Walking motion visualization device and walking motion visualization method, and aligned state determination device and aligned state determination method

Abstract

Provided is a walking motion visualization device comprising: an acceleration data acquisition unit that acquires stationary-state acceleration data and determination acceleration data from an acceleration sensor disposed on a midline, which is the center line of the body of a subject in the left-right direction, the stationary-state acceleration data being for use in determining the direction of gravity when the subject is in a stationary state, the determination acceleration data being acceleration data collected when the subject is walking for use in determining whether or not the acceleration sensor is aligned with the midline; a determination unit that determines whether or not the acceleration sensor is aligned with the midline on the basis of the acquired stationary-state acceleration data and determination acceleration data; a walking-state acceleration data acquisition unit that acquires, from the acceleration sensor, walking-state acceleration data collected while the subject is walking if the acceleration sensor is determined to be aligned with the midline as a result of the determination by the determination unit; a walking motion analysis unit that analyzes walking motion of the subject on the basis of the acquired walking-state acceleration data; and a display control unit that displays a walking motion model image for the subject on the basis of the result of the analysis by the walking motion analysis unit.

Description

Walking motion visualization device, walking motion visualization method, facing state determination device, facing state determination method

[0001] The present invention relates to a walking motion visualization device and a walking motion visualization method, and a facing state determination device and a facing state determination method.

[0002] In the above technical field, Patent Document 1 discloses a technology for quantitatively calculating a physical quantity corresponding to the position of the waist of a person being measured while walking, using an acceleration sensor attached on the midline of the waist of the person being measured (Claim 1, etc.).

[0003] US2016 / 038059A1

[0004] In order to solve the above problems, the walking motion visualization device of the present invention comprises: an acceleration data acquisition unit that acquires, from an acceleration sensor placed on the midline, which is the center line between the left and right sides of the body of the subject, stationary state acceleration data for determining the direction of gravity when the subject is stationary, and determination acceleration data, which is acceleration data when the subject is walking, in order to determine whether the acceleration sensor is facing the midline; a determination unit that determines whether the acceleration sensor is facing the midline based on the acquired stationary state acceleration data and the determination acceleration data; a walking acceleration data acquisition unit that acquires walking acceleration data from the acceleration sensor while the subject is walking, when the determination unit determines that the acceleration sensor is facing the midline; a walking motion analysis unit that analyzes the walking motion of the subject based on the acquired walking acceleration data; and a display control unit that displays a walking motion model image of the subject based on the analysis result by the walking motion analysis unit.

[0005] Furthermore, in order to solve the above-mentioned problems, the walking motion visualization method of the present invention includes: an acceleration data acquisition step of acquiring, from an acceleration sensor placed on a midline, which is the center line between the left and right sides of the body of the subject, stationary state acceleration data for determining the direction of gravity when the subject is stationary, and determination acceleration data, which is acceleration data when the subject is walking, in order to determine whether the acceleration sensor is facing the midline; a determination step of determining whether the acceleration sensor is facing the midline based on the acquired stationary state acceleration data and the determination acceleration data; a walking acceleration data acquisition step of acquiring walking acceleration data from the acceleration sensor while the subject is walking, if it is determined in the determination step that the acceleration sensor is facing the midline; a walking motion analysis step of analyzing the walking motion of the subject based on the acquired walking acceleration data; and a display control step of displaying a walking motion model image of the subject based on the analysis result in the walking motion analysis step.

[0006] In order to solve the above problems, the facing state determination device of the present invention includes an acceleration data acquisition unit that acquires, from an acceleration sensor placed on a midline that is the center line between the left and right sides of the subject's body, stationary state acceleration data for determining the direction of gravity when the subject is stationary, and determination acceleration data that is acceleration data when the subject is walking, in order to determine whether the acceleration sensor is facing the midline; and a determination unit that determines whether the acceleration sensor is facing the midline based on the acquired stationary state acceleration data and determination acceleration data.

[0007] In order to solve the above problem, the method for determining a facing state according to the present invention includes: an acceleration data acquisition step of acquiring, from an acceleration sensor placed on a midline, which is the center line between the left and right sides of the body of the subject, stationary state acceleration data for determining the direction of gravity when the subject is stationary, and determination acceleration data, which is acceleration data when the subject is walking, in order to determine whether the acceleration sensor is facing the midline; and a determination step of determining whether the acceleration sensor is facing the midline based on the acquired stationary state acceleration data and determination acceleration data.

[0008] FIG. 1 is a diagram for explaining an overview of analysis of a walking motion by the walking motion visualization device according to the first embodiment of the present invention. FIG. 2 is a diagram showing an example (horizontal bar graph) of analysis results of a walking motion by the walking motion visualization device according to the first embodiment of the present invention. FIG. 3 is a diagram showing an example (pie chart) of analysis results of a walking motion by the walking motion visualization device according to the first embodiment of the present invention. FIG. 4 is a diagram showing an example (pendulum graph) of analysis results of a walking motion by the walking motion visualization device according to the first embodiment of the present invention. FIG. 5 is a diagram showing an example (balance graph) of analysis results of a walking motion by the walking motion visualization device according to the first embodiment of the present invention. FIG. 6 is a diagram showing an example (radar chart) of analysis results of a walking motion by the walking motion visualization device according to the first embodiment of the present invention. FIG. 7 is a diagram showing an example when analysis results of a walking motion by the walking motion visualization device according to the first embodiment of the present invention are displayed using a skeletal model image. FIG. 8 is a diagram showing another example when analysis results of a walking motion by the walking motion visualization device according to the first embodiment of the present invention are displayed using a skeletal model image. FIG. 9 is a block diagram for explaining the configuration of the walking motion visualization device according to the first embodiment of the present invention. FIG. 10 is a diagram for explaining an example of a joint angle table included in the walking motion visualization device according to the first embodiment of the present invention. FIG. 1 is a diagram for explaining the hardware configuration of a walking motion visualization device according to a first embodiment of the present invention. FIG. 2 is a flowchart for explaining a processing procedure of the walking motion visualization device according to the first embodiment of the present invention. FIG. 3 is a flowchart for explaining a facing state determination process of the walking motion visualization device according to the first embodiment of the present invention. FIG. 4 is a block diagram for explaining the configuration of a walking motion visualization device according to a second embodiment of the present invention. Detailed Description of the Invention

[0009] In the technology described in Patent Document 1, a predetermined physical quantity is calculated from the measurement value of the acceleration sensor while the acceleration sensor is attached to the midline of the waist of the person being measured, but it is not determined whether the acceleration sensor is in a state where it can output a correct measurement value. Therefore, the evaluation of the walking posture of the person being measured based on the physical quantity calculated using the measurement value output from the acceleration sensor is unreliable.

