Electronic device, form determination method and program

Abstract

To enable a user's exercise form to be determined on the basis of information on the user's exercise.SOLUTION: Electronic equipment 100 is attached to a user's arm. The electronic equipment 100 comprises a detection part 160 for detecting information on the user's exercise, and a control part 110. The control part 110 determines the user's exercise form on the basis of the exercise information detected by the detection part 160.SELECTED DRAWING: Figure 1

Description

[Technical field]

[0001] The present invention relates to an electronic device, a form determination method, and a program. [Background technology]

[0002] In recent years, electronic devices that are worn on the arm and detect the movement of the user's body, such as wearable devices such as smart watches and activity meters, have been developed. As a technology used in such electronic devices, for example, Patent Document 1 discloses a technology for detecting the number of steps taken by a user using an acceleration sensor. [Prior art documents] [Patent documents]

[0003] [Patent Document 1] JP 2011-90548 A Summary of the Invention [Problem to be solved by the invention]

[0004] The technology disclosed in Patent Document 1 calculates the user's forward and backward acceleration from acceleration data obtained by an acceleration sensor, and counts the number of steps by counting the time when the calculated forward and backward acceleration becomes 0 as one step. In practice, it is difficult to calculate accurate forward and backward acceleration, but since it is sufficient to detect the reversal of the sign of the forward and backward acceleration to count the number of steps, this method can count the number of steps without any problems. However, although this method can count the number of steps, it is not suitable for determining (estimating) the actual form of exercise.

[0005] The present invention has been made in consideration of the above-mentioned situation, and aims to provide an electronic device, a form judgment method, and a program that enable the judgment of a user's exercise form based on the user's exercise information. [Means for solving the problem]

[0006] In order to achieve the above object, one aspect of the electronic device according to the present invention is to An electronic device worn on a user's arm, A detection unit that detects motion information of the user; A control unit, The detection unit detects acceleration components of three mutually orthogonal axes as the motion information, The control unit is A horizontal velocity, which is a horizontal velocity component, is obtained based on the three-axis acceleration components detected by the detection unit; The acquired horizontal velocity is used as a judgment value, and a direction of the user's arm swing is judged based on the judgment value. . Effect of the Invention

[0007] According to the present invention, it is possible to determine a user's exercise form based on the user's exercise information. [Brief description of the drawings]

[0008] [Figure 1] 1 is a block diagram showing an example of a functional configuration of an electronic device according to an embodiment. [Diagram 2] 11A to 11C are diagrams illustrating the axes of acceleration detected by a detection unit when the electronic device according to the embodiment is worn on the left wrist of a user. [Diagram 3] 5A to 5C are diagrams illustrating an example of acceleration detected by the electronic device of the embodiment. [Figure 4] 13 is an example of a flowchart of an arm swing determination process according to an embodiment. [Diagram 5] 11A to 11C are diagrams illustrating the acceleration of the x2 axis calculated in the arm swing determination process in the embodiment. [Figure 6] 11A to 11C are diagrams illustrating horizontal acceleration ha and the like calculated in the arm swing determination process in the embodiment. [Figure 7] 5A to 5C are diagrams illustrating an example of a norm n and a leveled horizontal signal Lha calculated in the arm swing determination process in the embodiment. [Figure 8] 11A to 11C are diagrams illustrating an example of a horizontal velocity obtained by the arm swing determination process in the embodiment. [Figure 9]11A and 11B are diagrams illustrating an example of acceleration detected by the electronic device of the embodiment when a user walks with his or her arms bent at approximately right angles. [Figure 10] 11A and 11B are diagrams showing an example of a norm n and a smoothed horizontal signal Lha calculated in the arm swing determination process according to the embodiment when a user walks with his or her arms bent at approximately a right angle. [Figure 11] 11A and 11B are diagrams illustrating an example of a horizontal velocity obtained by the arm swing determination process according to the embodiment when a user walks with their arms bent at approximately right angles. DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS

[0009] Electronic devices and the like according to embodiments will be described with reference to the drawings. Note that the same or corresponding parts in the drawings are given the same reference numerals.

