Coordinate transformation method, coordinate transformation device, motion analysis method, motion analysis device, and computer program
Patent Information
- Application Number
- MYPI2025004841
- Authority / Receiving Office
- MY · MY
- Patent Type
- Applications
- Current Assignee / Owner
- Priority Date
- 2023-02-13
- Filing Date
- 2024-02-13
- Publication Date
- 2024-08-13
AI Technical Summary
Markerless motion capture systems face challenges in accurately analyzing movements like walking due to the use of a coordinate system fixed to the system, which deteriorates measurement accuracy and requires complex processing to align motion information collected from multiple positions.
A coordinate transformation method that converts three-dimensional skeletal information from a first coordinate system to a second system with orthogonal X, Y, and Z directions, allowing for detailed motion analysis using data collected from a single position, by calculating the traveling direction, torso direction, and perpendicular directions, and applying a matrix transformation.
Enables accurate and detailed motion analysis of walking and other movements without the need for multiple camera setups or marker installation, improving measurement accuracy and simplifying data alignment.
Smart Images

Figure PI2025004841_DRAWING_001 
Figure PI2025004841_DRAWING_002 
Figure PI2025004841_DRAWING_003
Abstract
Description
Coordinate transformation method, coordinate transformation device, motion analysis method, motion analysis device, and computer program
[0001] The present invention relates to a coordinate transformation method, a coordinate transformation device, a motion analysis method, a motion analysis device, and a computer program that can be suitably used for analyzing motion such as walking.
[0002] Markerless motion capture systems enable simple motion analysis, and are expected to see future development in a variety of fields. However, in order to perform detailed motion analysis using a markerless motion capture system, measurement accuracy and coordinate system definition are issues. In particular, for movements that involve moving in a fixed direction, such as walking, it is necessary to set an appropriate coordinate system (e.g., a world coordinate system fixed to the ground) to analyze the movement. However, many markerless motion capture systems use a coordinate system fixed to the system, which can reduce the accuracy of the measured data, making it impossible to use the measured data directly for analyzing walking movements.
[0003] Alternatively, for example, Patent Document 1 (Japanese Patent No. 6381918) discloses a motion information processing device including: an acquisition unit that acquires motion information of a subject performing a predetermined motion collected from multiple different positions of the subject; a calculation unit that calculates related information for aligning the motion information based on positions of feature points of the subject included in each of the motion information acquired by the acquisition unit; and an output control unit that controls an output unit to output output information in which the motion information is aligned based on the related information calculated by the calculation unit. However, because such a device requires motion information collected from multiple positions, complex processing is required to align the acquired motion information.
[0004] Patent No. 6381918
[0005] An object of the present invention is to provide a coordinate transformation technique that enables detailed analysis of movements such as walking using movement information collected from a single position.
[0006] In order to solve the above-mentioned problems, a first aspect of the present invention provides a coordinate transformation method comprising the steps of: acquiring three-dimensional skeletal information of a subject in motion in a first coordinate system consisting of x', y', and z' directions which are orthogonal to each other; calculating, using the skeletal information, a Y direction which is the subject's direction of movement, a Z direction which follows the subject's torso, and an X direction which is orthogonal to the Y direction and the Z direction; and transforming the first coordinate system into a second coordinate system consisting of the X direction, the Y direction, and the Z direction, thereby acquiring coordinate-transformed skeletal information.
[0007] In the coordinate transformation method of the present invention, it is preferable that the Z direction is a direction from the pelvis toward the chest of the subject.
[0008] In the coordinate transformation method of the present invention, it is preferable that the transformation into the second coordinate system is performed using a matrix corresponding to the first coordinate system and a matrix corresponding to the second coordinate system.
[0009] A second aspect of the present invention provides a computer program for executing the steps of: acquiring three-dimensional skeletal information of a subject in motion in a first coordinate system consisting of mutually perpendicular x', y', and z' directions; calculating, using the skeletal information, a Y direction which is the subject's direction of movement, a Z direction along the subject's torso, and an X direction which is perpendicular to the Y direction and Z direction; and transforming the first coordinate system into a second coordinate system consisting of the X direction, the Y direction, and the Z direction, and acquiring the coordinate-transformed skeletal information.
