invention, in the subject motion step, at the second position, the imaging... Turn in the direction toward the imaging means and walk or run the imaging means toward a third position closer to the imaging means than the second position. In the imaging step, continuously image the front of the subject during the operation in the subject movement step described above with the imaging means. In the feature point generation step, based on the data output from the imaging means regarding the imaging executed in the imaging step, generate second analysis data indicating the coordinates of the plurality of feature points at each timing of the subject during the movement from the second position to the third position, and preferably cause the feature point derivation means to generate the second analysis data. According to this, for example, data for evaluating body functions can be obtained based on the situation of the movement seen from the front of the subject, such as the lateral sway of the trunk due to walking. Also, in the present invention, in the subject movement step, a visible marker for the subject to recognize the movement path is provided, and the marker preferably includes at least one of a position marker indicating the second position and the third position, respectively, and a path marker extending along a line segment indicating an assumed straight line path through which the subject passes. According to this, the subject can accurately recognize the movement path by visually recognizing the marker. Therefore, data for accurately evaluating body functions can be obtained. Further, in the present invention, it is preferable that the path marker extends along two line segments extending in parallel to the assumed straight line path so as to sandwich the assumed straight line path. For example, if the assumed straight line path is indicated by only one line segment, when the subject aligns both feet on that one line segment and moves,

[0009]

[0010] ​​​​​​​​​​​​​​​There is a risk of movement and it may feel difficult to move. On the other hand, by forming two line segments sandwiching the assumed straight-line path, it is possible to secure a width for placing the feet for the subject, making it possible to feel easy to move. By forming two line segments that sandwich , it is possible to secure a width for placing the feet for the subject, making it possible to feel easy to move. Also, in the present invention, it preferably includes a derivation step of deriving the coordinates of the marker based on the data output from the imaging means regarding the imaging performed in the imaging step. According to this, the position of the subject can be grasped based on the derived coordinates of the marker.

[0011] Also, in the present invention, it preferably includes a derivation step of deriving the coordinates of the marker based on the data output from the imaging means regarding the imaging performed in the imaging step. According to this, the position of the subject can be grasped based on the derived coordinates of the marker. By forming two line segments that sandwich , it is possible to secure a width for placing the feet for the subject, making it possible to feel easy to move. Also, in the present invention, it preferably includes a derivation step of deriving the coordinates of the marker based on the data output from the imaging means regarding the imaging performed in the imaging step. According to this, the position of the subject can be grasped based on the derived coordinates of the marker. Also, in the present invention, it preferably includes a derivation step of deriving the coordinates of the marker based on the data output from the imaging means regarding the imaging performed in the imaging step. According to this, the position of the subject can be grasped based on the derived coordinates of the marker.

[0012] Also, in the present invention, it is preferable to use a pre-trained neural network to perform object detection on the marker in the derivation step. According to this, since a neural network is used, the accuracy of detecting the coordinates of the marker is increased. Also, in the present invention, it is preferable to use a pre-trained neural network to perform object detection on the marker in the derivation step. According to this, since a neural network is used, the accuracy of detecting the coordinates of the marker is increased. Also, in the present invention, it is preferable to use a pre-trained neural network to perform object detection on the marker in the derivation step. According to this, since a neural network is used, the accuracy of detecting the coordinates of the marker is increased. Also, in the present invention, it is preferable to use a pre-trained neural network to perform object detection on the marker in the derivation step. According to this, since a neural network is used, the accuracy of detecting the coordinates of the marker is increased.

[0013] Also, in the present invention, the feature point derivation means individually generates data indicating the coordinates of the plurality of feature points for each human body in the subject, and based on the coordinates of the marker derived in the derivation step and the first analysis data and the second analysis data generated in the feature point generation step, for each human body, an evaluation step of evaluating the positional relationship between the plurality of feature points and the assumed straight-line path, and a determination step of determining which of the human bodies is the subject based on the evaluation result in the evaluation step are preferably provided. According to this, even when there are a plurality of people as the subject, it is possible to determine which person is the subject. Therefore, Also, in the present invention, the feature point derivation means individually generates data indicating the coordinates of the plurality of feature points for each human body in the subject, and based on the coordinates of the marker derived in the derivation step and the first analysis data and the second analysis data generated in the feature point generation step, for each human body, an evaluation step of evaluating the positional relationship between the plurality of feature points and the assumed straight-line path, and a determination step of determining which of the human bodies is the subject based on the evaluation result in the evaluation step are preferably provided. According to this, even when there are a plurality of people as the subject, it is possible to determine which person is the subject. Therefore, Also, in the present invention, the feature point derivation means individually generates data indicating the coordinates of the plurality of feature points for each human body in the subject, and based on the coordinates of the marker derived in the derivation step and the first analysis data and the second analysis data generated in the feature point generation step, for each human body, an evaluation step of evaluating the positional relationship between the plurality of feature points and the assumed straight-line path, and a determination step of determining which of the human bodies is the subject based on the evaluation result in the evaluation step are preferably provided. According to this, even when there are a plurality of people as the subject, it is possible to determine which person is the subject. Therefore, Also, in the present invention, the feature point derivation means individually generates data indicating the coordinates of the plurality of feature points for each human body in the subject, and based on the coordinates of the marker derived in the derivation step and the first analysis data and the second analysis data generated in the feature point generation step, for each human body, an evaluation step of evaluating the positional relationship between the plurality of feature points and the assumed straight-line path, and a determination step of determining which of the human bodies is the subject based on the evaluation result in the evaluation step are preferably provided. According to this, even when there are a plurality of people as the subject, it is possible to determine which person is the subject. Therefore, Also, in the present invention, the feature point derivation means individually generates data indicating the coordinates of the plurality of feature points for each human body in the subject, and based on the coordinates of the marker derived in the derivation step and the first analysis data and the second analysis data generated in the feature point generation step, for each human body, an evaluation step of evaluating the positional relationship between the plurality of feature points and the assumed straight-line path, and a determination step of determining which of the human bodies is the subject based on the evaluation result in the evaluation step are preferably provided. According to this, even when there are a plurality of people as the subject, it is possible to determine which person is the subject. Therefore, Also, in the present invention, the feature point derivation means individually generates data indicating the coordinates of the plurality of feature points for each human body in the subject, and based on the coordinates of the marker derived in the derivation step and the first analysis data and the second analysis data generated in the feature point generation step, for each human body, an evaluation step of evaluating the positional relationship between the plurality of feature points and the assumed straight-line path, and a determination step of determining which of the human bodies is the subject based on the evaluation result in the evaluation step are preferably provided. According to this, even when there are a plurality of people as the subject, it is possible to determine which person is the subject. Therefore, Also, in the present invention, the feature point derivation means individually generates data indicating the coordinates of the plurality of feature points for each human body in the subject, and based on the coordinates of the marker derived in the derivation step and the first analysis data and the second analysis data generated in the feature point generation step, for each human body, an evaluation step of evaluating the positional relationship between the plurality of feature points and the assumed straight-line path, and a determination step of determining which of the human bodies is the subject based on the evaluation result in the evaluation step are preferably provided. According to this, even when there are a plurality of people as the subject, it is possible to determine which person is the subject. Therefore, Also, in the present invention, the feature point derivation means individually generates data indicating the coordinates of the plurality of feature points for each human body in the subject, and based on the coordinates of the marker derived in the derivation step and the first analysis data and the second analysis data generated in the feature point generation step, for each human body, an evaluation step of evaluating the positional relationship between the plurality of feature points and the assumed straight-line path, and a determination step of determining which of the human bodies is the subject based on the evaluation result in the evaluation step are preferably provided. According to this, even when there are a plurality of people as the subject, it is possible to determine which person is the subject. Therefore, Even if multiple people are captured during imaging, data about the subject can be properly obtained.

