CN111803902B - Swimming stroke identification method and device, wearable device and storage medium - Google Patents
Swimming stroke identification method and device, wearable device and storage medium Download PDFInfo
- Publication number
- CN111803902B CN111803902B CN201910284643.6A CN201910284643A CN111803902B CN 111803902 B CN111803902 B CN 111803902B CN 201910284643 A CN201910284643 A CN 201910284643A CN 111803902 B CN111803902 B CN 111803902B
- Authority
- CN
- China
- Prior art keywords
- acceleration data
- data
- axis
- swimming
- determining
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B71/00—Games or sports accessories not covered in groups A63B1/00 - A63B69/00
- A63B71/06—Indicating or scoring devices for games or players, or for other sports activities
- A63B71/0605—Decision makers and devices using detection means facilitating arbitration
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2220/00—Measuring of physical parameters relating to sporting activity
- A63B2220/30—Speed
- A63B2220/34—Angular speed
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2220/00—Measuring of physical parameters relating to sporting activity
- A63B2220/40—Acceleration
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2220/00—Measuring of physical parameters relating to sporting activity
- A63B2220/80—Special sensors, transducers or devices therefor
- A63B2220/803—Motion sensors
-
- A—HUMAN NECESSITIES
- A63—SPORTS; GAMES; AMUSEMENTS
- A63B—APPARATUS FOR PHYSICAL TRAINING, GYMNASTICS, SWIMMING, CLIMBING, OR FENCING; BALL GAMES; TRAINING EQUIPMENT
- A63B2220/00—Measuring of physical parameters relating to sporting activity
- A63B2220/80—Special sensors, transducers or devices therefor
- A63B2220/83—Special sensors, transducers or devices therefor characterised by the position of the sensor
- A63B2220/836—Sensors arranged on the body of the user
Abstract
The embodiment of the invention discloses a swimming stroke identification method and device, wearable equipment and a storage medium. The method comprises the following steps: the method comprises the steps of obtaining motion data of a user during swimming, collected by a six-axis sensor in wearable equipment, wherein the motion data comprise three-axis acceleration data and three-axis angular velocity data, analyzing the three-axis acceleration data, determining a peak point or a valley point of main shaft acceleration data, and determining the swimming posture of the user according to the three-axis acceleration data and the three-axis angular velocity data between adjacent peak points or adjacent valley points. Compared with the prior art, the embodiment of the invention selects the peak point or the valley point of the main shaft acceleration data based on the analysis of the three-axis acceleration data, and determines the swimming stroke of the user based on the three-axis acceleration data and the three-axis angular velocity data between the adjacent peak points or the adjacent valley points, thereby realizing the automatic identification of the swimming stroke.
Description
Technical Field
The embodiment of the invention relates to the technical field of automatic identification, in particular to a swimming stroke identification method and device, wearable equipment and a storage medium.
Background
Swimming as an aerobic exercise is helpful for enhancing resistance, improving the cardiovascular system, improving the lung capacity and the like, and is popular with the majority of users.
Along with the continuous progress of waterproof technique, be applied to swimming with wearable equipment and move, discern the motion state of swimming in order to satisfy user's demand, become current hotspot. At present, some intelligent watches or bracelets emerge in the market, and these intelligent watches or bracelets are focused on drowning and are reminded, have certain restriction in the aspect of motion state recognition.
Disclosure of Invention
The embodiment of the invention provides a swimming stroke identification method and device, wearable equipment and a storage medium, which are used for identifying a swimming stroke of a user.
In a first aspect, an embodiment of the present invention provides a swimming stroke recognition method, including:
the method comprises the steps of obtaining motion data of a user during swimming, wherein the motion data are collected by six sensors in wearable equipment and comprise triaxial acceleration data and triaxial angular velocity data;
analyzing the triaxial acceleration data, and determining a peak point or a valley point of the main shaft acceleration data;
and determining the swimming postures of the user according to the triaxial acceleration data and the triaxial angular velocity data between the adjacent peak points or the adjacent valley points.
Further, the analyzing the triaxial acceleration data to determine a peak point or a valley point of the spindle acceleration data includes:
determining main shaft acceleration data according to the fluctuation range of the acceleration data of each shaft;
and determining a peak point or a valley point of the spindle acceleration data according to a preset detection rule.
Further, the determining the spindle acceleration data according to the fluctuation range of the acceleration data of each axis includes:
comparing the fluctuation range of the acceleration data of each axis with the set range threshold value;
and taking the axis with the fluctuation amplitude larger than the set amplitude threshold value as a main axis, and taking the acceleration data corresponding to the axis as main axis acceleration data.
