JP7134418B2 - Motion analysis device, motion analysis method and program - Google Patents

Description

The present invention relates to a motion analysis device, motion analysis method and program.

2. Description of the Related Art Conventionally, there is a technique of detecting an impact in golf swing data of a user and specifying the range of a swing motion of a target person based on the time of the detected impact (see Patent Document 1).

JP 2015-178026 A

However, in the motion analysis technique described in Patent Document 1, for example, when specifying the range of motion in a golf swing, the swing motion by the target person is based on the point in time when the amount of motion takes a maximum or minimum value, such as an impact motion. I needed to specify the range.

The present invention has been made in view of such a situation, and an object of the present invention is to specify the range of motion without using the point of time when the momentum is maximum or minimum in a series of motions.

In order to achieve the above object, a motion analysis device according to one aspect of the present invention includes:
Acquisition means for acquiring exercise information from a sensor device that is attached to a subject and that senses a series of golf swings by the subject for a period from the start to the end of the golf swing;
Using an intensity threshold indicating the strength of the exercise information, a frequency threshold indicating how many times the exercise information occurred, and a time threshold indicating how long the exercise information continued. and identifying means for identifying a plurality of states in the golf swing by determining
The identification means identifies a resting state that identifies a resting state before starting the golf swing, and determines the point at which the strength threshold for detecting the resting state is exceeded when the backswing in the golf swing is started. A plurality of states including specifying the start of the motion to be detected as the time point, specifying the candidate for specifying the candidate for the main swing in the golf swing, and specifying the motion for specifying whether the candidate corresponds to the main swing. specify and further
The identification means identifies the stationary state when the motion information is below the threshold A, which is the intensity threshold, for a period of time equal to or longer than the threshold Ta, which is the time threshold, and
detecting a state in which the motion information exceeds the threshold value A as a time point at which the backswing is started, and specifying the start of the motion;
At a timing after the stationary state, the state in which the motion information is lower than the threshold value C, which is the intensity threshold value higher than the threshold value A, is determined as a threshold value, which is the time threshold value shorter than the threshold value Ta. If it continues for Tc or more, it is determined that the golf swing is finished, and the period from the start of the golf swing to the end of the golf swing is specified as the candidate for the main swing.
It is characterized by

ADVANTAGE OF THE INVENTION According to this invention, the range of motion can be specified without using the time of the maximum or the minimum amount of momentum in a series of motions as a reference.

1 is a system configuration diagram showing a system configuration of a motion analysis system S according to one embodiment of the present invention; FIG. 2 is a block diagram showing the hardware configuration of the sensor unit 1 according to one embodiment of the present invention; FIG. 1 is a block diagram showing the hardware configuration of a motion analysis device 2 according to one embodiment of the present invention; FIG. It is a schematic diagram for demonstrating the swing identification method of this embodiment. FIG. 4 is a functional block diagram showing a functional configuration for executing a swing specifying process among the functional configurations of the motion analysis device 2 of FIG. 3; FIG. 6 is a flowchart for explaining the flow of swing identification processing executed by the motion analysis device 2 of FIG. 3 having the functional configuration of FIG. 5; 6 is a flowchart for explaining the flow of swing identification processing executed by the motion analysis device 2 of FIG. 3 having the functional configuration of FIG. 5; 6 is a flowchart illustrating another flow of swing identification processing executed by the motion analysis device 2 of FIG. 3 having the functional configuration of FIG. 5; 6 is a flowchart illustrating another flow of swing identification processing executed by the motion analysis device 2 of FIG. 3 having the functional configuration of FIG. 5;

BEST MODE FOR CARRYING OUT THE INVENTION Hereinafter, embodiments of the present invention will be described with reference to the drawings.

<First Embodiment>
FIG. 1 is a system configuration diagram showing the system configuration of a motion analysis system S according to one embodiment of the present invention.
The motion analysis system S includes a sensor unit 1 and a motion analysis device 2, as shown in FIG.

The sensor unit 1 has at least a sensing function that senses the movement of the wearer and a communication function that transmits sensed data (hereinafter referred to as “sensor information”) to the motion analysis device 2 .
In this embodiment, the sensor unit 1 is worn near the waist of a golf swinger, and senses a series of motions in the swing as motions to be worn.

The motion analysis device 2 has at least a communication function for receiving sensor information transmitted from the sensor unit 1, and an analysis function for analyzing the sensor information and identifying a series of movements and each movement within the series of movements. have.
In this embodiment, the motion analysis device 2 identifies a series of motions of the swing and each motion such as address, take-back, downswing, follow-up, and finish that constitute the swing through analysis.

FIG. 2 is a block diagram showing the hardware configuration of the sensor unit 1 according to one embodiment of the present invention.
As shown in FIG. 2, the sensor unit 1 includes a CPU (Central Processing Unit) 11-1, a ROM (Read Only Memory) 12-1, a RAM (Random Access Memory) 13-1, and a bus 14-1. , an input/output interface 15-1, a sensor unit 16-1, an input unit 17-1, an output unit 18-1, a storage unit 19-1, a communication unit 20-1, a drive 21-1, It has

The CPU 11-1 executes various processes according to programs recorded in the ROM 12-1 or programs loaded from the storage unit 19-1 to the RAM 13-1.