[0014] In addition, a motion analysis data acquisition system according to another aspect of the present invention converts an image of a subject into data. An imaging means for converting and outputting the data, and a method for converting the data output from the imaging means. and generating data indicating the coordinates of a plurality of feature points on the body of a person included in the subject indicated by the data. a feature point deriving means for deriving a feature point from the first position; , to a second position spaced apart from the first position in a direction intersecting the optical axis of the imaging means. A visible marker for allowing the subject to recognize the route along which the subject moves, The subject stands up from a seated position on the object and moves from the first position to the second position. When the subject moves, at least one of the left and right halves of the subject is captured by the imaging means. and based on the data output from the imaging means, During the motion of standing up from the body and during the motion of moving from the first position to the second position The analysis data indicating the coordinates of the plurality of feature points at each timing of the subject is The feature point derivation means generates the feature point.

[0015] According to the motion analysis data acquisition system of the present invention, the subject tracks his / her movement path using markers. By recognizing the position, the object is moved from the first position to the second position along a direction intersecting the optical axis of the imaging means. Then, at least one of the right and left halves of the subject's body is connected to the imaging means. Therefore, the subject's walking or running posture is continuously captured from the side in the direction of movement. Based on the subject images, the human body is Data showing the coordinates of multiple feature points is acquired. For this reason, such data includes the subject's The situation of the movement as viewed from the side, for example, the degree of the subject's forward-leaning posture, the speed of starting to swing the legs, the speed of swinging the hands, the degree of the knees rising, etc. can be appropriately reflected. The strength and weakness of a person's physical function often appear in these elements. For example, a subject in a weak physical condition tends to have a forward-leaning posture or weak hand swings. Thus, the situation of the movement as viewed from the side of the subject can become an important judgment factor for evaluating a person's physical function and the like. In the present invention, information indicating such an important judgment factor can be numerically obtained as the coordinates of characteristic points on the body. Therefore, by analyzing the numerical values, it is possible to directly and in detail evaluate the physical function and the like. As described above, according to the present invention, data can be obtained such that a direct and detailed analysis of the movement of the subject can be performed for evaluating the physical function of a person. Also, in the present invention, a mobile terminal and first and second computers are provided, and data converted from a subject image via a wired connection from the mobile terminal functioning as the imaging means is output to the first computer, and data indicating the coordinates of the plurality of characteristic points from the first computer functioning as the characteristic point derivation means is preferably output to the second computer via a wired connection. Since the output data reflects the posture of the moving subject, personal information of the subject is included. In contrast, data output between the mobile terminal and the first and second computers is performed via a wired connection. Therefore, the risk of data related to personal information leaking to the outside can be suppressed.

[0016]

[0017] In the present invention, the first computer receives data from the mobile terminal. A data recording unit is provided for recording the coordinates of the plurality of feature points. It is preferable to later delete the data from the portable terminal that has been recorded in the data recording unit. According to this, used data will be deleted. Therefore, data related to personal information This can further reduce the risk of data leaking to the outside. [Brief description of the drawings]

[0018]

Figure 1

Figure 2

Figure 3

Figure 4

Figure 5

Figure 6

Figure 7

Figure 8

Figure 9

Figure 10

Embodiments for Carrying Out the Invention

[0019] An analysis data acquisition system 1 according to an embodiment of the present invention will be described with reference to FIGS. 1 to 10. The analysis data acquisition system 1 acquires analysis data used for analyzing the actions of a subject based on the results of continuously imaging the subject performing a predetermined action. Details thereof will be described below. As shown in FIG. 1, the analysis data acquisition system 1 includes a mobile terminal 10 (imaging means in the present invention), a data acquisition device 20 (the first computer and feature point derivation means in the present invention),

[0020] and a PC 30 (the second computer in the present invention). The mobile terminal 10 and the data acquisition device 20, as well as the data acquisition device 20 and the PC 30, are respectively connected by a wired connection such as USB (Universal Serial Bus). Thereby, data communication is performed between the mobile terminal 10 and the data acquisition device 20, and between the data acquisition device 20 and the PC 30. Any of the mobile terminal 10, the data acquisition device 20, and the PC 30 is constructed by hardware such as a computer and software such as program data stored in a memory device (hereinafter referred to as a memory). These software can be recorded on various recording media and distributed. The computer includes a CPU (Central Processing Unit), a ROM (Read-Only Memory), and a RAM (Random Access Memory). The software of these can be recorded on various recording media and distributed. The computer includes a CPU (Central Processing Unit), a ROM (Read-Only Memory), and a RAM (Random Access Memory). The software of these can be recorded on various recording media and distributed. The computer includes a CPU (Central Processing Unit), a ROM (Read-Only Memory), and a RAM (Random Access Memory). The software of these can be recorded on various recording media and distributed. The computer includes a CPU (Central Processing Unit), a ROM (Read-Only Memory), and a RAM (Random Access Memory). Memory such as Main Memory), hard disk drives, and various interfaces such as input / output interfaces It includes hardware such as various interfaces such as touch faces. In each of the mobile terminal 10, the data acquisition device 20, and the PC 30, the hardware executes various information processes such as arithmetic processing and input / output processing according to the software As a result, the following functions in these devices are realized are realized

