Motion scoring method and system based on real-time fitness

Abstract

The invention provides an action scoring method and system based on real-time fitness, and the method comprises the steps: obtaining a human body motion image, and extracting an initial human body key point set from the human body motion image through a preset extraction algorithm; screening the initial human body key point set to obtain a representative key point set; obtaining a preset standard action, and performing first matching with the representative key point set based on the preset standard action to obtain a first score; and obtaining a continuous representative key point set of the human body motion image in the first preset time period and a continuous preset standard action in the second preset time period, and performing second matching on the continuous representative key point set and the continuous preset standard action based on the first score to obtain a second score. The accuracy of scoring and the universality of application scenes are greatly improved, and the method is particularly suitable for continuous action feedback in fitness dance.

Description

Technical Field

[0001] The present invention belongs to the technical field of action recognition scoring, and in particular relates to an action scoring method and system based on real-time fitness. Background Art

[0002] In recent years, with the rapid development of artificial intelligence technology, smart fitness has become a hot trend in the field of fitness, and more and more smart products are being used in fitness. Current smart fitness applications are mainly focused on two directions: one is exercise counting, and the other is posture scoring. Exercise counting is used to count the number of times a user performs a certain fitness exercise, such as squats or push-ups, to provide quantitative feedback. Posture scoring scores the user's exercise posture, prompts and corrects irregular movements, thereby improving the user's fitness effect, such as helping users complete standard movements in equipment training.

[0003] The existing motion counting and posture scoring functions are based on the user's posture detection, and the corresponding functions are realized by analyzing the posture. The realization of motion counting depends on the change pattern of certain joint angles in a specific movement. For example, in a squat movement, the knee joint angle of the leg changes periodically. By setting upper and lower thresholds and analyzing the changes in the knee joint angle, it can be determined whether a squat is completed.

[0004] However, motion counting requires designing specific counting rules for each sport, and the feedback form is single, with only numbers, lacking interactivity and fun. Posture scoring is usually achieved by comparing the user's action posture with the standard posture. For example, in dumbbell training, the similarity between the user's elbow angle and the standard posture is calculated to obtain a score. This method is mostly based on the comparison of single-frame images and is suitable for posture scoring in some equipment training, but its scoring accuracy is relatively insufficient for fitness dances with more continuous movements.

[0005] In summary, the action scoring process in the prior art lacks accuracy and cannot achieve a precise scoring process. Summary of the invention

[0006] In order to solve the above technical problems, the present invention provides a method and system for scoring actions based on real-time fitness, which are used to solve the technical problems in the prior art.

[0007] On the one hand, the present invention provides the following technical solution, a method for scoring actions based on real-time fitness, comprising: Acquire a human motion image, and extract an initial human key point set from the human motion image using a preset extraction algorithm; Screening the initial human body key point set to obtain a representative key point set; Acquire a preset standard action, and perform a first match based on the preset standard action and the representative key point set to obtain a first score; A continuous representative key point set of a human motion image within a first preset time period and continuous preset standard actions within a second preset time period are obtained, and a second match is performed on the continuous representative key point set and the continuous preset standard actions based on the first score to obtain a second score.

[0008] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention first obtains a human motion image, and extracts an initial human key point set from the human motion image through a preset extraction algorithm; then the initial human key point set is screened and processed to obtain a representative key point set; then the preset standard action is obtained, and a first match is performed with the representative key point set based on the preset standard action to obtain a first score; finally, a continuous representative key point set of the human motion image within a first preset time period and a continuous preset standard action within a second preset time period are obtained, and a second match is performed with the continuous representative key point set and the continuous preset standard action based on the first score to obtain a second score. The present invention can efficiently score real-time fitness exercises and realize instant effect feedback, and at the same time adds a matching score for sequential actions, which greatly improves the accuracy of the score and the breadth of application scenarios, and is particularly suitable for continuous action feedback in fitness dance.

[0009] Preferably, the preset extraction algorithm is specifically a Lite-HRNet algorithm.

[0010] Preferably, the representative key point set includes left shoulder bone points, left elbow bone points, left hip bone points, left knee joint bone points, right shoulder bone points, right elbow bone points, right hip bone points, and right knee joint bone points.

