Rope skipping evaluation method and device, electronic equipment and storage medium
By obtaining the video stream and historical motion information of skipping rope evaluation, combining the bone point and rope trajectory status, the adaptive jump state is realized, which solves the problem of misjudgment and low counting efficiency in the existing technology, and provides low-cost and accurate skipping rope analysis , help athletes correct their posture and improve their physical fitness.
Patent Information
- Application Number
- CN202411096078.8
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-08-09
- Publication Date
- 2024-11-19
AI Technical Summary
The existing rope skipping analysis plan has misjudgment phenomenon, making it difficult to accurately identify complex or high-speed movements, cannot provide detailed motion analysis, and is costly and limited, so it is impossible to effectively correct the movement posture and improve physical fitness.
By obtaining the rope skipping evaluation video stream, determining the bone point information and rope trajectory status, combining historical motion information and jump recognition standards, adaptive adjustment of jump status identification, eliminating violations such as interruptions and shaking, and performing accurate counting.
It realizes low-cost and accurate counting of rope skipping times, improves statistical efficiency, and helps athletes correct their postures and improve their physical fitness.
Smart Images

Figure CN118982870A_ABST
Abstract
Description
Technical Field
[0001] The embodiments of the present application relate to the field of visual processing technology. More specifically, the embodiments of the present application relate to a skipping rope evaluation method, device, electronic device and storage medium. Background Art
[0002] This section is intended to provide background or context for the embodiments of the present application set forth in the claims. The descriptions herein may include concepts that may be explored, but not necessarily concepts that have been previously thought of or explored. Therefore, unless otherwise noted herein, the content described in this section is not prior art with respect to the specification and claims of the present application, and is not admitted to be prior art by inclusion in this section.
[0003] Rope skipping can not only effectively enhance cardiopulmonary function and promote blood circulation, but also comprehensively exercise the legs, arms and core muscles. It is an ideal way to improve body coordination and explosive power. Currently, rope skipping has become an important part of campus physical education and personal daily exercise. However, in order to popularize correct rope skipping skills and realize personalized training guidance, a rope skipping analysis system that combines high technology, high convenience and high accuracy is urgently needed.
[0004] In the prior art, the main rope skipping analysis scheme can be to manually count the number of times a statistician observes the motion state of the athlete based on manual experience, and subjectively judge and analyze the results based on the technical results to give artificial suggestions. This method requires more human resources and time costs, and it is difficult to have a unified standard for whether the action is standardized, so it is easy to have problems such as rope skipping movements are difficult to standardize and counting results are difficult to trust. Another existing rope skipping analysis scheme can be to use a semi-automatic counting device based on Bluetooth for rope skipping analysis, but the device may misjudge in complex or high-speed actions such as double-shaking techniques, multi-shaking techniques, or when the rope jumper's movement amplitude changes greatly, and the device can usually only track basic data points, such as the number of jumps and time, and may not provide detailed motion analysis such as jump height, rhythm changes, or identification of technical errors, and requires users to wear matching smart devices to receive and display the data of the device, which is costly and has great limitations. Another existing rope skipping analysis solution is a counting solution based on deep learning. It can use the skeleton point recognition model to analyze the key point data of the athlete's body posture and the human body detection frame data, and then generate a waveform according to the distance from the hip joint key point in the human body posture key point data to the baseline, so as to count each trough-peak-trough process in the waveform. However, this kind of solution actually counts jumps, and the accuracy of rope skipping performance analysis is relatively low, and it cannot identify violations such as athlete interruption, empty swing, empty jump, and tiptoe jump.
[0005] In view of this, there is an urgent need to propose a rope skipping evaluation method so that rope skippers can be accurately counted at low cost and the statistical efficiency of the standard effective number of rope skipping can be improved, which will help rope skippers correct their exercise posture and improve their physical fitness. Summary of the invention
[0006] In order to overcome the problems existing in the related art, the embodiments of the present application are intended to provide a rope skipping evaluation method, device, electronic device and storage medium. The rope skipping evaluation method can accurately count rope skippers at a low cost, improve the statistical efficiency of the standard effective rope skipping times, and help rope skippers correct their exercise posture and improve their physical fitness.
[0007] In a first aspect of the implementation manner of the present application, a skipping rope evaluation method is provided, including: obtaining a skipping rope evaluation video stream; determining the skeleton point information of a rope jumper in a preset calibrated motion area based on the skipping rope evaluation video stream; determining a jump recognition standard based on the historical motion information of the rope jumper, and determining a jumping action completion result based on the skeleton point information and the jumping recognition standard; determining a rope trajectory state based on the skipping rope evaluation video stream; and counting the number of effective rope jumps based on the jumping action completion result and the rope trajectory state.
[0008] In one embodiment of the present application, historical motion information includes historical jump height and historical jump frequency; wherein, determining the jump recognition standard based on the historical motion information of the rope skipper includes: determining the minimum jump height standard value based on the historical jump height; determining the standard number of frames of continuous vertical change based on the historical jump frequency; determining the standard value of the minimum number of vertical change pixels in a single frame based on the historical jump height and the historical jump frequency.
[0009] In one embodiment of the present application, determining the completion result of a jumping action based on skeleton point information and a jumping recognition standard includes: determining a jumping state based on skeleton point information, a standard number of frames of continuous vertical change, and a standard value of a minimum number of vertical change pixels in a single frame; determining an actual jumping height based on the jumping state; and determining a jumping action completion result based on the actual jumping height and a standard value of a minimum jumping height.
[0010] In one embodiment of the present application, determining the jump state based on the skeleton point information, the standard number of frames of continuous vertical change and the standard value of the minimum number of vertical changes in a single frame includes: if the actual number of continuous vertical rising frames of the target skeleton point in the skeleton point information is greater than or equal to the standard number of continuous vertical changes, and the actual number of rising changes in pixels in a single frame is greater than or equal to the standard value of the minimum number of vertical changes in a single frame, then the jump state is determined to be a rising state; if the actual number of continuous vertical falling frames of the target skeleton point is greater than or equal to the standard number of continuous vertical changes, and the actual number of falling changes in pixels in a single frame is greater than or equal to the standard value of the minimum number of vertical changes in a single frame, then the jump state is determined to be a falling state; if the actual number of vertical changes in pixels in a single frame in the standard number of continuous vertical changes of the target skeleton point is less than the standard value of the minimum number of vertical changes in a single frame, then the jump state is determined to be a stationary state.