Further, the determining a peak point or a valley point of the spindle acceleration data according to a preset detection rule includes:
filtering the spindle acceleration data;
and detecting a peak point or a valley point of the filtered main shaft acceleration data to obtain a corresponding peak point or a corresponding valley point.
Further, the determining the swimming stroke of the user according to the triaxial acceleration data and the triaxial angular velocity data between adjacent peak points or valley points includes:
extracting data characteristics of triaxial acceleration data and triaxial angular velocity data between adjacent peak points or adjacent valley points;
And taking the data characteristics as the input of a preset swimming stroke model, acquiring the swimming stroke output by the preset swimming stroke model as the current swimming stroke of the user.
In a second aspect, an embodiment of the present invention further provides a swimming stroke recognition device, where the device includes:
the wearable device comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring motion data of a user during swimming, which is acquired by six sensors in the wearable device, and the motion data comprises three-axis acceleration data and three-axis angular velocity data;
the peak-valley value determining module is used for analyzing the triaxial acceleration data and determining a peak value point or a valley value point of the main shaft acceleration data;
and the swimming stroke determining module is used for determining the swimming stroke of the user according to the three-axis acceleration data and the three-axis angular velocity data between the adjacent peak points or the adjacent valley points.
Further, the peak-to-valley value determination module includes:
the first determining unit is used for determining the acceleration data of the main shaft according to the fluctuation range of the acceleration data of each shaft;
and the second determining unit is used for determining a peak point or a valley point of the spindle acceleration data according to a preset detection rule.
Further, the first determining unit includes:
the comparison subunit is used for comparing the fluctuation amplitude of the acceleration data of each axis with the set amplitude threshold value;
And the main shaft determining subunit is used for taking the shaft with the fluctuation amplitude larger than the set amplitude threshold value as the main shaft and taking the acceleration data corresponding to the shaft as the main shaft acceleration data.
In a third aspect, an embodiment of the present invention further provides a wearable device, including:
the device comprises a six-axis sensor, a three-axis sensor and a controller, wherein the six-axis sensor is used for collecting motion data of a user during swimming, and the motion data comprises three-axis acceleration data and three-axis angular velocity data;
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a method of swim gesture recognition as described in the first aspect.
In a fourth aspect, an embodiment of the present invention further provides a storage medium, on which a computer program is stored, where the program, when executed by a controller, implements the swimming stroke recognition method according to the first aspect.
The embodiment of the invention provides a swimming stroke identification method, a device, wearable equipment and a storage medium, wherein the swimming stroke identification method comprises the steps of acquiring motion data of a user during swimming, which is acquired by a six-axis sensor in the wearable equipment, analyzing the three-axis acceleration data to determine a peak point or a valley point of main axis acceleration data, and determining the swimming stroke of the user according to the three-axis acceleration data and the three-axis angular velocity data between adjacent peak points or valley points. Compared with the prior art, the embodiment of the invention selects the peak point or the valley point of the main shaft acceleration data based on the analysis of the three-axis acceleration data, and determines the swimming stroke of the user based on the three-axis acceleration data and the three-axis angular velocity data between the adjacent peak points or the adjacent valley points, thereby realizing the automatic identification of the swimming stroke.
Drawings
Fig. 1 is a flowchart of a swimming stroke recognition method according to an embodiment of the present invention;
fig. 2 is a flowchart of a swimming stroke recognition method according to a second embodiment of the present invention;
fig. 3 is a schematic diagram of a three-axis acceleration data waveform according to a second embodiment of the present invention;
fig. 4 is a schematic waveform diagram of filtered spindle acceleration data according to a second embodiment of the present invention;
fig. 5 is a schematic diagram of a peak point detection result provided in the second embodiment of the present invention;
fig. 6 is a flowchart illustrating an implementation of swimming stroke recognition according to a second embodiment of the present invention;
fig. 7 is a structural diagram of a swimming stroke recognition device according to a third embodiment of the present invention;
fig. 8 is a structural diagram of a wearable device according to a fourth embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the accompanying drawings and examples. It is to be understood that the specific embodiments described herein are merely illustrative of the invention and are not limiting of the invention. It should be further noted that, for the convenience of description, only some of the structures related to the present invention are shown in the drawings, not all of the structures. In addition, the embodiments and features of the embodiments in the present invention may be combined with each other without conflict.
Example one
Fig. 1 is a flowchart of a swimming stroke recognition method according to an embodiment of the present invention, where the embodiment is applicable to recognition of a motion state, especially to a swimming stroke recognition situation, and the method may be executed by a swimming stroke recognition device, where the device may be implemented by software and/or hardware, and is generally integrated in a wearable device, such as a smart watch or a bracelet, and specifically, the method includes the following steps:
s110, acquiring motion data of the user during swimming, wherein the motion data are acquired by six sensors in the wearable device and comprise triaxial acceleration data and triaxial angular velocity data.
