A physical fitness testing method based on human skeleton trajectory tracking

Abstract

The present application discloses a physical fitness test method based on human skeleton trajectory tracking, which starts to identify the tester based on limb feature points at the beginning of video acquisition, providing conditions for incorporating the tester's performance at the beginning of the test into the judgment of the validity of the test results. Moreover, when the method in this specification realizes the tester identification based on limb feature points, the action corresponding to the second point is corrected by the maximum change of the first point. Even if the tester's posture is not conducive to the embodiment of the tester's behavior in the collected video, the tester's real action can be restored, which is conducive to the objective judgment of the validity of the test results of the tester.

Description

Technical Field

[0001] The present application relates to the technical field of data processing based on image recognition, and in particular to a physical fitness testing method based on human skeleton trajectory tracking. Background Art

[0002] The development of technology has brought great convenience to people's production and life. However, in some fields, it is still difficult to convert manual work to automatic work. For example, in the field of physical fitness testing, usually, there may not be only one person taking the test at the same time. How to judge whether the actions of each tester meet the standards when there are multiple testers taking the test at the same time has become an urgent problem to be solved. Summary of the invention

[0003] An embodiment of the present application provides a physical fitness testing method based on human skeleton trajectory tracking to at least partially solve the above technical problems.

[0004] The present application embodiment adopts the following technical solutions:

[0005] In a first aspect, an embodiment of the present application provides a physical fitness testing method based on human skeleton trajectory tracking, the method comprising:

[0006] When performing video acquisition, identifying the body feature points of the tester in each frame image of the video;

[0007] Determine a curve of a change in the distance of a specified feature point in the video compared to an edge of the image over time; the specified feature point is any one of the limb feature points;

[0008] The limb feature points to which the variation curves with the same variation rate at each moment in the first time period belong are determined as a point cluster, so that each point cluster corresponds to one of the testers; the first time period is positively correlated with a preset parameter, and is positively correlated with the duration when the ratio of the variation curves with the maximum variation rate detected to all the variation curves reaches a preset ratio threshold; the preset parameter is preset for the test item corresponding to the video;

[0009] For each of the point clusters, determine a first point and a second point of the point cluster; the first point is the limb feature point with the largest variation in the point cluster; the second point is the limb feature point corresponding to a reference point preset for the test item;

[0010] determining a correction value based on a maximum change of the change curve of the first point; the correction value is positively correlated with the maximum change of the change curve of the first point;

[0011] Using the correction value, correct the difference between the maximum changes of the change amount curve corresponding to the first target point to obtain a correction result; the first target point is the second point corresponding to the change amount curve to which the maximum value and the minimum value of each maximum change amount belong;

[0012] If the ratio of the distance between the correction result and the first target point matches the ratio of the reference result preset for the second target point and the reference distance preset for the second target point, the test result obtained for the tester is determined to be a valid result; wherein the second target point is the reference point corresponding to the first target point.

[0013] In an optional embodiment of the present specification, the test items include at least one of the following: sit-ups, push-ups, pull-ups, and bent-arm hangs.

[0014] In an optional embodiment of the present specification, the limb feature points include at least one of the following: feature points corresponding to the tester's joints, feature points corresponding to the tester's bone endpoints, feature points corresponding to the tester's bone midpoints, and feature points corresponding to the tester's skull top.

[0015] In an optional embodiment of this specification, the method further includes:

[0016] Determine the test subject corresponding to the point cluster to which the limb feature point to which the change amount curve whose change rate does not reach the maximum value in the first time period belongs as the target test subject;

[0017] Determine whether the change rate of the change amount curve of the limb feature point of the target tester reaches a maximum value in a second time period after the first time period;

[0018] If yes, then determine the first point and the second point of the point cluster corresponding to the target tester.

[0019] In an optional embodiment of this specification, the method further includes:

[0020] If not, then directly set failure as the test result of the target tester.