[0011] Preferably, the step of obtaining a preset standard action and performing a first match based on the preset standard action and the representative key point set to obtain a first score includes: Obtain the coordinate position of each bone point in the representative key point set, and calculate the bone angle of each bone point based on the coordinate position of the bone point : ; In the formula, Represents bone points The bone angle, They are three adjacent bone points. , Respectively represent the bone points Point to bone point , by bone point Point to bone point A vector of The bone angles of all the bone points in the key point set are combined into a one-dimensional angle vector ; Calculate a first score between the angle one-dimensional vector and the preset standard action : ; In the formula, Represents the one-dimensional vector of angles corresponding to the preset standard action, Represents the balance index.

[0012] Preferably, the step of performing a second matching between the continuous representative key point set and the continuous preset standard action based on the first score to obtain a second score comprises: The continuous representative key point set and the continuous preset standard action are respectively converted into a first time series With the second time series ,in, Indicates The representative keypoint set of the frame, Indicates Preset standard actions for frames; Construct a distance matrix based on the first time series and the second time series : ; In the formula, Represents the distance matrix Line The elements of the column, Indicates The representative key point set of the frame is The first score between the preset standard actions of the frame; Construct a cumulative distance matrix based on the distance matrix : ; In the formula, Indicates the cumulative distance matrix Line The elements of the column, Respectively represent the cumulative distance matrix Line Column, No. Line Column, No. Line Elements of a column; From the cumulative distance matrix Start backtracking from the last element in and determine the path with the smallest cumulative distance to obtain the optimal alignment path; Calculate the shortest distance of the optimal alignment path , and calculate the second score based on the shortest distance : .

[0013] In a second aspect, the present invention provides the following technical solution, a real-time fitness-based action scoring system, the system comprising: An extraction module, used for acquiring a human motion image, and extracting an initial human key point set from the human motion image by using a preset extraction algorithm; A screening module, used for screening the initial human body key point set to obtain a representative key point set; A first scoring module, used for obtaining a preset standard action, and performing a first match between the preset standard action and the representative key point set to obtain a first score; The second scoring module is used to obtain a continuous representative key point set of the human motion image within a first preset time period and a continuous preset standard action within a second preset time period, and perform a second match between the continuous representative key point set and the continuous preset standard action based on the first score to obtain a second score.

[0014] Preferably, the first scoring module includes: Angle submodule, used to obtain the coordinate position of each bone point in the representative key point set, and calculate the bone angle of each bone point based on the coordinate position of the bone point : ; In the formula, Represents bone points The bone angle, They are three adjacent bone points. , Respectively represent the bone points Point to bone point , by bone point Point to bone point A vector of A vector submodule, used to form a one-dimensional vector of angles of all the bone angles of the key point set ; The first scoring submodule is used to calculate the first score between the angle one-dimensional vector and the preset standard action. : ; In the formula, Represents the one-dimensional vector of angles corresponding to the preset standard action, Represents the balance index.

[0015] Preferably, the second scoring module includes: A sequence submodule is used to convert the continuous representative key point set and the continuous preset standard action into a first time sequence respectively With the second time series ,in, Indicates The representative keypoint set of the frame, Indicates Preset standard actions for frames; The distance submodule is used to construct a distance matrix based on the first time series and the second time series. : ; In the formula, Represents the distance matrix Line The elements of the column, Indicates The representative key point set of the frame is The first score between the preset standard actions of the frame; The accumulation submodule is used to construct a cumulative distance matrix based on the distance matrix : ; In the formula, Indicates the cumulative distance matrix Line The elements of the column, Respectively represent the cumulative distance matrix Line Column, No. Line Column, No. Line Elements of a column; From the cumulative distance matrix Start backtracking from the last element in and determine the path with the smallest cumulative distance to obtain the optimal alignment path; The second scoring submodule is used to calculate the shortest distance of the optimal alignment path , and calculate the second score based on the shortest distance : .

[0016] In a third aspect, the present invention provides the following technical solution: a computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above-mentioned real-time fitness-based action scoring method when executing the computer program.

[0017] In a fourth aspect, the present invention provides the following technical solution: a storage medium having a computer program stored thereon, wherein the computer program, when executed by a processor, implements the above-mentioned action scoring method based on real-time fitness. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0019] Figure 1 A flowchart of a method for scoring an action based on real-time fitness provided in Embodiment 1 of the present invention; Figure 2 A structural block diagram of a real-time fitness-based action scoring system provided in Embodiment 2 of the present invention; Figure 3 A schematic diagram of the hardware structure of a computer provided in another embodiment of the present invention.