[0021] The mobile terminal 10 is provided with a touch panel display. On the screen of the touch panel display photographic images, control images for user input, etc. are displayed . When the user touches the screen of the touch panel display with a finger or the like, various user input processes are executed

[0022] The mobile terminal 10 is equipped with a camera. The camera has an optical system, a photoelectric conversion element, and various electronic circuits, and converts the subject image into data and outputs it as follows. The optical system includes lenses, slits, etc., and forms the subject image on the photoelectric conversion element through these. The photoelectric conversion element converts the subject image into an analog electrical signal. The electronic circuit converts the analog electrical signal generated by the photoelectric conversion element into a digital electrical signal and outputs it. The mobile terminal 10 generates a video data file showing a moving image of the subject based on the digital electrical signal output from the camera. The moving image in this embodiment refers to a series of images in which images showing the subject image at each time point are arranged continuously in time to represent the movement of the subject. The camera of the mobile terminal 10 is used to capture the actions of the subject, as will be described later. When capturing the actions of the subject , the mobile terminal 10 is used in a state where it is not connected to the data acquisition device 20 ​​It is obtained. After imaging the subject's movement, the mobile terminal 10 and the data acquisition device 20 are connected, and the video data file is transmitted from the mobile terminal 10 to the data acquisition device 20.

[0023] In addition, a web browser application (hereinafter referred to as "browser") is installed in the mobile terminal 10. When the browser is launched in the mobile terminal 10, data communication processing is executed according to the specified IP (Internet Protocol) address or URL (Uni form Resource Locator). For example, in the image (see image C1 in FIG. 7) displayed on the touch panel display by the function of the browser, the IP address corresponding to the data acquisition device 20 is input , and data communication is started between the mobile terminal 10 and the data acquisition device 20. For this data communication, TCP / IP (Transmission Control Protoc ol / Internet Protocol) is used. According to the function of such a browser, data including the video data file is sent and received between the mobile terminal 10 and the data acquisition device 20. The data acquisition device 20 generates data for analyzing the subject's movement based on the video data file transmitted from the mobile terminal 10. The detailed method of data generation will be described later. The data for movement analysis includes data indicating the subject's body at each time point. This data represents, as shown in FIG. 2, the coordinates of a plurality of feature points indicating the positions of each part included in the subject's body and the way these feature points are connected. For example, the feature point F1 corresponds to the subject's nose

[0024] The point. The feature point F2 corresponds to the subject's right shoulder. The feature point F3 corresponds to the subject's left shoulder. The data for movement analysis includes data indicating the subject's body at each time point. This data represents, as shown in FIG. 2, the coordinates of a plurality of feature points indicating the positions of each part included in the subject's body and the way these feature points are connected. For example, the feature point F1 corresponds to the subject's nose The point. The feature point F2 corresponds to the subject's right shoulder. The feature point F3 corresponds to the subject's left It is the point corresponding to the knee. Feature point F4 is the point corresponding to the right heel of the subject. Feature point F5 is the point corresponding to the neck of the subject. Also, in FIG. 2, these feature points are connected to each other by line segments For example, line segment L1 is the line segment connecting feature point F1 and feature point F5. Line segment L2 is the line segment connecting feature point F2 and feature point F5. These line segments show the connection method between the feature points, and as a whole, represent the general shape of the subject's body such as the head, neck, torso, arms, and legs. The motion analysis data includes, as shown in FIG. 2, the feature points and the data indicating the connection method between the feature points in a temporally continuous manner. Thereby, the arrangement of each part of the body at each time point in the subject's motion is shown by the motion analysis data, and how the arrangement of each part of the body changes over time is shown by the motion analysis data. For example, FIG. 3 shows the coordinates of the feature points and the connection method between the feature points represented by the motion analysis data generated based on the video data file related to the walking subject. As shown in FIG. 3, the general shape of the body of the walking subject at each of the temporally continuous times T1, T2, T3, T4, T5, T6, and T7 is represented by the feature points and the line segments connecting them. The motion analysis data may be, for example, data representing the coordinate values of the feature points and the vector values indicating their connection method, or data representing the circles corresponding to the feature points and the images of the line segments connecting them. Also, both of these types of data may be included in the motion analysis data. PC30 is a personal computer that receives the motion analysis data from the data acquisition device 20. As PC30, a desktop personal computer, a notebook personal computer, a tablet can be used.

[0025] PC30 is a personal computer that receives the motion analysis data from the data acquisition device 20. As PC30, a desktop personal computer, a notebook personal computer, a tablet can be used. ​​​A PC or the like is used. The PC 30 is equipped with a display and a keyboard, mouse, etc. An input device for user input is connected or installed. The PC 30 displays the real image and the control image for user input. When the browser is started on the PC30, the specified Data communication processing is performed according to the IP address or URL. For example, the function of the browser In the image displayed on the display by the function, the I corresponding to the data acquisition device 20 When the P address is input, data communication starts between the PC 30 and the data acquisition device 20. This data communication is carried out using TCP / IP (Transmission Control Protocol / Internet Protocol). ol Protocol / Internet Protocol) is used. According to the browser function, the data for motion analysis is transmitted between the PC 30 and the data acquisition device 20. Data including the IP address is sent and received.