[0021] In an optional embodiment of the present specification, after determining the target tester, the method further includes:

[0022] Sending a motion adjustment prompt to the target tester so that the target tester can standardize his / her motion.

[0023] In an optional embodiment of the present specification, when the target tester is unique, the duration of the second time period is positively correlated with the maximum value of the change amount of the limb feature points detected for the target tester in the first time period, and negatively correlated with the duration of the first time period;

[0024] In the case that the target tester is not unique and the positions of the target testers in the image are not adjacent, using a preset designated time length as the length of the second time period;

[0025] When the target tester is not unique and the positions of at least two target testers in the image are adjacent, the duration of the second time period is set to zero.

[0026] At least one of the above technical solutions adopted in the embodiments of the present application can achieve the following beneficial effects:

[0027] The method in this specification starts to identify the test subject based on the body feature points at the beginning of the video acquisition, which provides conditions for incorporating the test subject's performance at the beginning of the test into the judgment of the validity of the test results. Moreover, when the method in this specification realizes the test subject identification based on the body feature points, the action corresponding to the second point is corrected by the maximum change of the first point. Even if the test subject's posture is not conducive to the reflection of the test subject's behavior in the collected video, the test subject's real action situation can be restored, which is conducive to the objective judgment of the validity of the test result of the test subject. BRIEF DESCRIPTION OF THE DRAWINGS

[0028] The drawings described herein are used to provide a further understanding of the present application and constitute a part of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application. In the drawings:

[0029] Figure 1 A schematic diagram of a physical fitness test method based on human skeleton trajectory tracking provided in an embodiment of this specification;

[0030] Figure 2 It is a schematic diagram of the structure of an electronic device in an embodiment of this specification. DETAILED DESCRIPTION

[0031] The present invention is further described in detail below by specific embodiments in conjunction with the accompanying drawings. Wherein similar elements in different embodiments adopt associated similar element numbers. In the following embodiments, many detailed descriptions are for making the present application better understood. However, those skilled in the art can easily recognize that some features can be omitted in different situations, or can be replaced by other elements, materials, methods. In some cases, some operations related to the present application are not shown or described in the specification, and this is to avoid the core part of the present application being overwhelmed by too much description, and for those skilled in the art, it is not necessary to describe these related operations in detail, and they can fully understand the related operations according to the description in the specification and the general technical knowledge in the art.

[0032] In addition, the features, operations or characteristics described in the specification can be combined in any appropriate manner to form various implementations. At the same time, the steps or actions in the method description can also be interchanged or adjusted in a manner that is obvious to those skilled in the art. Therefore, the various sequences in the specification and the drawings are only for the purpose of clearly describing a certain embodiment and are not meant to be a required sequence, unless otherwise specified that a certain sequence must be followed.

[0033] The serial numbers of the components in this document, such as "first", "second", etc., are only used to distinguish the objects described and do not have any order or technical meaning. The "connection" and "coupling" mentioned in this application, unless otherwise specified, include direct and indirect connections (couplings).

[0034] The technical solutions provided by various embodiments of the present application are described in detail below in conjunction with the accompanying drawings.

[0035] like Figure 1 As shown, the physical fitness test method based on human skeleton trajectory tracking in this specification includes the following steps:

[0036] S100: When capturing a video, identifying body feature points of the tester in each frame of the video.

[0037] The method in this specification is applicable to the case where multiple people (more than one) participate in the test at the same time. Limb feature points are points that can express the characteristics of the tester's limbs when they are in action. In the relevant technology, technical means that can capture limb feature points based on images and videos that can be segmented into images are applicable to this specification when conditions permit.

[0038] This step is executed when the video acquisition starts, that is, when the video acquisition starts, the body feature points of the tester begin to be captured, so as to determine the body feature points more timely.

[0039] This specification does not specifically limit the order of when the test starts and when the video acquisition starts. Preferably, video acquisition is performed before starting the test to identify the limb feature points before clustering the limb feature points.