The RAM 13-1 also stores data necessary for the CPU 11-1 to execute various processes.

The CPU 11-1, ROM 12-1 and RAM 13-1 are interconnected via a bus 14-1. An input/output interface 15-1 is also connected to this bus 14-1. A sensor section 16-1, an input section 17-1, an output section 18-1, a storage section 19-1, a communication section 20-1 and a drive 21-1 are connected to the input/output interface 15-1.

The sensor unit 16-1 is composed of various sensors such as a gyro sensor and a triaxial angular velocity sensor, detects at least the angular velocity generated in the sensor unit 1 according to the user's motion, and outputs it as sensor information.
Note that the sampling rate is set to 200 Hz in this embodiment.

The input unit 17-1 is composed of various buttons and the like, and inputs various kinds of information in accordance with the instruction operation of the user.
The output unit 18-1 is composed of a display, a speaker, etc., and outputs images and sounds.
The storage unit 19-1 is composed of a hard disk, a DRAM (Dynamic Random Access Memory), or the like, and stores data of various images.
The communication unit 20-1 controls communication with another device (not shown) via a network including the Internet.

A removable medium 31-1 composed of a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, or the like is appropriately mounted in the drive 21-1. A program read from the removable medium 31 by the drive 21-1 is installed in the storage unit 19-1 as required. The removable medium 31-1 can also store various data such as image data stored in the storage unit 19-1 in the same manner as the storage unit 19-1.

FIG. 3 is a block diagram showing the hardware configuration of the motion analysis device 2 according to one embodiment of the present invention.
The motion analysis device 2 is configured as an information device such as a smart phone, for example.

The motion analysis device 2, as shown in FIG. It includes a unit 18-2, a storage unit 19-2, a communication unit 20-2, a drive 21-2, and an imaging unit 22-2.
That is, the sensor unit 1 and the motion analysis device 2 have the same configurations of the CPU 11-1 through the drive 21-1 and the CPU 11-2 through the drive 21-2 except for the sensor unit 16-1. In the motion analysis device 2, description of the same configuration as that of the sensor unit 1 is omitted.

The motion analysis device 2 further includes an imaging unit 22-2 in addition to the CPU 11-2 to the drive 21-2.

The imaging unit 22-2 includes an optical lens unit and an image sensor (not shown).

The optical lens section is composed of a lens for condensing light, such as a focus lens and a zoom lens, in order to photograph an object.
A focus lens is a lens that forms a subject image on the light receiving surface of the image sensor. A zoom lens is a lens that can freely change the focal length within a certain range.
The imaging unit 22-2 is also provided with peripheral circuits for adjusting setting parameters such as focus, exposure, and white balance, if necessary.

The image sensor is composed of a photoelectric conversion element, an AFE (Analog Front End), and the like.
The photoelectric conversion element is composed of, for example, a CMOS (Complementary Metal Oxide Semiconductor) type photoelectric conversion element or the like. A subject image is incident on the photoelectric conversion element from the optical lens section. Therefore, the photoelectric conversion element photoelectrically converts (pictures) a subject image, accumulates an image signal for a certain period of time, and sequentially supplies the accumulated image signal to the AFE as an analog signal.
The AFE executes various signal processing such as A/D (Analog/Digital) conversion processing on this analog image signal. A digital signal is generated by various signal processing and output as an output signal of the imaging unit 22 .
Such an output signal of the imaging unit 22-2 is hereinafter referred to as "captured image data". The data of the captured image is appropriately supplied to the CPU 11-2, an image processing unit (not shown), and the like.

The motion analysis device 2 configured in this manner has a function of easily specifying a golf swing portion by using various thresholds for the sensor information acquired from the sensor unit 1 .

In the motion analysis device 2, first, the [resting state] (Status0) is specified from the sensor information (in this embodiment), and the state in which the backswing is started from the specified resting state [motion start state] (Status1). , a series of motions that are likely to be a swing are specified as a [swing candidate] (Status 2) from a series of motions including the specified stationary state, and finally whether the swing candidate corresponds to a [swing] (Status 3) is specified. .
That is, in the motion analysis device 2, under the four statuses of [resting state], [movement start state], [swing candidate], and [swing], a threshold corresponding to each status (threshold A . . . , D) to identify swings.

なお、「ｘ」はＸ軸の角速度の値であり、「ｙ」はＹ軸の角速度の値であり、「ｚ」はＺ軸の角速度の値である。 FIG. 4 is a schematic diagram for explaining a method of specifying a swing according to this embodiment.
In specifying the swing, first, among the acquired sensor information, the values of the angular velocities of the X-axis, the Y-axis, and the Z-axis are combined to calculate a combined gyro value.
The combined gyro value J is calculated using the following formula (1).

Here, "x" is the value of the angular velocity of the X-axis, "y" is the value of the angular velocity of the Y-axis, and "z" is the value of the angular velocity of the Z-axis.

In this embodiment, as shown in FIG. 4, from a time-varying graph in which the calculated synthetic gyro values J are arranged in chronological order, thresholds corresponding to Status 0 to 3 are compared with the synthetic gyro value J. Identify swing parts.