[0010] A third aspect of the present invention provides a coordinate transformation device comprising: an acquisition unit that acquires three-dimensional skeletal information of a subject in motion in a first coordinate system consisting of mutually perpendicular x', y', and z' directions; an axial direction calculation unit that uses the skeletal information to calculate a Y direction that is the subject's direction of movement, a Z direction along the subject's torso, and an X direction that is perpendicular to the Y direction and Z direction; and a coordinate transformation unit that transforms the first coordinate system into a second coordinate system consisting of the X direction, the Y direction, and the Z direction.
[0011] A fourth aspect of the present invention provides a motion analysis method comprising: acquiring three-dimensional skeletal information of a subject in motion in a first coordinate system consisting of mutually perpendicular x', y', and z' directions; calculating, using the skeletal information, a Y direction which is the subject's direction of movement, a Z direction along the subject's body, and an X direction which is perpendicular to the Y direction and Z direction; transforming the first coordinate system into a second coordinate system consisting of the X direction, the Y direction, and the Z direction; and performing motion analysis using the coordinate-transformed skeletal information.
[0012] A fifth aspect of the present invention provides a computer program for executing the steps of: acquiring three-dimensional skeletal information of a subject in motion in a first coordinate system consisting of mutually perpendicular x', y', and z' directions; calculating, using the skeletal information, a Y direction which is the subject's direction of movement, a Z direction along the subject's body, and an X direction which is perpendicular to the Y direction and Z direction; transforming the first coordinate system into a second coordinate system consisting of the X direction, the Y direction, and the Z direction; and performing motion analysis using the coordinate-transformed skeletal information.
[0013] A sixth aspect of the present invention provides a motion analysis device comprising: an acquisition unit that acquires three-dimensional skeletal information of a subject in motion in a first coordinate system consisting of mutually orthogonal x', y', and z' directions; an axial direction calculation unit that uses the skeletal information to calculate a Y direction, which is the subject's direction of movement, a Z direction along the subject's torso, and an X direction, which is orthogonal to the Y direction and the Z direction; a coordinate transformation unit that transforms the first coordinate system into a second coordinate system consisting of the X direction, the Y direction, and the Z direction; and an analysis unit that performs motion analysis using the coordinate-transformed skeletal information. Here, each of the above methods is a computer-implemented method. Furthermore, each of the above computer programs may be stored in a non-transitory computer-readable storage medium and executed by a processor.
[0014] According to the present invention, since the motion information is described in an appropriately transformed coordinate system, motions such as walking can be analyzed in detail using motion information collected from a single position.
[0015] 1 is a schematic diagram showing the overall configuration of a system including a motion analysis device 10 according to the present embodiment. FIG. 2 is a block diagram showing the software configuration of the motion analysis device 10. FIG. 3 is a block diagram showing the hardware configuration of a computer 100 that constitutes the motion analysis device 10. FIG. 4 is a flowchart showing the procedure of motion analysis. FIG. 5 is a diagram showing an example of joints and their connection relationships in body tracking. FIG. 6 is a diagram showing an example of a method for defining a coordinate system used for coordinate transformation. FIG. 7 is a diagram showing the position and trajectory of the right ankle joint while walking, measured with Azure Kinect and VICON. FIG. 8 is a diagram showing the positions of the center of the shoulder joint and the center of the hip joint, measured with Azure Kinect and VICON. FIG. 9 is a diagram showing the trajectory of the center of the shoulder joint while walking, measured with Azure Kinect and VICON. FIG. 10 is a diagram showing the trajectory of the center of the hip joint while walking, measured with Azure Kinect and VICON.
[0016] Representative embodiments of the coordinate transformation method, coordinate transformation device, motion analysis method, motion analysis device, and computer program according to the present invention will be described in detail below with reference to the drawings. However, the present invention is not limited to these drawings. Furthermore, since the drawings are intended to conceptually explain the present invention, dimensions, ratios, or numbers may be exaggerated or simplified as necessary to facilitate understanding.
[0017] 1. About the Motion Analysis Device 10 and the Coordinate Transformation Device The motion analysis device 10 is a device or system that performs motion analysis using three-dimensional coordinate data obtained by photographing a subject P. Examples of the subject P include, but are not limited to, patients undergoing rehabilitation or examinations, athletes, etc. In other words, the subject P is in motion, performing some kind of movement, such as walking or running, or jumping or doing exercises such as gymnastics.