[0040] In an optional embodiment of the present specification, the test scenario may include the following test items: sit-ups, push-ups, pull-ups, bent-arm hangs, etc. The test scenario may be a daily training scenario, a physical education test scenario, a sports team test scenario, a military training scenario, etc.

[0041] Optionally, the limb feature points include at least one of the following: feature points corresponding to the tester's joints, feature points corresponding to the tester's bone endpoints, feature points corresponding to the tester's bone midpoints, and feature points corresponding to the tester's skull top.

[0042] S102: Determine a curve of a change in the distance of a specified feature point in the video compared to an edge of the image over time.

[0043] The designated feature point in this specification is any one of the limb feature points. In other words, it is necessary to determine the change amount curve for each limb feature point. Factors affecting the change amount curve include: the specific test items, the tester's movements during the test, the relative position relationship between the image acquisition device and the tester when capturing the video, and mutual occlusion between the testers.

[0044] Exemplarily, the horizontal axis of the variation curve is time, and the vertical axis is the variation.

[0045] S104: Determine the limb feature points to which the change amount curves having the same change rate at each moment in the first time period belong as a point cluster.

[0046] The clustering achieved by this step can make each point cluster correspond to one of the testers. In this way, even if there is a phenomenon of mutual occlusion between the testers, the attribution of the limb feature points can be accurately determined. For example, in the sit-up test, tester A blocked the tester B, and more comprehensive and continuously distributed limb feature points can be collected for tester A. However, tester B can only collect the limb feature points of the head and the limb feature points of the legs, and cannot collect the limb feature points of the upper limbs and buttocks. Usually, during the exercise of the tester, there is mutual cooperation and coordination between the limbs, and the possibility of highly coordinated and unified movements between different testers is low. It can be seen that through the method in this specification, the limb feature points of the head and the limb feature points of the legs with discontinuous distribution can be more accurately attributed to tester B.

[0047] The first time period is positively correlated with the preset parameter and the duration when the ratio of the change amount curve with the maximum change rate to all change amount curves reaches a ratio threshold. Optionally, the first time period is the sum of the preset parameter and the duration.

[0048] The preset parameter is set for the test item corresponding to the video and is preset based on experience. For example, if a pull-up has a short action cycle, the preset parameter for pull-ups is small; if a sit-up has a long action cycle, the preset parameter for pull-ups is large. The preset parameter is the time it takes for an action cycle to obtain a qualified test result.

[0049] In general, the actions of the test items are periodic, and the relative distance between at least one part of the tester's limbs and the reference object at a fixed position on the ground or a certain position changes periodically. When the relative distance reaches the maximum, a movement cycle is completed. The comparison achieved by the ratio threshold is to identify that most of the testers have completed a movement cycle. Usually, a group of testers are mostly people with similar situations. For example, in the military training scene, the test participants are all people of similar age, and there are indeed differences in physical fitness, but the difference will not be too large. Comparison through the ratio threshold is to provide a certain time margin for those with poor physical fitness on the basis of the preset parameters, so as to capture a complete movement cycle of those with poor physical fitness as much as possible. In addition, the occlusion problem between testers is also taken into account. Even if there is full occlusion for a certain tester in the movement cycle, considering the differences in the movement frequency amplitude between the testers, the occluded tester can be collected after all as time goes on.

[0050] It should be noted that the point cluster is determined based on the limb feature points contained in the video collected in the first time period, so it is possible that a certain limb feature point in the point cluster is captured less frequently in the first time period, while another limb feature point is captured more frequently in the first time period. The limb feature points in the point cluster are not repeated.

[0051] S106: For each of the point clusters, determine a first point and a second point of the point cluster.

[0052] The first point in this specification is the limb feature point with the largest variation in the point cluster identified by the video. For example, if the test item is sit-ups, the first point determined for the tester is most likely the limb feature point corresponding to the top of the tester's skull. If there is occlusion, it is possible that the limb feature point corresponding to the tester's shoulder joint is the first point. What the first point is specifically depends on the content captured by the video.