[Identification of static state] (Status0)
In this Status, the swing address state is detected from the graph of the synthetic gyro value J that changes along the time series.
In the present embodiment, when the player is in a stationary state continuously for a predetermined time, the stationary state continuously performed for a predetermined period of time is specified as a swing address state with a high possibility.
For example, a state in which the threshold A (the threshold value (strength) for determining the stationary state) is below the threshold value Ta (the threshold value (time) for determining the stationary state) is detected as the stationary state. To identify the quiescent state, threshold A is used first and is the lowest value among the thresholds. The threshold Ta is a value that is the time required for a general golf player to address.

[Specification of operation start] (Status1)
In this Status, the point in time when the backswing starts from the address state of the swing is detected from the graph of the synthetic gyro value J that changes along the time series.
In this embodiment, after the transition from Status 0 to Status 1, if the threshold value for stationary state detection is exceeded, it is assumed that there is a high possibility that the backswing has started from the stationary state. identify when the threshold for
In identifying the motion start, for example, a state in which the synthesized gyro value J exceeds a threshold value A, which is a threshold value (strength) for determining a stationary state, is detected as the motion start point of the backswing. After this detection process is performed, the status shifts to Status2.

[Identified as a swing candidate] (Status2)
In this Status, swing candidates are detected by specifying the swing end point corresponding to the start point of the backswing detected in Status1. After starting the backswing, the swing motion goes through a certain or more instantaneous motion (impact motion), and finally ends with a finish in which a stationary state continues for a certain period of time.
In the present embodiment, the threshold C: the threshold (strength) for determining the finish, which is the resting state of the final action after the start of the backswing, is below the threshold Tc: for determining the resting state. A state that continues continuously for a threshold (time) or more is specified as a finish in the swing motion.
Threshold C is used at a timing after threshold A, and is set to a value higher than threshold A because it varies from player to player in a stationary state. The threshold Tc is a value representing the time required for a general finish, and in this embodiment, it is a value for a period shorter than the threshold Ta.

[Identified as swing] (Status 3)
In this Status, in a state (swing candidate state) in which the probability of the swing specified up to Status 2 is high, the characteristics of the swing are further determined by a threshold value, and the swing is specified as the actual swing.
1) The maximum value in the section of Status2 exceeds a threshold B: a threshold (strength) for specifying a steep value of a downswing and determining it as a swing.
2) Threshold D: The intersection with a threshold (number of times) for not determining noise data as a swing is within a specified number (5 to 10 times in this embodiment).
3) The period specified as the swing candidate is within a specified time (threshold TminTmax: threshold (time) for determining the swing time, 650 to 3000 frames in this embodiment).
If the above three conditions are met, the motion within the period is identified as a swing.
Threshold B is used in a period between threshold A and threshold C, and is the highest value among the thresholds.
Threshold D is used in a period between threshold A and threshold C, and is lower than threshold B and higher than threshold A and threshold C.
The threshold TminTmax is a value representing the time required for a typical golf player to swing from the start to the end of the swing.

FIG. 5 is a functional block diagram showing the functional configuration for executing the swing specifying process among the functional configurations of the motion analysis device 2 of FIG.
The swing identification process refers to a series of processes for detecting a swing from motion information acquired from the sensor unit 1 .

When executing the swing identification process, as shown in FIG. 5, the sensor information acquisition unit 51 and the swing identification processing unit 52 function in the CPU 11-2.

A sensor information storage unit 71 is set in one area of the storage unit 19-2.
Sensor information acquired from the sensor unit 1 is stored in the sensor information storage unit 71 .

The sensor information acquisition unit 51 can acquire sensor information stored in the sensor information storage unit 71, for example.
Specifically, the sensor information acquisition unit 51 calculates the synthesized gyro value by synthesizing the values of the X-axis, Y-axis, and Z-axis angular velocities in the sensor information using the above-described formula (1). Get J.

The swing identification processing unit 52, for example, executes processing related to identification of a swing, and uses a predetermined threshold value for each Status from the acquired sensor information to identify the timing of each action that constitutes the swing and the swing range. be able to. Specifically, in addition to specifying the swing, it is possible to specify the address, the start of the backswing, the vicinity of the finish time, and the time of the downswing as the vicinity of each motion that constitutes the swing.

6 and 7 are flowcharts for explaining the flow of swing identification processing executed by the motion analysis device 2 of FIG. 3 having the functional configuration of FIG.
The swing specifying process is started by the user's operation to start the swing specifying process on the input unit 17-2. At the start of the swing identification process, an instruction to start sensing is transmitted from the motion analysis device 2 to the sensor unit 1, and sensing is started by the sensor unit 1 according to the instruction. The sensor unit 1 sequentially transmits sensor information obtained by sensing to the motion analysis device 2 . The motion analysis device 2 receives the sensor information transmitted from the sensor unit 1 and stores it in the sensor information storage section 71 .

In step S11, the swing identification processing unit 52 sets Status to [0] (that is, initializes).

In step S<b>12 , the sensor information acquisition unit 51 acquires and reads sensor information stored in the sensor information storage unit 71 .