[0018] 2 , motion analysis device 10 includes an acquisition unit 11, an axial direction calculation unit 13, a coordinate conversion unit 15, and an analysis unit 17. Of these components, acquisition unit 11, axial direction calculation unit 13, and coordinate conversion unit 15 constitute a coordinate conversion device 20.
[0019] The acquisition unit 11 acquires three-dimensional skeletal information of the subject P during movement. Here, the skeletal information includes three-dimensional coordinate data. The acquisition unit 11 may primitively acquire (i.e., generate) the skeletal information, or may secondarily acquire the skeletal information by transfer or the like.
[0020] In the former case, the acquisition unit 11 can be configured as a body tracking system that acquires image data including depth information using an imaging device such as an IR camera (depth sensor), generates a human skeletal model (skeleton) from the image data (see Figure 5), and can measure the three-dimensional coordinates of joint points.
[0021] Alternatively, in the latter case, the acquisition unit 11 may be a communication interface that receives three-dimensional skeletal information from this type of body tracking system, or a memory that stores the skeletal information.
[0022] An example of a body tracking system is Azure Kinect (trademark) from Microsoft Corporation, but is not limited to this. For example, the body tracking system may be Intel RealSense Depth (trademark) Camera from Intel Corporation, ASTRA (trademark) 3D camera from Orbbec 3D Tech. Intl. Inc., Xtion (trademark) from ASUSTeK Computer Inc., or ZED (trademark) camera from Stereolabs Inc.
[0023] The skeletal information acquired by the acquisition unit 11 is described in a coordinate system (hereinafter sometimes referred to as the original coordinate system or the first coordinate system) fixed to the body tracking system. For example, in Azure Kinect, the origin of the three-dimensional coordinate values is the center of the IR camera (depth sensor), and the coordinate axes are set as follows: the horizontal axis is the x' axis, the vertical axis is the y' axis, and the depth axis is the z' axis when viewed from the front of the IR camera (see Figure 1).
[0024] The acquisition unit 11 acquires skeletal information at a predetermined time interval, which may be the same timing as the generation of image data or skeletal information by the body tracking system, for example, 30 fps.
[0025] Next, the axis direction calculation unit 13 calculates the axis directions of a new coordinate system (hereinafter sometimes referred to as a second coordinate system) using the acquired skeletal information. That is, the axis directions of the new coordinate system are the Y direction which is the direction of travel of the subject P, the Z direction along the torso of the subject P, and the X direction which is perpendicular to the Y direction and the Z direction. The Z direction is preferably the direction from the pelvis toward the chest of the subject P. Note that it is arbitrary which directions are named the X, Y, and Z directions.
[0026] In this embodiment, the Y direction is set as the direction from the position of SPINE_NAVAL before walking starts to the position of SPINE_NAVAL after walking ends. In other words, the Y direction can be obtained by subtracting the coordinate of SPINE_NAVAL before walking starts from the coordinate of SPINE_NAVAL after walking ends.
[0027] The Z' direction is set as the direction from the position of the PELVIS to the position of the SPINE_NAVAL. That is, the Z' direction can be obtained by subtracting the coordinate of the PELVIS from the coordinate of the SPINE_NAVAL at the same time. The Z' direction may be an average of multiple Z' directions calculated over a predetermined period.
[0028] The X direction is then defined to be orthogonal to the Y direction and the Z′ direction, and the Z direction is defined to be orthogonal to the X direction and the Y direction. The calculated vector indicating the X direction, vector indicating the Y direction, and vector indicating the Z direction may be normalized to a unit length.
[0029] Next, the coordinate conversion unit 15 converts the original coordinate system describing the skeletal information into a new coordinate system with coordinate axes in the X, Y, and Z directions. For example, the coordinate conversion unit 15 can perform conversion to the new coordinate system using a matrix corresponding to the original coordinate system and a matrix corresponding to the new coordinate system.
[0030] Let us consider the case where the position p of a point on an original coordinate system whose axes are three unit vectors i', j', and k' that are orthogonal to each other is transformed into a new coordinate system whose axes are three other unit vectors i, j, and k that share the same origin as the original coordinate system. If the coordinates of position p in each coordinate system are (x', y', z') and (x, y, z), then position p can be expressed as follows: This equation can be written using matrices as follows: Therefore, the position p(x, y, z) in the new coordinate system is given by the following equation: Here, since the matrices (i, j, k) and (i', j', k') are orthogonal matrices, their inverse matrices are equal to their transposes. Therefore, a transformation matrix M is obtained that transforms a position representation (x', y', z') in the original coordinate system into a position representation (x, y, z) in the new coordinate system. Therefore, by applying the transformation matrix M to the representation (x', y', z') in the original coordinate system from the left side, it is possible to obtain the representation (x, y, z) in the new coordinate system.