[0020] The embodiments of the present invention will be further described below with reference to the accompanying drawings. DETAILED DESCRIPTION

[0021] Embodiments of the present invention are described in detail below, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the embodiments of the present invention, and should not be construed as limiting the present invention.

[0022] In the description of the embodiments of the present invention, it should be understood that the terms "length", "width", "up", "down", "front", "back", "left", "right", "vertical", "horizontal", "top", "bottom", "inside" and "outside" etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings, and are only for the convenience of describing the embodiments of the present invention and simplifying the description, and do not indicate or imply that the referred device or element must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be understood as a limitation on the present invention.

[0023] In addition, the terms "first" and "second" are used for descriptive purposes only and should not be understood as indicating or implying relative importance or implicitly indicating the number of the indicated technical features. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of the features. In the description of the embodiments of the present invention, the meaning of "plurality" is two or more, unless otherwise clearly and specifically defined.

[0024] In the embodiments of the present invention, unless otherwise clearly specified and limited, the terms "installed", "connected", "connected", "fixed" and the like should be understood in a broad sense, for example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, it can be the internal connection of two elements or the interaction relationship between two elements. For ordinary technicians in this field, the specific meanings of the above terms in the embodiments of the present invention can be understood according to specific circumstances.

[0025] Embodiment 1 In the first embodiment of the present invention, Figure 1 As shown, a real-time fitness-based action scoring method comprises: S1, obtaining a human motion image, and extracting an initial human key point set from the human motion image using a preset extraction algorithm; Specifically, the preset extraction algorithm is the Lite-HRNet algorithm.

[0026] Among them, Lite-HRNet is based on the HRNet (High-Resolution Network) structure. Through a series of optimizations, it reduces the amount of calculation and model size while ensuring efficient key point detection. Its network structure is divided into four stages, each of which contains two feature branches: low-resolution and high-resolution: Multi-scale feature processing: Lite-HRNet retains the design of multi-resolution feature fusion to ensure the joint representation of features of different scales to meet different resolution requirements. Branch fusion: Through multiple cross-resolution feature fusions, information interaction between low-resolution and high-resolution features is achieved to ensure the integrity of feature expression; The position data of 17 key points of the human body can be extracted through the above algorithm.

[0027] S2, screening the initial human body key point set to obtain a representative key point set; Among them, the representative key point set includes left shoulder bone points, left elbow bone points, left hip bone points, left knee joint bone points, right shoulder bone points, right elbow bone points, right hip bone points, and right knee joint bone points.

[0028] In order to improve the speed of the algorithm, in this application, the above eight representative skeleton points are selected as the basis for scoring.

[0029] S3, obtaining a preset standard action, and performing a first match between the preset standard action and the representative key point set to obtain a first score; Wherein, the step S3 comprises: S31, obtaining the coordinate position of each skeleton point in the representative key point set, and calculating the skeleton angle of each skeleton point based on the coordinate position of the skeleton point : ; In the formula, Represents bone points The bone angle, They are three adjacent bone points. , Respectively represent the bone points Point to bone point , by bone point Point to bone point Vector.

[0030] S32, forming a one-dimensional angle vector of all the skeleton angles of the skeleton points in the representative key point set .

[0031] S33, calculating a first score between the one-dimensional angle vector and the preset standard action : ; In the formula, Represents the one-dimensional vector of angles corresponding to the preset standard action, represents the balance index; Specifically, the balance index can be determined according to the actual situation. In the actual calculation process of the first score, due to the similarity of the human body, It is close to 1. Therefore, in order to improve the accuracy of the scoring, a balance index greater than 1 is set to improve the accuracy of the scoring. In this embodiment, the balance index is 5.

[0032] S4. Obtain a set of continuous representative key points of human motion images within a first preset time period and continuous preset standard actions within a second preset time period, and perform a second match between the continuous representative key point set and the continuous preset standard actions based on the first score to obtain a second score.