[0011] In one embodiment of the present application, determining the rope trajectory state based on the rope skipping evaluation video stream includes: subtracting each frame of the video stream image in the jumping action cycle of the rope skipping evaluation video stream from the previous frame of the video stream image of each frame, and performing binarization processing to obtain multiple binary images of moving objects; performing feature enhancement processing on the multiple binary images of moving objects respectively to obtain multiple rope trajectory images; segmenting the multiple rope trajectory images according to a preset image size and a preset segmentation position to obtain at least one image to be spliced; splicing the at least one image to be spliced in the channel dimension to obtain a rope feature map; and determining the rope trajectory state based on the rope feature map.
[0012] In one embodiment of the present application, determining the rope trajectory state based on the rope feature map includes: inputting the rope feature map into the rope state classification network to obtain the rope trajectory state output by the rope state classification network; wherein the rope trajectory state includes: rope upper state, rope lower state and rope-free state.
[0013] In one embodiment of the present application, counting the effective number of rope jumps based on the jumping action completion result and the rope trajectory state includes: if the jumping action completion result is the completion of the jumping action, and the rope trajectory state has the rope upper state and the rope lower state in the jumping action cycle, then counting the effective number of rope jumps is performed.
[0014] In one embodiment of the present application, determining the skeleton point information of a rope skipping athlete in a preset calibrated motion area based on a rope skipping evaluation video stream includes: preprocessing each frame of the rope skipping evaluation video stream to obtain an evaluation video stream to be analyzed; determining the human body area position of the rope skipping athlete in the calibrated motion area based on the evaluation video stream to be analyzed; and determining the skeleton point information based on the human body area position.
[0015] In one embodiment of the present application, preprocessing each frame of the video stream image of the rope skipping evaluation video stream includes: determining the distortion parameters of each frame of the video stream image by Zhang Zhengyou calibration method, and performing distortion correction on each frame of the video stream image based on the distortion parameters to obtain each distortion corrected image; updating the current frame distortion corrected image and the previous frame distortion corrected image of the current frame distortion corrected image by deep copy; preprocessing the current frame distortion corrected image, wherein the preprocessing includes image scaling processing, denoising processing, cropping processing and averaging processing.
[0016] In one embodiment of the present application, determining the human body area position of a rope jumper in a calibrated motion area based on the evaluation video stream to be analyzed includes: inputting each frame of the image to be analyzed in the evaluation video stream to be analyzed into a pedestrian detection network, and obtaining the human body area position corresponding to each frame of the image to be analyzed output by the pedestrian detection network.
[0017] In one embodiment of the present application, determining the skeleton point information based on the human body region position includes: enlarging the human body region position by a preset multiple to obtain an enlarged human body region; cropping the human body region image in the image to be analyzed based on the enlarged human body region; filling the human body region image with pixels based on a preset aspect ratio to obtain a target human body image; inputting the target human body image into a skeleton point detection model to obtain the skeleton point information output by the skeleton point detection model.
[0018] In one embodiment of the present application, before obtaining the skipping rope evaluation video stream, the method also includes: defining at least one movement position according to a preset upper limit on the number of evaluation persons; calibrating the movement position by a minimum circumscribed rectangle to obtain a preset calibrated movement area.
[0019] In a second aspect of the implementation manner of the present application, a skipping rope evaluation device is provided, which is used to execute the skipping rope evaluation method as described in any one of the first aspects, including: a video stream acquisition module, which is used to acquire a skipping rope evaluation video stream; a skeleton point determination module, which is used to determine the skeleton point information of a skipper in a preset calibrated motion area based on the skipping rope evaluation video stream; a jump determination module, which is used to determine a jump recognition standard based on the historical motion information of the skipper, and determine a completion result of the jumping action based on the skeleton point information and the jump recognition standard; a trajectory determination module, which is used to determine a rope trajectory state based on the skipping rope evaluation video stream; and a counting module, which is used to count the number of effective jumps based on the jumping action completion result and the rope trajectory state.
[0020] In one embodiment of the present application, historical motion information includes historical jump heights and historical jump frequencies; wherein the jump determination module is used to: determine a standard value for a minimum jump height based on historical jump heights; determine a standard number of frames for continuous vertical changes based on historical jump frequencies; and determine a standard value for a minimum number of vertical changes in pixels in a single frame based on historical jump heights and historical jump frequencies.
[0021] In one embodiment of the present application, the jumping judgment module is used to: determine the jumping state based on skeleton point information, the standard number of frames of continuous vertical change and the standard value of the minimum number of vertical change pixels in a single frame; determine the actual jumping height based on the jumping state; determine the completion result of the jumping action based on the actual jumping height and the standard value of the minimum jumping height.
[0022] In one embodiment of the present application, the jump determination module is used to: if the actual continuous vertical rising frame number of the target bone point in the bone point information is greater than or equal to the standard number of continuous vertical changes, and the actual single-frame rising change pixel number is greater than or equal to the single-frame minimum vertical change pixel number standard value, then the jump state is determined to be a rising state; if the actual continuous vertical falling frame number of the target bone point is greater than or equal to the standard number of continuous vertical changes, and the actual single-frame falling change pixel number is greater than or equal to the single-frame minimum vertical change pixel number standard value, then the jump state is determined to be a falling state; if the actual single-frame vertical change pixel number of the target bone point in the standard number of continuous vertical changes is less than the single-frame minimum vertical change pixel number standard value, then the jump state is determined to be a stationary state.
[0023] In one embodiment of the present application, the trajectory determination module is used to: subtract each frame of the video stream image in the jumping action cycle of the skipping rope evaluation video stream from the previous frame of the video stream image, and perform binarization processing to obtain multiple binary images of the moving object; perform feature enhancement processing on the multiple binary images of the moving object respectively to obtain multiple rope trajectory images; segment the multiple rope trajectory images according to a preset image size and a preset segmentation position to obtain at least one image to be spliced; splice the at least one image to be spliced in the channel dimension to obtain a rope feature map; determine the rope trajectory state based on the rope feature map.
[0024] In one embodiment of the present application, the trajectory determination module is used to: input the rope feature map into the rope state classification network to obtain the rope trajectory state output by the rope state classification network; wherein the rope trajectory state includes: rope upper state, rope lower state and rope-free state.