[0031] The analysis unit 17 performs a motion analysis using the coordinate-transformed skeletal information. Examples of motion analysis include walking analysis, running analysis, swimming analysis, jumping analysis, and gymnastics analysis, but other analyses of the above-mentioned motions (progression by walking, running, or swimming, or some movement by exercise such as jumping or gymnastics) are also possible, and analysis of motions such as running and standing long jump is suitable.
[0032] In particular, analysis of movements such as walking, running, swimming, and jumping includes, but is not limited to, walking cycle, walking speed, joint angle, posture, stride length, step width, foot height, arm (elbow) swing range, arm (elbow) height, left-right balance, and front-to-back and left-to-right body sway.
[0033] The results of the motion analysis are displayed on a screen, printed, or sent to another computer for use by doctors, physical therapists, researchers, etc. These people can use the results of the motion analysis to devise treatment methods that are individually suited to the subject P, and utilize them in accordance with the purpose of treatment, rehabilitation, etc.
[0034] 2. Regarding the computer 100 constituting the motion analysis device 10 and the coordinate transformation device 20: As shown in Fig. 3, the computer 100 includes a processor 101, a memory 103, and a communication interface 105, and may further include an input device 107 and an output device 109. The computer 100 may be composed of a single computer or multiple computers.
[0035] The processor 101 reads various programs and data into the memory 103 and executes them to realize various functions of the motion analysis device 10 and the coordinate transformation device 20. The processor 101 may be configured by a semiconductor integrated circuit such as a central processing unit (CPU), a graphics processing unit (GPU), or a microprocessor.
[0036] The memory 103 is a random access memory (RAM) and a read-only memory (ROM) that store various data and programs. The memory 103 includes a non-transitory computer-readable storage medium, such as a hard disk drive, a solid-state drive, or a flash memory.
[0037] The communication interface 105 is an interface for connecting to wired and wireless communication networks, such as an adapter for connecting to Ethernet (registered trademark), a modem for connecting to a public telephone network, a wireless communication device for wireless communication, a USB (Universal Serial Bus) connector or an RS232C connector for serial communication, etc.
[0038] The input device 107 is used to input various data and includes, for example, a keyboard, a mouse, a touch panel, a button, a microphone, etc. The output device 109 is used to output various data and includes, for example, a display, a printer, a speaker, etc.
[0039] 3. Motion Analysis Method and Coordinate Transformation Method The motion analysis method including the coordinate transformation method will be described with reference to Fig. 4. The motion analysis method is a computer-implemented method. Of the steps constituting the motion analysis method, steps S11 to S13 correspond to the coordinate transformation method.
[0040] In step S11, skeletal information of the subject P is acquired. At this time, the skeletal information is described in a coordinate system (X', Y', Z' axes; unit vectors i', j', k') fixed to the body tracking system or camera (see FIG. 1). The skeletal information is acquired at predetermined time intervals.
[0041] Next, in step S12, the X, Y, and Z axis directions (unit vectors i, j, k) of the new coordinate system are calculated from the skeletal information. For example, the Y direction is the direction of travel, the Z direction is the direction along the torso of the subject P, and the X direction is the direction perpendicular to the Y and Z directions.
[0042] Then, in step S13, coordinate transformation of the skeleton information is performed. For example, the above-mentioned transformation matrix M is generated and applied to the original coordinate system representation (x', y', z') from the left side to obtain a new coordinate system representation (x, y, z).
[0043] Furthermore, in step S14, the converted coordinates are used to perform a motion analysis such as a gait analysis, and then the series of processes is completed.
[0044] 4. Effects of the Present Embodiment As can be seen from the present embodiment, the inventors have defined a new coordinate system for motion analysis based on motion data such as walking measured using a motion capture system such as Azure Kinect, and developed an algorithm for performing coordinate transformation.