A wearable device is a portable device, such as a smart band or watch, worn directly on the body or integrated into a user's clothing or accessory. The six-axis sensor is specifically a six-axis motion sensor and is used for collecting motion data of a user during swimming, wherein the three-axis acceleration data are acceleration data in three different directions and can be measured by one three-axis acceleration sensor or by three single-axis acceleration sensors respectively measuring the acceleration data in the three directions to obtain the three-axis acceleration data, similarly, the three-axis angular velocity data can be measured by one three-axis angular velocity sensor or by three single-axis angular velocity sensors respectively measuring the angular velocities in the three directions to obtain the three-axis angular velocity data, optionally, the three-axis acceleration data and the three-axis angular velocity data are respectively measured by the three-axis accelerometer and the three-axis gyroscope in the embodiment, and the models of the three-axis accelerometer and the three-axis gyroscope are not limited.
It can be understood that, the position and the direction that intelligent bracelet or wrist-watch were worn to different users are different, and when adding swimming, the action of paddling is different, and the triaxial accelerometer that this embodiment adopted can acquire the acceleration data of three direction simultaneously, compares with the acceleration data that simply acquires a direction, can improve the degree of accuracy that follow-up swimming stroke judged. The three-axis gyroscope is sensitive to the change of angles, can acquire the detail characteristics of the hands and the wrist of a user, and improves the accuracy of swimming stroke recognition by the cooperation of the three-axis accelerometer and the three-axis gyroscope.
And S120, analyzing the triaxial acceleration data, and determining a peak point or a valley point of the main shaft acceleration data.
The main axis is an axis with the largest fluctuation amplitude of the acceleration data, that is, the axis with the most obvious characteristics, the main axis acceleration data is the acceleration data corresponding to the main axis, for example, the acceleration data in three directions acquired by the three-axis accelerometer are the acceleration data corresponding to the X axis, the Y axis and the Z axis, if the fluctuation amplitude of the acceleration data in the X axis is greater than the fluctuation amplitudes of the acceleration data in the Y axis and the Z axis, the X axis is called the main axis, and the acceleration data corresponding to the X axis is called the main axis acceleration data. The peak point is a point corresponding to a peak in the waveform of the spindle acceleration data, the valley point is a point corresponding to a valley in the waveform of the spindle acceleration data, and the peak point or the valley point of the spindle acceleration data can be determined according to a peak-valley point detection algorithm.
The swimming posture is determined based on the stroke motion, different users have different stroke motions, the acceleration data of the three directions acquired by the three-axis accelerometer are different for the same user, the periods corresponding to the three directions are also different, therefore, the embodiment selects the axis with the largest fluctuation range, namely the axis with the most obvious characteristic as the main axis based on the fluctuation range of the acceleration data of the three directions, the period corresponding to the acceleration data of the axis is taken as the standard, the swimming posture of the user is determined based on the motion data in the period, and the accuracy of swimming posture identification is improved.
S130, determining the swimming posture of the user according to the three-axis acceleration data and the three-axis angular velocity data between the adjacent peak points or the adjacent valley points.
After the peak point or the valley point is determined, the swimming posture of the user can be determined according to the motion data between the adjacent peak points or the adjacent valley points, namely the triaxial acceleration data and the triaxial angular velocity data. Optionally, a pre-trained swimming stroke determination model may be adopted, the motion data between adjacent peak points or adjacent valley points is input into the model, and the model outputs the swimming stroke as the current swimming stroke of the user. Or extracting the data characteristics of the motion data between adjacent peak points or adjacent valley points, matching the data characteristics with the pre-stored data characteristics of known swimming gestures, and determining the current swimming gesture of the user according to the matching result. The swimming stroke of the present embodiment includes, but is not limited to, breaststroke, freestyle stroke, backstroke, and butterfly stroke.
The embodiment of the invention provides a swimming stroke identification method, which comprises the steps of acquiring motion data of a user during swimming, which is acquired by a six-axis sensor in wearable equipment, analyzing the three-axis acceleration data, determining a peak point or a valley point of main axis acceleration data, and determining the swimming stroke of the user according to the three-axis acceleration data and the three-axis angular velocity data between adjacent peak points or adjacent valley points. Compared with the prior art, the embodiment of the invention selects the peak point or the valley point of the main shaft acceleration data based on the analysis of the three-axis acceleration data, and determines the swimming stroke of the user based on the three-axis acceleration data and the three-axis angular velocity data between the adjacent peak points or the adjacent valley points, thereby realizing the automatic identification of the swimming stroke.