[0025] In one embodiment of the present application, the counting module is used to count the effective number of rope jumps if the jumping action completion result is the completion of the jumping action, and the rope trajectory state has the rope upper state and the rope lower state in the jumping action cycle.
[0026] In one embodiment of the present application, the skeleton point determination module is used to: pre-process each frame of the rope skipping evaluation video stream to obtain the evaluation video stream to be analyzed; determine the human body area position of the rope skipper in the calibrated exercise area based on the evaluation video stream to be analyzed; and determine the skeleton point information based on the human body area position.
[0027] In one embodiment of the present application, the skeleton point determination module is used to: determine the distortion parameters of each frame of the video stream image through the Zhang Zhengyou calibration method, and perform distortion correction on each frame of the video stream image based on the distortion parameters to obtain each distortion corrected image; update the current frame distortion corrected image and the previous frame distortion corrected image of the current frame distortion corrected image through deep copy; preprocess the current frame distortion corrected image, wherein the preprocessing includes image scaling processing, denoising processing, cropping processing and averaging processing.
[0028] In one embodiment of the present application, the skeleton point determination module is used to: input each frame of the image to be analyzed in the evaluation video stream to be analyzed into the pedestrian detection network, and obtain the human body area position corresponding to each frame of the image to be analyzed output by the pedestrian detection network.
[0029] In one embodiment of the present application, the skeleton point determination module is used to: enlarge the position of the human body area by a preset multiple to obtain an enlarged human body area; crop the human body area image in the image to be analyzed based on the enlarged human body area to obtain a target human body image; fill the human body area image with pixels based on a preset aspect ratio to obtain a target human body image; input the target human body image into the skeleton point detection model to obtain the skeleton point information output by the skeleton point detection model.
[0030] In one embodiment of the present application, the device also includes: an area calibration module; the area calibration module is used to: define at least one motion position according to a preset upper limit on the number of people to be evaluated; calibrate the motion position through a minimum circumscribed rectangle to obtain a calibrated motion area.
[0031] A third aspect of the present application provides an electronic device, comprising: a processor; and a memory, on which is stored an executable code for rope skipping evaluation, and when the executable code is executed by the processor, the processor executes the method described above.
[0032] A fourth aspect of the present application provides a non-temporary machine-readable storage medium on which executable code for rope skipping evaluation is stored. When the executable code is executed by a processor of an electronic device, the processor executes the method described above.
[0033] The technical solution provided by the implementation method of this application has the following beneficial effects:
[0034] The rope skipping evaluation method, device, electronic device and storage medium provided in the embodiments of the present application obtain a rope skipping evaluation video stream, and then determine the skeleton point information of the rope skipper in a preset calibrated motion area based on the rope skipping evaluation video stream, and further determine the jumping recognition standard based on the historical motion information of the rope skipper, and then determine the completion result of the jumping action based on the skeleton point information and the jumping recognition standard, thereby realizing adaptive adjustment of the jumping state recognition standard, avoiding the problem of incorrect jumping state judgment due to different jumping rhythms and different jumping abilities of different rope skippers, and can effectively suppress the situation of jumping misjudgment compared with fixed standards.
[0035] Furthermore, the present application can determine the rope trajectory state based on the skipping rope evaluation video stream, and then count the effective number of skipping ropes based on the jumping action completion result and the rope trajectory state, so that the rope trajectory state can be used to eliminate skipping rope violations such as interruptions, empty swings, double swings, and tiptoe jumps, thereby achieving accurate counting of the effective number of skipping ropes.
[0036] In general, the embodiment of the present application has a low degree of hardware dependence, can accurately count rope jumpers at a low cost, improve the statistical efficiency of the standard effective number of rope jumps, and help rope jumpers correct their exercise posture and improve their physical fitness. BRIEF DESCRIPTION OF THE DRAWINGS
[0037] By reading the detailed description below with reference to the accompanying drawings, the above and other purposes, features and advantages of the exemplary embodiments of the present application will become readily understood. In the accompanying drawings, several embodiments of the present application are shown in an exemplary and non-limiting manner, wherein:
[0038] Figure 1 Schematically shows a block diagram of an exemplary computing system 100 suitable for implementing the embodiments of the present application;
[0039] Figure 2 The flowchart of the rope skipping evaluation method according to an embodiment of the present application is schematically shown;
[0040] Figure 3 The following schematically shows a flow chart of a rope skipping evaluation method according to another embodiment of the present application;
[0041] Figure 4 The following schematically shows a flow chart of a rope skipping evaluation method according to another embodiment of the present application;
[0042] Figure 5 The structure diagram of a rope skipping evaluation device according to an embodiment of the present application is schematically shown;
[0043] Figure 6 A schematic block diagram of an electronic device according to an embodiment of the present application is schematically shown.
[0044] In the drawings, the same or corresponding reference numerals represent the same or corresponding parts. DETAILED DESCRIPTION
[0045] The principles and spirit of the present application will be described below with reference to several exemplary embodiments. It should be understood that these embodiments are provided only to enable those skilled in the art to better understand and implement the present application, and are not intended to limit the scope of the present application in any way. On the contrary, these embodiments are provided to make the present disclosure more thorough and complete, and to fully convey the scope of the present disclosure to those skilled in the art.
[0046] Figure 1 1 is a block diagram of an exemplary computing system 100 suitable for implementing the embodiments of the present application. Figure 1 As shown, the computing system 100 may include: a central processing unit (CPU) 101, a random access memory (RAM) 102, a read-only memory (ROM) 103, a system bus 104, a hard disk controller 105, a keyboard controller 106, a serial interface controller 107, a parallel interface controller 108, a display controller 109, a hard disk 110, a keyboard 111, a serial external device 112, a parallel external device 113, and a display 114. Among these devices, the CPU 101, the RAM 102, the ROM 103, the hard disk controller 105, the keyboard controller 106, the serial controller 107, the parallel controller 108, and the display controller 109 are coupled to the system bus 104. The hard disk 110 is coupled to the hard disk controller 105, the keyboard 111 is coupled to the keyboard controller 106, the serial external device 112 is coupled to the serial interface controller 107, the parallel external device 113 is coupled to the parallel interface controller 108, and the display 114 is coupled to the display controller 109. It should be understood that Figure 1 The structural block diagram is only for the purpose of illustration, and is not intended to limit the scope of the present application. In some cases, some devices may be added or reduced according to specific circumstances.