[0045] In conventional analyses of walking movements using markerless motion capture systems, the above-mentioned problems have been addressed by focusing on parameters such as joint angles and angular velocities that are independent of the coordinate system, or by acquiring information for coordinate transformation in advance (such as markers installed in the laboratory).In this embodiment, information on the coordinate transformation required for motion analysis can be acquired from measurement data, enabling detailed analysis of movements such as walking without using a complex system.
[0046] 5. Analysis Example Here, gait analysis is used as an example of motion analysis, and the results of verifying the accuracy of motion analysis in this embodiment are shown. To evaluate the accuracy of gait analysis, a comparison was made with measurement data obtained using VICON (trademark) manufactured by Vicon Motion Systems Ltd. VICON is a type of motion capture system that uses an infrared camera to track retroreflective markers attached to the body of subject P, and is thought to provide accurate and reliable data.
[0047] In this analysis example, Azure Kinect (trademark) is used as the motion capture system. Azure Kinect is a markerless motion capture system that can automatically fit a human skeletal model (skeleton) from depth images obtained by projecting an infrared dot pattern onto a subject, and measure the coordinates of 20 joint points (see Figure 5).
[0048] In Azure Kinect, the built-in processor estimates the joint locations of the body and reads the three-dimensional coordinate values (x, y, z) of the joint data when constructing skeletal information. The origin of the three-dimensional coordinate values read by the joint data is the center of the IR camera (depth sensor), and the coordinate axes, when viewed from the front of the IR camera, are X on the horizontal axis, Y on the vertical axis, and Z on the depth axis (see Figure 1). The IR camera uses infrared rays to measure the distance (depth) from the camera to an object.
[0049] In Azure Kinect, the origin of the coordinate system is at the focal point of the camera. This coordinate system is set so that the positive X-axis points to the right, the positive Y-axis points down, and the positive Z-axis points forward. Therefore, in Azure Kinect, the positions of the joints are expressed as values relative to the reference frame of the depth sensor. In other words, the skeletal information of subject P is expressed in a coordinate system fixed to Azure Kinect.
[0050] Here, the subject P may move in any desired direction relative to the camera of the motion capture system. In this case, in the above coordinate system, depending on the direction of movement of the subject P, the measurement accuracy for joints hidden from the camera may be degraded.
[0051] The axes of the new coordinate system are set as follows (see Figure 6): Y direction: direction from SPINE_NAVEL at the start of walking to SPINE_NAVEL at the end of walking Z' direction: direction from PELVIS to SPINE_CHEST while walking (average) X direction: direction perpendicular to the Y and Z' axes Z direction: direction perpendicular to the X and Y axes
[0052] 5-1. Measuring ankle joint position while walking The ankle joint positions of subject P were measured using Azure Kinect and VICON while he was walking, and the resulting trajectories were compared. However, the measurement results using Azure Kinect were subjected to the coordinate transformation described above. An example of the measurement results for the right ankle joint is shown in Figures 7(A) and (B). The example shown is the measurement result when subject P walked diagonally forward relative to the camera, and the original coordinate system (x', y', z' axes) is displayed for reference. Table 1 also shows the correlation coefficient between the left and right ankle joint positions while walking, measured using Azure Kinect and VICON. Generally, for the correlation coefficient r, a positive correlation is observed when 0.4≦r≦0.7, and a strong positive correlation is observed when 0.7≦r≦1. Therefore, Table 1 shows that there is a particularly strong correlation in the longitudinal and vertical directions.
[0053] Table 2 also shows the root mean square error of the positions of the left and right ankle joints during walking measured with Azure Kinect and VICON. From Table 2, it can be seen that the errors are particularly small in the left-right and vertical directions.
[0054] In addition, the stride length (average) can be calculated from the trajectory of the ankle joint position. Table 3 below shows an example of the left and right stride lengths during walking measured with Azure Kinect and VICON. Table 3 shows that the difference in the measured values between Azure Kinect and VICON is within a few percent.
[0055] 5-2. Midpoints of left and right hip joints The positions of the midpoints of the left and right shoulder joints and left and right hip joints of subject P were measured using Azure Kinect and VICON (see Figure 8A), and the trajectories were compared (see Figures 8B and 8C). The measurement results using Azure Kinect were subjected to the coordinate transformation described above. Table 4 below shows the root mean square errors of the measured centers of the left and right shoulders and hip joints.
[0056] Table 5 also shows the correlation coefficients of the measured shoulder joint centers and hip joint centers. Table 5 shows that there is a particularly strong correlation in the left-right and front-back directions.