Example two
Fig. 2 is a flowchart of a swimming stroke recognition method according to a second embodiment of the present invention, which is embodied on the basis of the second embodiment, and specifically, the method includes the following steps:
s210, acquiring the motion data of the user during swimming, which is acquired by a six-axis sensor in the wearable device, wherein the motion data comprises three-axis acceleration data and three-axis angular velocity data.
And S220, determining the acceleration data of the main shaft according to the fluctuation range of the acceleration data of each shaft.
Exemplarily, referring to fig. 3, fig. 3 is a schematic diagram of a three-axis acceleration data waveform according to a second embodiment of the present invention. It can be seen that the fluctuation amplitudes of the three axis acceleration data are different, and based on the fluctuation amplitudes, the main axis and the main axis acceleration data can be determined. Specifically, the spindle acceleration data may be determined as follows:
comparing the fluctuation range of the acceleration data of each axis with the set range threshold value;
and taking the axis with the fluctuation amplitude larger than the set amplitude threshold value as a main axis, and taking the acceleration data corresponding to the axis as main axis acceleration data.
Specifically, the fluctuation ranges of the three axis acceleration data may be respectively compared with a set threshold, an axis having a fluctuation range greater than the set threshold may be used as a main axis, and the acceleration data of the axis may be used as main axis acceleration data, where the set threshold may be a fluctuation range, that is, if the fluctuation range of the acceleration data of a certain axis exceeds the set fluctuation range, the axis may be used as a main axis, and the fluctuation range may be set according to actual needs. As can be seen from fig. 3, the fluctuation range of the X axis is the largest, the characteristic is obvious, the X axis is selected as the main axis, and the acceleration data of the X axis is used as the main axis acceleration data.
And S230, determining a peak point or a valley point of the spindle acceleration data according to a preset detection rule.
The preset detection rule is used for detecting a peak point or a valley point of the spindle acceleration data, and can be a peak-valley detection algorithm realized by Python, and filtering processing is required before peak-valley point detection considering the existence of noise in a swimming environment. Accordingly, S230 may be embodied as:
filtering the spindle acceleration data;
and detecting a peak point or a valley point of the filtered main shaft acceleration data to obtain a corresponding peak point or a corresponding valley point.
The filtering mode can be designed according to practical situations, for example, a low-pass filter can be selected to filter out high-frequency noise of the spindle acceleration data, wherein the low-pass filter includes but is not limited to a Bessel filter, a Chebyshev filter and a Butterworth filter. An averaging filter may also be used to remove the gravitational component in the principal axis, and accordingly, the averaging filter includes, but is not limited to, a sliding window averaging filter. Exemplarily, referring to fig. 4, fig. 4 is a schematic waveform diagram of the filtered spindle acceleration data according to the second embodiment of the present invention, which eliminates high-frequency noise of the spindle acceleration data.
Using a peak-valley point detection algorithm to perform peak point or valley point detection on the filtered spindle acceleration data, so as to obtain a corresponding peak point or valley point, for example, referring to fig. 5, fig. 5 is a schematic diagram of a peak point detection result provided by a second embodiment of the present invention, where the detected peak point is labeled in fig. 5.
And S240, extracting data characteristics of triaxial acceleration data and triaxial angular velocity data between adjacent peak points or adjacent valley points.
The data characteristics are the basis of swimming stroke identification, and comprise direct characteristics and indirect characteristics, the direct characteristics are all motion data acquired by a six-axis sensor between adjacent peak points, the direct characteristics comprise three-axis acceleration data and three-axis angular velocity data, namely, the swimming stroke is identified by directly taking original motion data between the adjacent peak points or the adjacent valley points as characteristics, or partial motion data between the adjacent peak points or the adjacent valley points is selected as characteristics according to actual requirements, and the swimming stroke is identified. The indirect features are obtained by converting triaxial acceleration data and triaxial angular velocity data between adjacent peak points or adjacent valley points into a limited number of discrete features in a feature extraction mode, and the types of the indirect features include but are not limited to action duration, frequency, action amplitude, gradient and kurtosis. In practice, the direct feature and the indirect feature can be used alone or in combination.
And S250, taking the data characteristics as the input of a preset swimming stroke model, acquiring the swimming stroke output by the preset swimming stroke model, and taking the swimming stroke as the current swimming stroke of the user.