[0010] Hereinafter, embodiments of the present invention will be described by way of example with reference to the drawings. However, the configurations, numerical values, processing flows, functional elements, etc. described in the following embodiments are merely examples, and are open to modification and alteration. The technical scope of the present invention is not limited to the following description.

[0011] 1A to 5C , a walking motion visualization device 100 according to a first embodiment of the present invention will be described. The walking motion visualization device 100 is a device for visualizing the walking motion, walking speed, and the like of a subject 110 using animation images or the like, using acceleration data obtained from an acceleration sensor built into a mobile terminal or the like. Note that in the following description, the walking motion visualization device 100 will be described using a mobile terminal such as a smartphone 120 as an example, but some or all of the functions of the walking motion visualization device 100 may be realized by a general-purpose computer device such as a server.

[0012] Walking behavior, such as walking speed, not only reflects general health and functional ability, but also serves as a predictor of various conditions, such as frailty and decline in ADL (Activities of Daily Living). For this reason, walking behavior (e.g., walking speed) is also called the sixth vital sign, along with blood pressure and body temperature. For example, in order to maintain walking speed and continue walking on one's own two feet, it is important to walk comfortably and correctly.

[0013] For example, in order to walk with large strides, it is important not only to move the muscles of the entire body, but also to move major joints such as the hip, knee, and ankle joints normally. In other words, understanding how to walk (walking movements) can help identify muscles, joints, etc. that are not being used properly or that are being used excessively, which can lead not only to training and exercise guidance but also to injury prevention.

[0014] Here, methods for measuring gait (walking movements) include, for example, motion analysis systems that show the walking posture of the entire body, depth sensor cameras (Kinect), wearable suits, and methods that involve attaching multiple sensors to the body (motion capture, etc.). These methods are characterized by their ability to measure even the joint angles of the body, but they require special measuring equipment and are therefore limited in the situations in which they can be used, making them methods for measuring gait in unusual situations.

[0015] In order to measure walking movements and walking postures in daily life, it is necessary to classify bodily movements and postures, such as left-right balance and forward leaning of the body, using an acceleration sensor attached to the waist or the like of the subject 110. However, whether the acceleration sensor is attached to the waist or the like correctly is left to the subject's judgment. Therefore, in order to accurately measure the walking movements and postures of the subject 110, it is first necessary to attach the acceleration sensor to the subject's body in a position suitable for measuring walking movements and walking postures.

[0016] Furthermore, the output results from the above-mentioned measurement methods mostly show the degree of swaying of the body from side to side, the degree of forward or backward leaning, etc., or show walking movements using predetermined patterns similar to some walking models, etc. Therefore, they are not measurement methods that can identify the cause of the current walking movements, etc.

[0017] Therefore, the walking motion visualization device 100 of this embodiment first determines whether the acceleration sensor is attached on the midline, which is the center between the left and right sides of the body of the subject 110. Then, the walking motion visualization device 100 measures acceleration data while the subject 110 is walking with the acceleration sensor attached on the midline. Next, the walking motion visualization device 100 selects acceleration data that is similar to the measured acceleration data from a predetermined database, estimates the joint angles of the subject 110 while walking, and visualizes the walking motion of the subject 110. Furthermore, when the acceleration sensor is located on the midline, the walking motion visualization device 100 can notify the subject 110 of a walking start instruction to prompt the subject 110 to start measurement.

[0018] 1A , in this embodiment, an acceleration sensor built into the smartphone 120, the smart watch 130, or the like, or an acceleration sensor included in the activity meter 140 can be used. The activity meter 140 can be built into a belt or the like and used. The acceleration sensor does not have to be built into the smartphone 120 or the smart watch 130, but may be an independent sensor. In this case, the acceleration sensor and the smartphone 120 or the like exchange measurement data via wireless communication or wired communication.

[0019] When measuring walking movements using the walking movement visualization device 100, the walking movement visualization device 100 first instructs the subject 110 by voice, image, or the like to hold the smartphone 120 or the like on the midline of their body. When data from the acceleration sensor maintains a constant value for approximately two or three seconds, the walking movement visualization device 100 determines that the subject 110 is holding the smartphone 120 or the like on the midline, and in that state, the walking movement visualization device 100 acquires acceleration data and determines the direction of gravity. When holding the smartphone 120, the subject 110 may touch the smartphone 120 to their abdomen. Furthermore, if the subject 110 uses a smartwatch 130, they may bring either their left or right wrist, on which they are wearing the smartwatch 130, to their abdomen. Furthermore, if the subject 110 uses an activity meter 140, they may wrap a belt to which the activity meter 140 is attached, around their abdomen. Note that any method other than the method shown here may be employed as long as the subject 110 can hold or position the acceleration sensor so that it faces the subject on the median line.

[0020] When the smartphone 120 or the like is facing the subject 110, the walking motion visualization device 100 instructs the subject 110 to start walking, for example, by vibration or voice, acquires acceleration data while the subject 110 is walking, and uses the acceleration data while walking to analyze the walking motion of the subject 110. When the analysis of the walking motion of the subject 110 is completed, the walking motion visualization device 100 displays the walking motion of the subject 110 as a walking motion model image 150 on, for example, the display of the smartphone 120. Note that, when it is detected that a sufficient amount of acceleration data necessary for analysis has been obtained, the walking motion visualization device 100 may be configured to instruct the subject 110 by voice to stop walking.

[0021] The subject 110 can recognize his / her current walking motion by looking at the walking motion model image 150. In addition, the walking motion visualization device 100 can display to the subject 110, together with the walking motion model image 150, defects in the walking motion of the subject 110, areas to be improved, improvement methods, advice, and the like.

[0022] Then, by practicing walking movements in accordance with the displayed improvement methods, etc., the subject 110 can naturally acquire walking movements that are suitable for the subject 110. The walking movement model image 150 and the improvement methods and advice displayed therewith can be displayed in various ways, for example, as shown in Figures 1B to 1I.

[0023] For example, as shown in Figure 1B, a horizontal bar graph can be used to display the state (angle) of the pelvic angle, hip joint angle, ankle joint angle, etc. Furthermore, the horizontal bar graph can also display the standard values ​​for these.

[0024] For example, the walking motion visualization device 100 can display the state (angle) of the posture of the subject 110 between forward tilt and backward tilt with respect to the pelvic angle. Note that the walking motion visualization device 100 can also display, together with the pelvic angle of the subject 110, an optimal angle range that indicates the range of values ​​within which the pelvic angle of the subject 110 should fall.

[0025] Similarly, the walking motion visualization device 100 can display the state (angle) of the posture of the subject 110 with respect to the hip joint angle. With respect to the hip joint angle, the walking motion visualization device 100 can display the degree to which the left and right hip joint angles are swung forward or backward. The walking motion visualization device 100 can also display an optimal angle range, which indicates the range within which the hip joint angles of the subject 110 should fall, with respect to the left and right hip joint angles.