[0053] The second point in this specification is the limb feature point corresponding to the preset reference point. The reference point is preset for the test item. Exemplarily, the reference points corresponding to the sit-up are the limb feature points corresponding to the top of the head, the limb feature points corresponding to the spine, and the limb feature points corresponding to the knee. It can be seen that the reference points include the limb feature points with the largest movement amplitude, the limb feature points with the smallest movement amplitude, and the limb feature points in transition between the largest and smallest movement amplitudes in an action cycle of the test item under ideal conditions. That is to say, ideally, in the sit-up test item, the limb feature point corresponding to the top of the tester's head is one of the second points. That is to say, there may be a situation where a limb feature point is both the first point and the second point. In actual application, there may be a preset reference point, and the corresponding limb feature point is not captured in the video. That is to say, there may be a situation where the number of reference points is greater than the number of second points.

[0054] S108: Determine a correction value based on the maximum change amount of the change amount curve of the first point.

[0055] Considering the effects of shooting angle and occlusion, the tester's movements in the video may not be clear enough, and it is difficult to fully reflect the tester's movements. Therefore, this manual designs a correction value, which is used to amplify the observability of the tester's movements.

[0056] The correction value in this specification is positively correlated with the maximum change of the change curve of the first point. In an optional embodiment of this specification, the largest of the maximum changes corresponding to each tester is used as the reference value. If the maximum change corresponding to a tester is greater than the reference value, the correction value corresponding to the tester is determined to be 1. If the maximum change corresponding to a tester is less than the reference value, the correction value is greater than 1 and is positively correlated with the maximum change of the change curve of the first point.

[0057] S110: Using the correction value, correct the difference of the maximum change amount of the change amount curve corresponding to the first target point to obtain a correction result.

[0058] The first target point is the second point corresponding to the variation curve to which the maximum value and the minimum value in each maximum variation belong.

[0059] In an optional embodiment of the present specification, the product of the correction value and the difference value may be used as the correction result.

[0060] S112: If the ratio of the distance between the correction result and the first target point matches the ratio of the reference result preset for the second target point and the reference distance preset for the second target point, the test result obtained for the tester is determined to be a valid result.

[0061] The second target point is one of the reference points corresponding to the first target point.

[0062] The reference result can represent the range of motion of the tester under ideal conditions. The reference distance can represent the relative position relationship between the reference points under the shooting conditions corresponding to the range of motion. The ratio of the two can represent the difference in the range of motion between the limb feature points that meet a certain relative position relationship under a certain shooting condition. If the difference in the range of motion matches the standard, it means that the tester's motion is standard, and if the motion meets the standard, it means that the corresponding test result is valid. Otherwise, it means that even if the prescribed motion is completed, the motion does not meet the standard and the test result is invalid.

[0063] For example, for sit-ups, the test result can be the number of sit-ups.

[0064] Matching means that the difference is not big, and the specific quantitative condition (threshold) for measuring whether it is matching can be determined according to actual needs. In the related art, the technical means that can be used to measure the matching degree between numerical values ​​and arrays are applicable to this specification when conditions permit.

[0065] The method in this specification starts to identify the test subject based on the body feature points at the beginning of the video acquisition, which provides conditions for incorporating the test subject's performance at the beginning of the test into the judgment of the validity of the test results. Moreover, when the method in this specification realizes the test subject identification based on the body feature points, the action corresponding to the second point is corrected by the maximum change of the first point. Even if the test subject's posture is not conducive to the reflection of the test subject's behavior in the collected video, the test subject's real action situation can be restored, which is conducive to the objective judgment of the validity of the test result of the test subject.