[0057] These comparative examples confirmed that the coordinate-converted measurement data of Azure Kinect has accuracy comparable to that of VICON measurement data. Therefore, it is considered that the coordinate-converted measurement results of Azure Kinect accurately represent the joint positions of subject P.
[0058] Therefore, the coordinate transformation technology presented here can be suitably used for motion analysis, including gait analysis. Therefore, reliable motion analysis does not require the installation of multiple cameras or the placement of markers on the floor, making it possible to easily build a motion capture system by using coordinate transformation technology.
[0059] Although typical embodiments of the present invention have been described above, the present invention is not limited to these, and various design modifications are possible, which are also included in the present invention.
[0060] 10 Motion analysis device 11 Acquisition unit 13 Axis direction calculation unit 15 Coordinate conversion unit 17 Analysis unit 20 Coordinate conversion device
Claims
1. A coordinate transformation method comprising the steps of: acquiring three-dimensional skeletal information of a subject in motion in a first coordinate system consisting of mutually perpendicular x', y', and z' directions; calculating, using said skeletal information, a Y direction which is the subject's direction of movement, a Z direction which follows the subject's torso, and an X direction which is perpendicular to the Y direction and the Z direction; and transforming said first coordinate system into a second coordinate system consisting of the X direction, the Y direction, and the Z direction, thereby acquiring coordinate-transformed skeletal information.
2. The coordinate transformation method according to claim 1, wherein the Z direction is a direction from the pelvis to the chest of the subject.
3. The coordinate transformation method according to claim 1, further comprising transforming the first coordinate system into the second coordinate system using a matrix corresponding to the first coordinate system and a matrix corresponding to the second coordinate system.
4. A computer program for executing the steps of: acquiring three-dimensional skeletal information of a subject in motion in a first coordinate system consisting of mutually perpendicular x', y', and z' directions; calculating, using said skeletal information, a Y direction which is the subject's direction of movement, a Z direction along the subject's torso, and an X direction which is perpendicular to the Y direction and Z direction; and transforming said first coordinate system into a second coordinate system consisting of the X direction, the Y direction, and the Z direction, and acquiring the coordinate-transformed skeletal information.
5. A coordinate conversion device comprising: an acquisition unit that acquires three-dimensional skeletal information of a subject in motion in a first coordinate system consisting of mutually perpendicular x', y', and z' directions; an axial direction calculation unit that uses the skeletal information to calculate a Y direction which is the subject's direction of movement, a Z direction along the subject's torso, and an X direction which is perpendicular to the Y direction and the Z direction; and a coordinate conversion unit that converts the first coordinate system into a second coordinate system consisting of the X direction, the Y direction, and the Z direction.
6. A motion analysis method comprising the steps of: acquiring three-dimensional skeletal information of a subject in motion in a first coordinate system consisting of mutually perpendicular x', y', and z' directions; calculating, using said skeletal information, a Y direction which is the subject's direction of movement, a Z direction along the subject's torso, and an X direction which is perpendicular to the Y direction and Z direction; transforming said first coordinate system into a second coordinate system consisting of the X direction, the Y direction, and the Z direction; and performing motion analysis using the coordinate-transformed skeletal information.
7. A computer program for executing the steps of: acquiring three-dimensional skeletal information of a subject in motion in a first coordinate system consisting of mutually perpendicular x', y', and z' directions; calculating, using said skeletal information, a Y direction which is the subject's direction of movement, a Z direction along the subject's torso, and an X direction which is perpendicular to the Y direction and Z direction; transforming said first coordinate system into a second coordinate system consisting of the X direction, the Y direction, and the Z direction; and performing motion analysis using the coordinate-transformed skeletal information.
8. A motion analysis device comprising: an acquisition unit that acquires three-dimensional skeletal information of a subject in motion in a first coordinate system consisting of mutually perpendicular x', y', and z' directions; an axial direction calculation unit that uses the skeletal information to calculate a Y direction which is the subject's direction of movement, a Z direction along the subject's torso, and an X direction which is perpendicular to the Y direction and the Z direction; a coordinate conversion unit that converts the first coordinate system into a second coordinate system consisting of the X direction, the Y direction, and the Z direction; and an analysis unit that performs motion analysis using the coordinate-converted skeletal information.