[0026] Furthermore, the walking motion visualization device 100 can also display the state (angle) of the posture of the subject 110 with respect to the knee joint angle. With respect to the knee joint angle, the walking motion visualization device 100 can display, for the left and right knee joint angles, the degree to which the knees are extended at the time of swinging out, and whether the knees are extended at the time of pushing off. Furthermore, the walking motion visualization device 100 can also display, for the left and right knee joint angles, an optimal angle range that indicates the range within which the knee joint angles of the subject 110 should fall.

[0027] Furthermore, the walking motion visualization device 100 can display the posture (angle) of the subject 110 with respect to the ankle joint angles. With respect to the ankle joint angles, the walking motion visualization device 100 displays the bending of the ankles when the left and right ankle joint angles are extended forward and whether the ankles are extended when the subject 110 pushes off. The walking motion visualization device 100 can also display the optimal angle ranges for the left and right ankle joint angles, which indicate the range within which the ankle joint angles of the subject 110 should fall.

[0028] 1C, the walking movement visualization device 100 can use a pie chart to display the state (angle) of the pelvic angle, hip joint angle, knee joint angle, ankle joint angle, etc. Furthermore, the pie chart can also display standard values ​​for these.

[0029] For example, the walking movement visualization device 100 can display the degree to which the pelvis angle is tilted forward or backward using a single pie chart. The pie chart display allows the subject 110 to visually recognize the state of his or her own pelvic angle at a glance. As will be described below, the subject 110 can also visually recognize the state of other joints.

[0030] Similarly, the walking motion visualization device 100 can display the state (angle) of the posture of the subject 110 with respect to the hip joint angle using two circular flags. With respect to the hip joint angle, the walking motion visualization device 100 can display, using two circular flags, how far the left and right hip joint angles are swung forward or backward. The walking motion visualization device 100 can also display, in the same circular graph, an optimal angle range that indicates the range within which the hip joint angles of the subject 110 should fall.

[0031] Furthermore, the walking motion visualization device 100 can display, using two pie charts, the posture (angle) of the subject 110 with respect to the knee joint angle. Regarding the knee joint angle, the walking motion visualization device 100 displays, for the left and right knee joint angles, the degree to which the knees are extended at the time of swinging out, and the degree to which the knees are extended at the time of pushing off. The walking motion visualization device 100 can also display, for the left and right knee joint angles, optimal angle ranges that indicate the range within which the knee joint angles of the subject 110 should fall.

[0032] Furthermore, the walking motion visualization device 100 can display, using two pie charts, the posture (angle) of the subject 110 with respect to the ankle joint angles. Regarding the ankle joint angles, the walking motion visualization device 100 displays, for the left and right ankle joint angles, the degree to which the ankles are bent when extended forward and whether the ankles are extended when pushing off. Furthermore, the walking motion visualization device 100 can also display, for the left and right ankle joint angles, optimal angle ranges that indicate the range within which the ankle joint angles of the subject 110 should fall.

[0033] Next, as shown in FIG. 1D , the walking motion visualization device 100 can use pendulum graphs to display the state (angle) of the pelvic angle, hip joint angle, knee joint angle, ankle joint angle, etc., and can also display their standard values ​​and left-right differences. For example, the walking motion visualization device 100 can use a single pendulum graph to display the degree to which the pelvic angle is tilted forward or backward. The pendulum graph display allows the subject 110 to visually recognize the state of his or her own pelvic angle at a glance. Note that, as will be described below, the subject 110 can also visually recognize the state of other joints.

[0034] Similarly, the walking motion visualization device 100 uses two pendulum graphs to display the posture (angle) of the subject 110 with respect to the hip joint angle, such as how far the subject is swinging forward or kicking back. The walking motion visualization device 100 can also display, within the same pendulum graph, an optimal angle range that indicates the range within which the hip joint angles of the subject 110 should fall. Furthermore, if there is a difference between the left and right hip joint angles, the walking motion visualization device 100 can also display this.

[0035] Furthermore, the walking motion visualization device 100 can display the posture (angle) of the subject 110 with respect to the knee joint angle using two pendulum graphs. With respect to the knee joint angle, the walking motion visualization device 100 can display, for the left and right knee joint angles, the degree to which the knees are extended at the time of swinging, and whether the knees are extended at the time of pushing off. The walking motion visualization device 100 can also display, for the left and right knee joint angles, an optimal angle range that indicates the range within which the knee joint angles of the subject 110 should fall.

[0036] Furthermore, the walking motion visualization device 100 can display the posture (angle) of the subject 110 with respect to the ankle joint angles using two pendulum graphs. Regarding the ankle joint angles, the walking motion visualization device 100 displays the bending of the ankles when the left and right ankle joint angles are extended forward and whether the ankles are extended when pushing off. Furthermore, the walking motion visualization device 100 can also display the optimal angle ranges, which indicate the range within which the ankle joint angles of the subject 110 should fall, for the left and right ankle joint angles.

[0037] 1E, the walking motion visualization device 100 can use a balance graph to display the states (angles) of the pelvic angle, hip joint angle, knee joint angle, ankle joint angle, etc. When using a balance graph, the walking motion visualization device 100 can emphasize and display the difference between the left and right sides of the subject 110, the left and right balance, etc.

[0038] For example, the walking movement visualization device 100 can use a balance graph to display the pelvic angle, showing the degree to which the pelvis is tilted forward or backward, as a front-to-back balance. The balance graph display allows the subject 110 to visually recognize the state of his or her pelvic angle at a glance. As will be described below, the subject 110 can also visually recognize the state of other joints.

[0039] Similarly, the walking motion visualization device 100 displays the state (angle) of the posture of the subject 110 with respect to the hip joint angle using a single balance graph, indicating how far the hand is swung forward, how far the hand is kicked back, etc. For example, if there is no difference between the left and right knee joint angles of the subject 110 while walking, the walking motion visualization device 100 can display the state of the subject 110 in various ways, such as by displaying a diagram of a balanced balance and the message "Good!"

[0040] Furthermore, the walking motion visualization device 100 can display the posture (angle) of the subject 110 with respect to the knee joint angle using a single balance graph. Regarding the knee joint angle, the walking motion visualization device 100 displays, for the left and right knee joint angles, the degree of knee extension at the start of the swing, the degree of knee extension at the push-off, and the like. Then, for the knee joint angle, for example, as a result of comparing the degree of knee extension at the start of the swing with the degree of knee extension at the push-off, if the degree of knee extension at the start of the swing is greater, the walking motion visualization device 100 displays an illustration of the balance graph in which the scale plate on the side of the knee extension at the start of the swing is lowered. This type of display allows the subject 110 to easily and reliably recognize that the strain on the knee extension at the start of the swing is heavy.