[0033] Wherein, the step S4 comprises: S41, converting the continuous representative key point set and the continuous preset standard action into a first time series respectively With the second time series ,in, Indicates The representative keypoint set of the frame, Indicates Preset standard actions for frames.

[0034] S42. Constructing a distance matrix based on the first time series and the second time series : ; In the formula, Represents the distance matrix Line The elements of the column, Indicates The representative key point set of the frame is The first score between the preset standard actions of the frame; in, Specific representation and The distance between.

[0035] S43, constructing a cumulative distance matrix based on the distance matrix : ; In the formula, Indicates the cumulative distance matrix Line The elements of the column, Respectively represent the cumulative distance matrix Line Column, No. Line Column, No. Line Elements of a column; For the cumulative distance matrix, we first need to initialize , and for the elements in the first row, , for the elements in the first column, .

[0036] S44, from the cumulative distance matrix Start backtracking from the last element in and determine the path with the smallest cumulative distance to obtain the optimal alignment path.

[0037] S45: Calculate the shortest distance of the optimal alignment path , and calculate the second score based on the shortest distance : .

[0038] The action scoring method based on real-time fitness provided in the first embodiment of the present invention first obtains a human motion image, and extracts an initial human key point set from the human motion image by a preset extraction algorithm; then the initial human key point set is screened to obtain a representative key point set; then a preset standard action is obtained, and a first matching is performed with the representative key point set based on the preset standard action to obtain a first score; finally, a continuous representative key point set of the human motion image within a first preset time period and a continuous preset standard action within a second preset time period are obtained, and a second matching is performed with the continuous representative key point set and the continuous preset standard action based on the first score to obtain a second score. The present invention can efficiently score real-time fitness exercises and realize instant effect feedback, and at the same time adds matching scoring for sequential actions, which greatly improves the accuracy of scoring and the breadth of application scenarios, and is particularly suitable for continuous action feedback in fitness dance.

[0039] Embodiment 2 like Figure 2 As shown, in the second embodiment of the present invention, a real-time fitness-based action scoring system is provided, and the system includes: Extraction module 1, used for acquiring a human motion image, and extracting an initial human key point set from the human motion image by using a preset extraction algorithm; Screening module 2, used for screening the initial human body key point set to obtain a representative key point set; A first scoring module 3 is used to obtain a preset standard action, and perform a first match based on the preset standard action and the representative key point set to obtain a first score; The second scoring module 4 is used to obtain a continuous representative key point set of the human motion image within a first preset time period and a continuous preset standard action within a second preset time period, and perform a second match between the continuous representative key point set and the continuous preset standard action based on the first score to obtain a second score.

[0040] Wherein, the first scoring module 3 includes: Angle submodule, used to obtain the coordinate position of each bone point in the representative key point set, and calculate the bone angle of each bone point based on the coordinate position of the bone point : ; In the formula, Represents bone points The bone angle, They are three adjacent bone points. , Respectively represent the bone points Point to bone point , by bone point Point to bone point A vector of A vector submodule, used to form a one-dimensional vector of angles of all the bone angles of the key point set ; The first scoring submodule is used to calculate the first score between the angle one-dimensional vector and the preset standard action. : ; In the formula, Represents the one-dimensional vector of angles corresponding to the preset standard action, Represents the balance index.

[0041] Wherein, the second scoring module 4 includes: A sequence submodule is used to convert the continuous representative key point set and the continuous preset standard action into a first time sequence respectively With the second time series ,in, Indicates The representative keypoint set of the frame, Indicates Preset standard actions for frames; The distance submodule is used to construct a distance matrix based on the first time series and the second time series. : ; In the formula, Represents the distance matrix Line The elements of the column, Indicates The representative key point set of the frame is The first score between the preset standard actions of the frame; The accumulation submodule is used to construct a cumulative distance matrix based on the distance matrix : ; In the formula, Indicates the cumulative distance matrix Line The elements of the column, Respectively represent the cumulative distance matrix Line Column, No. Line Column, No. Line Elements of a column; From the cumulative distance matrix Start backtracking from the last element in and determine the path with the smallest cumulative distance to obtain the optimal alignment path; The second scoring submodule is used to calculate the shortest distance of the optimal alignment path , and calculate the second score based on the shortest distance : .