[0010] (Embodiment) The electronic device according to the embodiment is an information processing device that is worn on the wrist of a user and can determine the form of exercise using an acceleration sensor, such as a smart watch or an electronic watch.

[0011] As shown in FIG. 1, the electronic device 100 includes a control unit 110, a storage unit 120, an input unit 130, an output unit 140, a communication unit 150, and a detection unit 160.

[0012] The control unit 110 is composed of a processor such as a CPU (Central Processing Unit). The control unit 110 executes processes for implementing various functions of the electronic device 100 and arm swing determination processes (described later) using programs stored in the storage unit 120. The control unit 110 also supports multi-threading and can execute multiple processes in parallel.

[0013] The storage unit 120 stores programs executed by the control unit 110 and necessary data. The storage unit 120 may include, but is not limited to, a RAM (Random Access Memory), a ROM (Read Only Memory), a flash memory, etc. Note that the storage unit 120 may be provided inside the control unit 110.

[0014] The input unit 130 is a user interface such as a push button switch, a touch panel, etc., and receives operational input from a user. When the input unit 130 includes a touch panel, the touch panel may be integrated with the display of the output unit 140.

[0015] The output unit 140 includes a display such as a liquid crystal display or an organic EL (Electro-Luminescence) display, and displays a display screen that provides the functions of the electronic device 100, an operation screen, and the like.

[0016] The communication unit 150 is a network interface compatible with, for example, a wireless local area network (LAN), a long term evolution (LTE), etc. The electronic device 100 can communicate with the Internet and other devices via the communication unit 150.

[0017] The detection unit 160 detects motion information of the user. In this embodiment, acceleration information is used as the motion information of the user. Therefore, the detection unit 160 is provided with an acceleration sensor that detects acceleration in each of three mutually orthogonal axes (X-axis, Y-axis, and Z-axis). It is preferable that this acceleration sensor detects acceleration with a sampling frequency of approximately 25 Hz or more and 100 Hz or less. The control unit 110 can acquire the value detected by the acceleration sensor provided in the detection unit 160 as a detection value at any timing (however, the temporal resolution depends on the sampling frequency).

[0018] Electronic device 100 is worn on the user's wrist with band 190 as shown in Fig. 2. The arm on which electronic device 100 is worn may be either the right arm or the left arm, but here, the case where electronic device 100 is worn on the back of the left hand as shown in Fig. 2 will be described. Note that whether the arm on which electronic device 100 is worn is the left or right arm may be input via input unit 130, or the like, and stored in storage unit 120.

[0019] In this case, as shown in Fig. 2, the axes of the acceleration sensor of the detection unit 160 are the x-axis, which is the direction from the little finger to the thumb, the y-axis, which is the direction from the side of the wrist where the palmaris longus muscle is located (palm side) to the back side (back of the hand), and the z-axis, which is the direction from the hand to the elbow. Note that gravity is a downward force, but gravitational acceleration cannot be distinguished from the acceleration that occurs when an object accelerates upward at 1G in a gravity-free space. For this reason, the acceleration sensor detects gravitational acceleration as a vertically upward acceleration.

[0020] When a user walks wearing electronic device 100 as shown in Fig. 2, detection unit 160 acquires the acceleration of each axis as a discrete signal sampled at a sampling frequency. When a user walks without bending his / her elbows, the acceleration of each axis is acquired as shown in Fig. 3, for example. In this case, the z-axis value, which is affected by the acceleration of gravity, is often the largest, followed by the x-axis value, which is affected by the forward and backward shaking of the hand. Also, since the hand rarely swings left and right when walking, the y-axis value is often relatively small.

[0021] Therefore, in such a case, it is reasonable to think that the direction of arm swing can be determined based on the value of the acceleration on the x-axis. However, in reality, due to the influence of misalignment of the position of wearing electronic device 100 and the user's habit of swinging their hand, the x-axis does not necessarily reflect only the swing of the arm forward and backward. Therefore, when determining the direction of arm swing, electronic device 100 resolves the values ​​of the acceleration of the three axes detected by detection unit 160 into the vertical direction (gravity direction) and a direction perpendicular to the vertical direction (horizontal direction), obtains the horizontal speed from the latter value (horizontal acceleration), and determines the direction of arm swing based on this horizontal speed.

[0022] The arm swing determination process for determining the direction of arm swing based on the acceleration values ​​of such three axes will be described with reference to Fig. 4. This process may be executed in parallel with other necessary processes when electronic device 100 is started up, or may be executed when an instruction to perform arm swing determination is received from the user via input unit 130 or the like.

[0023] First, the control unit 110 acquires the acceleration values ​​of the x-axis, y-axis, and z-axis (x-axis signal, y-axis signal, z-axis signal) from the detection unit 160 (step S101). Next, the control unit 110 calculates the acceleration of the x2 axis (x2 signal) in the xy plane from the x-axis component (x-axis signal) and y-axis component (y-axis signal) of the acceleration (step S102).

[0024] As shown in FIG. 5, the acceleration on the x2 axis is the sum vector of the acceleration vector in the x-axis direction and the acceleration vector in the y-axis direction, and this sum vector is perpendicular to the z-axis. The value (scalar value) of the acceleration on the x2 axis (x2 signal) is the L2 norm of the vector that is the sum of the acceleration in the x-axis direction and the y-axis direction. For convenience, the sign of the acceleration on the x2 axis (x2 signal) is given as the sign of the acceleration on the x-axis. In other words, if the x-axis signal at time i is expressed as x i and the y-axis signal is represented by y i In other words, the x2 signal (x2 i ) is calculated using the following formula (1), where sign(x) is a function that returns 1 if the sign of x is positive, and -1 if it is negative. x2 i =√(x i 2 +y i 2 )×sign(x i )…(1)

[0025] Then, the control unit 110 applies a low pass filter (LPF) that cuts high frequency components equal to or higher than a first reference frequency (0.05 Hz to 1 Hz, for example, 0.1 Hz) to each of a signal (first signal) indicating time series data of acceleration on the z axis (first acceleration component that is the acceleration component of the first axis (z axis) selected from the three axes) and a signal (second signal) indicating time series data of acceleration on the x2 axis (second acceleration component that is the component of the sum of the acceleration components of the two axes (x axis and y axis) other than the first axis), to generate a first smoothed signal (z signal after application of the LPF). i ) and the second leveled signal (x2 after applying LPF i ) is obtained (step S103).

[0026] Then, the control unit 110 calculates an angle v_ang from the x2 axis of a leveling vector Lv (Leveling vector), which is a composite vector of a vector represented by the first leveling signal and a vector represented by the second leveling signal (step S104). i and the z-axis signal is represented by z i Expressed as v_ang i is calculated using the following formula (2). v_ang i =tan -1 (z after applying LPF i / x2 after LPF applied i )…(2)

[0027] Next, the control unit 110 calculates n, which is the L2 norm of the resultant vector vn of the z-axis signal (first acceleration component) and the x2-axis signal (second acceleration component), and n_ang, which is the angle of vn from the x2-axis (step S105). i and the z-axis signal is represented by z i Expressed as n i and n_ang i is calculated using the following equations (3) and (4). n i =√(x2 i 2 +z i 2 ) …(3) n_ang i=tan -1 (z i / x2 i )…(4)

[0028] Then, the control unit 110 calculates the horizontal acceleration ha (horizontal acceleration) by taking the component of the resultant vector vn of the z-axis signal (first acceleration component) and the x2-axis signal (second acceleration component) in a direction perpendicular to v_ang on the x2-z plane (step S106). i and v_ang is expressed as v_ang i and n_ang is expressed as n_ang i Expressed as ha i is calculated using the following formula (5). ha i =n i ×sin(n_ang i -v_ang i ) × (-1) … (5)

[0029] The relationship between the above values ​​is shown in Figure 6. By applying a low-pass filter to the z-axis acceleration (first acceleration component) and the x2-axis acceleration (second acceleration component), various noise components caused by walking and arm swinging are removed and the gravitational acceleration becomes the dominant value, so the smoothed vector Lv, which is the composite vector of the vector represented by the first smoothed signal and the vector represented by the second smoothed signal, becomes a vector in the vertical direction (the direction of average gravity). Therefore, the vector ha, which is perpendicular to the smoothed vector Lv, can be considered a horizontal vector, and it can be seen that the vector ha represents the horizontal acceleration.

[0030] Then, in order to remove high-frequency noise components of the horizontal acceleration ha, the control unit 110 applies a low-pass filter that cuts high-frequency components equal to or higher than a second reference frequency (1.5 Hz to 3 Hz, for example, 2 Hz) to the signal indicating the time-series data of the horizontal acceleration ha to obtain a leveled horizontal signal Lha (Leveling ha) (step S107). For example, when the norm n of the composite vector vn and the leveled horizontal signal Lha are calculated from the signal indicating the time-series data of the acceleration of the three axes (time-series signal) shown in FIG. 3, a graph as shown in FIG. 7 is obtained.

[0031] Then, the control unit 110 integrates the smoothed horizontal signal Lha to calculate the horizontal velocity hv (step S108). However, the smoothed horizontal signal Lha also contains noise components such as signals other than horizontal signals and signals due to walking or running (associated with the movement of the user). Therefore, in order to suppress the influence of these noise components, the control unit 110 may calculate a horizontal acceleration moving average MAha (Moving Average of ha), which is the moving average of the smoothed horizontal signal Lha, and calculate the horizontal velocity hv by subtracting the horizontal acceleration moving average MAha from the smoothed horizontal signal Lha and then integrating it.

[0032] Then, the control unit 110 calculates a judgment value JV for judging the direction of arm swing from the horizontal velocity hv (step S109). Here, the control unit 110 may use the horizontal velocity hv as the judgment value JV as it is. However, the horizontal velocity hv also contains noise components such as components other than the horizontal direction and components due to walking or running (associated with the movement of the user). Therefore, in order to suppress the influence of these noise components, the control unit 110 may calculate a horizontal velocity moving average MAhv (Moving Average of hv), which is the moving average of the horizontal velocity hv, and calculate the judgment value JV (Judgement Value) by subtracting the horizontal velocity moving average MAhv from the horizontal velocity hv.

[0033] Then, the control unit 110 determines the direction of the arm swing based on the judgment value JV (step S110), and ends the arm swing judgment process. The judgment value JV (i.e., the horizontal velocity hv) is a positive value when the arm is moving forward, and is a negative value when the arm is moving backward. The value becomes 0 at the point where the arm swing turns around. For example, when the horizontal velocity hv is calculated from the leveled horizontal signal Lha shown in FIG. 7, a graph as shown in FIG. 8 is obtained. The direction of the arm swing changes at the timing when the value becomes 0 in this graph, and the direction of the arm swing when the value is positive is the forward direction, and the direction of the arm swing when the value is negative is the backward direction. Therefore, the control unit 110 can determine the direction of the arm swing based on the value of the horizontal velocity hv (i.e., the judgment value JV).

[0034] Furthermore, the control unit 110 can also determine whether a foot is on the ground from the timing of the foot touching the ground and the judgment value JV. For example, if the time during which the judgment value JV takes a positive value is longer than the time during which it takes a negative value during the period from the timing of one foot touching the ground to the timing of the other foot touching the ground, the control unit 110 determines that the foot on the same side as the arm on which the electronic device 100 is worn has touched the ground.

[0035] Also, if the arm on which the electronic device 100 is worn is stored in advance in the storage unit 120 as being either the left or right arm by inputting through the input unit 130, the grounded foot can be determined (estimated) based on at least the value taken by the judgment value JV. For example, if the arm on which the electronic device is worn is the left arm and the user is walking, when the judgment value JV changes from 0 to a positive value, it is determined (estimated) that the left foot is the grounded foot. Also, at the moment when the judgment value JV changes from 0 to a positive value, it is highly likely that both feet are on the ground, but the right foot is no longer a grounded foot as the judgment value JV increases, and when the judgment value JV decreases and the judgment value JV becomes 0 again, it can be determined (estimated) that the right foot is again a grounded foot. Also, when the judgment value JV takes an extreme value, it may be determined (estimated) that the arm is beside the user's body. Regarding the above, a similar determination (estimate) can be made when the judgment value JV takes a negative value or when the user is wearing the electronic device on the right arm.