[0041] Furthermore, the walking motion visualization device 100 can display the posture (angle) of the subject 110 with respect to the ankle joint angle using a single balance graph. Regarding the ankle joint angles, the walking motion visualization device 100 displays the bending of the ankle when the left and right ankle joint angles are extended forward and whether the ankle is extended during push-off. For example, if there is no difference between the front and rear ankle joint angles of the subject 110 during walking, the walking motion visualization device 100 displays a diagram of a balanced balance. Furthermore, if the ankle is extended more at push-off than the bending of the ankle when extended forward, the walking motion visualization device 100 displays a diagram in which the scale on the side where the ankle is extended during push-off is lowered. This allows the subject 110 to easily and reliably recognize that the push-off is strong during push-off.

[0042] Next, as shown in FIG. 1F , the walking motion visualization device 100 can display the states (angles) of the pelvic angle, hip joint angle, knee joint angle, ankle joint angle, etc., using a radar chart. When displaying using a radar chart, the walking motion visualization device 100 displays, for example, the angles of the joints on the right side of the body of the subject 110 on the right side of the radar chart, and the angles of the joints on the left side of the body of the subject 110 on the left side of the radar chart. By displaying in this manner, the subject 110 can recognize the difference between his or her left and right sides and the left and right balance at a glance.

[0043] The walking motion visualization device 100 can display, for example, the degree to which the pelvic angle is tilted forward or backward on a radar chart. The walking motion visualization device 100 also displays the optimum angle range, which indicates the range within which the posture of the subject 110 should fall.

[0044] Similarly, the walking motion visualization device 100 can display the state (angle) of the posture of the subject 110 with respect to the hip joint angle. With respect to the hip joint angle, the walking motion visualization device 100 can display the degree to which the left and right hip joint angles are swung forward or backward. Furthermore, the walking motion visualization device 100 can also display an optimal angle range, which indicates the range within which the hip joint angles of the subject 110 should fall, with respect to the left and right hip joint angles.

[0045] Furthermore, the walking motion visualization device 100 can display the posture (angle) of the subject 110 with respect to the knee joint angle. Regarding the knee joint angle, the walking motion visualization device 100 can display, for the left and right knee joint angles, the degree to which the knees are extended during a swing and whether the knees are extended during a push-off. The walking motion visualization device 100 displays the state of the knee joint angle using a radar chart, allowing the subject 110 to recognize the difference between the left and right knee joint angles and the balance at a glance. Joint angles include left and right rotation and abduction / abduction in addition to forward and backward flexion and extension. Furthermore, by acquiring data on the neck joint, shoulder joint, elbow joint, and wrist joint using measurement data other than midline acceleration data, for example, data from an acceleration sensor attached to the subject's body, such as data from an acceleration sensor built into earphones or headphones or data from an acceleration sensor in a wristwatch-type biometric device attached to the wrist, the movement states of the joints can be similarly displayed.

[0046] Furthermore, the walking motion visualization device 100 can display the posture (angle) of the subject 110 with respect to the ankle joint angles. Regarding the ankle joint angles, the walking motion visualization device 100 displays the bending of the ankles when the left and right ankle joint angles are extended forward and whether the ankles are extended when the subject 110 pushes off. Furthermore, the walking motion visualization device 100 can also display the optimal angle ranges for the left and right ankle joint angles, indicating the range within which the ankle joint angles of the subject 110 should fall. In this way, the walking motion visualization device 100 uses a radar chart to display the state of each joint. This allows the subject 110 to visually recognize shortcomings and areas for improvement in their own walking motion, thereby motivating them to improve their own walking motion.

[0047] Next, a method for displaying the analysis results of the walking movement of the subject 110 will be described with reference to FIGS. 1G to 1I. For example, as shown in FIG. 1G, the walking movement visualization device 100 displays circles 113 on a skeletal model image 111 of the lower body of the subject 110 at the positions of joints that the subject 110 should consciously move in order to improve his walking movement. The walking movement visualization device 100 can also display advice such as "places to move more widely." Furthermore, for example, when the ankle joints of the right foot are less used than those of the left foot, the walking movement visualization device 100 can also display advice such as "you are using less of your left foot, so you need to push out more."

[0048] 1H , for example, the walking motion visualization device 100 displays arrows 114 and straight lines 115 on a skeletal model image of the lower body of the subject 110. That is, the walking motion visualization device 100 uses the arrows 114 to indicate the direction in which joints, muscles, etc. should be moved, and displays, for example, straight lines 115 next to the thighs to indicate muscles under stress (areas that need to be trained). In this way, the walking motion visualization device 100 also displays advice that is useful for improving walking motion, allowing the subject 110 to improve their walking motion by following the displayed advice.

[0049] 1I, the walking motion visualization device 100 may display a skeletal model image 111 of the subject 110 and a skeletal model image 112 to which the subject 110 should aim, side by side, and may further display areas to which the subject 110 should be aware with a circle 116 or the like (left diagram in FIG. 1I). By displaying these images side by side, the subject 110 can compare his or her own walking motion with the walking motion to which the subject should aim, and therefore can work on improving his or her walking while more clearly being aware of areas to be improved.

[0050] Furthermore, the walking motion visualization device 100 may display a skeletal model image 111 of the subject 110 and a skeletal model image 112 to which the subject 110 should aim, side by side, and may further display a location or the like to which the subject 110 should be aware with an arrow 117 or the like (center diagram in FIG. 1I). In this way, an arrow may be displayed to indicate the direction and magnitude of the movement, so that the position where the movement of the joints of the subject 110 is lacking can be moved more significantly.

[0051] Furthermore, the walking motion visualization device 100 displays, on the skeletal model image 111 of the subject 110, positions where there is a possibility of future risk of injury or disability if the subject 110 continues walking as is, using circles 116 and arrows 117. The walking motion visualization device 100 may also display, for example, a radar chart 118 below the skeletal model image of the subject 110 to display the probability of risk occurrence (right diagram in FIG. 1I). The radar chart 118 displays in large letters the probability of D position of joints at risk of disability, etc. In this way, by displaying the possibility of injury, etc., if the subject 110 continues walking as is, it is possible to motivate the subject 110 to improve his or her walking.

[0052] The risk is estimated by estimating at least two of the stride length, walking speed, and left-right difference from the joint angles, and using two, preferably three, of these parameters.

[0053] Furthermore, the walking motion visualization device 100 can move and display the skeletal model images 111 and 112 shown in Figures 1G to 1I, etc., like animated images. By moving and displaying the skeletal model image 111 of the subject 110 in this manner, the subject 110 can easily recognize the current state of his or her own walking motion (walking posture). Furthermore, the walking motion visualization device 100 can also move and display the skeletal model image 111 of the subject 110, and can also display the above-mentioned advice and the like in parallel. By displaying hints and advice for improving the walking motion to the subject 110 in this manner, the subject 110 can easily recognize which joints and parts he or she should pay attention to. If the walking motion visualization device 100 further displays advice and the like regarding how to move the joints, the subject 110 can more easily improve his or her own walking motion.