[0026] Next, the behavior of the subject from which the analysis data is to be obtained will be described. The results were obtained by a test using an L-shaped course 40 (the moving path in the present invention) shown in FIG. The course 40 is set on an indoor floor, and the first course is set along the X direction in FIG. The straight line path 40a (the assumed straight line path in the present invention) and the second straight line path along the Y direction in FIG. The X-direction and the Y-direction are parallel to the floor. The first linear paths 40a are located at positions P1 (corresponding to the first position in the present invention) and position P2 (corresponding to the second position in the present invention). The second straight path 40b is formed by a position P2 and a position P3 (in the present invention) which are spaced apart from each other in the Y direction. connected to the third position in the specification). At position P1, a chair 41 on which the subject sits at the start of the operation is installed. The chair 41 is installed at a predetermined distance in the Y direction from position P3. A mobile terminal 10 is installed at a position separated from position P3 by a predetermined distance in the Y direction. The mobile terminal 10 is arranged such that the optical axis LX of the camera passes through positions P2 and P3 along the Y direction in a plan view. The mobile terminal 10 is arranged such that the entire chair 41 and the course 40 are included within its imaging range. The image of the shooting scene by the camera of the mobile terminal 10 is as shown in FIG. 5. Also, the position of the mobile terminal 10 is fixed using a camera stand or the like. On the floor of the room where the course 40 is set, markers 42 to 48 for allowing the subject to recognize the course 40 are formed. Markers 42 to 46 (path markers in the present invention) have a linear shape. These may be formed, for example, by linearly attaching a colored elongated adhesive tape to the floor surface, or by drawing on the floor surface with paint or the like.

[0027] Among these, marker 42 extends from position P1 to position P2 along the first straight path 40a. Markers 43 and 44 extend in parallel with the first straight path 40a so as to sandwich the first straight path 40a between them in the Y direction. The distance between marker 42 and marker 43 in the Y direction is equal to the distance between marker 42 and marker 44 in the Y direction. Marker 45 is connected to the end point of marker 42 at position P2 and extends from there to position P3 along the second straight path 40b. Markers 46 and 47 are connected to the end points of markers 43 and 44 and extend from there in parallel with the second straight path 40b. Markers 46 and 47 sandwich the first straight path 40a between them in the X direction. Marker 45 is connected to the end point of marker 42 at position P2 and extends from there to position P3 along the second straight path 40b. Markers 46 and 47 are connected to the end points of markers 43 and 44 and extend from there in parallel with the second straight path 40b. Markers 46 and 47 sandwich the first straight path 40a between them in the X direction. Marker 45 is connected to the end point of marker 42 at position P2 and extends from there to position P3 along the second straight path 40b. Markers 46 and 47 are connected to the end points of markers 43 and 44 and extend from there in parallel with the second straight path 40b. Markers 46 and 47 sandwich the first straight path 40a between them in the X direction. Marker 45 is connected to the end point of marker 42 at position P2 and extends from there to position P3 along the second straight path 40b. The distance of the marker 46 in the X direction is equal to the distance of the marker 45 and the marker 47 in the X direction. As a result, the markers 42 to 46 are aligned along the first straight path 40a and the second straight path 40b. The markers 48 and 49 (positions in the present invention) indicate the entire course 40 consisting of the markers 48 and 49 (positions in the present invention). The markers are in the form of circles filled with a given color. Alternatively, the marker may be formed by sticking a solid circular adhesive tape of a certain color onto the floor surface. Alternatively, the marker 48 may be formed by drawing the marker 48 on the floor surface with paint or the like. The marker 48 is placed at the position P2. The marker 49 is placed at position P3. As a result, the marker 48 is placed at position P2. Markers 49 each point to position P3.

[0028] The test using Course 40 was as follows. As shown in Figure 5, the subject first The motion starts from a state where the subject sits on the chair 41 at position P1. Next, the subject stands up from the chair 41. Then, the subject walks along the marker 42 in the area between the marker 43 and the marker 44 to the position P2. At position P2, the vehicle turns toward position P3 and enters the area between markers 46 and 47. The subject walks along the marker 45 to position P3. When the subject reaches position P3, the movement ends. The subject's behavior from the start of the movement to the end of the movement is captured by the mobile terminal 10. .

[0029] Next, analysis data according to an embodiment of the present invention using the analysis data acquisition system 1 will be described. The overall flow of the acquisition method will be explained with reference to Figure 6. First, The table 40, the chair 41, and the mobile terminal 10 are set up (step S1). A person sits on a chair 41 and places an ID recording board in front of the mobile terminal 10. Imaging by 10 is started (step S2). The ID recording board records in advance the subject's ID number and the imaging date (see Fig. 7). Next, the subject is made to perform the above test using course 40, and the movement of the subject from the start to the end is imaged as a video by the mobile terminal 10 (step S3). Note that step S3 corresponds to the subject movement step and the imaging step in the present invention. As a result, the right half of the subject walking along the first straight path 40a which is the movement path from position P1 to position P2 (see Fig. 3) is imaged, and the front of the subject walking along the second straight path 40b which is the movement path from position P2 to position P3 (see Fig. 3) is imaged. The video data file showing the imaging result is stored in the memory or the like in the mobile terminal 10. Next, the mobile terminal 10

[0030] is connected to the data acquisition device 20 (step S4).