In step S13, the swing identification processing unit 52 determines whether or not the current Status is [0].
If Status is not [0], NO is determined in step S13, and the process proceeds to step S16.
If Status is [0], YES is determined in step S13, and the process proceeds to step S14.

In step S14, the swing identification processing unit 52 determines whether or not the combined gyro value J has been below the threshold A continuously for the time of the threshold Ta.
If the synthesized gyro value J has not been below the threshold A continuously for the time of the threshold Ta, NO is determined in step S14, and the process returns to step S12.
If the combined gyro value J is below the threshold A continuously for the time of the threshold Ta, a determination of YES is made in step S14, and the process proceeds to step S15.

In step S15, the swing identification processing unit 52 sets Status to [1]. After that, the process returns to step S12.

In step S16, the swing identification processing unit 52 determines whether or not the Status is [1].
If the Status is not [1], NO is determined in step S16, and the process proceeds to step S19.
If the Status is [1], YES is determined in step S16, and the process proceeds to step S17.

In step S<b>17 , the swing identification processing unit 52 determines whether or not the combined gyro value J exceeds the threshold A.
If the combined gyro value J does not exceed the threshold value A, NO is determined in step S18, and the process returns to step S12.
If the synthesized gyro value J exceeds the threshold value A, YES is determined in step S18, and the process proceeds to step S18.

In step S18, the swing identification processing unit 52 sets Status to [2]. After that, the process returns to step S12.

In step S19, the swing identification processing unit 52 determines whether or not the Status is [2].
If the Status is not [2], NO is determined in step S19, and the process proceeds to step S22.
If the Status is [2], YES is determined in step S19, and the process proceeds to step S20.

In step S20, the swing identification processing unit 52 determines whether or not the combined gyro value J has been below the threshold value C continuously for the time period of the threshold value Tc.
If the combined gyro value J has not been below the threshold value C continuously for the time period of the threshold value Tc, NO is determined in step S20, and the process returns to step S12.
If the combined gyro value J is below the threshold value C continuously for the time period of the threshold value Tc, YES is determined in step S20, and the process proceeds to step S21.

In step S21, the swing identification processing unit 52 sets Status to [3]. After that, the process returns to step S12.

In step S22, the swing identification processing unit 52 determines whether or not the maximum value of the combined gyro value J exceeds the threshold value B in the section of Status2.
If the maximum value of the combined gyro value J does not exceed the threshold value B in the section of Status2, NO is determined in step S22, and the process proceeds to step S26.
If the maximum value of the combined gyro value J exceeds the threshold value B in the section of Status2, YES is determined in step S22, and the process proceeds to step S23.

In step S23, the swing identification processing unit 52 determines whether or not the intersection of the synthesized gyro value J and the threshold value D is within the prescribed number of times in the section of Status2.
In the section of Status2, if the intersection of the synthesized gyro value J and the threshold value D is not within the range of the specified number of times, NO is determined in step S23, and the process proceeds to step S26.
In the section of Status2, if the intersection of the synthesized gyro value J and the threshold value D is within the specified number of times, a determination of YES is made in step S23, and the process proceeds to step S24.

In step S24, the swing identification processing unit 52 determines whether the composite gyro value J is below the threshold C continuously for a predetermined time (threshold Tc) from the start point where the composite gyro value J is below the threshold A continuously for a predetermined time (threshold Ta). It is determined whether or not the time until the end point of the lower state is within a predetermined time (the period of the threshold value TminTmax). That is, it is determined whether or not the length from the start point to the end point is within the threshold value TminTmax.
If the length from the start point to the end point is not within the threshold value TminTmax, NO is determined in step S24 and the process proceeds to step S26.
If the length from the start point to the end point is within the threshold value TminTmax, YES is determined in step S24 and the process proceeds to step S25.

In step S25, the swing identification processing unit 52 identifies the motion from the start point (Tmin) to the end point (Tmax) as a swing.

In step S26, the swing identification processing unit 52 sets Status to [0]. After that, the process returns to step S12.

By performing the processing as described above, it is possible to specify the swing range in the swing motion of the player without using the point of impact as a reference, and the swing range can be determined by a simple calculation process of comparing the synthetic gyro value J and each threshold value. It has the effect of being able to specify.

<Second embodiment>
In this example, unlike the first embodiment described above, when the downswing is specified without detecting the finish, the swing range is specified based on that time point. Therefore, more accurate address detection processing, downswing detection processing, timeout processing when downswing cannot be detected, and wait processing when downswing is detected are added. That is, in this example, since the timeout processing and the wait processing when the downswing can be detected are added, the Status is increased. Specifically, Status 0 specifies the stationary state, Status 1 specifies the start of movement, Status 2 detects downswing and time-out processing, Status 3 is wait processing when downswing can be detected, and Status 4 is the main swing. specific processing.

8 and 9 are flowcharts for explaining the flow of swing identification processing executed by the motion analysis device 2 of FIG. 3 having the functional configuration of FIG.
Since steps S41 to S49 are performed in the same manner as in the first embodiment, the added flow portion will be described in detail with reference to FIGS. 8 and 9. FIG.

[Operation start identification and address detection processing]
In step S47, the swing identification processing unit 52 determines whether or not the current composite gyro value J exceeds the threshold value A for determining the stationary state, and identifies movement start.
If the threshold A is not exceeded, NO is determined in step S47, and the process returns to step S42.
If it exceeds the threshold A, YES is determined in step S47, and the process proceeds to step S48.

In step S48, the swing identification processing unit 52 sets Status to [2]. After that, the process proceeds to step S49.

[Address specific processing]
In step S49, the swing identification processing unit 52 identifies from the graph of the combined gyro value J the time t seconds before the motion start time as the address start time, and then the process returns to step S42.
At this time, the value of t may be a value arbitrarily set by the user, or a fixed value stored in the storage unit 19-2 in advance may be used.

[Timeout processing when downswing could not be detected]
In step S51, the swing identification processing unit 52 determines that the time in the Status 2 state is the threshold value Tα (in the present embodiment, 1.5 seconds to 1.5 seconds within a range not exceeding at least 3 seconds). 2.5 seconds, and when converted to the number of determination processes, it is determined whether or not it exceeds 300 to 500 times.
When the state of Status2 continues for a predetermined time, YES is determined in step S51, and the process proceeds to step S52.
If the state of Status2 has not continued for the predetermined time, NO is determined in step S51, and the process proceeds to step S53.

In step S52, the swing identification processing unit 52 sets Status to [0]. After that, the process returns to step S42.

[Waggle detection processing]
In step S53, the swing identification processing unit 52 determines whether or not the combined gyro value J has been below the threshold value A continuously for the time period of the threshold value Ta.
If the synthesized gyro value J has not been below the threshold A continuously for the time of the threshold Ta, NO is determined in step S53, and the process proceeds to step S55.
If the synthesized gyro value J is below the threshold A continuously for the time of the threshold Ta, a determination of YES is made in step S53, and the process proceeds to step S54.

In step S54, the swing identification processing unit 52 sets Status to [1]. After that, the process returns to step S42.

[Downswing detection process]
In step S55, the swing identification processing unit 52 determines whether or not the difference between the current composite gyro value J and the average value of the composite gyro values J a predetermined time ago (N times before) exceeds a threshold value E. . In this embodiment, the predetermined time before is defined as 10 times before, and the threshold value E is set to 0.5. However, the values are not limited to the above values, and may be configured to be adjusted according to individual swing specifications.
If the threshold E is not exceeded, NO is determined in step S55, and the process returns to step S42.
If the threshold value E is exceeded, YES is determined in step S55, and the process proceeds to step S56.

In step S56, the swing identification processing unit 52 sets Status to [3]. After that, the process returns to step S42.

[Wait processing when downswing is detected]
In step S58, the swing identification processing unit 52 determines that the time spent in the Status 3 state is the threshold value Tβ (in the present embodiment, at least 1.5 seconds to 2.5 seconds within a range not exceeding 3.0 seconds). Yes, and when converted to the number of times of determination processing, it is determined whether or not it exceeds 400 times to 500 times).
If the time spent in the Status 3 state does not exceed the threshold Tβ time, NO is determined in step S58, and the process returns to step S42.
If the time spent in the Status 3 state exceeds the time of the threshold value Tβ, YES is determined in step S58, and the process proceeds to step S59. After that, the swing identification processing unit 52 sets the Status to [4].

In step S59, the swing identification processing unit 52 sets Status to [4]. After that, the process returns to step S42.

The motion analysis device 2 configured as described above includes a sensor information acquisition unit 51 and a swing identification processing unit 52 .
The sensor information acquisition unit 51 acquires sensor information, which is exercise information, from the sensor unit 1 that senses a series of motions by the subject.
The swing identification processing unit 52 does not detect the point of time of the maximum or minimum value of the amount of exercise from the exercise information, but based on the exercise information acquired by the sensor information acquisition unit 51 and a predetermined threshold value, determines the start point of the motion. and end point.
Further, the swing identification processing unit 52 identifies a motion within the range of the motion based on the start time and end time of the specified motion.
As a result, the motion analysis device 2 can easily identify the movement range of the swing with high accuracy.

The swing identification processing unit 52 determines whether or not the time range between the identified start time and end time is valid.
As a result, the motion analysis device 2 can easily identify the movement range of the swing with high accuracy.

Sensor information, which is motion information, includes information on angular velocity or acceleration as the amount of motion.
If the angular velocity or acceleration exceeds a predetermined threshold a predetermined number of times in the time range between the identified start time and end time, the swing identification processing unit 52 determines that the time range is valid.
As a result, the motion analysis device 2 can easily specify the motion range of the swing with high accuracy based on the angular velocity or the acceleration.

A series of motions by the subject includes specific postures.
The swing identification processing unit 52 determines that the time range is valid when a specific posture is included in the time range of the exercise information.
As a result, the motion analysis device 2 can easily identify the movement range of the swing with high accuracy.

The swing identification processing unit 52 determines that the time range is valid when the time range of the motion information includes the time point of the maximum value or the minimum value of the amount of motion.
As a result, the motion analysis device 2 can easily identify the movement range of the swing with high accuracy.

The swing identification processing unit 52 determines that the time range is invalid when the elapsed time from the start of the motion to the end of the motion exceeds a predetermined length.
As a result, the motion analysis device 2 can determine that the probability of the specific motion is low.

The sensor information acquisition unit 51 acquires sensor information, which is exercise information, in real time for each sensing by the sensor unit 1 .
The swing identification processing unit 52 identifies the start point and the end point of the motion when the sensor information acquisition unit 51 acquires sensor information, which is exercise information.
As a result, the motion analysis device 2 can specify the motion in real time.

The motion analysis device 2 further includes a communication unit 20-2 that transmits sensor information, which is motion information within a range including the start and end times of the series of motions identified by the swing identification processing unit 52, to an external device.
As a result, in the motion analysis device 2, the amount of data to be stored and transmitted can be reduced.

The swing identification processing unit 52 can change the timing of starting the motion of the target person, and changes the timing retroactive from the identified timing of starting the motion as the start time of the motion.
Thereby, the address can be specified in the motion analysis device 2 .

The target person's motion is a swing motion including at least a downswing.
The swing identification processing unit 52 identifies the timing of the subject's downswing based on the exercise information and the predetermined threshold, and when the downswing is identified, the timing after a predetermined time has passed from the timing when the downswing was identified is determined. Identifies the end point of the subject's movement.
Thereby, the downswing can be specified in the motion analysis device 2 .

The swing identification processing unit 52 stops the identification processing when the timing of the movement start of the target person is identified and the timing of the downswing by the target person is not identified.
Accordingly, in the motion analysis device 2, the processing can be stopped in the middle of the processing when the downswing is not identified.

The predetermined threshold includes a value set by the user or a value set based on motion information sensed in the past.
As a result, in the motion analysis device 2, individual user settings can be reflected, and values can be automatically set based on swing history.

It should be noted that the present invention is not limited to the above-described embodiments, and includes modifications, improvements, and the like within the scope of achieving the object of the present invention.

In the above-described embodiment, the value of the threshold D is determined by the statistics of the noise data and the actual swing. You may make it change.
Also, the number of intersections with the threshold D is determined by the statistics of the noise data and the actual swing. Therefore, in the present embodiment, the specified value is set to 2 times, but a range may be provided, for example, 5 times to 10 times or less. Also, since there is no swing without an intersection point, at least one swing may be set, or more than 10 swings may be set in consideration of various swing variations. Further, the number of times may be increased when a downswing is detected early or when a finishing action is detected.

Further, in the above-described embodiment, the threshold value (strength, number of times, time, etc.) is configured to be defined by a value derived from statistical data, but the user can arbitrarily set the threshold according to the tendency of the individual swing. It may be configured to be changeable.

Further, in the above-described embodiment, the threshold values (intensity, number of times, time, etc.) are defined by values derived from statistical data. The threshold value may be set according to data obtained by analyzing the swing motion (motion rhythm and motion speed) by performing image analysis on the image. At this time, a known and commonly used general technique is used for the image analysis technique.

Further, in the above-described embodiment, the threshold value (strength, number of times, time, etc.) is configured to be defined by a value derived from statistical data, but the user can arbitrarily set the threshold according to the tendency of the individual swing. It may be configured to be changeable.

Further, in the above-described embodiment, the swing identification process is executed by the motion analysis device 2, but it may be configured to be executed by the sensor unit 1, an external server, or the like.

Moreover, in the above-described embodiment, the sensor unit 1 is configured separately from the motion analysis device 2 , but may be a part of the motion analysis device 2 .

Further, in the above-described embodiment, the motion analysis device 2 to which the present invention is applied has been described as an example of a smart phone, but it is not particularly limited to this.
For example, the present invention can be applied to general electronic devices having a swing specific processing function. Specifically, for example, the present invention is applicable to notebook personal computers, printers, television receivers, video cameras, portable navigation devices, mobile phones, digital cameras, smart watches, portable game machines, and the like. .

The series of processes described above can be executed by hardware or by software.
In other words, the functional configuration of FIG. 5 is merely an example and is not particularly limited. That is, it is sufficient that the motion analysis device 2 has a function capable of executing the series of processes described above as a whole, and what kind of functional block is used to realize this function is not particularly limited to the example of FIG. .
Also, one functional block may be composed of hardware alone, software alone, or a combination thereof.
The functional configuration in this embodiment is realized by a processor that executes arithmetic processing, and processors that can be used in this embodiment are composed of various single processing units such as single processors, multiprocessors, and multicore processors. In addition, it includes a combination of these various processing devices and a processing circuit such as ASIC (Application Specific Integrated Circuit) or FPGA (Field-Programmable Gate Array).

When a series of processes is to be executed by software, a program constituting the software is installed in a computer or the like from a network or a recording medium.
The computer may be a computer built into dedicated hardware. The computer may also be a computer capable of executing various functions by installing various programs, such as a general-purpose personal computer.

A recording medium containing such a program is not only constituted by the removable medium 31-2 of FIG. It consists of a recording medium, etc. provided to the user in the The removable medium 31 is composed of, for example, a magnetic disk (including a floppy disk), an optical disk, or a magneto-optical disk. Optical discs are composed of, for example, CD-ROMs (Compact Disk-Read Only Memory), DVDs (Digital Versatile Disks), Blu-ray (registered trademark) Discs, and the like. The magneto-optical disk is composed of an MD (Mini-Disk) or the like. Further, the recording medium provided to the user in a state of being pre-installed in the device main body is, for example, the ROM 12-2 in FIG. Configured.

In this specification, the steps of writing a program recorded on a recording medium are not only processes that are performed chronologically in that order, but also processes that are not necessarily chronologically processed, and that are performed in parallel or individually. It also includes the processing to be executed.
Further, in this specification, the term "system" means an overall device composed of a plurality of devices, a plurality of means, or the like.

Although several embodiments of the present invention have been described above, these embodiments are merely examples and do not limit the technical scope of the present invention. The present invention can take various other embodiments, and various modifications such as omissions and substitutions can be made without departing from the gist of the present invention. These embodiments and modifications thereof are included in the scope and gist of the invention described in this specification and the like, and are included in the scope of the invention described in the claims and equivalents thereof.

The invention described in the scope of claims at the time of filing of the present application will be additionally described below.
[Appendix 1]
Acquisition means for acquiring exercise information from a sensor device attached to a subject and sensing a series of motions by the subject;
a point of time at which the motion starts and ends based on the motion information acquired by the acquisition means and a predetermined threshold value without detecting the time point of the maximum or minimum value of the amount of motion from the motion information; 1 identifying means;
A motion analysis device comprising:
[Appendix 2]
Further comprising determining means for determining whether the time range between the start time and the end time specified by the first specifying means is valid,
The motion analysis device according to Supplementary Note 1, characterized by:
[Appendix 3]
The motion information includes information on angular velocity or acceleration as the momentum,
If the angular velocity or the acceleration exceeds a predetermined threshold a predetermined number of times in the time range between the start time point and the end time point identified by the first identification means, the determination means determines that the time range is valid. determine that
The motion analysis device according to appendix 2, characterized by:
[Appendix 4]
The series of actions by the subject includes a specific posture,
The determination means determines that the time range is valid when the specific posture is included in the time range in the exercise information.
The motion analysis device according to appendix 2 or 3, characterized by:
[Appendix 5]
The determination means determines that the time range is valid when the time range in the exercise information includes a time point of the maximum value or the minimum value of the amount of exercise.
The motion analysis device according to any one of appendices 2 to 4, characterized by:
[Appendix 6]
The determination means determines that the first range is invalid when the elapsed time from the start of the action to the end of the action exceeds a predetermined length.
The motion analysis device according to any one of appendices 2 to 5, characterized by:
[Appendix 7]
The acquisition means acquires the exercise information in real time for each sensing by the sensor device,
The first specifying means specifies a start point and an end point of the motion when the exercise information is acquired by the acquisition means.
The motion analysis device according to any one of appendices 1 to 6, characterized by:
[Appendix 8]
Further comprising transmission means for transmitting exercise information in a range including the start time and end time of the series of actions specified by the first specifying means to an external device,
The motion analysis device according to any one of appendices 1 to 7, characterized by:
[Appendix 9]
Further comprising a first change means for changing the timing of the target person's movement start specified by the first specifying means,
The first changing means changes the timing, which is a predetermined time before the operation start timing specified by the first specifying means, as the operation start time.
The motion analysis device according to any one of appendices 1 to 8, characterized by:
[Appendix 10]
the motion of the subject is a swing motion including at least a downswing;
A second identifying means for identifying the subject's downswing based on the exercise information and the predetermined threshold;
When the downswing is specified by the second specifying means, the first specifying means specifies a timing when a predetermined time has passed from the timing when the downswing is specified as the end point of the motion of the subject. ,
The motion analysis device according to any one of appendices 1 to 9, characterized by:
[Appendix 11]
The first specifying means stops the specifying process when the target person's motion start timing is specified and the target person's downswing timing is not specified.
The motion analysis device according to appendix 10, characterized by:
[Appendix 12]
The predetermined threshold includes a value set by the user or a value set based on previously sensed exercise information,
The motion analysis device according to any one of appendices 1 to 11, characterized by:
[Appendix 13]
A motion analysis method executed by a motion analysis device,
an acquisition step of acquiring exercise information from a sensor device attached to a subject and sensing a series of motions of the subject;
Identifying the start and end points of the motion based on the motion information acquired in the acquiring step and a predetermined threshold value without detecting the time point of the maximum or minimum value of the amount of exercise from the motion information. a step;
A motion analysis method comprising:
[Appendix 14]
A computer that controls the motion analysis device,
Acquisition means for acquiring exercise information from a sensor device attached to a subject and sensing a series of motions of the subject;
Identifying the start and end points of the motion based on the motion information acquired by the acquisition means and a predetermined threshold without detecting the time point of the maximum or minimum value of the amount of motion from the motion information. means,
A program characterized by functioning as

DESCRIPTION OF SYMBOLS 1... Motion analysis apparatus, 2... Sensor unit, 11... CPU, 12... ROM, 13... RAM, 14... Bus, 15... Input/output interface, 16... Sensor unit 17 Input unit 18 Output unit 19 Storage unit 20 Communication unit 21 Drive 22 Imaging unit 31 Removable Media, 51...Sensor information acquisition unit, 52...Swing identification processing unit, 71...Sensor information storage unit, S...Kinematic analysis system

Claims (5)

Acquisition means for acquiring exercise information from a sensor device that is attached to a subject and that senses a series of golf swings by the subject from the start to the end of the golf swing;
The motion information is processed using an intensity threshold indicating the strength of the motion information, a frequency threshold indicating how many times the motion information has occurred, and a time threshold indicating how long the motion information has continued. and identifying means for identifying a plurality of states in the golf swing by determining
The identification means identifies a resting state that identifies a resting state before starting the golf swing, and determines the point at which the strength threshold for detecting the resting state is exceeded when the backswing in the golf swing is started. A plurality of states including specifying the start of the motion to be detected as the time point of the golf swing, specifying a candidate for specifying a candidate for the main swing in the golf swing, and specifying a motion for specifying whether the candidate corresponds to the main swing. identificationand furthermore,
The identifying means identifies the stationary state when the motion information is below the threshold A, which is the intensity threshold, for a period of time equal to or longer than the threshold Ta, which is the time threshold, and
detecting a state in which the motion information exceeds the threshold value A as a time point at which the backswing is started, and specifying the start of the motion;
At a timing after the stationary state, the state in which the motion information is lower than the threshold value C, which is the intensity threshold value higher than the threshold value A, is defined as a threshold value, which is the time threshold value shorter than the threshold value Ta. If it continues for Tc or more, it is determined that the golf swing has ended, and the period from the start of the golf swing to the end of the golf swing is specified as the candidate for the main swing.
A motion analysis device characterized by: In the candidate for the main swing, the identifying means determines whether the motion information exceeds the threshold D after the motion information crosses the threshold D, which is the strength threshold higher than the threshold C, equal to or less than the threshold of the number of times. is greater than the threshold B, which is the strength threshold, and the period specified as the candidate for the main swing is within the threshold TminTmax, which is the threshold for the time longer than the sum of the Ta and the Tc. identifying the candidate as the main swing;
The motion analysis device according to claim 1 , characterized in that: The intensity threshold, the number of times threshold, and the time threshold include values set by the user or values set based on previously sensed exercise information,
The motion analysis device according to claim 1 or 2 , characterized in that: A motion analysis method executed by a motion analysis device,
an acquisition step of acquiring exercise information from a sensor device attached to a subject and sensing a series of golf swings of the subject for a period from the start to the end of the golf swing;
Using an intensity threshold indicating the strength of the exercise information, a frequency threshold indicating how many times the exercise information occurred, and a time threshold indicating how long the exercise information continued. identifying a plurality of conditions in the golf swing by determining;
The identifying step includes identifying a resting state that identifies a resting state before starting the golf swing, and determining the point at which the strength threshold for detecting the resting state is exceeded when the backswing in the golf swing is started. A plurality of states including specifying the start of the motion to be detected as the time point, specifying the candidate for specifying the candidate for the main swing in the golf swing, and specifying the motion for specifying whether the candidate corresponds to the main swing. specify and further
In the specifying step, if the motion information is below the intensity threshold A for a period of time equal to or longer than the time threshold Ta, the stationary state is specified;
detecting a state in which the motion information exceeds the threshold value A as a time point at which the backswing is started, and specifying the start of the motion;
At a timing after the stationary state, the state in which the motion information is lower than the threshold value C, which is the intensity threshold value higher than the threshold value A, is determined as a threshold value, which is the time threshold value shorter than the threshold value Ta. If it continues for Tc or more, it is determined that the golf swing is finished, and the period from the start of the golf swing to the end of the golf swing is specified as the candidate for the main swing.
A motion analysis method characterized by: A computer that controls the motion analysis device,
Acquisition means for acquiring exercise information from a sensor device that is attached to a subject and that senses a series of golf swings of the subject for a period from the start to the end of the golf swing;
The motion information is processed using an intensity threshold indicating the strength of the motion information, a frequency threshold indicating how many times the motion information has occurred, and a time threshold indicating how long the motion information has continued. A program that functions as a specifying means for specifying a plurality of states in the golf swing by determining,
The identification means identifies a resting state that identifies a resting state before starting the golf swing, and determines the point at which the strength threshold for detecting the resting state is exceeded when the backswing in the golf swing is started. A plurality of states including specifying the start of the motion to be detected as the time point of the golf swing, specifying a candidate for specifying a candidate for the main swing in the golf swing, and specifying a motion for specifying whether the candidate corresponds to the main swing. identificationand furthermore,
The identification means identifies the stationary state when the motion information is below the threshold A, which is the intensity threshold, for a period of time equal to or longer than the threshold Ta, which is the time threshold, and
detecting a state in which the motion information exceeds the threshold value A as a time point at which the backswing is started, and specifying the start of the motion;
At a timing after the stationary state, the state in which the motion information is lower than the threshold value C, which is the intensity threshold value higher than the threshold value A, is determined as a threshold value, which is the time threshold value shorter than the threshold value Ta. If it continues for Tc or more, it is determined that the golf swing is finished, and the period from the start of the golf swing to the end of the golf swing is specified as the candidate for the main swing.
A program characterized by

Images