[0054] Next, the configuration of the walking motion visualization device 100 will be described with reference to Fig. 2. The walking motion visualization device 100 has an acceleration data acquisition unit 201, a determination unit 202, a walking acceleration data acquisition unit 203, a walking motion analysis unit 204, a display control unit 205, and a notification unit 206. The walking motion analysis unit 204 further has an approximate acceleration data selection unit 241 and an extraction unit 242.

[0055] The acceleration data acquiring unit 201 acquires stationary state acceleration data for determining the direction of gravity when the subject 110 is stationary from an acceleration sensor placed on the median line, which is the center line between the left and right sides of the body of the subject 110. Similarly, the acceleration data acquiring unit 201 acquires determination acceleration data, which is acceleration data when the subject 110 is walking, from the acceleration sensor to determine whether the acceleration sensor is facing directly toward the median line.

[0056] First, the subject 110 follows the instructions displayed on the screen of the smartphone 120 and holds the smartphone 120 with an acceleration sensor in both hands, positions it in front of the abdomen of the subject, and maintains a stationary state without moving the smartphone 120. In this state, if it is detected that there is no change in acceleration for a predetermined time, for example, two seconds, the acceleration data acquisition unit 201 acquires stationary state acceleration data.

[0057] Next, with the subject 110 placing the smartphone 120 in front of his or her abdomen, the walking motion visualization device 100 prompts the subject 110 to take a few steps. The walking motion visualization device 100 prompts the subject 110 to take a few steps, for example, by outputting a sound from a speaker of the smartphone 120 to prompt the subject 110 to take action, or by vibrating the smartphone using a vibration function. Then, the acceleration data acquisition unit 201 acquires acceleration data while the subject 110 is taking a few steps as determination acceleration data for determining whether the acceleration sensor is facing directly toward the midline.

[0058] The determination unit 202 determines whether the acceleration sensor is facing the median line based on the acquired stationary state acceleration data and determination acceleration data. Specifically, the determination unit 202 determines whether the acceleration sensor is facing the median line based on a comparison between the left-right axis component, the front-back axis component, and the vertical axis component of the stationary state acceleration data and the left-right axis component, the front-back axis component, and the vertical axis component of the determination acceleration data.

[0059] The determination unit 202 first determines the direction of gravity using the left-right axis component, the front-back axis component, and the vertical axis component of the stationary state acceleration data, i.e., the waveform data of the stationary state acceleration in each axial direction. Next, the determination unit 202 determines the facing state by comparing the left-right axis component, the front-back axis component, and the vertical axis component of the determination acceleration data, i.e., the waveform data of the determination acceleration in each axial direction, with the determined direction of gravity, etc.

[0060] More specifically, the determination unit 202 first determines the direction of gravity using the left-right axis component, front-back axis component, and vertical axis component of the stationary state acceleration data, i.e., the stationary state acceleration data for each axis. Next, the determination unit 202 determines the direction of travel using the determination acceleration data. Based on the direction of travel and the vertical direction, the acceleration sensor calculates the rotation axis angles of the three axes (up / down, left / right, front / back) by combining the gravity vector and the vertical vector in a predetermined rotation order. The forward facing state is determined based on the magnitude of this rotation angle.

[0061] For example, HR (Harmonic Ratio) can be used as a method for determining the facing state from each axial component of acceleration (waveform data in each axial direction) obtained from the acceleration sensor. HR is obtained by decomposing the acceleration data (acceleration signal) of the left-right axis component, the front-back axis component, and the vertical axis component and calculating harmonics using a discrete Fourier transform. HR is obtained by calculating the ratio of even frequency components to odd frequency components using a discrete Fourier transform. For example, if any of the axial components has an HR value of 0.9 or less, it is determined that the axial component is far from the facing state, and the subject 110 can be prompted to correct the position of the axial component. Then, if the HR value of each axial component is 0.9 or greater, the determination unit 202 determines that the acceleration sensor (smartphone 120) is facing the midline of the subject 110's body. It is preferable to prompt the subject 110 to correct the position, and if the value does not exceed 0.9, to instruct the subject to maintain the position if the value after the correction is large, or to return to the original position, i.e., the position before the correction, before performing subsequent measurements.

[0062] Furthermore, instead of using the HR value, the determination unit 202 may estimate the central waveform from the waveform of acceleration data obtained from an acceleration sensor using an algorithm or the like. For example, an estimation formula for estimating the central waveform may be created by performing principal component analysis on the R / L waveform. Alternatively, the determination unit 202 may use machine learning such as SVM (Support-vector Machine) to determine whether or not the vehicle is in a facing state using AI (Artificial Intelligence). Note that the method for determining the facing state is not limited to the method described here, and various methods can be used.

[0063] When using a device that has a gyroscope, such as the smartphone 120, the determination unit 202 may determine the facing state by adding gyroscope data to the acceleration sensor data.

[0064] When the determination unit 202 determines that the acceleration sensor is facing the median line as a result of the determination, the walking acceleration data acquisition unit 203 acquires walking acceleration data from the acceleration sensor while the subject 110 is walking. When the determination unit 202 determines that the acceleration sensor is facing the median line, the walking motion visualization device 100 may, for example, output a sound or the like from a speaker of the smartphone 120 to urge the subject 110 to start walking. Note that instead of outputting a sound, a message urging the subject 110 to start walking may be output on a display or the like, or the smartphone 120 may vibrate using a vibration function. The subject 110 starts walking in response to the output from the speaker or vibration, and the walking acceleration data acquisition unit 203 acquires acceleration data measured by the acceleration sensor thereafter as walking acceleration data while the subject 110 is walking.

[0065] The walking movement analysis unit 204 analyzes the walking movement of the subject 110 based on the acquired walking acceleration data. The walking movement analysis unit 204 analyzes the walking movement of the subject 110 by selecting acceleration data that approximates the acquired walking acceleration data from a predetermined database. Here, the walking movement analysis unit 204 further includes an approximate acceleration data selection unit 241 and an extraction unit 242.

[0066] First, the approximate acceleration data selection unit 241 compares the left-right axis component, the front-back axis component, and the vertical axis component of the acceleration data acquired by the walking acceleration data acquisition unit 203 with the left-right axis component, the front-back axis component, and the vertical axis component of acceleration stored in a predetermined database. Then, the approximate acceleration data selection unit 241 identifies acceleration data that approximates the acquired walking acceleration data. That is, the approximate acceleration data selection unit 241 matches the waveform (waveform features) of the acquired walking acceleration data with the waveform (waveform features) of the acceleration data stored in the predetermined database, thereby identifying and selecting a waveform of acceleration data that approximates (is similar to) the waveform of the walking acceleration data. Note that the approximate acceleration data selection unit 241 may also identify and select a waveform of acceleration data that matches the waveform of the walking acceleration data.