[0030] Next, a browser is launched on the mobile terminal 10, and data communication is started between the mobile terminal 10 and the data acquisition device 20 (step S5). Based on the data transmitted from the data acquisition device 20 to the mobile terminal 10, the screen IM1 shown in Fig. 7 is displayed on the touch panel display of the mobile terminal 10. The screen IM1 is an image for transferring the video data file stored in the memory in the mobile terminal 10 in step S3 to the data acquisition device 20. The screen IM1 includes a control image C1 for specifying an IP address or a URL, a control image C2 for inputting an ID number, a control image C3 for selecting a video data file to be transferred, and a control image C4 for starting the transfer (hereinafter referred to as "image C1", is present. When a user touches the position of these control images on the touch panel display, the control image corresponding to the touch position is selected, and processes such as inputting characters and numbers and selecting items from a list are executed. In the image C1 of FIG. 7, the result of inputting the IP address corresponding to the data acquisition device 20 is displayed. The ID number input through the image C2 corresponds to the ID number recorded on the ID recording board in step S2. When a video data file is selected from the file list through the image C3, an image V corresponding to the beginning part of the selected video data file is displayed below the image C3. In step S2, since the ID recording board is imaged immediately after the start of imaging, the ID number recorded on the board is visible through the image V of FIG. 7. The user can confirm the ID number displayed as the image V and input the ID number through the image C2 after selecting the video data file through the image C3, and can also confirm the content of the input ID number. After inputting the ID number through the image C2 and selecting the video data file through the image C3, by selecting the image C4, the transfer of the video file data and the ID number from the mobile terminal 10 to the data acquisition device 20 is started (step S6). In the data acquisition device 20, the video file data transferred together with the ID number is stored in a memory or the like in association with the ID number. When a user touches the position of these control images on the touch panel display, the control image corresponding to the touch position is selected, and processes such as inputting characters and numbers and selecting items from a list are executed. When a user touches the position of these control images on the touch panel display, the control image corresponding to the touch position is selected, and processes such as inputting characters and numbers and selecting items from a list are executed. In the image C1 of FIG. 7, the result of inputting the IP address corresponding to the data acquisition device 20 is displayed. The ID number input through the image C2 corresponds to the ID number recorded on the ID recording board in step S2. When a video data file is selected from the file list through the image C3, an image V corresponding to the beginning part of the selected video data file is displayed below the image C3. When a video data file is selected from the file list through the image C3, an image V corresponding to the beginning part of the selected video data file is displayed below the image C3. In step S2, since the ID recording board is imaged immediately after the start of imaging, the ID number recorded on the board is visible through the image V of FIG. 7. In step S2, since the ID recording board is imaged immediately after the start of imaging, the ID number recorded on the board is visible through the image V of FIG. 7. The user can confirm the ID number displayed as the image V and input the ID number through the image C2 after selecting the video data file through the image C3, and can also confirm the content of the input ID number. The user can confirm the ID number displayed as the image V and input the ID number through the image C2 after selecting the video data file through the image C3, and can also confirm the content of the input ID number. After inputting the ID number through the image C2 and selecting the video data file through the image C3, by selecting the image C4, the transfer of the video file data and the ID number from the mobile terminal 10 to the data acquisition device 20 is started (step S6). After inputting the ID number through the image C2 and selecting the video data file through the image C3, by selecting the image C4, the transfer of the video file data and the ID number from the mobile terminal 10 to the data acquisition device 20 is started (step S6). After inputting the ID number through the image C2 and selecting the video data file through the image C3, by selecting the image C4, the transfer of the video file data and the ID number from the mobile terminal 10 to the data acquisition device 20 is started (step S6). In the data acquisition device 20, the video file data transferred together with the ID number is stored in a memory or the like in association with the ID number. In the data acquisition device 20, the video file data transferred together with the ID number is stored in a memory or the like in association with the ID number.

[0031] Next, in the data acquisition device 20, based on the video data file transferred from the mobile terminal 10, the process of acquiring operation analysis data is executed (step S7). The details of this process will be described later. Note that step S7 corresponds to the feature point generation step in the present invention. Next, in the data acquisition device 20, based on the video data file transferred from the mobile terminal 10, the process of acquiring operation analysis data is executed (step S7). The details of this process will be described later. Note that step S7 corresponds to the feature point generation step in the present invention. Next, in the data acquisition device 20, based on the video data file transferred from the mobile terminal 10, the process of acquiring operation analysis data is executed (step S7). The details of this process will be described later. Note that step S7 corresponds to the feature point generation step in the present invention. . When the acquisition process of the motion analysis data is completed, the data acquisition device 20 uses the video data file used for the acquisition of the motion analysis data to delete it from a memory, a hard disk drive, etc. (the data recording unit in the present invention).

[0032] Next, on the PC 30 connected to the data acquisition device 20, a download process of the motion analysis data generated by the data acquisition device 20 is executed (step S8). The browser is launched on the PC 30, and an IP address etc. corresponding to the data acquisition device 20 is specified . As a result, based on the data transmitted from the data acquisition device 20, the screen IM2 shown in FIG. 8 is displayed on the display of the PC 30. The screen IM2 is an image for transferring the motion analysis data generated by the data acquisition device 20 to the PC 30 in step S7 . The screen IM2 includes an information display T showing file information. Also, on the screen IM 2, based on the data transmitted from the data acquisition device 20, a control image C11 for starting the download and a control image C12 for deleting the file (hereinafter referred to as "image C11" and "image C12") are included. The information display T as well as

[0033] the images C11 and C12 are displayed in a table format with a plurality of character strings and icon images. The information display T includes character strings indicating the ID number, the registration date and time of the file, and the status . These character strings are displayed in a table format arranged vertically and horizontally, thereby showing the association between the ID number and the registration date and time and status of the file corresponding to the ID number . The status has four types: "acquired", "converting", "completed", and "error" . The information display T and the images C11 and C12 are displayed in a table format with a plurality of character strings and icon images. The information display T includes character strings indicating the ID number, the registration date and time of the file, and the status . These character strings are arranged vertically and horizontally in a table format, thereby showing the association between the ID number and the registration date and time and status of the file corresponding to the ID number . The status has four types: "acquired", "converting", "completed", and "error" . is shown. 。"Acquired" indicates that the transfer of operation analysis data to the PC 30 has been completed. "Converting" indicates that the conversion process from video file data to operation analysis data is in progress in the data acquisition device 20. "Completed" indicates that the conversion process from video file data to operation analysis data in the data acquisition device 20 has been completed. "Error" indicates that an error has occurred for some reason in the conversion process from video file data to operation analysis data in the data acquisition device 20, indicating that the conversion process is incomplete.

[0034] The image C11 includes an icon image for starting the download. The icon image is displayed at each position corresponding to the ID number in the information display T in the vertical direction. Note that at the position corresponding to the ID number for which the conversion process from video file data to operation analysis data is incomplete, a character string "Preparing" is displayed instead of the icon image. When the icon image is selected using an input device such as a mouse, the operation analysis data associated with the ID number corresponding to the icon image is downloaded from the data acquisition device 20 to the PC 30.

[0035] The image C12 includes an icon image for deleting the file. The icon image is displayed at each position corresponding to the ID number in the information display T in the vertical direction. When the icon image is selected using the input device, the operation analysis data associated with the ID number corresponding to the icon image is deleted from the memory etc. in the data acquisition device 20 (step S9). Note that in this embodiment, before starting the conversion process to operation analysis data, after starting the conversion process to operation analysis data, the data acquisition device 20 ​ configured to delete a video data file that has elapsed a predetermined length of time (e.g., 10 minutes) from a memory or the like. Since the data acquisition device 20 is configured in this way, when the conversion process abnormally ends or stops, it is possible to avoid the video data file remaining in the device.