[0047] Those skilled in the art know that the embodiments of the present application can be implemented as a system, method or computer program product. Therefore, the present disclosure can be specifically implemented in the following forms, namely: complete hardware, complete software (including firmware, resident software, microcode, etc.), or a combination of hardware and software, generally referred to herein as "circuit", "module" or "system". In addition, in some embodiments, the present application can also be implemented in the form of a computer program product in one or more computer-readable media, which contains computer-readable program code.
[0048] Any combination of one or more computer-readable media may be used. A computer-readable medium may be a computer-readable signal medium or a computer-readable storage medium. A computer-readable storage medium may be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or device, or any combination of the above. More specific examples (non-exhaustive examples) of computer-readable storage media may include, for example: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this document, a computer-readable storage medium may be any tangible medium containing or storing a program that may be used by or in combination with an instruction execution system, device or device.
[0049] Computer-readable signal media may include data signals propagated in baseband or as part of a carrier wave, which carry computer-readable program code. Such propagated data signals may take a variety of forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. Computer-readable signal media may also be any computer-readable medium other than a computer-readable storage medium, which may send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device.
[0050] The program code embodied on the computer readable medium may be transmitted using any appropriate medium, including but not limited to wireless, wireline, optical fiber cable, RF, etc., or any suitable combination of the foregoing.
[0051] Computer program code for performing the operation of the present application can be written in one or more programming languages or a combination thereof, including object-oriented programming languages, such as Java, Smalltalk, C++, and conventional procedural programming languages, such as "C" language or similar programming languages. The program code can be executed entirely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or can be connected to an external computer (e.g., using an Internet service provider to connect through the Internet).
[0052] The following will describe the implementation of the present application with reference to the flowchart of the method of the present application embodiment and the block diagram of the device (or system). It should be understood that each square frame of the flowchart and / or block diagram and the combination of each square frame in the flowchart and / or block diagram can be implemented by computer program instructions. These computer program instructions can be provided to the processor of a general-purpose computer, a special-purpose computer or other programmable data processing device, so as to produce a kind of machine, and these computer program instructions are executed by a computer or other programmable data processing device, and a device for realizing the function / operation specified in the square frame in the flowchart and / or block diagram is generated.
[0053] These computer program instructions may also be stored in a computer-readable medium that enables a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable medium produce a product that includes an instruction device that implements the functions / operations specified in the blocks in the flowchart and / or block diagram.
[0054] Computer program instructions may also be loaded onto a computer, other programmable data processing apparatus, or other device so that a series of operational steps are performed on the computer, other programmable data processing apparatus, or other device to produce a computer-implemented process, thereby enabling the instructions executed on the computer or other programmable device to provide a process for implementing the functions / operations specified in the blocks in the flowchart and / or block diagram.
[0055] According to the implementation mode of the present application, a rope skipping evaluation method and device are proposed.
[0056] It should be understood herein that any number of elements in the drawings is for illustration rather than limitation, and any naming is only for distinction rather than having any limiting meaning.
[0057] The principles and spirit of the present application are explained in detail below with reference to several representative implementations of the present application. SUMMARY OF THE INVENTION
[0059] The applicant has found that the main rope skipping analysis scheme in the prior art can be to manually count by statisticians relying on manual experience to observe the movement state of the athlete, and subjectively judge and analyze based on the technical results to give manual suggestions, or to use a semi-automatic counting device based on Bluetooth for rope skipping analysis, or a counting scheme based on deep learning, which can use a bone point recognition model to analyze the athlete's body posture key point data and human body detection frame data, and then generate a waveform according to the distance from the hip joint key point in the human body posture key point data to the baseline, so as to count by obtaining each trough-peak-trough process in the waveform. However, the aforementioned various existing rope skipping analysis schemes cannot well meet the actual needs of current rope skipping analysis.
[0060] Based on this, the present application obtains the skipping evaluation video stream, and then determines the skeleton point information of the skipping athlete in the preset calibration motion area based on the skipping evaluation video stream, and further determines the jump identification standard based on the historical motion information of the skipping athlete, and then determines the jumping action completion result based on the skeleton point information and the jump identification standard, realizes the adaptive adjustment of the jumping state identification standard, avoids the problem of wrong jumping state judgment caused by different jumping rhythms and different jumping abilities of different skipping athletes, and can effectively suppress the situation of misjudgment of jumping relative to the fixed standard. Further, the present application can determine the rope trajectory state based on the skipping evaluation video stream, and then count the effective number of skipping ropes based on the jumping action completion result and the rope trajectory state, so that the rope trajectory state can be used to exclude the skipping rope violations such as interruption, empty shaking, double shaking, and tiptoe jumping, and realize the accurate counting of the effective number of skipping ropes. In general, the hardware dependence of the embodiment of the present application is low, and the skipping rope athletes can be accurately counted at low cost, and the statistical efficiency of the standard effective number of skipping ropes is improved, which is conducive to helping the skipping rope athletes correct their exercise posture and improve their physical fitness.
[0061] After introducing the basic principles of the present application, various non-limiting implementation methods of the present application are described in detail below.
[0062] Application Scenario Overview
[0063] The rope skipping evaluation method of the implementation mode of the present application is applicable to various types of electronic devices used for evaluating and analyzing rope skipping results, such as servers, computer equipment, and mobile electronic devices. By using the method proposed in the present application on these electronic devices used for evaluating and analyzing rope skipping results, it is possible to accurately count rope skippers at a low cost, improve the statistical efficiency of the standard effective number of rope skipping times, and help rope skippers correct their exercise posture and improve their physical fitness.
[0064] Exemplary Methods
[0065] Figure 2 The flowchart 200 of the rope skipping evaluation method according to an embodiment of the present application is schematically shown. Figure 2 To describe the rope skipping evaluation method according to the exemplary embodiment of the present application. It should be noted that the above application scenarios are only shown to facilitate understanding of the spirit and principle of the present application, and the embodiments of the present application are not limited in this respect. On the contrary, the embodiments of the present application can be applied to any applicable scenario.
[0066] In step S201, a skipping evaluation video stream is obtained. In an embodiment of the present application, the skipping evaluation video stream can be obtained by an image capture device such as a camera. It is understandable that the image information of at least one skipping athlete during the actual skipping exercise process can be recorded in the imaging field of the skipping evaluation video stream, and the skipping evaluation results of each skipping athlete can be obtained by analyzing this image information. It is also understandable that the way to obtain the skipping evaluation video stream can be various. In practical applications, it is necessary to select a suitable acquisition method according to the actual application situation, and the present application does not make any restrictions in this regard.