[0042] In some other embodiments of the present invention, the embodiments of the present invention provide the following technical solution: a computer, comprising a memory 102, a processor 101, and a computer program stored in the memory 102 and executable on the processor 101, wherein the processor 101 implements the above-described real-time fitness-based action scoring method when executing the computer program.

[0043] Specifically, the processor 101 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiment of the present invention.

[0044] Among them, the memory 102 may include a large-capacity memory for data or instructions. By way of example and not limitation, the memory 102 may include a hard disk drive (HDD), a floppy disk drive, a solid state drive (SSD), a flash memory, an optical disk, a magneto-optical disk, a magnetic tape, or a universal serial bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 102 may include a removable or non-removable (or fixed) medium. Where appropriate, the memory 102 may be inside or outside the data processing device. In a specific embodiment, the memory 102 is a non-volatile memory. In a specific embodiment, the memory 102 includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically alterable ROM (EAROM) or a flash memory (FLASH), or a combination of two or more of these. Under appropriate circumstances, the RAM can be a static random access memory (SRAM) or a dynamic random access memory (DRAM), wherein the DRAM can be a fast page mode dynamic random access memory (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.

[0045] The memory 102 may be used to store or cache various data files that need to be processed and / or used for communication, as well as possible computer program instructions executed by the processor 101 .

[0046] The processor 101 implements the above-mentioned action scoring method based on real-time fitness by reading and executing the computer program instructions stored in the memory 102 .

[0047] In some embodiments, the computer may further include a communication interface 103 and a bus 100. Figure 3 As shown, the processor 101, the memory 102, and the communication interface 103 are connected via a bus 100 and communicate with each other.

[0048] The communication interface 103 is used to implement communication between the modules, devices, units and / or equipment in the embodiment of the present invention. The communication interface 103 can also implement data communication with other components such as: external devices, image / data acquisition equipment, databases, external storage, and image / data processing workstations.

[0049] The bus 100 includes hardware, software or both, and couples the components of the computer device to each other. The bus 100 includes but is not limited to at least one of the following: a data bus, an address bus, a control bus, an expansion bus, and a local bus. By way of example and not limitation, bus 100 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses or a combination of two or more of these. Where appropriate, bus 100 may include one or more buses. Although embodiments of the present invention describe and illustrate a particular bus, the present invention contemplates any suitable bus or interconnect.

[0050] The computer can execute the action scoring method based on real-time fitness of the present invention based on the acquired action scoring system based on real-time fitness, thereby realizing action scoring based on real-time fitness.

[0051] In some further embodiments of the present invention, in combination with the above-mentioned action scoring method based on real-time fitness, the embodiments of the present invention provide the following technical solutions: a storage medium having a computer program stored thereon, and the computer program implements the above-mentioned action scoring method based on real-time fitness when executed by a processor.

[0052] Those skilled in the art will appreciate that the logic and / or steps represented in the flowchart or otherwise described herein, for example, may be considered as an ordered list of executable instructions for implementing logical functions, and may be specifically implemented in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For purposes of this specification, "computer-readable medium" may be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0053] More specific examples of readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0054] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or a combination thereof: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0055] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0056] The above-mentioned embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the invention patent. It should be pointed out that, for ordinary technicians in this field, several variations and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention shall be subject to the attached claims.

Claims

1. A method for scoring actions based on real-time fitness, characterized in that: include: Acquire a human motion image, and extract an initial human key point set from the human motion image using a preset extraction algorithm; Screening the initial human body key point set to obtain a representative key point set; Acquire a preset standard action, and perform a first match based on the preset standard action and the representative key point set to obtain a first score; A continuous representative key point set of a human motion image within a first preset time period and continuous preset standard actions within a second preset time period are obtained, and a second match is performed on the continuous representative key point set and the continuous preset standard actions based on the first score to obtain a second score.

2. The action scoring method based on real-time fitness according to claim 1, characterized in that: The preset extraction algorithm is specifically the Lite-HRNet algorithm.

3. The action scoring method based on real-time fitness according to claim 1, characterized in that: The representative key point set includes left shoulder bone points, left elbow bone points, left hip bone points, left knee joint bone points, right shoulder bone points, right elbow bone points, right hip bone points, and right knee joint bone points.