[0067] The matching by the approximate acceleration data selection unit 241 can be performed using, for example, the Euclidean distance or the cosine distance between the waveform data. Furthermore, the matching by the approximate acceleration data selection unit 241 may be performed by, for example, calculating using DTW (Dynamic Time Warping) as a distance measure in the machine learning library tslearn. That is, the matching can be performed by pattern matching of time series data in tslearn (the closer to 0, the more similar it is determined to be).

[0068] Furthermore, the matching by the approximate acceleration data selection unit 241 may be performed by arranging acceleration waveform data and examining the correlation between them (the closer to 1 the value is, the more similar it is determined to be). In addition to this, for example, the approximate acceleration data selection unit 241 may perform matching using the joint angles of the subject 110 (AIST Gait Database 2019), or may perform matching using AI with machine learning such as SVM.

[0069] Next, the extraction unit 242 extracts joint angle data, which is the joint angle associated with the selected approximate acceleration data, from a predetermined database. Here, the predetermined database stores the relationship between the value of each component of the acceleration data and the joint angle. Then, the extraction unit 242 extracts the joint angle data associated with the acceleration value (waveform data, etc.) of each axial component stored in the predetermined database, etc., as an estimated value of the joint angle of the subject 110. Note that the predetermined database, etc., may also include joint angle information of the upper body. In this case, unlike the above, the joint angle of the upper body is estimated only from data from the acceleration sensor on the midline.

[0070] The display control unit 205 displays a walking movement model image 150 of the subject 110 based on the analysis result by the walking movement analysis unit 204. The display control unit 205 displays the walking movement model image 150 on, for example, a display of the smartphone 120 or a display external to the walking movement visualization device 100. The displayed walking movement model image 150 may be a still image or a moving image such as an animation.

[0071] Furthermore, the display control unit 205 displays a skeletal model image of the lower body of the subject 110 as the walking motion model image 150. Note that in addition to the skeletal model image of the lower body of the subject 110, the display control unit 205 may also display, for example, a model image of the lower body of the subject 110 (an image showing not only the skeleton but also muscles, skin, etc.). Note that it goes without saying that the upper body can also be displayed if data from an acceleration sensor or joint angle information of the upper body estimated using a database can be used.

[0072] Furthermore, the display control unit 205 displays guidance information for guiding the subject 110 to a walking motion suitable for the subject 110, along with the walking motion model image 150 (a skeletal model image of the lower body). For example, the display control unit 205 can also display, along with the skeletal model image, the subject 110's degree of forward and backward lean, left and right balance, advice for improving walking motion, and the like. The display control unit 205 may also display information for guiding how to move the joints, etc., by displaying circles 113, 116 indicating the positions of joints to be moved, and arrows 114, 117 (arrow direction and line thickness) indicating the direction and amount of joint movement, etc. In addition, the display control unit 205 may display, along with the walking motion model image 150, numbers indicating the order in which joints, muscles, etc. should be moved so that the subject 110 can achieve a walking motion suitable for the subject 110.

[0073] The notification unit 206 notifies the user to start walking when the acceleration sensor is positioned directly facing the midline and measurement is possible as a result of the determination by the determination unit 202. The instruction to start walking notified by the notification unit 206 is, for example, vibration, sound, light, etc., but is not limited to these.

[0074] In addition to vibrating the smartphone 120, the notification unit 206 may output an approaching sound from, for example, a speaker of the smartphone 120 or a wireless earphone using electromagnetic waves or optical communication.

[0075] In addition, among the components of the walking motion visualization device 100, the acceleration data acquisition unit 201 and the judgment unit 202 can be removed to form a facing state judgment device for determining whether the acceleration sensor is facing directly toward the midline of the subject 110.

[0076] Next, an example of a joint angle table 301 included in the walking motion visualization device 100 will be described with reference to FIG. 3 . The joint angle table 301 stores time 312, acceleration data 313, and joint angle data 314 in association with an ID (Identifier) ​​311. The ID 311 is an identifier for identifying various data such as the time 312. The time 312 is the time when the acceleration data 313 is measured. The acceleration data 313 is data measured by an acceleration sensor. The joint angle data 314 is data on the angle of each joint corresponding to the acceleration data measured by the acceleration sensor. These data may be collected as so-called big data. The walking motion visualization device 100 then refers to the joint angle table 301 and extracts joint angle data that approximates the estimated joint angles of the subject 110.

[0077] The hardware configuration of the walking motion visualization device 100 will be described with reference to FIG. 4 . The CPU (Central Processing Unit) 410 is a processor for arithmetic and control, and executes programs to realize the various functional components of the walking motion visualization device 100 shown in FIG. 2 . The CPU 410 may have multiple processors and execute different programs, modules, tasks, threads, etc. in parallel. The ROM (Read Only Memory) 420 stores fixed data such as initial data and programs, as well as other programs. The network interface 430 communicates with other devices via a network. The CPU 410 is not limited to one CPU, and may include multiple CPUs or a GPU (Graphics Processing Unit) for image processing. The network interface 430 preferably has a CPU independent of the CPU 410 and writes and reads transmitted and received data to and from an area of ​​the RAM (Random Access Memory) 440. It is also desirable to provide a DMAC (Direct Memory Access Controller) (not shown) that transfers data between the RAM 440 and the storage 450. Furthermore, the CPU 410 processes the data upon recognizing that data has been received or transferred to the RAM 440. The CPU 410 also prepares the processing results in the RAM 440, and leaves subsequent transmission or transfer to the network interface 430 or the DMAC.

[0078] The RAM 440 is a random access memory used by the CPU 410 as a temporary storage work area. The RAM 440 has a storage area reserved for storing data necessary for implementing this embodiment. The static state acceleration data 441 is acceleration data measured by the acceleration sensor when the subject 110 holds the acceleration sensor in a position facing the midline in front of his or her body. The determination acceleration data 442 is acceleration data when the subject 110 walks with the acceleration sensor held by the subject 110 in a position facing the midline in front of his or her body. The walking acceleration data 443 is acceleration data when the subject 110 is walking with the acceleration sensor facing forward. The estimated joint angle data 444 is an estimate of the joint angle of the lower body of the subject 110 while walking. The approximate joint angle data 445 is data of joint angles that are approximate to the estimated joint angles of the subject 110, and is data extracted from a predetermined database, for example. The skeleton model image data 446 is data representing the skeleton of the lower body of the subject 110 as the walking motion model image 150 of the subject 110, and is data for reproducing the walking motion of the subject 110 as a moving image or a still image.

[0079] The transmitted / received data 447 is data transmitted and received via the network interface 430. The RAM 440 also has an application execution area 448 for executing various application modules.