[0036] Any method can be used to detect the touchdown of the foot, but for example, the control unit 110 can detect the touchdown of the foot by detecting the peak of a composite signal of the acceleration of all three axes detected by the detection unit 160. In this case, the control unit 110 also functions as a touchdown detection unit.

[0037] By the above arm swing determination process, the control unit 110 can determine the direction of the user's arm swing based on the three-axis acceleration data. The control unit 110 can also determine the foot that is touching the ground by detecting the foot's contact timing.

[0038] In the above explanation, we have explained the case where the user walks without bending the elbows, but next we will consider the case where the user walks with bending the elbows (for example, bending the arms at a nearly right angle). In this case, the x-axis is most affected by the gravitational acceleration, and the z-axis is affected by the swinging of the arms back and forth, and the acceleration of each axis is obtained as shown in Figure 9, for example.

[0039] As can be seen from FIGS. 5 and 6, the norm n is significantly affected by the axis with the largest amplitude among the three axes x, y, and z, and as shown in FIG. 10, the graph resembles the acceleration on the x-axis in FIG.

[0040] The horizontal acceleration ha is a vector perpendicular to the leveled vector Lv, but even in this case, various noise components are removed from the leveled vector Lv, and the leveled vector Lv is a vector in the vertical direction (the direction of average gravity) because the gravitational acceleration is the dominant value. Therefore, even when walking with bent elbows, the value of a vector perpendicular to the vertical direction (Lv) is obtained as the horizontal acceleration ha, and the control unit 110 can obtain a leveled horizontal signal Lha as shown in FIG. 10 by leveling this.

[0041] Then, the control unit 110 can calculate the horizontal velocity hv as shown in FIG. 11, for example, by integrating the leveled horizontal signal Lha.

[0042] In this way, even if the first axis is not the axis most affected by gravity (the z-axis when the elbow is not bent, and the x-axis when the elbow is bent), a vector that is approximately vertical can be obtained by calculating the leveling vector Lv, and the horizontal acceleration ha can be obtained by calculating a vector perpendicular to the leveling vector Lv.

[0043] (Modification) In the above embodiment, acceleration is used as the user's motion information, but the user's motion information is not limited to acceleration. For example, angular velocity may be used as the user's motion information. When angular velocity is used as the motion information, the detection unit 160 is provided with a gyro sensor. The control unit 110 determines the direction of the user's arm swing based on the angular velocity of the arm detected by the gyro sensor. In addition, both acceleration and angular velocity may be used as the user's motion information. In this case, the control unit 110 can improve the accuracy of the arm swing determination by comparing the arm swing direction determined based on the acceleration with the arm swing direction determined based on the angular velocity.

[0044] In the above embodiment, the user's exercise form is judged by judging the direction of arm swing and the foot on the ground, but the control unit 110 may analyze the user's exercise form (displaying the exercise form in animation and giving advice on how to improve, etc.) based on the judged arm swing and foot on the ground information. The control unit 110 may also transmit the judged arm swing, foot on the ground, form analysis results, etc. to another device (smartwatch, smartphone, etc.) via the communication unit 150 and display them on the display unit of the other device.

[0045] Furthermore, the electronic device 100 is not limited to a smart watch, but may also be realized by a computer such as a smartphone equipped with the detection unit 160, a portable tablet, or a PC (Personal Computer). Specifically, in the above embodiment, the program for the arm swing determination process and the like executed by the control unit 110 has been described as being stored in advance in the storage unit 120. However, the program may be stored in a non-transitory computer-readable recording medium such as a flexible disk, a CD-ROM (Compact Disc Read Only Memory), a DVD (Digital Versatile Disc), an MO (Magneto-Optical disc), a memory card, or a USB memory device and distributed, and the program may be read and installed in a computer to configure a computer capable of executing each of the above-mentioned processes.

[0046] Furthermore, the program may be superimposed on a carrier wave and applied via a communication medium such as the Internet. For example, the program may be distributed by posting it on a bulletin board system (BBS) on a communication network. The program may then be started and executed under the control of an OS (Operating System) in the same manner as other application programs, thereby enabling the above-mentioned processes to be performed.

[0047] In addition, the control unit 110 may be configured by any processor alone, such as a single processor, a multiprocessor, or a multi-core processor, or may be configured by combining any of these processors with a processing circuit such as an ASIC (Application Specific Integrated Circuit) or an FPGA (Field-Programmable Gate Array).

[0048] Although the above describes a preferred embodiment of the present invention, the present invention is not limited to such a specific embodiment, and the present invention includes the invention described in the claims and its equivalents. [Explanation of symbols]

[0049] 100: electronic device, 110: control unit, 120: memory unit, 130: input unit, 140: output unit, 150: communication unit, 160: detection unit, 190: band

Claims

1. An electronic device worn on a user's arm, A detection unit that detects motion information of the user; A control unit, The detection unit detects acceleration components of three mutually orthogonal axes as the motion information, The control unit is A horizontal velocity, which is a horizontal velocity component, is obtained based on the three-axis acceleration components detected by the detection unit; using the acquired horizontal velocity as a determination value, and determining a direction of the user's arm swing based on the determination value; electronic equipment.

2. The control unit is decomposing the acceleration components of the three axes into a first acceleration component which is an acceleration component of a first axis selected from the three axes, and a second acceleration component which is a sum of acceleration components of two axes other than the first axis; obtaining the horizontal velocity based on the first acceleration component and the second acceleration component; 2. The electronic device according to claim 1.

3. The control unit is calculating a horizontal acceleration based on a first smoothed signal obtained by cutting high-frequency components equal to or higher than a first reference frequency in a first signal which is a signal indicating time-series data of the first acceleration component, and a second smoothed signal obtained by cutting high-frequency components equal to or higher than the first reference frequency in a second signal which is a signal indicating time-series data of the second acceleration component; obtaining the horizontal velocity from the calculated horizontal acceleration; 3. The electronic device according to claim 2.

4. The control unit is The horizontal velocity is obtained from a smoothed horizontal signal obtained by cutting high-frequency components equal to or higher than a second reference frequency in a signal indicating the time-series data of the horizontal acceleration.

4. The electronic device according to claim 3.

5. The control unit is Calculating a horizontal acceleration moving average which is a moving average of the smoothed horizontal signal; and integrating a value obtained by subtracting the horizontal acceleration moving average from the smoothed horizontal signal to obtain the horizontal velocity.

5. The electronic device according to claim 4.

6. The control unit is Calculating a horizontal velocity moving average, which is a moving average of the horizontal velocity; a value obtained by subtracting the horizontal velocity moving average from the horizontal velocity is set as the determination value; 6. The electronic device according to claim 5.

7. The control unit determines a grounded foot of the user based on at least the determined arm swing direction. The electronic device according to claim 1 .

8. The control unit detects a timing at which the user's foot touches the ground, determining a grounded foot of the user based on the detected grounding timing and the determined arm swing direction; 8. The electronic device according to claim 7.

9. The control unit is If the time during which the determination value is a positive value is longer than the time during which the determination value is a negative value during the period from the detected time of ground contact to the next time of ground contact, it is determined that the foot on the same side as the arm on which the device is worn is on the ground.

9. The electronic device according to claim 8.

10. An information processing device includes a detection unit that is worn on a user's arm and detects motion information of the user, and a control unit, A horizontal velocity, which is a horizontal velocity component, is obtained based on the three-axis acceleration components detected by the detection unit; using the acquired horizontal velocity as a determination value, and determining a direction of the user's arm swing based on the determination value; Form validation method.

11. An information processing device includes a detection unit that is worn on a user's arm and detects motion information of the user, and a control unit, a horizontal velocity, which is a horizontal velocity component, is acquired based on the three-axis acceleration components detected by the detection unit, and the acquired horizontal velocity is used as a determination value, and a direction of the user's arm swing is determined based on the determination value. A program that executes a process.

Images