[0067] In step S202, the skeleton point information of the rope jumper in the preset calibrated motion area is determined based on the rope skipping evaluation video stream. In the embodiment of the present application, the aforementioned preset calibrated motion area is a pre-demarcated area provided to the rope jumper for rope skipping. In addition, the skeleton point information usually includes stable and distinguishable feature points in the image of the human body's hands, feet, etc., which can be re-identified and matched even after the image is transformed by rotation, scaling or partial occlusion.
[0068] In step S203, the jump recognition standard is determined based on the historical motion information of the rope skipper, and the jump action completion result is determined based on the skeleton point information and the jump recognition standard. In the embodiment of the present application, the historical motion information of the rope skipper refers to the motion information of the previous moment or the previous frame relative to the current motion information of the rope skipper, so as to continuously and adaptively adjust the jump recognition standard of the rope skipper in this rope skipping exercise by using the historical motion information. Then, whether the jump action is completed is judged based on the skeleton point information and the jump recognition standard, so as to determine the jump action completion result.
[0069] In step S204, the rope trajectory state is determined based on the rope skipping evaluation video stream. In the embodiment of the present application, the aforementioned rope trajectory state may refer to the movement trajectory information of the rope, and the rope trajectory state may include but is not limited to the rope upper state, the rope lower state and the rope-free state. Among them, the rope upper state refers to the state where the rope exceeds the head, the rope lower state refers to the state where the rope is lower than the feet, and the rope-free state refers to the state where the rope cannot be detected at the current position.
[0070] In step S205, the effective number of rope skipping is counted based on the jumping action completion result and the rope trajectory state. In the embodiment of the present application, it is necessary not only to determine whether the jumping action is completed, but also to determine in combination with the rope trajectory state, accurately remove rope skipping violations such as rope skipping interruption, empty swing, double swing, tiptoe jump, etc., and achieve accurate counting of the effective number of rope skipping.
[0071] The embodiment of the present application obtains a skipping evaluation video stream, and then determines the skeleton point information of the skipper in the preset calibrated motion area based on the skipping evaluation video stream, and further determines the jump identification standard based on the historical motion information of the skipper, and then determines the completion result of the jumping action based on the skeleton point information and the jump identification standard, so as to realize adaptive adjustment of the jump state identification standard, avoid the problem of wrong jump state judgment due to different jumping rhythms and different jumping abilities of different skippers, and effectively suppress the situation of jump misjudgment compared with the fixed standard. Further, the present application can determine the rope trajectory state based on the skipping evaluation video stream, and then count the effective number of skipping based on the completion result of the jumping action and the rope trajectory state, so that the rope trajectory state can be used to exclude skipping violations such as interruption, empty swing, double swing, and tiptoe jump, and realize accurate counting of the effective number of skipping.
[0072] In general, the embodiment of the present application has a low degree of hardware dependence, can accurately count rope jumpers at a low cost, improve the statistical efficiency of the standard effective number of rope jumps, and help rope jumpers correct their exercise posture and improve their physical fitness.
[0073] In some embodiments, the process of determining the completion result of the jumping action can be further designed. Figure 3 The process of determining the completion result of the jump action is described in detail. Figure 3 A schematic diagram 300 of a skipping rope evaluation method according to another embodiment of the present application is schematically shown. Figure 3 The rope skipping evaluation method shown in the embodiment of the present application may include:
[0074] In step S301, a preset calibrated motion area is determined. In an embodiment of the present application, at least one motion position can be firstly delineated according to a preset upper limit of the number of people to be evaluated, wherein the preset upper limit of the number of people to be evaluated refers to the maximum number of people who can perform rope skipping at the same time in this round of evaluation, which can be set to 3-5 people, and can be set by the user inputting the preset upper limit of the number of people to be evaluated. Furthermore, motion positions consistent with the preset upper limit of the number of people to be evaluated can be delineated, and it is necessary to ensure that these motion positions can be located within the imaging field of view of the image capture device.
[0075] Then, the motion position may be calibrated by a minimum circumscribed rectangle to obtain a preset calibrated motion region, and the center point position coordinates of the preset calibrated motion region may be calibrated at the same time to represent the position information of the preset calibrated motion region.
[0076] In step S302, a skipping rope evaluation video stream is obtained. In the embodiment of the present application, the content of step S302 is substantially the same as that of step S201, and the present application will not repeat them here.
[0077] In step S303, the skeleton point information of the rope jumper in the preset calibrated motion area is determined based on the rope skipping evaluation video stream. First, each frame of the video stream image of the rope skipping evaluation video stream can be preprocessed to obtain the evaluation video stream to be analyzed. Specifically, the distortion parameters of each frame of the video stream image can be first determined by the Zhang Zhengyou calibration method, and each frame of the video stream image can be subjected to distortion correction based on the distortion parameters to obtain each distortion corrected image. Then, the current frame distortion corrected image and the previous frame distortion corrected image of the current frame distortion corrected image can be updated through deep copy. Then, the current frame distortion corrected image can be preprocessed, wherein the preprocessing includes image scaling processing, denoising processing, cropping processing and averaging processing.
[0078] Then, the human body area position of the rope skipper in the calibrated motion area can be determined based on the evaluation video stream to be analyzed. Specifically, each frame of the image to be analyzed in the evaluation video stream to be analyzed can be input into the pedestrian detection network to obtain the human body area position corresponding to each frame of the image to be analyzed output by the pedestrian detection network. The pedestrian detection network can identify and locate the coordinate position of the pedestrian in the image or video frame.
[0079] Then, the skeleton point information can be determined based on the human body region position. Specifically, the human body region position can be enlarged by a preset multiple to obtain an enlarged human body region. The preset multiple can be set to any value between 1.5-2, and in practical applications it needs to be determined according to the actual application situation. The present application does not impose any restrictions in this regard. Then, the human body region image can be obtained by cropping in the image to be analyzed based on the enlarged human body region. Then, the human body region image can be pixel-filled based on the preset aspect ratio to obtain a target human body image, wherein the pixel value filled in the pixel filling process can be (0, 0, 0), that is, black pixels are filled. Then, the target human body image is input into the skeleton point detection model to obtain the skeleton point information output by the skeleton point detection model. Among them, the skeleton point detection model is used to identify and locate specific significant feature points in an image or video frame, which can include stable and distinguishable feature points in images such as the hands and feet of the human body.