4. The action scoring method based on real-time fitness according to claim 1, characterized in that: The step of obtaining a preset standard action and performing a first match based on the preset standard action and the representative key point set to obtain a first score includes: Obtain the coordinate position of each bone point in the representative key point set, and calculate the bone angle of each bone point based on the coordinate position of the bone point : ； In the formula, Represents bone points The bone angle, They are three adjacent bone points. , Respectively represent the bone points Point to bone point , by bone point Point to bone point A vector of The bone angles of all the bone points in the key point set are combined into a one-dimensional angle vector ; Calculate a first score between the angle one-dimensional vector and the preset standard action : ； In the formula, Represents the one-dimensional vector of angles corresponding to the preset standard action, Represents the balance index.

5. The action scoring method based on real-time fitness according to claim 1, characterized in that: The step of performing a second matching between the continuous representative key point set and the continuous preset standard action based on the first score to obtain a second score comprises: The continuous representative key point set and the continuous preset standard action are respectively converted into a first time series With the second time series ,in, Indicates The representative keypoint set of the frame, Indicates Preset standard actions for frames; Construct a distance matrix based on the first time series and the second time series : ； In the formula, Represents the distance matrix Line The elements of the column, Indicates The representative key point set of the frame is The first score between the preset standard actions of the frame; Construct a cumulative distance matrix based on the distance matrix : ； In the formula, Indicates the cumulative distance matrix Line The elements of the column, Respectively represent the cumulative distance matrix Line Column, No. Line Column, No. Line Elements of a column; From the cumulative distance matrix Start backtracking from the last element in and determine the path with the smallest cumulative distance to obtain the optimal alignment path; Calculate the shortest distance of the optimal alignment path , and calculate the second score based on the shortest distance : 。 6. A real-time fitness-based action scoring system, characterized in that: The system comprises: An extraction module, used for acquiring a human motion image, and extracting an initial human key point set from the human motion image by using a preset extraction algorithm; A screening module, used for screening the initial human body key point set to obtain a representative key point set; A first scoring module, used for obtaining a preset standard action, and performing a first match between the preset standard action and the representative key point set to obtain a first score; The second scoring module is used to obtain a continuous representative key point set of the human motion image within a first preset time period and a continuous preset standard action within a second preset time period, and perform a second match between the continuous representative key point set and the continuous preset standard action based on the first score to obtain a second score.

7. The action scoring system based on real-time fitness according to claim 6, characterized in that: The first scoring module comprises: Angle submodule, used to obtain the coordinate position of each bone point in the representative key point set, and calculate the bone angle of each bone point based on the coordinate position of the bone point : ； In the formula, Represents bone points The bone angle, They are three adjacent bone points. , Respectively represent the bone points Point to bone point , by bone point Point to bone point A vector of A vector submodule, used to form a one-dimensional vector of angles of all the bone angles of the key point set ; The first scoring submodule is used to calculate the first score between the angle one-dimensional vector and the preset standard action. : ； In the formula, Represents the one-dimensional vector of angles corresponding to the preset standard action, Represents the balance index.

8. The real-time fitness-based action scoring system according to claim 6, characterized in that: The second scoring module includes: A sequence submodule is used to convert the continuous representative key point set and the continuous preset standard action into a first time sequence respectively With the second time series ,in, Indicates The representative keypoint set of the frame, Indicates Preset standard actions for frames; The distance submodule is used to construct a distance matrix based on the first time series and the second time series. : ； In the formula, Represents the distance matrix Line The elements of the column, Indicates The representative key point set of the frame is The first score between the preset standard actions of the frame; The accumulation submodule is used to construct a cumulative distance matrix based on the distance matrix : ； In the formula, Indicates the cumulative distance matrix Line The elements of the column, Respectively represent the cumulative distance matrix Line Column, No. Line Column, No. Line Elements of a column; From the cumulative distance matrix Start backtracking from the last element in and determine the path with the smallest cumulative distance to obtain the optimal alignment path; The second scoring submodule is used to calculate the shortest distance of the optimal alignment path , and calculate the second score based on the shortest distance : 。 9. A computer comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the action scoring method based on real-time fitness is implemented as described in any one of claims 1 to 5.

10. A storage medium, characterized in that: The storage medium stores a computer program, and when the computer program is executed by the processor, the action scoring method based on real-time fitness according to any one of claims 1 to 5 is implemented.

Images