[0080] The storage 450 stores a database, various parameters, or the following data or programs required to implement this embodiment. The storage 450 stores a joint angle table 301. The joint angle table 301 is a table that manages the relationship between the ID 311 and the acceleration data 313, joint angle data 314, etc., as shown in FIG. 3 .

[0081] The storage 450 further stores an acceleration data acquisition module 451, a determination module 452, a walking acceleration data acquisition module 453, a walking movement analysis module 454, a display control module 457, and a notification module 458. The walking movement analysis module 454 further includes an approximate acceleration data selection module 455 and an extraction module 456. The acceleration data acquisition module 451 is a module that acquires stationary state acceleration data and determination acceleration data. The determination module 452 is a module that determines whether the acceleration sensor is facing directly with respect to the midline. The walking acceleration data acquisition module 453 is a module that acquires walking acceleration data while the subject 110 is walking when the acceleration sensor is facing directly. The walking movement analysis module 454 is a module that analyzes the walking movement of the subject 110 based on the walking acceleration data. The approximate acceleration data selection module 455 is a module that compares the acquired walking acceleration data with a predetermined database (e.g., the joint angle table 301) and selects approximate acceleration data that approximates the walking acceleration data from the predetermined database. The extraction module 456 is a module that extracts joint angle data, which are joint angles associated with the selected approximate acceleration data, from the predetermined database. The display control module 457 is a module that displays a walking motion model image 150 of the subject 110 based on the analysis results of the walking motion of the subject 110. The notification module 458 is a module that issues an alert in response to deviations of the acceleration sensor from a state where it is facing directly toward the midline. These modules 451 to 458 are read into the application execution area 448 of the RAM 440 by the CPU 410 and executed. The control program 459 is a program for controlling the entire walking motion visualization device 100.

[0082] The input / output interface 460 interfaces input / output data with input / output devices. A display unit 461 and an operation unit 462 are connected to the input / output interface 460. A storage medium 464 may also be connected to the input / output interface 460. A speaker 463 serving as an audio output unit, a microphone (not shown) serving as an audio input unit, or a GPS position determination unit may also be connected. Note that the RAM 440 and storage 450 shown in FIG. 4 do not include programs or data related to the general-purpose functions of the walking movement visualization device 100 or other feasible functions.

[0083] 5A to 5C, the processing procedures of the walking movement visualization device 100 will be described. These flowcharts are executed by the CPU 410 in FIG. 4 using the RAM 440, and realize the respective functional components of the walking movement visualization device 100 in FIG. 2.

[0084] First, with reference to Fig. 5A, the overall processing flow of the walking motion visualization device 100 will be described. In step S501, the walking motion visualization device 100 determines whether the acceleration sensor held by the subject 110 in front of the midline of his or her body is facing directly toward the midline. In step S503, the walking motion visualization device 100 analyzes the walking motion of the subject 110. In step S505, the walking motion visualization device 100 displays a walking motion model image 150 on a display or the like based on the analysis results of the walking motion.

[0085] Next, the details of the facing state determination process of step S501 will be described with reference to FIG. 5B . In step S531, the walking motion visualization device 100 instructs the subject 110 to position the acceleration sensor so that it faces the midline of their body. In step S533, the walking motion visualization device 100 determines whether the acceleration sensor is stationary. If it is determined that the acceleration sensor is not stationary (NO in step S533), the walking motion visualization device 100 waits until the acceleration sensor comes to a standstill. If it is determined that the acceleration sensor is stationary (YES in step S533), the walking motion visualization device 100 proceeds to the next step.

[0086] In step S535, the acceleration data acquisition unit 201 acquires stationary state acceleration data, which is a measurement value when the acceleration sensor is stationary. In step S537, the walking motion visualization device 100 determines the direction of gravity from the acquired stationary state acceleration data. In step S539, the walking motion visualization device 100 instructs the subject 110 to start walking. The walking motion visualization device 100 instructs the subject 110 to take, for example, a few steps. In step S541, the acceleration data acquisition unit 201 acquires determination acceleration data, which is acceleration data for determining whether the acceleration sensor is facing forward. The determination acceleration data is acceleration data acquired while the subject 110 is walking a few steps.

[0087] In step S543, the determination unit 202 determines whether the acceleration sensor is facing directly with respect to the midline of the subject 110. Whether the acceleration sensor is facing directly is determined, for example, using the value of the Harmonic Ratio (HR) described above. If it is determined that the acceleration sensor is not facing directly (NO in step S543), the walking motion visualization device 100 repeats the determination until the acceleration sensor is in the physiological state.

[0088] If it is determined that the acceleration sensor is facing forward (YES in step S543), the walking motion visualization device 100 proceeds to step S545. In step S545, the walking motion visualization device 100 notifies the subject 110 that walking has begun. In step S547, the walking acceleration data acquisition unit 203 acquires walking acceleration data while the subject 110 is walking.

[0089] Next, the walking movement analysis process in step S503 will be described in detail with reference to FIG. 5C. In step S561, the approximate acceleration data selection unit 241 compares the acquired walking acceleration data with a predetermined database. The comparison is performed, for example, for each of the left-right axis component, the front-back axis component, and the vertical axis component of the acquired walking acceleration data.

[0090] In step S563, the approximate acceleration data selection unit 241 selects approximate acceleration data that approximates the walking acceleration data as a result of comparing each axial component of the walking acceleration data. The selection of approximate acceleration data is performed, for example, by matching the acquired walking acceleration data with acceleration data stored in a predetermined database, but is not limited to this method as long as it is possible to select approximate acceleration data. Note that if acceleration data that matches the walking acceleration data exists, the approximate acceleration data selection unit 241 may select that acceleration data as approximate acceleration data.

[0091] In step S565, the extraction unit 242 extracts joint angle data, which are joint angles associated with the selected approximate acceleration data, from a predetermined database. In step S567, the walking motion visualization device 100 generates a walking motion model image 150 of the subject 110 using the extracted joint angle data. The generated walking motion model image 150 is, for example, a skeletal model image of the lower body of the subject 110. The walking motion visualization device 100 also generates, as the generated skeletal model image, an animation image (video) reproducing the walking motion of the subject 110, a slide image (a combined image of multiple still images), or the like. Then, in step S505, the display control unit 205 displays the generated skeletal model image on a display or the like.

[0092] According to this embodiment, the analysis of the subject's walking motion is performed in a state where the acceleration sensor can output accurate measurement values, thereby enabling highly reliable analysis of the subject's walking motion with fewer calculation steps and less calculation time. Furthermore, the subject's walking motion is displayed to the subject using a skeletal model image, allowing the subject to easily identify areas that need improvement and how to move their body. Furthermore, when the acceleration sensor is positioned directly facing the midline of the subject's body, the walking motion is analyzed using the acceleration measured while the subject is walking, thereby significantly reducing the amount of calculation, calculation steps, and calculation time required for the walking motion analysis process. Furthermore, since the amount of calculation and the like can be significantly reduced, the analysis results of the walking motion can be quickly provided to the subject.