[0080] In step S304, the jump identification standard is determined based on the historical motion information of the rope skipper. In the embodiment of the present application, the historical motion information may include but is not limited to the historical jump height and the historical jump frequency. The historical jump height may refer to the jump height of the previous moment or the previous frame relative to the current moment or the current frame of the rope skipper, the historical jump frequency may refer to the jump frequency of the previous moment or the previous frame relative to the current moment or the current frame of the rope skipper, and the jump frequency may refer to the number of frames or time required for the rope skipper to complete a jump.
[0081] Specifically, the minimum jump height standard value can be determined based on the historical jump height. It is understandable that when a rope skipper enters a preset calibration motion area to perform rope skipping, its initial minimum jump height standard value is zero pixel number, and when it performs the first jump, it generates the first jump height data (the jump height data can be represented by the number of pixel changes in the vertical direction), so the first jump height data can be used as the current minimum jump height standard value. When it performs the second jump, it generates the second jump height data, and the minimum jump height standard value can be updated according to the first jump height data and the second jump height data, for example, the average value of a jump height data and the second jump height data can be used as the current minimum jump height standard value. It is understandable that the adaptive adjustment method of the minimum jump height standard value is various, and in practical applications, it needs to be adjusted according to the actual application situation, and the present application does not make any restrictions in this regard.
[0082] Further, the continuous vertical change standard frame number can be determined based on the historical jump frequency. It is understandable that when the rope skipper enters a preset calibration motion area to perform rope skipping, the initial jump frequency is zero. After the first jump, the first jump frequency data is generated. The number of frames sustained by the jump rising state and the number of frames sustained by the jump falling state can be analyzed in this first jump frequency data. The number of frames sustained by the jump rising state or the number of frames sustained by the jump falling state can be used as the current continuous vertical change standard frame number. When the second jump is performed, the second jump frequency data is generated. The continuous vertical change standard frame number can be updated according to the first jump frequency data and the second jump frequency data. For example, the average value of the number of frames sustained by the jump rising state in the first jump frequency data and the number of frames sustained by the jump rising state in the second jump frequency data can be used as the current continuous vertical change standard frame number. It is understandable that the adaptive adjustment method of the continuous vertical change standard frame number is diverse, and in practical applications, it needs to be adjusted according to the actual application situation. The present application does not impose any restrictions in this regard.
[0083] Further, the standard value of the minimum vertical change pixel number of a single frame can be determined based on the historical jump height and the historical jump frequency. In the embodiment of the present application, the standard value of the minimum vertical change pixel number of a single frame can refer to the lower limit of the change value of the number of rising pixels in each frame in the jump rising state or the lower limit of the change value of the number of falling pixels in each frame in the jump falling state. It can be obtained by dividing the rising height in the jump rising state in the historical jump height by the number of frames in which the jump rising state lasts, or by dividing the falling height in the jump falling state in the historical jump height by the number of frames in which the jump falling state lasts.
[0084] By doing so, the judging criteria can be adaptively adjusted for different rope skipping athletes, and the jumping status of each rope skipping athlete can be accurately analyzed based on this criteria, avoiding the problem of misjudgment of jumping status due to different jumping rhythms and different jumping abilities of different rope skipping athletes. Compared with fixed standards, it can effectively suppress misjudgment of jumping.
[0085] In step S305, the jump state is determined based on the skeleton point information, the continuous vertical change standard frame number and the single-frame minimum vertical change pixel number standard value. Specifically: if the actual continuous vertical rising frame number of the target skeleton point in the skeleton point information is greater than or equal to the continuous vertical change standard frame number, and the actual single-frame rising change pixel number is greater than or equal to the single-frame minimum vertical change pixel number standard value, the jump state is determined to be the rising state; if the actual continuous vertical falling frame number of the target skeleton point is greater than or equal to the continuous vertical change standard frame number, and the actual single-frame falling change pixel number is greater than or equal to the single-frame minimum vertical change pixel number standard value, the jump state is determined to be the falling state; if the actual single-frame vertical change pixel number of the target skeleton point in the continuous vertical change standard frame number is less than the single-frame minimum vertical change pixel number standard value, the jump state is determined to be the static state.
[0086] In step S306, the actual jumping height is determined based on the jumping state. In the embodiment of the present application, the highest position of the rope skipper can be determined according to the jumping state of the rope skipper, that is, the position where the rope skipper is in the last rising state, and the height above the ground of the highest position is the actual jumping height.
[0087] In step S307, the jumping action completion result is determined based on the actual jumping height and the minimum jumping height standard value. It is understandable that when the actual jumping height is greater than or equal to the minimum jumping height standard value, it can be determined that the jumping action of the rope skipper is completed, otherwise the jumping action is not completed.
[0088] In some embodiments, the process of determining the rope trajectory state can be further designed, and the effective number of rope skipping can be counted in combination with the rope trajectory state and the jumping action completion result. Figure 4 The process of determining the rope trajectory state and the method of counting the effective number of rope skipping are described in detail. Figure 4 The flowchart 400 of the rope skipping evaluation method according to another embodiment of the present application is schematically shown. Figure 4 The rope skipping evaluation method shown in the embodiment of the present application may include:
[0089] In step S401, each frame of video stream image in the jumping action cycle of the skipping rope evaluation video stream is subtracted from the previous frame of video stream image of each frame of video stream image, and binarization is performed to obtain multiple binary images of moving objects. It can be understood that the result obtained by subtracting each frame of video stream image from the previous frame of video stream image of each frame of video stream image is that the pixel value of the static part between the two frames of image is 0, and the pixel value of the moving part is greater than 0, thereby highlighting the area where the rope moves and enhancing the image characteristics of the rope. After the binarization process, a binary image (black and white image) of the moving object can be obtained, that is, a binary image of the rope in the motion process.
[0090] In step S402, feature enhancement processing is performed on multiple binary images of moving objects respectively to obtain multiple rope trajectory images. In the embodiment of the present application, image operations such as Gaussian denoising, dilation corrosion, etc. can be performed on the binary images of moving objects to further enhance the rope features, thereby obtaining rope trajectory images.
[0091] In step S403, at least one image to be spliced is obtained by segmenting the multiple rope trajectory images according to the preset image size and the preset segmentation position. In the embodiment of the present application, the preset segmentation position may include but is not limited to the five positions above the top of the head, above the left shoulder, above the right shoulder, below the left foot, and below the right foot. The preset image size may be N×N, where N is the number of pixels, and N is greater than 0. N may be 10 for example. In actual applications, it depends on the actual application situation. The present application does not impose any restrictions in this regard. In this way, five N×N images to be spliced corresponding to the above five positions can be obtained.
[0092] In step S404, at least one image to be spliced is spliced in the channel dimension to obtain a rope feature map. In the embodiment of the present application, at least one image to be spliced can be spliced in the channel dimension by a splicing function of the OpenCV library to obtain an N×N×5 rope feature map.
[0093] Specifically, a common color image is composed of three channels, RGB, and a binary image is a single channel. The above five N×N images to be spliced are all single-channel images, and these five channels need to be connected to form a new image feature. Then each single-channel image is N×N×1, where N×N is the resolution of the image and “1” is the number of channels. Therefore, the image feature of the rope feature map after splicing is N×N×5.
[0094] In step S405, the rope trajectory state is determined based on the rope feature map. In an embodiment of the present application, the rope feature map can be input into the rope state classification network to obtain the rope trajectory state output by the rope state classification network, wherein the rope trajectory state includes: rope upper state, rope lower state and rope-free state. The rope state classification network can be composed of a fully connected network that is not limited to depth, and is an artificial neural network model for image, text or other data classification tasks. These models are usually composed of a series of convolutional layers, pooling layers, fully connected layers and activation functions, the purpose of which is to map the input data to one of a set of category labels.
[0095] In step S406, effective rope skipping count is performed based on the jumping action completion result and the rope track state. In the embodiment of the present application, if the jumping action completion result is to complete the jumping action, and the rope track state has the rope upper state and the rope lower state in the jumping action cycle, it can be understood that the rope upper state should occur when the jumping state is in a descending state, and the rope lower state should occur when the jumping state is in an ascending state, then the effective rope skipping count is performed. On the contrary, the effective rope skipping count is not performed, and the invalid rope skipping count can be performed. In combination with the jumping action completion result and the rope track state, the rope skipping violations such as interruption, empty swing, double swing, and tiptoe jumping can be effectively excluded, and the accurate counting of the effective rope skipping count is realized.
[0096] Exemplary Devices
[0097] After introducing the method of the exemplary embodiment of the present application, next, refer to Figure 5 and Figure 6 The related products of the rope skipping evaluation method according to the exemplary embodiment of the present application are described.
[0098] Figure 5 The structure diagram of the rope skipping evaluation device according to an embodiment of the present application is schematically shown. Figure 5 The rope skipping evaluation device 500 shown in the embodiment of the present application may include:
[0099] The video stream acquisition module 501 is used to acquire the rope skipping evaluation video stream;
[0100] Skeleton point determination module 502, used to determine the skeleton point information of the rope skipping athlete in the preset calibrated motion area based on the rope skipping evaluation video stream;
[0101] A jump determination module 503 is used to determine a jump determination standard based on the historical movement information of the rope skipper, and to determine a jump action completion result based on the skeleton point information and the jump determination standard;
[0102] A trajectory determination module 504, for determining the rope trajectory state based on the rope skipping evaluation video stream;
[0103] The counting module 505 is used to count the effective number of rope skipping based on the jumping action completion result and the rope trajectory state.
[0104] The rope skipping evaluation device shown in the present application obtains the rope skipping evaluation video stream, and then determines the skeleton point information of the rope skipper in the preset calibrated motion area based on the rope skipping evaluation video stream, and further determines the jump identification standard based on the historical motion information of the rope skipper, and then determines the jump action completion result based on the skeleton point information and the jump identification standard, so as to realize the adaptive adjustment of the jump state identification standard, avoid the problem of wrong jump state judgment caused by different jump rhythms and different jump abilities of different rope skippers, and effectively suppress the situation of jump misjudgment compared with the fixed standard. Further, the present application can determine the rope trajectory state based on the rope skipping evaluation video stream, and then count the effective rope skipping times based on the jump action completion result and the rope trajectory state, so as to eliminate the rope skipping violations such as interruption, empty swing, double swing, tiptoe jump, etc. by using the rope trajectory state, and realize the accurate counting of the effective rope skipping times.
[0105] In general, the embodiment of the present application has a low degree of hardware dependence, can accurately count rope jumpers at a low cost, improve the statistical efficiency of the standard effective number of rope jumps, and help rope jumpers correct their exercise posture and improve their physical fitness.
[0106] Since the specific functions realized by the rope skipping evaluation device are the same as those of the rope skipping evaluation method described above, the specific details or further implementation methods can refer to the above description of the rope skipping evaluation method and will not be described in detail here.
[0107] Figure 6 Schematically shows a schematic block diagram of an electronic device according to an embodiment of the present application. Figure 6 , the electronic device 600 may include a processor 601. Further, the electronic device may also include a memory 602 storing computer instructions, which, when executed by the processor 601, enables the electronic device 600 to execute the methods described in the above multiple embodiments or implementations.
[0108] In some implementation scenarios, the electronic device 600 may include a server or a terminal device, such as a physical server, a cloud server, a server cluster, a data processing device, an application testing robot, a computer terminal, a smart terminal, a PC device, an Internet of Things terminal, etc.
[0109] According to different implementation scenarios, the processor 601 mentioned above may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc.
[0110] Based on the above, the present application further discloses a computer-readable storage medium, which includes program instructions. When the program instructions are executed by a processor, the methods described in the above multiple embodiments or implementations are implemented.
[0111] In some implementation scenarios, the above-mentioned computer-readable storage medium may be any appropriate magnetic storage medium or magneto-optical storage medium, such as resistive random access memory RRAM (Resistive Random Access Memory), dynamic random access memory DRAM (Dynamic Random Access Memory), static random access memory SRAM (Static Random-Access Memory), enhanced dynamic random access memory EDRAM (Enhanced Dynamic Random Access Memory), high-bandwidth memory HBM (High-Bandwidth Memory), hybrid memory cube HMC (Hybrid Memory Cube), etc., or any other medium that can be used to store the required information and can be accessed by the application, module or both. Any such computer storage medium may be part of the device or accessible or connectable to the device. Any application or module described in the present invention may be implemented using computer-readable / executable instructions that may be stored or otherwise maintained by such a computer-readable medium.
[0112] It should be noted that although several devices or sub-devices of the rope skipping evaluation device are mentioned in the above detailed description, this division is not mandatory. In fact, according to the embodiment of the present application, the features and functions of two or more devices described above can be embodied in one device. Conversely, the features and functions of one device described above can be further divided into multiple devices to be embodied.
[0113] In addition, although the operations of the present method are described in a specific order in the accompanying drawings, this does not require or imply that the operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. On the contrary, the steps depicted in the flow chart can be performed in a different order. Additionally or alternatively, some steps can be omitted, multiple steps can be combined into one step, and / or one step can be decomposed into multiple steps.
[0114] The use of the verbs "comprise", "include" and their conjugations mentioned in the application documents does not exclude the presence of elements or steps other than those recorded in the application documents. The article "a" or "an" before an element does not exclude the presence of a plurality of such elements.
[0115] Although the spirit and principle of the present application have been described with reference to several specific embodiments, it should be understood that the present application is not limited to the disclosed specific embodiments, and the division of various aspects does not mean that the features in these aspects cannot be combined to benefit, and this division is only for the convenience of expression. The present application is intended to cover various modifications and equivalent arrangements included in the spirit and scope of the attached claims. The scope of the attached claims conforms to the broadest interpretation, thereby including all such modifications and equivalent structures and functions.
Claims
1. A rope skipping evaluation method, characterized in that: include: Get the video stream of the skipping rope evaluation; Determine the skeleton point information of the rope skipping athlete in the preset calibrated motion area based on the rope skipping evaluation video stream; Determining a jumping recognition standard based on the historical movement information of the rope skipping athlete, and determining a jumping action completion result based on the skeleton point information and the jumping recognition standard; Determining a rope trajectory state based on the rope skipping evaluation video stream; The effective number of rope skipping is counted based on the jumping action completion result and the rope trajectory state.
2. The rope skipping evaluation method according to claim 1, characterized in that: The historical sports information includes historical jumping height and historical jumping frequency; wherein the jump identification criteria determined based on the historical sports information of the rope skipper include: Determining a minimum jump height standard value based on the historical jump height; Determining a standard number of frames for continuous vertical changes based on the historical jump frequency; The standard value of the minimum vertical change pixel number of a single frame is determined based on the historical jump height and the historical jump frequency.
3. The rope skipping evaluation method according to claim 2, characterized in that: The determining of the jumping action completion result based on the skeleton point information and the jumping identification standard comprises: Determine the jump state based on the skeleton point information, the continuous vertical change standard frame number and the single frame minimum vertical change pixel number standard value; determining an actual jump height based on the jump state; The jumping action completion result is determined based on the actual jumping height and the minimum jumping height standard value.
4. The rope skipping evaluation method according to claim 3, characterized in that: The step of determining the jump state based on the skeleton point information, the continuous vertical change standard frame number and the single frame minimum vertical change pixel number standard value comprises: If the actual continuous vertical rising frame number of the target skeleton point in the skeleton point information is greater than or equal to the continuous vertical change standard frame number, and the actual single-frame rising change pixel number is greater than or equal to the single-frame minimum vertical change pixel number standard value, then the jump state is determined to be a rising state; If the actual continuous vertical drop frame number of the target skeleton point is greater than or equal to the continuous vertical change standard frame number, and the actual single-frame drop change pixel number is greater than or equal to the single-frame minimum vertical change pixel number standard value, then the jump state is determined to be a drop state; If the actual single-frame vertical change pixel number of the target skeleton point in the continuous vertical change standard frame number is less than the single-frame minimum vertical change pixel number standard value, it is determined that the jumping state is a static state.
5. The rope skipping evaluation method according to claim 1, characterized in that: Determining the rope trajectory state based on the rope skipping evaluation video stream includes: Subtracting each frame of the video stream image in the jumping action cycle of the rope skipping evaluation video stream from the previous frame of the video stream image, and performing binarization processing to obtain multiple binary images of the moving object; Performing feature enhancement processing on the plurality of binary images of the moving object respectively to obtain a plurality of rope trajectory images; Segmenting the plurality of rope trajectory images to obtain at least one image to be spliced according to a preset image size and a preset segmentation position; Splicing the at least one image to be spliced in a channel dimension to obtain a rope feature map; The rope trajectory state is determined based on the rope characteristic map.
6. The rope skipping evaluation method according to claim 5, characterized in that: The determining the rope trajectory state based on the rope characteristic graph comprises: Inputting the rope feature map into a rope state classification network to obtain the rope trajectory state output by the rope state classification network; The rope trajectory states include: rope upper state, rope lower state and rope-free state.
7. The rope skipping evaluation method according to claim 6, characterized in that: The counting of the effective number of rope skipping based on the jumping action completion result and the rope trajectory state comprises: If the jumping action completion result is the completion of the jumping action, and the rope trajectory state has the rope upper state and the rope lower state in the jumping action cycle, the effective rope skipping times are counted.
8. A rope skipping evaluation device, characterized in that: Used to perform the rope skipping evaluation method according to any one of claims 1 to 7, comprising: Video stream acquisition module, used to obtain the skipping rope evaluation video stream; A skeleton point determination module, used to determine skeleton point information of a rope skipper in a preset calibrated motion area based on the rope skipping evaluation video stream; A jumping determination module, used to determine a jumping determination standard based on the historical movement information of the rope skipper, and to determine a jumping action completion result based on the skeleton point information and the jumping determination standard; A trajectory determination module, used to determine the rope trajectory state based on the rope skipping evaluation video stream; The counting module is used to count the effective number of rope skipping based on the completion result of the jumping action and the rope trajectory state.
9. An electronic device, characterized in that: include: processor; as well as A memory having executable codes for rope skipping evaluation stored thereon, wherein when the executable codes are executed by the processor, the processor is caused to execute the method as described in any one of claims 1-7.
10. A non-transitory machine-readable storage medium having stored thereon an executable code for rope skipping assessment, wherein when the executable code is executed by a processor of an electronic device, the processor is caused to execute the method as described in any one of claims 1-7.
Citation Information
Cited By
Rope skipping counting method, system, equipment and medium
CN121661715A
A method, system, device, and medium for jump rope counting
CN121661715B