[0036] Hereinafter, in step S7 of FIG. 6, the process of the data acquisition device 20 that obtains operation analysis data from the video data file will be described with reference to FIG. 9. First, the data acquisition device 20 executes a process of detecting the positions of the markers 48 and 49 in the image based on a specific frame image in the video data file (step S11). The frame image corresponds to a still image of the subject at each timing. Detecting the positions of the markers 48 and 49 in the image is because, based on the positions, the exact position of the subject with respect to the code 40 reflected in the imaging shown by the video data file can be grasped (see step S15). Note that step S11 corresponds to the derivation step in the present invention.

[0037] In this embodiment, "SSD" object detection (Liu, W., Anguelov, D., Erhan, D., Szegedy, C., Reed, S., Fu, C. Y., & Berg, A. C. (2016, Oct ober). SSD: Single shot multibox detector. In European conference on computer vision (pp. 21-37)) is adopted as the process of step S11. The outline of the image processing by "SSD" object detection is as follows. By "SSD" object detection, at which position in the original image to be processed ​​​​​​​​Information indicating whether an object to be detected is included is obtained. This information is the coordinates of the four corners of a bounding box, which is a rectangular frame indicating the region where the object to be detected exists (corresponding to frames B1 and B2 in Fig. 5). To obtain this information, for each position in the original image to be processed, multiple types of rectangular frames with different shapes and sizes, i.e., default boxes, are set. Then, as a neural network, when the original image is input, for each default box, a network learned to output the difference between the default box and the bounding box and a value indicating the classification of the subject included in the default box is used. The difference between the default box and the bounding box is obtained, for example, as the difference in the X position and Y position between the centers of the boxes and the difference in width and height between the boxes. The value indicating the classification of the subject included in the default box is obtained as a value indicating the likelihood that the subject included in the default box belongs to a preset type. In this embodiment, since the objects to be detected are limited to markers 48 and 49, a neural network specially learned to output the likelihoods corresponding to markers 48 and 49 with high accuracy is used. And in this embodiment, for each of markers 48 and 49, the default box with the highest likelihood is extracted as a candidate for object detection. From the coordinates indicating the extracted default box and its difference, the predicted coordinates of the bounding box are obtained as the coordinates of frames B1 and B2 indicating markers 48 and 49.

[0038] Next, for each frame image, the data acquisition device 20 executes a process of deriving the feature points of the body of each person included in the subject and the way they are connected (step S12). In this embodiment, as this process, "OpenPose" (Zhe Cao and Tomas Simon and Shih-En Wei and Yaser Sheikh. Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields. In CVPR, 2017.) is adopted. The neural network used in "OpenPose" is configured to mainly execute the following first to third processes. The first process is a process of generating a feature map image which is a rough image that extracts the features of the subject included in the original image. The second process is a process of generating an image corresponding to a vector map indicating the direction connecting the positions corresponding to the body parts in the region corresponding to the person in the input image. For example, as shown in FIG. 2, in the region between the feature point F1 indicating the subject's neck and the feature point F5 indicating the right shoulder, in the vector map, a vector indicating the direction connecting the feature point F1 and the feature point F5 is distributed. The third process is a process of generating an image corresponding to a confidence map showing the two-dimensional distribution of the probability that each body part (for example, the feature point F1 indicating the subject's neck, the feature point F5 indicating the right shoulder, etc.) exists in the region corresponding to the person in the input image. This neural network repeats the second and third processes respectively a plurality of times with the images generated in the first to third processes as inputs, so that the finally obtained output becomes data indicating the coordinates of the feature points of the person shown in the original image and the way of connecting the feature points (that is, data representing the general shape of the body as shown in FIG. 2). That is, the data representing the general shape of the body as shown in FIG. 2). This neural network repeats the second and third processes respectively a plurality of times with the images generated in the first to third processes as inputs, so that the finally obtained output becomes data indicating the coordinates of the feature points of the person shown in the original image and the way of connecting the feature points (that is, data representing the general shape of the body as shown in FIG. 2). is learned using deep learning. When a plurality of persons are included in the image the way of connecting the feature points is derived for each person while distinguishing the persons. That is data indicating the feature points and the way of connecting the feature points is generated individually for each person. Also this neural network derives a numerical value indicating the plausibility of each feature point for each feature point. Note that the neural network may be configured to derive feature points and a way of connection not only for a person but also for a humanoid object as well.

[0039] Next, the data acquisition device 20 extracts candidates for the subject from among the persons indicated by the coordinates of the feature points and the way of connecting the feature points derived in step S12 (step S13 ). When a plurality of persons are included in the image, what is derived in step S12 is data indicating the coordinates of the feature points and the way of connecting the feature points for a plurality of persons. Therefore in step S13, among the numerical values indicating the plausibility of the feature points extracted in step S12 a person in which there are a predetermined number (for example, 5) or more feature points whose plausibility is a numerical value equal to or higher than a predetermined height (for example, 0.4 when the numerical value is derived in the range of 0 to 1 is extracted as a subject candidate.

[0040] Next, the data acquisition device 20 evaluates the positional relationship between the person and the course 40 for each subject candidate extracted in step S13 (step S14). Note that step S14 corresponds to the evaluation step in the present invention. Specifically, based on the coordinates of the feature points in a predetermined frame (for example a frame in which the state of the subject walking is shown S14 corresponds to the evaluation step in the present invention. Specifically, based on the coordinates of the feature points in a predetermined frame (for example a frame in which the state of the subject walking is shown Execute the following process. For each person, calculate the average value of the X coordinate values of the feature points and the maximum value of the Y coordinate values of the feature points (the Y coordinate value of the feature point located at the bottommost in the image), and use them as the representative position of that person. The data acquisition device 20 derives the straight-line distance between this representative position and the course 40. To derive the straight-line distance, the positions (coordinates) of the markers 4 8 and 49 in the images acquired in step S11 are used. That is, based on the positions of the markers 48 and 49, the positions of the line segments along the markers 42 and 43 shown in FIG. 10 in the image are acquired. Based on this, by calculating the straight-line distance between the representative position and the line segment, the straight-line distance between the representative position and the course 40 is calculated.

[0041] Then, the data acquisition device 20 determines that the person with the smallest straight-line distance derived in step S14 is the subject (step S15). Note that step S15 corresponds to the determination step in the present invention. For example, in FIG. 10, the representative position R1 (X1, Y1) regarding the person M1 and the representative position R2 (X2, Y2) regarding the person M2 are shown. In this case, since the straight-line distance D1 between R1 regarding the person M1 and the course 40 is smaller than the straight-line distance D2 between R2 regarding the person M2 and the course 40, the person M 1 is determined to be the subject. The data indicating the coordinates of the feature points related to the subject determined in step S15 and the way of associating the feature points with each other corresponds to the motion analysis data acquired in step S7 of FIG. 9. The motion analysis data includes, for the right half body image of the subject, the coordinates of the feature points and the data indicating the way of associating the feature points with each other during the operation of standing up from the chair at the position P1 and during the operation of moving from the position P1 to the position 2 (the first solution in the present invention). The data indicating the coordinates of the feature points related to the subject determined in step S15 and the way of associating the feature points with each other corresponds to the motion analysis data acquired in step S7 of FIG. 9. The motion analysis data includes, for the right half body image of the subject, the coordinates of the feature points and the data indicating the way of associating the feature points with each other during the operation of standing up from the chair at the position P1 and during the operation of moving from the position P1 to the position 2 (the first solution in the present invention). coordinates of the feature points and the data indicating the way of associating the feature points with each other during the operation of standing up from the chair at the position P1 and during the operation of moving from the position P1 to the position 2 (the first solution in the present invention). Analysis data), and for the front image of the subject, the movement from position P2 to position 3 Data showing the coordinates of the feature points and the connection method between the feature points in (the second analysis data in the present invention) is included.

[0042] According to the present embodiment described above, in the test using the course 40 shown in FIG. 4, the subject is made to walk from position P1 to position P2 along the X direction, that is, along the direction orthogonal to the optical axis LX of the camera of the mobile terminal 10. Then, the right half of the subject is continuously imaged as a video by the camera of the mobile terminal 10. For this reason, a video that continuously captures the walking posture of the subject from the side with respect to the traveling direction is obtained. Then, based on the video, the data acquisition device 20 acquires motion analysis data showing the coordinates of a plurality of feature points in the human body and the connection method between the feature points . For this reason, such data can appropriately reflect the situation of the motion seen from the side of the subject, for example, the degree of the forward leaning posture of the subject, the starting speed of the foot, the speed of waving the hand , the degree of knee lifting, etc. The strength of the human body function often appears in these elements. For example, in a subject in a weak physical condition , there is a tendency to have a forward leaning posture or a weak hand wave. Thus, the situation of the motion seen from the side of the subject can be an important judgment factor for evaluating the human body function etc. . The present embodiment can numerically acquire information indicating such an important judgment factor as the coordinates of the feature points in the body . For this reason, by analyzing the numerical values, it is possible to directly and in detail evaluate the body function etc . As described above, according to the present embodiment, a motion analysis that enables a direct and detailed analysis of the motion of the subject for evaluating the human body function etc is possible. . The present embodiment can numerically acquire information indicating such an important judgment factor as the coordinates of the feature points in the body . For this reason, by analyzing the numerical values, it is possible to directly and in detail evaluate the body function etc . As described above, according to the present embodiment, a motion analysis that enables a direct and detailed analysis of the motion of the subject for evaluating the human body function etc is possible. The usage data can be obtained.

[0043] Also, in this embodiment, in the test using the course 40 shown in FIG. 4, at the position P 2, the direction is changed toward the mobile terminal 10, and from there, the subject walks toward the mobile terminal 1 0 up to the position P3. Then, the front of the subject is continuously imaged as a video by the camera of the mobile terminal 10. For this reason, a video that continuously captures the walking posture of the subject from the front thereof can be obtained. Then, based on the video, the data acquisition device 20 acquires motion analysis data indicating the coordinates of a plurality of feature points on the human body and the connection method between the feature points. According to this, for example, motion analysis data for performing an evaluation of the body function or the like can be obtained based on the situation of the motion seen from the front of the subject, such as the lateral sway of the torso due to walking.

[0044] Also, in this embodiment, markers 4 2 to 49 indicating the course 40 are installed so as to be visible to the subject. According to this, the subject can recognize the movement path more accurately by visually recognizing these markers. Therefore, motion analysis data for accurately performing an evaluation of the body function or the like can be obtained. Among these markers, markers 43 and 44 are formed so as to sandwich the marker 42 along the first linear path 40a therebetween. Similarly, markers 46 and 47 are formed so as to sandwich the marker 45 along the second linear path 40b therebetween. For example, if the movement path is indicated only by markers 42 and 45, there is a possibility that the subject walks with both feet aligned with markers 42 and 45 (as if moving on an average table), and it may be difficult to walk and feel uncomfortable. In contrast, marker 42 By forming markers 43 and 44, and 46 and 47 so as to sandwich 45, for the subject, since a width for placing a foot can be secured between them, it is possible to make the subject feel easy to walk. For the subject, since a width for placing a foot can be secured between them, it is possible to make the subject feel easy to walk. It can be done.

[0045] Also, in the present embodiment, between the mobile terminal 10 and the data acquisition device 20, and between the data acquisition device 20 and the PC 30 are respectively connected by a wired connection such as the USB method. The video data files and video analysis data exchanged between these devices reflect the walking posture of the subject, so personal information of the subject is included. For the subject, this will include personal information. On the other hand, as described above, the data exchange is performed via a wired connection. Therefore, the risk of data related to personal information leaking to the outside can be suppressed. Furthermore In the present embodiment, when the acquisition process of the motion analysis data is completed, the data acquisition device 20 deletes the video data file used for acquiring the motion analysis data from the memory or the like. Also, when the power of the data acquisition device 20 is once turned off and then turned on again, the data acquisition device 20 automatically deletes all video data files from the memory or the like. At this time, the data acquisition device 20 deletes all video data files from the memory or the like. Therefore, the risk of data related to personal information leaking to the outside can be further suppressed. For this reason, the risk of data related to personal information leaking to the outside can be further suppressed. It can be.

[0046] <Other Modifications> The above is an explanation of the preferred embodiment of the present invention. However, the present invention is not limited to the above-described embodiment and various changes are possible as long as they are within the scope described in the means for solving the problems. It is possible.

[0047] For example, in the above-described embodiment, the path along which the subject walks is the first straight path 40a and the second The path is set as a straight line 40b. However, it does not necessarily have to be a straight line. The first straight path 40a may be set as a path that runs along a curved line. The position is set along the X direction perpendicular to the optical axis of the camera of the mobile terminal 10. A video of the right half of the subject walking along the first straight path 40a can be acquired. The first straight path 40a is a straight path that can capture a moving image of the right or left half of the subject's body. For example, the first straight path 40a may not be perpendicular to the optical axis of the camera. The angle may be set to intersect with the optical axis at an angle other than 90°. In addition, the route can be not only from position P1 to position P2 to position P3, but also from position P2 to position P3. After reaching position P3, the subject walks along the path from position P3 to position P2 to position P1. In this case, video of the left half and back of the subject, as well as the right half and front, may be recorded. can be obtained.

[0048] In the above embodiment, the detection of the positions of the markers 48 and 49 is performed using a neural network. However, other methods may be used. For example, Alternatively, the detection may be performed based on color information of the pixels.

[0049] In the above embodiment, in step S15, the The straight-line distance between the representative position of the subject candidate derived in step S14 and the course 40 The person with the smallest score is judged to be the subject. However, the subject's judgment is It is not the straight-line distance between the table position and the course 40, but the specific position relative to the representative position and the course 40. The specific position may be a position that is in a predetermined positional relationship with the course 40. a position, for example, the same position as the midpoint of the marker 42 with respect to the X direction and the same position as the midpoint of the marker 45 with respect to the Y direction.

Explanation of Signs

[0050] 1 Analysis data acquisition system 10 Mobile terminal 20 Data acquisition device 30 PC

Claims

1. An imaging unit that converts a subject image into data and outputs it, and a feature point derivation unit that generates data indicating the coordinates of a plurality of feature points on the body of a person included in the subject indicated by the data based on the data output from the imaging unit. A method for acquiring data for analyzing the movement of a person, comprising: A subject movement step of causing the subject to stand up from a state of sitting on an object at a first position and walk or run to a second position separated from the first position in a direction intersecting the optical axis of the imaging unit and parallel to the horizontal direction; An imaging step of continuously imaging at least one of the left and right halves of the subject during the movement in the subject movement step by the imaging unit; A feature point generation step of causing the feature point derivation unit to generate first analysis data indicating the coordinates of the plurality of feature points at each timing of the subject during the movement of standing up from the object and during the movement from the first position to the second position based on the data output from the imaging unit regarding the imaging performed in the imaging step; In the subject movement step, causing the subject to change direction toward the imaging unit at the second position and walk or run toward the imaging unit to a third position closer to the imaging unit than the second position; In the imaging step, continuously imaging the front of the subject during the movement in the subject movement step by the imaging unit; In the feature point generation step, causing the feature point derivation unit to generate second analysis data indicating the coordinates of the plurality of feature points at each timing of the subject during the movement from the second position to the third position based on the data output from the imaging unit regarding the imaging performed in the imaging step; In the subject movement step, a visible marker for the subject to recognize the movement path is installed; The marker includes at least one of a position marker that indicates the second position and the third position, and a path marker that extends along a line segment indicating an assumed straight-line path through which the subject passes. The feature point derivation means individually generates data indicating the coordinates of the plurality of feature points for each human body in the subject. A derivation step of deriving the coordinates of the marker based on data output from the imaging means regarding the imaging performed in the imaging step; An evaluation step of evaluating the positional relationship between the plurality of feature points and the assumed straight-line path for each of the human bodies based on the coordinates of the marker derived in the derivation step and the first analysis data and the second analysis data generated in the feature point generation step; The method for acquiring motion analysis data further includes a determination step of determining which of the human bodies is the subject based on the evaluation result in the evaluation step.

2. The method for acquiring motion analysis data according to claim 1, wherein the path marker extends along two line segments that extend parallel to the assumed straight-line path so as to sandwich the assumed straight-line path.

3. The method for acquiring motion analysis data according to claim 1 or 2, wherein in the derivation step, a learned neural network is used to perform object detection on the marker.

4. Imaging means for converting a subject image into data and outputting it; Feature point derivation means for generating data indicating the coordinates of a plurality of feature points in the human body included in the subject indicated by the data based on the data output from the imaging means; An object on which a subject sitting at a first position sits; And a visible marker for allowing the subject to recognize a movement path. When the subject stands up from the state of sitting on the object and moves from the first position to a second position separated from the first position in a direction intersecting the optical axis of the imaging means, at least one of the left and right halves of the subject is imaged by the imaging means. At this time, based on the data output from the imaging means, the feature point derivation means is caused to generate first analysis data indicating the coordinates of the plurality of feature points at each timing of the subject during the operation of standing up from the object and during the operation of moving from the first position to the second position. When the subject changes direction toward the imaging means at the second position and walks toward the imaging means to a third position closer to the imaging means than the second position, the front of the subject is continuously imaged by the imaging means. At this time, based on the data output from the imaging means, the feature point derivation means is caused to generate second analysis data indicating the coordinates of the plurality of feature points at each timing of the subject during the operation of moving from the second position to the third position. The marker includes at least one of a position marker for indicating the second position and the third position, and a path marker extending along a line segment indicating an assumed straight-line path through which the subject passes, for allowing the subject to recognize a path from the first position to the second position. The feature point derivation means individually generates data indicating the coordinates of the plurality of feature points for each body of a person in the subject. Based on the data output from the imaging means, the coordinates of the marker are derived. Based on the derived coordinates of the marker and the first analysis data and the second analysis data generated by the feature point derivation means, for each body of the person, the positional relationship between the plurality of feature points and the assumed straight-line path is evaluated. An operation analysis data acquisition system characterized by determining which of the bodies of the person is the subject based on the evaluation result.

5. It includes a mobile terminal and first and second computers. Data converted from a subject image is output from the mobile terminal that functioned as the imaging means to the first computer via a wired connection. The operation analysis data acquisition system according to claim 4, characterized in that data indicating the coordinates of the plurality of feature points is output from the first computer that functioned as the feature point derivation means to the second computer via a wired connection.

6. The operation analysis data acquisition system according to claim 5, characterized in that the first computer includes a data recording unit that records data from the mobile terminal, and deletes the data from the mobile terminal that was recorded in the data recording unit after generating data indicating the coordinates of the plurality of feature points.

Images