[0066] In actual application scenarios, there may be some testers who are severely blocked and do not meet the test conditions; there may also be testers whose physical fitness is too poor, too different from other testers, or whose movements are too non-standard, and it is impossible to obtain qualified test results. In view of this situation, in an optional embodiment of the present specification, the tester corresponding to the point cluster to which the limb feature points of the change amount curve whose change rate does not reach the maximum value in the first time period (that is, the tester's movement fails to complete an action cycle) belong is determined as the target tester. Determine whether the change rate of the change amount curve of the limb feature points of the target tester reaches the maximum value in the second time period after the first time period; if so, determine the first point and the second point of the point cluster corresponding to the target tester, and then continue to execute the subsequent steps based on the first point and the second point. If not, directly use unqualified as the test result of the target tester.

[0067] In addition, after the target tester is determined, a motion adjustment prompt (which may be a voice prompt) is sent to the target tester so that the target tester can standardize his or her motions.

[0068] In an optional embodiment of the present specification, when there is only one target tester, the duration of the second time period is positively correlated with the maximum value of the variation of the limb feature points detected for the target tester during the first time period, and negatively correlated with the duration of the first time period. The larger the maximum value of the variation detected for the target tester, the greater the possibility that the tester can complete an action cycle in a short time, and it is meaningful to continue testing the tester. If the tester is really unable to complete an action cycle, continuing to wait will further waste the target tester's time, which is not conducive to the target tester entering the next round of testing.

[0069] In the case that the target tester is not unique, a preset designated duration is used as the duration of the second time period. The designated duration is preset for the test item and is an empirical value.

[0070] If the target tester is not unique and at least two target testers are adjacent in the image, the duration of the second time period is set to zero, indicating that the target tester may be blocked, and there is no need to continue the test, so that the target tester can enter the next round of testing.

[0071] Figure 2 This is a schematic diagram of the structure of an electronic device according to an embodiment of the present application. Figure 2 At the hardware level, the electronic device includes a processor, and optionally also includes an internal bus, a network interface, and a memory. The memory may include a memory, such as a high-speed random access memory (RAM), and may also include a non-volatile memory (non-volatile memory), such as at least one disk storage. Of course, the electronic device may also include hardware required for other services.

[0072] The processor, network interface and memory can be interconnected through an internal bus, which can be an ISA (Industry Standard Architecture) bus, a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, Figure 2Only one bidirectional arrow is used in the diagram, but this does not mean that there is only one bus or only one type of bus.

[0073] The memory is used to store the program. Specifically, the program may include a program code, and the program code includes a computer operation instruction. The memory may include a memory and a non-volatile memory, and provides instructions and data to the processor.

[0074] The processor reads the corresponding computer program from the non-volatile memory into the memory and then runs it, forming a physical fitness test device based on human skeleton trajectory tracking at the logical level. The processor executes the program stored in the memory and is specifically used to execute any of the aforementioned physical fitness test methods based on human skeleton trajectory tracking.

[0075] The above application Figure 1 A physical fitness test method based on human skeleton trajectory tracking disclosed in the illustrated embodiment can be applied to a processor or implemented by a processor. The processor may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the above method can be completed by an integrated logic circuit of hardware in the processor or an instruction in the form of software. The above processor can be a general-purpose processor, including a central processing unit (CPU), a network processor (NP), etc.; it can also be a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The methods, steps and logic block diagrams disclosed in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor, etc. The steps of the method disclosed in the embodiments of the present application can be directly embodied as a hardware decoding processor for execution, or a combination of hardware and software modules in the decoding processor for execution. The software module can be located in a storage medium mature in the art such as a random access memory, a flash memory, a read-only memory, a programmable read-only memory, or an electrically erasable programmable memory, a register, etc. The storage medium is located in the memory, and the processor reads the information in the memory and completes the steps of the above method in combination with its hardware.

[0076] The electronic device may also perform Figure 1 A physical fitness test method based on human skeleton trajectory tracking is implemented Figure 1The functions of the illustrated embodiment will not be described in detail in the embodiments of the present application.

[0077] An embodiment of the present application also proposes a computer-readable storage medium, which stores one or more programs, and the one or more programs include instructions. When the instructions are executed by an electronic device including multiple application programs, any one of the aforementioned physical fitness testing methods based on human skeleton trajectory tracking is executed.

[0078] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems, or computer program products. Therefore, the present application may adopt the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present application may adopt the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0079] The present application is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of the present application. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to generate a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.

[0080] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.

[0081] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.

[0082] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.

[0083] Memory may include non-permanent storage in a computer-readable medium, in the form of random access memory (RAM) and / or non-volatile memory, such as read-only memory (ROM) or flash RAM. Memory is an example of a computer-readable medium.

[0084] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.

[0085] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.

[0086] Those skilled in the art will appreciate that the embodiments of the present application may be provided as methods, systems or computer program products. Therefore, the present application may take the form of a complete hardware embodiment, a complete software embodiment or an embodiment combining software and hardware. Moreover, the present application may take the form of a computer program product implemented on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program codes.

[0087] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A physical fitness testing method based on human skeleton trajectory tracking, characterized in that: The method comprises: When performing video acquisition, identifying the body feature points of the tester in each frame image of the video; Determine a curve of a change in the distance of a specified feature point in the video compared to an edge of the image over time; the specified feature point is any one of the limb feature points; The limb feature points to which the variation curves with the same variation rate at each moment in the first time period belong are determined as a point cluster, so that each point cluster corresponds to one of the testers; the first time period is positively correlated with a preset parameter, and is positively correlated with the duration when the ratio of the variation curves with the maximum variation rate detected to all the variation curves reaches a preset ratio threshold; the preset parameter is preset for the test item corresponding to the video; For each of the point clusters, determine a first point and a second point of the point cluster; the first point is the limb feature point with the largest variation in the point cluster; the second point is the limb feature point corresponding to a reference point preset for the test item; determining a correction value based on a maximum change of the change curve of the first point; the correction value is positively correlated with the maximum change of the change curve of the first point; Using the correction value, correct the difference between the maximum changes of the change amount curve corresponding to the first target point to obtain a correction result; the first target point is the second point corresponding to the change amount curve to which the maximum value and the minimum value of each maximum change amount belong; If the ratio of the distance between the correction result and the first target point matches the ratio of the reference result preset for the second target point and the reference distance preset for the second target point, the test result obtained for the tester is determined to be a valid result; wherein the second target point is the reference point corresponding to the first target point.

2. The method according to claim 1, characterized in that: The test items include at least one of the following: sit-ups, push-ups, pull-ups, and bent-arm hangs.

3. The method according to claim 1, characterized in that: The limb feature points include at least one of the following: feature points corresponding to the tester's joints, feature points corresponding to the tester's bone endpoints, feature points corresponding to the tester's bone midpoints, and feature points corresponding to the tester's skull.

4. The method according to claim 1, characterized in that: The method further comprises: Determine the test subject corresponding to the point cluster to which the limb feature point to which the change amount curve whose change rate does not reach the maximum value in the first time period belongs as the target test subject; Determine whether the change rate of the change amount curve of the limb feature point of the target tester reaches a maximum value in a second time period after the first time period; If yes, then determine the first point and the second point of the point cluster corresponding to the target tester.

5. The method according to claim 4, characterized in that: The method further comprises: If not, then directly set failure as the test result of the target tester.

6. The method according to claim 4, characterized in that: After determining the target tester, the method further includes: Sending a motion adjustment prompt to the target tester so that the target tester can standardize his / her motion.

7. The method according to claim 4, characterized in that: In the case where the target tester is unique, the duration of the second time period is positively correlated with the maximum value of the change amount of the limb feature points detected for the target tester in the first time period, and negatively correlated with the duration of the first time period; In the case that the target tester is not unique and the positions of the target testers in the image are not adjacent, using a preset designated time length as the length of the second time period; When the target tester is not unique and the positions of at least two target testers in the image are adjacent, the duration of the second time period is set to zero.

Images