[0093] Second Embodiment Next, a walking motion visualization device according to a second embodiment of the present invention will be described with reference to Fig. 6. Fig. 6 is a block diagram for explaining the configuration of a walking motion visualization device 600 according to this embodiment.

[0094] The walking motion visualization device 600 includes an acceleration data acquisition unit 601, a determination unit 602, a walking acceleration data acquisition unit 603, a walking motion analysis unit 604, and a display control unit 605. The acceleration data acquisition unit 601 acquires, from an acceleration sensor disposed on the midline, which is the center line between the left and right sides of the body of the subject 110, stationary state acceleration data for determining the direction of gravity when the subject 110 is stationary, and determination acceleration data, which is acceleration data when the subject 110 is walking, for determining whether the acceleration sensor is facing the midline. The determination unit 602 determines whether the acceleration sensor is facing the midline based on the acquired stationary state acceleration data and determination acceleration data. When the determination unit determines that the acceleration sensor is facing the midline, the walking acceleration data acquisition unit 603 acquires walking acceleration data from the acceleration sensor while the subject 110 is walking. The walking motion analysis unit 604 analyzes the walking motion of the subject 110 based on the acquired walking acceleration data. The display control unit 605 displays a walking motion model image of the subject 110 based on the analysis results by the walking motion analysis unit.

[0095] According to this embodiment, the walking movement of the subject is analyzed in a state where the acceleration sensor can output correct measurement values, so that the walking movement can be analyzed with high reliability.

[0096] Although the present invention has been described above with reference to the embodiments, the present invention is not limited to the above-described embodiments and can be modified as appropriate. Various modifications that can be understood by those skilled in the art can be made to the configuration and details of the present invention within the scope of the present invention. Furthermore, systems or devices that combine separate features included in each embodiment in any manner are also included in the scope of the present invention.

[0097] The present invention may be applied to a system consisting of multiple devices or to a single device. Furthermore, the present invention may also be applied when an information processing program that realizes the functions of the embodiments is supplied to a system or device and executed by a built-in processor. Therefore, the technical scope of the present invention also includes a program installed on a computer to realize the functions of the present invention, a medium storing the program, a World Wide Web (WWW) server from which the program is downloaded, and a processor that executes the program. In particular, the technical scope of the present invention also includes a non-transitory computer-readable medium storing a program that causes a computer to execute at least the processing steps included in the above-described embodiments.

[0098] According to the present invention, the walking movement of the subject is analyzed in a state where the acceleration sensor can output correct measurement values, so that the walking movement can be analyzed with high reliability.

Claims

1. an acceleration data acquisition unit that acquires, from an acceleration sensor disposed on a median line that is the center line between the left and right sides of the body of the subject, stationary state acceleration data for determining the direction of gravity when the subject is stationary, and determination acceleration data that is acceleration data when the subject is walking, in order to determine whether the acceleration sensor is facing the median line; a determination unit that determines whether the acceleration sensor is facing directly with respect to a median line based on the acquired stationary state acceleration data and the determination acceleration data; a walking acceleration data acquisition unit that acquires walking acceleration data from the acceleration sensor while the subject is walking when the determination unit determines that the acceleration sensor is facing the median line; a walking motion analysis unit that analyzes the walking motion of the subject based on the acquired walking acceleration data; a display control unit that displays a walking motion model image of the subject based on the analysis result by the walking motion analysis unit; A walking motion visualization device equipped with

2. 2. The walking motion visualization device according to claim 1, wherein the determination unit determines whether the acceleration sensor is facing forward based on a comparison between the left-right axis component, the front-back axis component, and the vertical axis component of the stationary state acceleration data and the left-right axis component, the front-back axis component, and the vertical axis component of the determination acceleration data.

3. The walking movement analysis unit an approximate acceleration data selection unit that compares the acquired walking acceleration data with a predetermined database and selects approximate acceleration data that is acceleration data that is approximate to the walking acceleration data; an extracting unit that extracts joint angle data, which is a joint angle associated with the selected approximate acceleration data, from the predetermined database; Furthermore, The walking motion visualization device according to claim 1 , wherein the display control unit displays the walking motion model image using the extracted joint angle data.

4. 3. The walking motion visualization device according to claim 1, further comprising a notification unit that notifies the user that walking has started when the acceleration sensor is positioned directly facing the median line as a result of the determination by the determination unit.

5. 3. The walking motion visualization device according to claim 1, wherein the display control unit displays, together with the walking motion model image, guidance information for guiding the subject to a walking motion suitable for the subject.

6. 3. The walking motion visualization device according to claim 1, wherein the walking motion model image is a skeletal model image of the lower body of the subject.

7. an acceleration data acquisition step of acquiring, from an acceleration sensor disposed on a median line, which is the center line between the left and right sides of the body of the subject, stationary state acceleration data for determining the direction of gravity when the subject is stationary, and determination acceleration data, which is acceleration data when the subject is walking, in order to determine whether the acceleration sensor is facing the median line; a determination step of determining whether the acceleration sensor is facing directly with respect to a median line based on the acquired stationary state acceleration data and the determination acceleration data; a walking acceleration data acquisition step of acquiring walking acceleration data from the acceleration sensor while the subject is walking, when it is determined in the determination step that the acceleration sensor is facing directly toward the median line; a walking motion analysis step of analyzing the walking motion of the subject based on the acquired walking acceleration data; a display control step of displaying a walking motion model image of the subject based on the analysis result in the walking motion analysis step; A walking motion visualization method including:

8. an acceleration data acquisition unit that acquires, from an acceleration sensor disposed on a median line that is the center line between the left and right sides of the body of the subject, stationary state acceleration data for determining the direction of gravity when the subject is stationary, and determination acceleration data that is acceleration data when the subject is walking, in order to determine whether the acceleration sensor is facing the median line; a determination unit that determines whether the acceleration sensor is facing directly toward the median line based on the acquired stationary state acceleration data and the determination acceleration data; A facing state determination device comprising:

9. 9. The facing state determination device according to claim 8, wherein the determination unit determines whether the acceleration sensor is in a facing state based on a comparison between a left-right axis component, a front-rear axis component, and a vertical axis component of the stationary state acceleration data and a left-right axis component, a front-rear axis component, and a vertical axis component of the determination acceleration data, respectively.

10. an acceleration data acquisition step of acquiring, from an acceleration sensor disposed on a median line, which is the center line between the left and right sides of the body of the subject, stationary state acceleration data for determining the direction of gravity when the subject is stationary, and determination acceleration data, which is acceleration data when the subject is walking, for determining whether the acceleration sensor is facing the median line; a determination step of determining whether the acceleration sensor is facing directly with respect to the median line based on the acquired stationary state acceleration data and the determination acceleration data; A method for determining a facing state, comprising: