Plate-type tennis racket swinging detection method and system and wearable intelligent device
By using a six-axis sensor and a multi-layer perceptron model to detect the paddle tennis swing action, the problem that existing equipment cannot detect the swing is solved, and efficient swing action recognition and speed evaluation are achieved.
Patent Information
- Application Number
- CN202510857909.7
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-06-25
- Publication Date
- 2025-09-26
AI Technical Summary
Existing smart wearable devices such as bracelets and watches fail to effectively detect the paddle tennis swing action.
The motion signal is acquired through a six-axis sensor, and the peak of the X-axis acceleration signal is detected using a six-axis sliding window. Combined with the multi-layer perceptron model, the type and speed of the swing action are determined.
The comprehensiveness and reliability of swing detection have been improved, and it can accurately identify the swing type and accurately assess the swing speed.
Smart Images

Figure CN120702459A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the technical field of wearable smart devices, and further relates to a paddle tennis racket swing detection method, system and wearable smart device. Background Art
[0002] In today's smart wearable device market, wristbands, watches, and other products are widely equipped with six-axis sensors. These sensors, composed of three-axis accelerometers and three-axis gyroscopes, enable a variety of functions. However, despite these devices' numerous features, the vast majority of these smart wristbands and watches currently on the market lack the ability to detect paddle tennis racket swings. Summary of the Invention
[0003] In order to solve the above technical problems, the present application provides a paddle tennis racket swing detection method, system and wearable smart device, which effectively improves the comprehensiveness and reliability of the swing action detection, and also solves the technical problem that the paddle tennis racket swing action detection cannot be performed in the related art.
[0004] In a first aspect, the present application provides a paddle tennis swing detection method, comprising: obtaining a six-axis signal of a user during exercise through a sensor; performing peak detection on an X-axis acceleration signal in the six-axis signal through a six-axis sliding window; determining that a swing action exists within the six-axis sliding window when the midpoint of the six-axis sliding window is the peak point of the X-axis acceleration signal and the X-axis acceleration value corresponding to the midpoint meets preset conditions; the preset conditions include that the X-axis acceleration value corresponding to the midpoint is greater than a first threshold, the X-axis acceleration value corresponding to the midpoint is greater than the X-axis acceleration values corresponding to a preset number of sample points on both sides of the midpoint, the sum of the acceleration values corresponding to all sample points in the six-axis sliding window is greater than a second threshold, and the interval between the midpoint and the peak point corresponding to the previous peak is greater than a third threshold.
[0005] The above-mentioned paddle tennis swing detection method obtains the six-axis signal during the user's movement through a six-axis sensor, and uses a six-axis sliding window to perform peak detection on the X-axis acceleration signal. When the midpoint of the six-axis sliding window is the peak point of the X-axis acceleration signal and the following preset conditions are met, it can be determined that there is a swing action in the window: the X-axis acceleration value corresponding to the midpoint is greater than the first threshold, greater than the X-axis acceleration value of a preset number of sample points on the left and right sides of the midpoint, the sum of the acceleration values of all sample points in the six-axis sliding window is greater than the second threshold, and the interval between the midpoint and the previous peak point is greater than the third threshold. This multi-condition comprehensive judgment method can effectively improve the comprehensiveness and reliability of the swing action detection, and also solves the technical problem that the paddle tennis swing action detection cannot be performed in the related art.
[0006] In one implementation, the method further includes: when a swinging action occurs within the six-axis sliding window, determining the classification features of the accelerations and angular velocities of each axis based on the acceleration values and angular velocity values corresponding to all sample points within the six-axis sliding window; and determining the type of the swinging action based on the multi-layer perceptron model, the classification features of the accelerations and angular velocities of each axis, and the angular velocity of each axis.
[0007] In one implementation, it also includes: when there is a swinging action in the six-axis sliding window, determining a first speed based on the acceleration values corresponding to all sample points in the six-axis sliding window, and determining a second speed based on the angular velocity values corresponding to all sample points in the six-axis sliding window; and determining a swinging speed corresponding to the swinging action based on the first speed and the second speed.
[0008] The above-described paddle tennis swing detection method, when detecting a swing within a six-axis sliding window, not only determines the classification features of each axis' acceleration and angular velocity based on the acceleration and angular velocity values of all sample points within the window, and then accurately determines the type of swing using a multi-layer perceptron model, but also determines a first velocity based on the acceleration values of all sample points within the window and a second velocity based on the angular velocity values, thereby determining the swing speed corresponding to the swing. This method not only accurately identifies the type of swing but also accurately estimates the swing speed, improving the compatibility and comprehensiveness of swing detection.
[0009] In one implementation, the sensor includes a six-axis sensor or an inertial measurement unit.
[0010] In a second aspect, the present application provides a paddle tennis swing detection system, comprising: a sensor for acquiring a six-axis signal of a user during exercise; a swing detection module for performing peak detection on an X-axis acceleration signal in the six-axis signal through a six-axis sliding window; a swing detection module for determining that a swing action exists within the six-axis sliding window when the midpoint of the six-axis sliding window is the peak point of the X-axis acceleration signal and the X-axis acceleration value corresponding to the midpoint meets preset conditions; the preset conditions include that the X-axis acceleration value corresponding to the midpoint is greater than a first threshold, the X-axis acceleration value corresponding to the midpoint is greater than the X-axis acceleration values corresponding to a preset number of sample points on both sides, the sum of the acceleration values corresponding to all sample points in the six-axis sliding window is greater than a second threshold, and the interval between the midpoint and the peak point corresponding to the previous peak is greater than a third threshold.
[0011] In one implementation, it also includes: a swing type determination module, which is used to determine the classification characteristics of the acceleration and angular velocity of each axis based on the acceleration values and angular velocity values corresponding to all sample points in the six-axis sliding window when there is a swing action in the six-axis sliding window; and a swing type determination module, which is used to determine the type of the swing action based on the multi-layer perceptron model, the classification characteristics of the acceleration and angular velocity of each axis.
[0012] In one implementation, it also includes: a swing speed calculation module, which is used to determine a first speed based on the acceleration values corresponding to all sample points in the six-axis sliding window when there is a swing action in the six-axis sliding window, and to determine a second speed based on the angular velocity values corresponding to all sample points in the six-axis sliding window; and a swing speed calculation module, which is used to determine the swing speed corresponding to the swing action based on the first speed and the second speed.
[0013] In one implementation, the sensor includes a six-axis sensor or an inertial measurement unit.
[0014] In a third aspect, the present application provides a wearable smart device comprising any of the above-implemented paddle tennis swing detection systems.
[0015] In one implementation, the wearable smart device includes a smart watch.
[0016] Compared with the prior art, the present invention has at least one of the following beneficial effects:
[0017] 1. The six-axis sensor is used to obtain the six-axis signal during the user's movement, and a six-axis sliding window is used to perform peak detection on the X-axis acceleration signal. When the midpoint of the six-axis sliding window is the peak point of the X-axis acceleration signal and the following preset conditions are met, it can be determined that there is a swing action within the window: the X-axis acceleration value corresponding to the midpoint is greater than the first threshold, greater than the X-axis acceleration values of a preset number of sample points on the left and right sides of the midpoint, the sum of the acceleration values of all sample points in the six-axis sliding window is greater than the second threshold, and the interval between the midpoint and the previous peak point is greater than the third threshold. This multi-condition comprehensive judgment method can effectively improve the comprehensiveness and reliability of swing action detection, and also solve the technical problem that the related art cannot perform paddle tennis swing action detection.
[0018] 2. When a swing is detected within a six-axis sliding window, not only is the classification feature of each axis' acceleration and angular velocity determined based on the acceleration and angular velocity values of all sample points within the window, and the type of swing accurately determined using a multi-layer perceptron model, but the first velocity is also determined based on the acceleration values of all sample points within the window, and the second velocity is determined based on the angular velocity values, and the corresponding swing speed is determined accordingly. This method not only accurately identifies the type of swing but also accurately estimates the swing speed, improving the compatibility and comprehensiveness of swing detection. BRIEF DESCRIPTION OF THE DRAWINGS
[0019] The preferred embodiments will be described below in a clear and understandable manner with reference to the accompanying drawings to further illustrate the above-mentioned characteristics, technical features, advantages and implementation methods of the present invention.
[0020] Figure 1A flow chart of a paddle tennis racket swing detection method provided in an embodiment of the present application is shown. DETAILED DESCRIPTION
[0021] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the specific embodiments of the present invention will be described below with reference to the accompanying drawings. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings and other embodiments can be obtained based on these drawings without inventive work.
[0022] To simplify the drawings, only portions relevant to the invention are schematically depicted in each figure; they do not represent the actual structure of the product. Furthermore, to simplify the drawings and facilitate understanding, in some figures, only one component with the same structure or function is schematically depicted or labeled. In this document, "one" not only means "only one" but also "more than one."
[0023] It should be further understood that the term "and / or" used in this specification and the appended claims refers to and includes any and all possible combinations of one or more of the associated listed items.
[0024] It should be noted that, unless otherwise specified or limited, the terms "mounted," "connected," and "connected" should be understood broadly. For example, they can refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediary; and internal communication between two components. Those skilled in the art will understand the specific meanings of these terms in the present invention based on the specific circumstances.
[0025] In addition, in the description of the present application, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.
[0026] It should be noted that the above embodiments can be freely combined as needed. The above are only preferred embodiments of the present invention. It should be noted that those skilled in the art can make several improvements and modifications without departing from the principles of the present invention, and such improvements and modifications should also be considered within the scope of protection of the present invention.
[0027] Wearable smart devices can be equipped with built-in six-axis sensors or inertial measurement units (IMUs). These sensors can be used to obtain three-dimensional acceleration data and three-dimensional angular velocity data of the user during exercise, and then analyze the user's exercise process based on these three-dimensional acceleration data and three-dimensional angular velocity data. For example, this includes but is not limited to counting the number of badminton swings during exercise based on the three-dimensional acceleration data and three-dimensional angular velocity data; determining the badminton swing action based on the peak value of the data after the three-dimensional acceleration data and three-dimensional angular velocity data are fused; and determining the type of table tennis shot by performing preprocessing, feature preprocessing, and feature matching on the three-dimensional acceleration data and three-dimensional angular velocity data. The embodiments of the present application use a six-axis sliding window to perform peak detection on the X-axis acceleration signal in the six-axis signal, and determine the presence of a swing action within the six-axis sliding window when the midpoint of the six-axis sliding window meets certain conditions. This embodiment can achieve at least one of the following beneficial effects: solving the technical problem of the inability to detect paddle tennis swing actions in the related art, and improving the comprehensiveness and reliability of paddle tennis swing action detection.
[0028] The following is explained with reference to the accompanying drawings:
[0029] Reference Attachment Figure 1 , which shows a flow chart of a method for detecting a paddle tennis racket swing provided by an embodiment of the present application. Figure 1 As shown, including:
[0030] S100 uses sensors to obtain six-axis signals during the user's exercise.
[0031] S110 , performing peak detection on the X-axis acceleration signal in the six-axis signal through a six-axis sliding window.
[0032] S120: When the midpoint of the six-axis sliding window is a peak point of the X-axis acceleration signal and the X-axis acceleration value corresponding to the midpoint satisfies preset conditions, it is determined that a swing action exists within the six-axis sliding window. The preset conditions include: the X-axis acceleration value corresponding to the midpoint is greater than a first threshold; the X-axis acceleration value corresponding to the midpoint is greater than the X-axis acceleration values corresponding to a preset number of sample points to the left and right of the midpoint; the sum of the acceleration values corresponding to all sample points within the six-axis sliding window is greater than a second threshold; and the interval between the midpoint and the peak point corresponding to the previous wave crest is greater than a third threshold.
[0033] The sensor acquires a six-axis signal of the user during paddle tennis play. The six-axis signal includes a three-axis acceleration signal and a three-axis angular velocity signal. Each sample point in the six-axis signal has corresponding X-, Y-, and Z-axis acceleration values and X-, Y-, and Z-axis angular velocity values. Then, a six-axis sliding window of a preset width is used to perform peak detection on the X-axis acceleration signal in the six-axis signal. That is, during the sliding of the six-axis sliding window, if the midpoint of the six-axis sliding window is the peak point of the X-axis acceleration signal (the peak point is the sample point), and the X-axis acceleration value corresponding to the midpoint meets the preset conditions, it is determined that a swing action has been detected within the six-axis sliding window. Among them, the X-axis acceleration value corresponding to the midpoint in the preset condition is greater than the X-axis acceleration values corresponding to a preset number of sample points on the left and right sides, which means that the X-axis acceleration value corresponding to the midpoint is greater than the X-axis acceleration values corresponding to all sample points within a preset range on the left and right sides of the midpoint; the sum of the acceleration values corresponding to all sample points in the six-axis sliding window is greater than the second threshold, which means that the sum of the X-axis, Y-axis, and Z-axis acceleration values corresponding to all sample points in the six-axis sliding window is greater than the second threshold.
[0034] The embodiment of the present application obtains the six-axis signal during the user's movement through a six-axis sensor, and uses a six-axis sliding window to perform peak detection on the X-axis acceleration signal. When the midpoint of the six-axis sliding window is the peak point of the X-axis acceleration signal and the following preset conditions are met, it can be determined that there is a swing action in the window: the X-axis acceleration value corresponding to the midpoint is greater than the first threshold, greater than the X-axis acceleration value of a preset number of sample points on the left and right sides of the midpoint, the sum of the acceleration values of all sample points in the six-axis sliding window is greater than the second threshold, and the interval between the midpoint and the previous peak point is greater than the third threshold. This multi-condition comprehensive judgment method can effectively improve the comprehensiveness and reliability of the swing action detection, and also solves the technical problem that the related art cannot perform the paddle tennis swing action detection.
[0035] In one embodiment of the present application, it also includes: when there is a swinging action in the six-axis sliding window, based on the acceleration values and angular velocity values corresponding to all sample points in the six-axis sliding window, determining the classification characteristics of each axis acceleration and each axis angular velocity; based on the multi-layer perceptron model, the classification characteristics of each axis acceleration and each axis angular velocity, determining the type of the swinging action.
[0036] After detecting the presence of a swinging action within the six-axis sliding window, the maximum value, minimum value, mean, standard deviation, skewness, and kurtosis corresponding to the X-axis acceleration are extracted from the X-, Y-, and Z-axis acceleration values and the X-, Y-, and Z-axis angular velocity values corresponding to all sample points in the six-axis sliding window, and the maximum value, minimum value, mean, standard deviation, skewness, and kurtosis corresponding to the X-axis acceleration are constructed as classification features of the X-axis acceleration; similarly, the maximum value, minimum value, mean, standard deviation, skewness, and kurtosis corresponding to the X-axis angular velocity are extracted from the X-, Y-, and Z-axis acceleration values and the X-, Y-, and Z-axis angular velocity values corresponding to all sample points in the six-axis sliding window, and the maximum value, minimum value, mean, standard deviation, skewness, and kurtosis corresponding to the X-axis angular velocity are constructed as classification features of the X-axis angular velocity; further, the classification features of the Y-axis acceleration and the Z-axis acceleration, as well as the classification features of the Y-axis angular velocity and the Z-axis angular velocity, are obtained through the same process. The classification features of the acceleration and angular velocity of each axis are then input into a multi-layer perceptron model (or MLP model) to obtain the type of the swing action.
[0037] In one embodiment of the present application, it also includes: when there is a swinging action in the six-axis sliding window, determining a first speed based on the acceleration values corresponding to all sample points in the six-axis sliding window, and determining a second speed based on the angular velocity values corresponding to all sample points in the six-axis sliding window; determining a swinging speed corresponding to the swinging action based on the first speed and the second speed.
[0038] After detecting a swinging motion within the six-axis sliding window, the X, Y, and Z acceleration values corresponding to all sample points in the six-axis sliding window are integrated to obtain a first velocity. The X, Y, and Z angular velocity values corresponding to all sample points in the six-axis sliding window are integrated to obtain a second velocity. The average of the first and second velocities is calculated to obtain the swing velocity corresponding to the swinging motion.
[0039] When a swing is detected within a six-axis sliding window, the present embodiment not only determines the classification features of the acceleration and angular velocity of each axis based on the acceleration and angular velocity values of all sample points within the window, and then accurately determines the type of the swing using a multi-layer perceptron model, but also determines a first velocity based on the acceleration values of all sample points within the window and a second velocity based on the angular velocity values, thereby determining the swing speed corresponding to the swing. This method not only accurately identifies the type of swing but also accurately assesses the swing speed, improving the compatibility and comprehensiveness of swing detection.
[0040] In one embodiment of the present application, the sensor includes a six-axis sensor or an inertial measurement unit.
[0041] An embodiment of the present application further provides a paddle tennis swing detection system, comprising: a sensor for acquiring a six-axis signal of a user during exercise; a swing detection module for performing peak detection on an X-axis acceleration signal in the six-axis signal through a six-axis sliding window; and a swing detection module for determining that a swing action is present within the six-axis sliding window when the midpoint of the six-axis sliding window is a peak point of the X-axis acceleration signal and the X-axis acceleration value corresponding to the midpoint meets preset conditions. The preset conditions include: the X-axis acceleration value corresponding to the midpoint being greater than a first threshold; the X-axis acceleration value corresponding to the midpoint being greater than the X-axis acceleration values corresponding to a preset number of sample points on its left and right sides; the sum of the acceleration values corresponding to all sample points within the six-axis sliding window being greater than a second threshold; and the interval between the midpoint and the peak point corresponding to the previous peak being greater than a third threshold.
[0042] The embodiment of the present application obtains the six-axis signal of the user during exercise through a sensor, and uses the swing detection module to perform peak detection on the X-axis acceleration signal. When the midpoint of the six-axis sliding window is the peak point of the X-axis acceleration signal and meets a series of preset conditions, it is determined that there is a swing action in the window. These preset conditions include that the X-axis acceleration value corresponding to the midpoint is greater than the first threshold, greater than the X-axis acceleration value of a preset number of sample points on the left and right sides, the sum of the acceleration values of all sample points in the six-axis sliding window is greater than the second threshold, and the interval between the midpoint and the previous peak point is greater than the third threshold. This multi-condition comprehensive judgment method can effectively improve the accuracy and reliability of swing action detection and avoid erroneous detection results caused by misjudgment of a single condition.
[0043] In one embodiment of the present application, it also includes: a swing type determination module, which is used to determine the classification characteristics of the acceleration of each axis and the angular velocity of each axis based on the acceleration values and angular velocity values corresponding to all sample points in the six-axis sliding window when there is a swing action in the six-axis sliding window; and a swing type determination module, which is used to determine the type of the swing action based on the multi-layer perceptron model, the classification characteristics of the acceleration of each axis and the angular velocity of each axis.
[0044] In one embodiment of the present application, it also includes: a swing speed calculation module, which is used to determine a first speed based on the acceleration values corresponding to all sample points in the six-axis sliding window when there is a swing action in the six-axis sliding window, and determine a second speed based on the angular velocity values corresponding to all sample points in the six-axis sliding window; a swing speed calculation module is used to determine the swing speed corresponding to the swing action based on the first speed and the second speed.
[0045] An embodiment of the present application also provides a wearable smart device, comprising the paddle tennis racket swing detection system of any of the above embodiments.
[0046] In one embodiment, the wearable smart device includes a smart watch.
[0047] A wearable smart device in an embodiment of the present application is used. Since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0048] It should be noted that the above embodiments can be freely combined as needed. The above are only preferred embodiments of the present invention. It should be pointed out that those skilled in the art can make several improvements and modifications without departing from the principles of the present invention, and such improvements and modifications should also be considered within the scope of protection of the present invention.
Claims
1. A method for detecting a tennis racket swing, characterized in that: include: Acquire the six-axis signals of the user during exercise through sensors; Performing peak detection on the X-axis acceleration signal in the six-axis signal through a six-axis sliding window; When the midpoint of the six-axis sliding window is the peak point of the X-axis acceleration signal and the X-axis acceleration value corresponding to the midpoint meets a preset condition, it is determined that a swing action exists within the six-axis sliding window; The preset conditions include that the X-axis acceleration value corresponding to the midpoint is greater than a first threshold, the X-axis acceleration value corresponding to the midpoint is greater than the X-axis acceleration values corresponding to a preset number of sample points on the left and right sides of the midpoint, the sum of the acceleration values corresponding to all sample points in the six-axis sliding window is greater than a second threshold, and the interval between the midpoint and the peak point corresponding to the previous peak is greater than a third threshold.
2. The paddle tennis racket swing detection method according to claim 1, wherein: Also includes: When a swinging motion occurs within the six-axis sliding window, determining classification features of accelerations and angular velocities of each axis based on acceleration values and angular velocity values corresponding to all sample points within the six-axis sliding window; The type of the swing action is determined based on a multi-layer perceptron model, the classification features of the accelerations of the axes, and the angular velocities of the axes.
3. The paddle tennis racket swing detection method according to claim 1, wherein: Also includes: When a swinging motion occurs within the six-axis sliding window, determining a first velocity based on acceleration values corresponding to all sample points within the six-axis sliding window, and determining a second velocity based on angular velocity values corresponding to all sample points within the six-axis sliding window; A swing speed corresponding to the swing action is determined based on the first speed and the second speed.
4. The paddle tennis racket swing detection method according to any one of claims 1 to 3, characterized in that: The sensor includes a six-axis sensor or an inertial measurement unit.
5. A paddle tennis racket swing detection system, characterized in that: include: Sensors, used to obtain six-axis signals during the user's exercise; a swing detection module, configured to perform peak detection on an X-axis acceleration signal in the six-axis signal through a six-axis sliding window; The swing detection module is configured to determine that a swing action exists within the six-axis sliding window when the midpoint of the six-axis sliding window is the peak point of the X-axis acceleration signal and the X-axis acceleration value corresponding to the midpoint meets a preset condition; The preset conditions include that the X-axis acceleration value corresponding to the midpoint is greater than a first threshold, the X-axis acceleration value corresponding to the midpoint is greater than the X-axis acceleration values corresponding to a preset number of sample points on the left and right sides, the sum of the acceleration values corresponding to all sample points in the six-axis sliding window is greater than a second threshold, and the interval between the midpoint and the peak point corresponding to the previous peak is greater than a third threshold.
6. The paddle tennis racket swing detection system according to claim 5, characterized in that: Also includes: a swing type determination module, configured to determine, when a swing action occurs within the six-axis sliding window, classification features of acceleration and angular velocity of each axis based on acceleration values and angular velocity values corresponding to all sample points within the six-axis sliding window; The swing type determination module is used to determine the type of the swing action based on a multi-layer perceptron model, the classification features of the accelerations of each axis, and the angular velocities of each axis.
7. The paddle tennis racket swing detection system according to claim 5, characterized in that: Also includes: a swing speed calculation module, configured to determine a first speed based on acceleration values corresponding to all sample points in the six-axis sliding window when a swing action occurs within the six-axis sliding window, and to determine a second speed based on angular velocity values corresponding to all sample points in the six-axis sliding window; The swing speed calculation module is used to determine the swing speed corresponding to the swing action based on the first speed and the second speed.
8. The paddle tennis racket swing detection system according to any one of claims 5 to 7, characterized in that: The sensor includes a six-axis sensor or an inertial measurement unit.
9. A wearable smart device, characterized in that: A paddle tennis racket swing detection system comprising the system described in any one of claims 5-8.
10. The wearable smart device according to claim 9, characterized in that: The wearable smart device includes a smart watch.
Citation Information
Patent Citations
Action judgment method and device, computer equipment and computer readable storage medium
CN111767932A
Method and device for detecting badminton racket swinging times and wearable equipment
CN111840948A
Step counting method and device, terminal and storage medium
CN117387655A
Fitness exercise recognition method based on wearable sensor
WO2021115064A1