The preset swimming posture model is a swimming posture model which is trained and debugged through offline data, discrete data comprise, but are not limited to, manually collected data, experience data and the like, the swimming posture model can be determined according to needs, for example, a decision tree model, a random forest model, a support vector machine model or a neural network model and the like, extracted data features are combined into a feature vector, and the feature vector is input into the preset swimming posture model, so that the swimming posture output by the preset swimming posture model can be obtained and used as the current swimming posture of the user.
Exemplarily, referring to fig. 6, fig. 6 is a flowchart for implementing swimming stroke recognition according to a second embodiment of the present invention. Specifically, the motion data collected by the six-axis sensor is obtained, the motion data includes three-axis acceleration data collected by a three-axis accelerometer and three-axis angular velocity data collected by a three-axis gyroscope, spindle and spindle acceleration data are determined according to the three-axis acceleration data, the spindle acceleration data is filtered in order to improve the identification accuracy, peak point detection is performed on the filtered spindle acceleration data, a peak point of the filtered spindle acceleration data is extracted, then the data characteristic of the motion data between adjacent peak points is extracted, the data characteristic is input into a preset swimming gesture model, the current swimming gesture of the user is output by the preset swimming gesture model, if swimming is finished, identification is stopped, otherwise, the swimming gesture is continuously identified based on the obtained motion data, the swimming gesture identification method provided by the embodiment can automatically identify the swimming gesture according to the collected motion data of the user, the user does not need to record himself, so that the user can be more focused on the normative and persistent practice of the swimming action.
The second embodiment of the invention provides a swimming stroke identification method, on the basis of the first embodiment, the main shaft acceleration data is determined according to the fluctuation range of the acceleration data of each shaft, the peak point of the main shaft acceleration data is further detected, a cycle standard is provided for swimming stroke judgment, the swimming stroke is identified according to the three-shaft acceleration data and the three-shaft angular velocity data between adjacent peak points, the detail characteristics of the hand and the wrist of a user during swimming are considered, and the accuracy of swimming stroke identification is improved.
EXAMPLE III
Fig. 7 is a structural diagram of a swimming stroke recognition device according to a third embodiment of the present invention, which can execute the swimming stroke recognition method according to the third embodiment of the present invention, specifically, the device includes:
the data acquisition module 310 is configured to acquire motion data of a user during swimming, which is acquired by six sensors in the wearable device, where the motion data includes three-axis acceleration data and three-axis angular velocity data;
a peak-valley determination module 320, configured to analyze the triaxial acceleration data and determine a peak point or a valley point of the spindle acceleration data;
and the swimming stroke determining module 330 is configured to determine the swimming stroke of the user according to the three-axis acceleration data and the three-axis angular velocity data between adjacent peak points or adjacent valley points.
The third embodiment of the invention provides a swimming stroke recognition device, which is characterized in that the swimming stroke of a user is determined according to three-axis acceleration data and three-axis angular velocity data between adjacent peak points or adjacent valley points by acquiring motion data of the user during swimming, which is acquired by a six-axis sensor in wearable equipment, wherein the motion data comprises three-axis acceleration data and three-axis angular velocity data, analyzing the three-axis acceleration data, determining peak points or valley points of main axis acceleration data, and determining the swimming stroke of the user according to the three-axis acceleration data and the three-axis angular velocity data between the adjacent peak points or adjacent valley points. Compared with the prior art, the embodiment of the invention selects the peak point or the valley point of the main shaft acceleration data based on the analysis of the three-axis acceleration data, and determines the swimming stroke of the user based on the three-axis acceleration data and the three-axis angular velocity data between the adjacent peak points or the adjacent valley points, thereby realizing the automatic identification of the swimming stroke.
On the basis of the above embodiment, the peak-to-valley value determining module 320 includes:
the first determining unit is used for determining the acceleration data of the main shaft according to the fluctuation range of the acceleration data of each shaft;
and the second determining unit is used for determining a peak point or a valley point of the spindle acceleration data according to a preset detection rule.
On the basis of the above embodiment, the first determination unit includes:
The comparison subunit is used for comparing the fluctuation amplitude of the acceleration data of each axis with the set amplitude threshold value;
and the main shaft determining subunit is used for taking the shaft with the fluctuation amplitude larger than the set amplitude threshold value as the main shaft and taking the acceleration data corresponding to the shaft as the main shaft acceleration data.
On the basis of the above embodiment, the second determination unit includes:
the filtering subunit is used for filtering the main shaft acceleration data;
and the detection subunit is used for detecting the peak point or the valley point of the filtered main shaft acceleration data to obtain a corresponding peak point or a corresponding valley point.
On the basis of the above embodiment, the swimming stroke determining module 330 includes:
the data characteristic extraction unit is used for extracting the data characteristics of the triaxial acceleration data and the triaxial angular velocity data between adjacent peak points or adjacent valley points;
the swimming stroke obtaining unit is used for obtaining the data characteristics as the input of a preset swimming stroke model, obtaining the swimming stroke output by the preset swimming stroke model as the current swimming stroke of the user.
The swimming stroke recognition device provided by the embodiment of the invention can execute the swimming stroke recognition method of the embodiment, and has the corresponding functions and beneficial effects of the execution method.
Example four
Fig. 8 is a structural diagram of a wearable device according to a fourth embodiment of the present invention, and specifically, referring to fig. 8, the wearable device includes: the wearable device comprises a six-axis sensor 400, a processor 410, a memory 420, an input device 430 and an output device 440, wherein the six-axis sensor 400 is used for collecting motion data of a user during swimming, the motion data comprises three-axis acceleration data and three-axis angular velocity data, the number of the processors 410 in the wearable device can be one or more, one processor 410 is taken as an example in fig. 8, the six-axis sensor 400, the processor 410, the memory 420, the input device 430 and the output device 440 in the wearable device can be connected through a bus or in other manners, and the six-axis sensor 400, the processor 410, the memory 420, the input device 430 and the output device 440 in the wearable device can be connected through the bus in fig. 8.
The memory 420 serves as a computer-readable storage medium for storing software programs, computer-executable programs, and modules, such as program instructions/modules corresponding to the swimming stroke recognition method in the embodiment of the present invention. The processor 410 executes various functional applications and data processing of the wearable device by running software programs, instructions and modules stored in the memory 420, that is, implements the swimming stroke recognition method of the above-described embodiment.
The memory 420 mainly includes a program storage area and a data storage area, wherein the program storage area can store an operating system and an application program required by at least one function; the storage data area may store data created according to the use of the terminal, and the like. Further, the memory 420 may include high speed random access memory, and may also include non-volatile memory, such as at least one magnetic disk storage device, flash memory device, or other non-volatile solid state storage device. In some examples, memory 420 may further include memory located remotely from processor 410, which may be connected to the wearable device through a network. Examples of such networks include, but are not limited to, the internet, intranets, local area networks, mobile communication networks, and combinations thereof.
The input device 430 may be used to receive input numeric or character information and generate key signal inputs related to user settings and function control of the wearable device. The output device 440 may include a display device such as a display screen, and an audio device such as a speaker and a buzzer.
The wearable device provided by the embodiment of the invention and the swimming stroke recognition method provided by the embodiment belong to the same inventive concept, technical details which are not described in detail in the embodiment can be referred to the embodiment, and the embodiment has the same beneficial effects as the execution of the swimming stroke recognition method.
EXAMPLE five
Fifth, an embodiment of the present invention further provides a storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the swimming stroke recognition method according to the embodiment of the present invention.
Of course, the storage medium provided by the embodiment of the present invention contains computer-executable instructions, and the computer-executable instructions are not limited to the operations in the swimming stroke recognition method described above, and may also perform related operations in the swimming stroke recognition method provided by any embodiment of the present invention, and have corresponding functions and advantages.
From the above description of the embodiments, it is obvious for those skilled in the art that the present invention can be implemented by software and necessary general hardware, and certainly, can also be implemented by hardware, but the former is a better embodiment in many cases. Based on such understanding, the technical solutions of the present invention may be embodied in the form of a software product, which may be stored in a computer-readable storage medium, such as a floppy disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a FLASH Memory (FLASH), a hard disk or an optical disk of a computer, and includes instructions for enabling a computer device (which may be a robot, a personal computer, a server, or a network device) to execute the swimming stroke recognition method according to the embodiments of the present invention.
It is to be noted that the foregoing description is only exemplary of the invention and that the principles of the technology may be employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (7)
1. A swimming stroke recognition method is characterized by comprising the following steps:
the method comprises the steps of obtaining motion data of a user during swimming, wherein the motion data are collected by six sensors in wearable equipment and comprise triaxial acceleration data and triaxial angular velocity data;
analyzing the triaxial acceleration data, and determining a peak point or a valley point of the main shaft acceleration data;
determining the swimming postures of the user according to the triaxial acceleration data and the triaxial angular velocity data between the adjacent peak points or the adjacent valley points;
wherein, the analyzing the triaxial acceleration data to determine a peak point or a valley point of the spindle acceleration data includes:
Determining main shaft acceleration data according to the fluctuation range of the acceleration data of each shaft;
determining a peak point or a valley point of the spindle acceleration data according to a preset detection rule;
wherein, the determining the swimming stroke of the user according to the triaxial acceleration data and the triaxial angular velocity data between the adjacent peak points or the adjacent valley points comprises:
extracting direct features and indirect features of triaxial acceleration data and triaxial angular velocity data between the adjacent peak points or the adjacent valley points; the direct features are the triaxial acceleration data and the triaxial angular velocity data, and the indirect features are discrete feature data obtained after feature extraction is carried out on the triaxial acceleration data and the triaxial angular velocity data; the indirect characteristics at least comprise action duration, frequency, action amplitude, gradient and kurtosis;
and taking the direct characteristics and the indirect characteristics as the input of a preset swimming stroke model, and acquiring the swimming stroke output by the preset swimming stroke model as the current swimming stroke of the user.
2. The method of claim 1, wherein determining the spindle acceleration data from the fluctuation amplitude of the respective axis acceleration data comprises:
Comparing the fluctuation range of the acceleration data of each axis with the set range threshold value;
and taking the axis with the fluctuation amplitude larger than the set amplitude threshold value as a main axis, and taking the acceleration data corresponding to the axis as main axis acceleration data.
3. The method of claim 1, wherein determining the peak or valley point of the spindle acceleration data according to a preset detection rule comprises:
filtering the spindle acceleration data;
and detecting a peak point or a valley point of the filtered main shaft acceleration data to obtain a corresponding peak point or a corresponding valley point.
4. A swimming stroke recognition device, comprising:
the wearable device comprises a data acquisition module, a data processing module and a data processing module, wherein the data acquisition module is used for acquiring motion data of a user during swimming, which is acquired by six sensors in the wearable device, and the motion data comprises three-axis acceleration data and three-axis angular velocity data;
the peak-valley value determining module is used for analyzing the triaxial acceleration data and determining a peak value point or a valley value point of the main shaft acceleration data;
the swimming stroke determining module is used for determining the swimming stroke of the user according to the three-axis acceleration data and the three-axis angular velocity data between the adjacent peak points or the adjacent valley points;
The peak-to-valley value determination module comprises:
the first determining unit is used for determining the acceleration data of the main shaft according to the fluctuation range of the acceleration data of each shaft;
the second determining unit is used for determining a peak point or a valley point of the spindle acceleration data according to a preset detection rule;
the swimming stroke determining module comprises:
the data feature extraction unit is used for extracting direct features and indirect features of triaxial acceleration data and triaxial angular velocity data between adjacent peak points or adjacent valley points; the direct features are the triaxial acceleration data and the triaxial angular velocity data, and the indirect features are discrete feature data obtained after feature extraction is carried out on the triaxial acceleration data and the triaxial angular velocity data; the indirect characteristics at least comprise action duration, frequency, action amplitude, gradient and kurtosis;
the swimming stroke obtaining unit is used for obtaining the direct characteristics and the indirect characteristics as the input of a preset swimming stroke model, obtaining the swimming stroke output by the preset swimming stroke model as the current swimming stroke of the user.
5. The apparatus of claim 4, wherein the first determining unit comprises:
the comparison subunit is used for comparing the fluctuation amplitude of the acceleration data of each axis with the set amplitude threshold value;
And the main shaft determining subunit is used for taking the shaft with the fluctuation amplitude larger than the set amplitude threshold value as the main shaft and taking the acceleration data corresponding to the shaft as the main shaft acceleration data.
6. A wearable device, comprising:
the device comprises a six-axis sensor, a three-axis sensor and a controller, wherein the six-axis sensor is used for collecting motion data of a user during swimming, and the motion data comprises three-axis acceleration data and three-axis angular velocity data;
one or more processors;
a memory for storing one or more programs;
when executed by the one or more processors, cause the one or more processors to implement a method of swim gesture recognition according to any one of claims 1-3.
7. A storage medium having stored thereon a computer program, characterized in that the program, when executed by a controller, implements a swimming stroke recognition method according to any one of claims 1-3.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910284643.6A CN111803902B (en) | 2019-04-10 | 2019-04-10 | Swimming stroke identification method and device, wearable device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910284643.6A CN111803902B (en) | 2019-04-10 | 2019-04-10 | Swimming stroke identification method and device, wearable device and storage medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111803902A CN111803902A (en) | 2020-10-23 |
| CN111803902B true CN111803902B (en) | 2022-08-12 |
Family
ID=72844510
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910284643.6A Active CN111803902B (en) | 2019-04-10 | 2019-04-10 | Swimming stroke identification method and device, wearable device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111803902B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115193010A (en) * | 2021-04-09 | 2022-10-18 | 广东小天才科技有限公司 | Rope skipping frequency calculation method and wearable device |
| CN115253256B (en) * | 2021-04-30 | 2024-02-27 | 安徽华米健康科技有限公司 | Periodic motion period counting method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102481479A (en) * | 2009-04-01 | 2012-05-30 | 达腾科技有限公司 | Swimming monitor |
| CN106175781A (en) * | 2016-08-25 | 2016-12-07 | 歌尔股份有限公司 | Utilize method and the wearable device of wearable device monitoring swimming state |
| CN106237604A (en) * | 2016-08-31 | 2016-12-21 | 歌尔股份有限公司 | Wearable device and the method utilizing its monitoring kinestate |
| CN207950567U (en) * | 2018-01-24 | 2018-10-12 | 西安科技大学 | A kind of swimming position monitoring system |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP6361951B2 (en) * | 2012-08-28 | 2018-07-25 | 学校法人慶應義塾 | Electronic device, swimming method discrimination method, and swimming method discrimination program |
| TW201618835A (en) * | 2014-11-25 | 2016-06-01 | 沅聖科技股份有限公司 | Wearable device analyzing swimming and the analyzing method of the same |
| JP2018153391A (en) * | 2017-03-17 | 2018-10-04 | セイコーエプソン株式会社 | Electronic apparatus, swimming form determination method, swimming form determination program, and storage medium |
| CN107270934A (en) * | 2017-06-08 | 2017-10-20 | 海能电子(深圳)有限公司 | A kind of swimming information monitoring recognition methods based on wearable intelligent equipment |
| CN107376247B (en) * | 2017-08-16 | 2019-07-12 | 高驰运动科技(深圳)有限公司 | A kind of swimming exercise analysis method based on smartwatch and the smartwatch |
| CN108460322A (en) * | 2017-12-28 | 2018-08-28 | 惠州市德赛工业研究院有限公司 | A kind of stroke recognition methods and application |
-
2019
- 2019-04-10 CN CN201910284643.6A patent/CN111803902B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102481479A (en) * | 2009-04-01 | 2012-05-30 | 达腾科技有限公司 | Swimming monitor |
| CN106175781A (en) * | 2016-08-25 | 2016-12-07 | 歌尔股份有限公司 | Utilize method and the wearable device of wearable device monitoring swimming state |
| CN106237604A (en) * | 2016-08-31 | 2016-12-21 | 歌尔股份有限公司 | Wearable device and the method utilizing its monitoring kinestate |
| CN207950567U (en) * | 2018-01-24 | 2018-10-12 | 西安科技大学 | A kind of swimming position monitoring system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111803902A (en) | 2020-10-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| AU2020273327B2 (en) | Systems and methods of swimming analysis | |
| JP6064280B2 (en) | System and method for recognizing gestures | |
| CN111288986B (en) | Motion recognition method and motion recognition device | |
| WO2019033586A1 (en) | Swimming exercise analysis method based on smartwatch and smartwatch | |
| Jensen et al. | Classification of kinematic swimming data with emphasis on resource consumption | |
| CN104297519B (en) | Human motion gesture recognition method and mobile terminal | |
| CN108245869B (en) | Swimming information detection method and device and electronic equipment | |
| CN111803902B (en) | Swimming stroke identification method and device, wearable device and storage medium | |
| CN109840480B (en) | Interaction method and interaction system of smart watch | |
| CN111536989B (en) | Adaptive time window step counting method based on peak detection | |
| CN107469326A (en) | Swimming monitoring method and device for wearable equipment and wearable equipment | |
| CN111265841B (en) | Swimming lap number determining method, device, equipment and storage medium | |
| CN109758154B (en) | Motion state determination method, device, equipment and storage medium | |
| WO2018014432A1 (en) | Voice application triggering control method, device and terminal | |
| CN110929766B (en) | Self-adaptive pedestrian mobile phone attitude identification method based on Gaussian mixture clustering algorithm | |
| Iyer et al. | Generalized hand gesture recognition for wearable devices in IoT: Application and implementation challenges | |
| KR101870542B1 (en) | Method and apparatus of recognizing a motion | |
| Kau et al. | A smart phone-based pocket fall accident detection system | |
| CN115439934A (en) | Self-adaptive step frequency detection method based on CNN-LSTM motion mode identification | |
| CN107992193A (en) | Gesture confirmation method, device and electronic equipment | |
| CN114533010A (en) | Heart rate detection method and device | |
| CN114585422B (en) | Apparatus and method for determining swimming metrics | |
| CN110926467A (en) | Novel mean value clustering algorithm-based self-adaptive pedestrian mobile phone attitude identification method | |
| KR101958334B1 (en) | Method and apparatus for recognizing motion to be considered noise | |
| CN108776358A (en) | A kind of the wearing state detection method and system of smart machine |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |