A physical fitness test automatic evaluation method and system based on single camera equipment

By obtaining and matching the action parameters of physical fitness tests through a single camera device, using depth cameras and point cloud images, the subjectivity and efficiency of physical fitness test evaluation in the existing technology is solved, and efficient and accurate multi-person physical fitness test evaluation is achieved, improving the efficiency and accuracy of multi-person physical fitness test evaluation. The fairness and applicability of the assessment were conducted.

CN114049654BActive Publication Date: 2024-11-15WUHAN DONGRI TECH
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202111322920.1
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2021-11-09
Publication Date
2024-11-15
Estimated Expiration
2041-11-09

AI Technical Summary

Technical Problem

The existing physical fitness test evaluation methods are subjective, low efficiency and high limitations. Manual evaluation is prone to misjudgment. Infrared devices cannot accurately judge the action type, wearable devices have low detection efficiency and poor comfort, and cannot perform multiple people at the same time. Efficient evaluation.

Method used

Using the automatic evaluation method of physical fitness test based on single camera equipment, by obtaining the camera status parameters and the action parameters of the person under test, using the depth information and point cloud images collected by the depth camera, divide the human body parts, match the action parameters and evaluation parameters, and judge the action. Standard, automatic evaluation.

Benefits of technology

It realizes efficient and accurate physical fitness test and evaluation, and can evaluate multiple people at the same time, without additional preparation time, the equipment is portable and has strong battery life, and supports offline use, improving the fairness, efficiency and applicability of physical testing.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114049654B_ABST
    Figure CN114049654B_ABST
Patent Text Reader

Abstract

The present invention discloses a method and system for automatic assessment of physical fitness test based on a single camera device. The implementation of the assessment method and system provided by the present invention is mainly based on the depth information collected by the depth camera, and uses a relevant algorithm to convert it into key point connection information of the human body that can be used for assessment work, and then uses the combined change relationship of the spatial distance and angle of these point information within a specific time interval to achieve the purpose of physical fitness test assessment, thereby solving the technical problems existing in the prior art.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present invention relates to the technical field of physical fitness assessment, and in particular to a method and system for automatic assessment of physical fitness test based on a single camera device. Background Art

[0002] At present, there are three types of assessment methods for physical fitness tests:

[0003] 1. Manual evaluation method: For items such as sit-ups, push-ups, and pull-ups, a one-to-one or one-to-many manual monitoring and evaluation method is adopted, relying on human eyes to see the number of items performed by the physical test personnel and whether a certain action meets the standard. However, the disadvantage of this evaluation method is that it is too subjective and inefficient. After all, human energy is limited. When there are many physical test personnel or the evaluation time is long, misjudgment or miscounting is prone to occur.

[0004] 2. Infrared equipment evaluation method, using infrared sensors, multiple infrared monitoring sensors are arranged at specific locations to achieve the purpose of counting. Taking sit-ups as an example, this method will arrange an infrared sensor at the position where the head lies down and the position where the head is raised. When the head passes over the lower sensor, the "lying down" state will be recorded, and when the head is raised, the "standing up" state will be recorded. By switching between the two states, the purpose of counting is achieved. However, this method has certain limitations, because the sensor cannot determine whether the limb that passes over is the head or other parts. If you shake your hands up and down, you can also count successfully. In addition, it is impossible to give a clear judgment whether the action is standard.

[0005] 3. Wearable assessment method uses refined sensors such as gyroscopes and angular accelerometers to collect relevant scenarios when performing actions in real time, and counts and evaluates standards through the collected data. This assessment method is relatively accurate, but it also has certain limitations. For example, a set of equipment can only handle one person under test, and when changing the person under test, the equipment needs to be taken off and put on again, which takes a long time and has low detection efficiency. In addition, the person under test feels restrained and uncomfortable, which affects the physical test results. Summary of the invention

[0006] The present invention solves the above-mentioned technical problems existing in the prior art by providing a method and system for automatic evaluation of physical fitness test based on a single camera device.

[0007] The present invention provides a method for automatically evaluating physical fitness test based on a single camera device, comprising:

[0008] Get the status parameters of the camera device;

[0009] Matching the state parameter with a preset state parameter to obtain an evaluation parameter corresponding to the matching result;

[0010] Obtaining motion parameters of the person under test;

[0011] The action parameters are matched with the evaluation parameters to obtain an evaluation result.

[0012] Specifically, obtaining the motion parameters of the tested person includes:

[0013] Acquire a point cloud image of the area of ​​the tested person; the point cloud image includes: the distance between each pixel point in the image and the camera device;

[0014] Dividing different parts of the person under test according to the distance between each pixel point in the point cloud image and the camera device;

[0015] The motion parameters of the tested person are obtained according to the divided different parts.

[0016] Specifically, matching the action parameter with the evaluation parameter to obtain an evaluation result includes:

[0017] Determining whether the action parameters match the benchmark standard action parameters in the evaluation parameters;

[0018] If there is a match, determining the degree of match between the action parameter and the process standard action parameter in the evaluation parameter during the time period between the action parameter matching the next benchmark standard action parameter;

[0019] If the matching degree between the action parameter and the process standard action parameter is equal to or higher than the preset matching degree, the accuracy is increased by one.

[0020] Specifically, it also includes:

[0021] Obtaining facial feature information of the tested person according to the divided different parts;

[0022] Matching the facial feature information with information in a personnel database to obtain matching personnel assessment parameters;

[0023] The determining whether the action parameter matches the reference standard action parameter in the evaluation parameter includes:

[0024] Determine whether the action parameters match the benchmark standard action parameters in the evaluation parameters of the matching person.

[0025] Specifically, the matching degree includes at least: the difference between the action parameter and the process standard action parameter and / or the matching time between the action parameter and the process standard action parameter.

[0026] The present invention also provides a physical fitness test automatic evaluation system based on a single camera device, comprising:

[0027] A status parameter acquisition module is used to obtain the status parameters of the camera device;

[0028] An evaluation parameter acquisition module, used to match the state parameter with a preset state parameter to obtain an evaluation parameter corresponding to the matching result;

[0029] An action parameter acquisition module is used to obtain the action parameters of the person under test;

[0030] The evaluation module is used to match the action parameters with the evaluation parameters to obtain an evaluation result.

[0031] Specifically, the action parameter acquisition module includes:

[0032] A point cloud image acquisition unit is used to acquire a point cloud image of the area of ​​the person under test; the point cloud image includes: the distance between each pixel point in the image and the camera device;

[0033] A part division unit, used for dividing different parts of the tested person according to the distance between each pixel point in the point cloud image and the camera device;

[0034] The motion parameter acquisition unit is used to obtain the motion parameters of the tested person according to the divided different parts.

[0035] Specifically, the evaluation module includes:

[0036] an action parameter determination unit, configured to determine whether the action parameter matches a reference standard action parameter in the evaluation parameter;

[0037] a matching degree judgment unit, for judging the matching degree of the action parameter with the process standard action parameter in the evaluation parameter within a time period between the action parameter matching with the next benchmark standard action parameter, if a match is found;

[0038] An evaluation unit is used to increase the accuracy by one if the matching degree between the action parameter and the process standard action parameter is equal to or higher than a preset matching degree.

[0039] Specifically, it also includes:

[0040] A facial feature information acquisition module, used to obtain facial feature information of the tested person according to the divided different parts;

[0041] A matching module, used to match the facial feature information with the information in the personnel database to obtain matching personnel assessment parameters;

[0042] The action parameter judgment unit is specifically used to judge whether the action parameter matches the benchmark standard action parameter in the evaluation parameter of the matching person.

[0043] Specifically, the matching degree includes at least: the difference between the action parameter and the process standard action parameter and / or the matching time between the action parameter and the process standard action parameter.

[0044] One or more technical solutions provided in the present invention have at least the following technical effects or advantages:

[0045] The implementation of the evaluation method and system provided by the present invention is mainly based on the depth information collected by the depth camera, and uses relevant algorithms to convert it into connection information of key points of the human body that can be used for evaluation work. Then, the combined change relationship of the spatial distance and angle of these point information within a specific time interval is used to achieve the purpose of physical fitness test evaluation, thereby solving the technical problems existing in the prior art. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 A flowchart of a method for automatic assessment of physical fitness test based on a single camera device provided in an embodiment of the present invention;

[0047] Figure 2 A matching diagram of the state of the camera device and the physical test items in an embodiment of the present invention;

[0048] Figure 3 Schematic diagram of the distance between the nose tip and the camera device in an embodiment of the present invention;

[0049] Figure 4 Schematic diagram of the distance between the ankle and the camera device in an embodiment of the present invention;

[0050] Figure 5 A schematic diagram of the structure of different parts of the human body divided in an embodiment of the present invention;

[0051] Figure 6 A schematic diagram of selecting key areas according to different divided parts of a human body in an embodiment of the present invention;

[0052] Figure 7 A schematic diagram of the motion status of a person under test obtained through an embodiment of the present invention;

[0053] Figure 8 Schematic diagram of evaluation parameter decomposition in an embodiment of the present invention;

[0054] Fig. 9 A schematic diagram of the principle of identifying different tested persons through an embodiment of the present invention;

[0055] Fig.10 It is a schematic diagram of the association between the information of different test persons, human motion data and evaluation parameters;

[0056] Fig.11 A physical examination scene photo in an embodiment of the present invention;

[0057] Fig.12 It is a physical test evaluation interface for sit-ups in an embodiment of the present invention;

[0058] Fig.13 A schematic diagram of a method for automatically evaluating physical fitness test based on a single-camera device provided by an embodiment of the present invention;

[0059] Fig.14 A module diagram of a physical fitness test automatic evaluation system based on a single camera device provided in an embodiment of the present invention;

[0060] Fig.15 A first on-site photo of a physical product developed according to the evaluation method and system provided in an embodiment of the present invention;

[0061] Fig.16 A second on-site photo of a physical product developed according to the evaluation method and system provided in the embodiment of the present invention;

[0062] Fig.17 This is a third on-site photo of a physical product developed according to the evaluation method and system provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0063] The embodiments of the present invention solve the technical problems existing in the prior art by providing a method and system for automatic assessment of physical fitness test based on a single camera device.

[0064] The technical solution in the embodiment of the present invention is to solve the technical problems existing in the prior art, and the overall idea is as follows:

[0065] The implementation of the evaluation method and system provided by the embodiments of the present invention is mainly based on the depth information collected by the depth camera, and uses relevant algorithms to convert it into connection information of key points of the human body that can be used for evaluation work, and then uses the combined change relationship of the spatial distance and angle of these point information within a specific time interval to achieve the purpose of physical fitness test evaluation.

[0066] In order to better understand the above technical solution, the above technical solution will be described in detail below in conjunction with the accompanying drawings and specific implementation methods.

[0067] See also Figure 1 The embodiment of the present invention provides a method for automatically evaluating physical fitness test based on a single camera device, comprising:

[0068] Step S110: Obtaining status parameters of the camera device;

[0069] In this embodiment, the state parameters of the camera device may be acceleration, angular velocity, position, orientation, and other state parameters.

[0070] Step S120: matching the state parameter with the preset state parameter to obtain an evaluation parameter corresponding to the matching result;

[0071] Specifically, when the camera device is deployed to the relevant detection site and is running, the device will obtain the physical state parameters such as acceleration and angular velocity of the current device through the built-in gyroscope and accelerometer, and automatically determine which item in the system the current detection item belongs to based on the detection scenario. Finally, it will automatically match the "evaluation standard" established in the library and inject it into the device. For example, when the device recognizes that the current height is 1.2 meters and the camera angle is tilted 45° downward from the horizontal, the system will automatically input the evaluation standard corresponding to "sit-ups" into the current evaluation item, such as Figure 2 shown.

[0072] Step S130: obtaining the motion parameters of the person under test;

[0073] This step is specifically described to obtain the motion parameters of the person under test, including:

[0074] Obtain a point cloud image of the area of ​​the person under test; the point cloud image includes: the distance between each pixel point in the image and the camera device;

[0075] Different parts of the person being tested are divided according to the distance between each pixel point in the point cloud image and the camera device;

[0076] The motion parameters of the tested person are obtained according to the divided different parts.

[0077] To further explain this step, use the Kinect depth camera plus the PCL point cloud tool to obtain the point cloud information in the shooting scene. This step will split the information collected by the camera into pixels one by one, and each pixel will contain the X, Y, and Z three-dimensional coordinate information of the pixel relative to the camera, with an accuracy of millimeters. Since the surface pixels of each object itself are continuous relative to the camera, for example, the difference between the tip of our nose and the lower part of the tip of the nose may be only about 0.1 mm. See Figure 3 , Z1, Z2, and Z3 are not very different, which shows that the same object will not have too much difference. However, there is no continuity between different objects, see Figure 4, the distance difference between Z1 and Z2 is not obvious, while the distance difference between Z2 and Z3 is relatively large. It can be seen that the distance difference between different objects is relatively obvious. Therefore, by comparing the information of the Z-axis coordinates (the distance between the pixel and the camera), the human body, objects, and scenes can be distinguished, and all pixel information related to the human body can be identified. In the same principle, for each identified object, due to the different X and Y coordinate differences of the boundary pixel points of each object, such as the difference of the arm, the human body can be further divided into the head, upper limbs, torso, lower limbs and other regions. Figure 5 As shown. Select the split human body area as needed, for example, for the identification of the spine, select the torso as the key area, as shown Figure 6 As shown in the figure. Since human body movements are composed of the most basic movement units, it represents the most intuitive human behavior during human movement, such as "raising head", "putting down left hand", "bending waist" and other basic human movements. By comparing the limb distribution during these movements, its current movement form can be inferred. For example Figure 7 In the figure, if the head, torso, upper limbs and lower limbs are arranged horizontally relative to the camera, it can be judged that the person is in a push-up position.

[0078] Step S140: Match the action parameters with the evaluation parameters to obtain the evaluation results.

[0079] This step is specifically described, and the action parameters are matched with the evaluation parameters to obtain the evaluation results, including:

[0080] Determine whether the action parameters match the benchmark standard action parameters in the evaluation parameters;

[0081] If they match, it means that the prepared action standard of the person being tested is met, and the physical assessment can begin to determine the degree of match between the action parameters and the process standard action parameters in the assessment parameters during the time period between the action parameters matching the next baseline standard action parameters;

[0082] If the matching degree between the action parameters and the process standard action parameters is equal to or higher than the preset matching degree, it means that the action is standard and the accuracy is increased by one.

[0083] The evaluation parameters in the embodiment of the present invention are specifically described as follows:

[0084] See also Figure 8According to the physical test evaluation standards provided by the user, the evaluation standards are divided into "preparation action", "counting standard" and "action standard". Among them, the "preparation action" is to establish the basic human indicators of a certain action, the "counting standard" means that when the subject's action meets certain requirements, his action will be counted, and the "action standard" means the action that meets the "counting standard", which is specifically a "standard" action or an "irregular" action. Taking "push-ups" as an example, its "preparation action" is a standard action of "supporting action", which is used to obtain the arm length, spinal curvature and other evaluation criteria of relevant personnel; the "counting standard" is that the arm shoulder is lower than the elbow during the "descending action", and the arm is straight without bending during the "supporting action"; and its "action standard" is that the neck, spine base, and knee form a line with no obvious bending of more than 175°.

[0085] In order to conduct targeted physical assessment according to different test subjects, thereby improving the applicability of physical assessment, it also includes:

[0086] Obtain facial feature information of the tested person according to the divided different parts;

[0087] Matching facial feature information with information in a personnel database to obtain matching personnel assessment parameters;

[0088] It should be noted here that the embodiment of the present invention can also perform physical assessment on multiple people at the same time, specifically including:

[0089] When the test subjects enter the site, the equipment identifies key parameters of each person, such as feature information, standing position information, and body physical information. Among them, the feature information is obtained by calculating and comparing the distance between the eyes, mouth corners, facial boundaries and nose tip. The "feature information" can be used to determine whether the person is a test subject; the standing position information is obtained based on the horizontal distance and line distance of each person relative to the camera, and the "standing position information" can be used to determine who the test subject is in this group of physical assessments; the body physical information can be obtained based on the distance of the specific split upper and lower limb boundary coordinates. The "body physical information" is about the person's arm length, leg length, height and other personal feature information, so as to achieve different and targeted evaluation standards for different test subjects. For example, different heights and arm lengths will result in different qualified judging criteria, such as Fig. 9 shown.

[0090] By comparing the position of the spine base point in the obtained "station information" with the station range of each tested person preset by the device, the binding association of relevant people in the group members in the system is realized, and in the subsequent data obtained, it is judged in real time whether there is anyone at a certain position, and if there is someone, what is the point data. Fig.10 , Fig.11 and Fig.12The camera obtains the relevant data of three persons A, B, and C, but it does not know who these three persons are specifically. The venue-related information defines that Zhang San (B's name), Li Si (A's name), and Wang Wu (C's name) should stand in the three areas A, B, and C respectively. By comparing the standing position information of A, B, and C obtained by the camera with the areas, the system can automatically match the information of the three persons, thereby realizing the association between the actual personnel information and the human motion data and evaluation parameters.

[0091] In this case, judging whether the action parameters match the benchmark standard action parameters in the evaluation parameters includes:

[0092] Determine whether the action parameters match the benchmark standard action parameters in the evaluation parameters of the matching person.

[0093] Specifically, the matching degree includes at least: the difference between the action parameter and the process standard action parameter and / or the matching time between the action parameter and the process standard action parameter.

[0094] For a detailed description of this step, see Fig.13 , using the collected human key information data, extract the main evaluation information required by the evaluation standard, compare it with the corresponding standards of "counting standard" and "action standard", and introduce the concept of time period, instead of using the human body movement data of a certain moment to compare it, it is compared with the combined data of a certain period of time, and the new data will squeeze out the old data to ensure that the data in the combination is the latest, and use this method to judge the proportion of data that meets the standard. For example, in "push-ups", within 3 seconds, if person A has a straight spine for 60% of the time, then we will judge that person A's action at that time is standard, and the total number can be "added by one", and finally give a relatively accurate evaluation conclusion for each action in this way.

[0095] See also Fig.14 The physical fitness test automatic evaluation system based on a single camera device provided by an embodiment of the present invention includes:

[0096] The state parameter acquisition module 100 is used to acquire the state parameters of the camera device;

[0097] In this embodiment, the state parameters of the camera device may be acceleration, angular velocity, position, orientation, and other state parameters.

[0098] An evaluation parameter acquisition module 200 is used to match the state parameter with the preset state parameter to obtain an evaluation parameter corresponding to the matching result;

[0099] The motion parameter acquisition module 300 is used to obtain the motion parameters of the tested person;

[0100] Specifically, the action parameter acquisition module 300 includes:

[0101] The point cloud image acquisition unit is used to acquire a point cloud image of the area of ​​the person under test; the point cloud image includes: the distance between each pixel point in the image and the camera device;

[0102] A part division unit, used to divide different parts of the person under test according to the distance between each pixel point in the point cloud image and the camera device;

[0103] The motion parameter acquisition unit is used to obtain the motion parameters of the tested person according to the divided different parts.

[0104] The evaluation module 400 is used to match the action parameters with the evaluation parameters to obtain the evaluation results.

[0105] Specifically, the evaluation module 400 includes:

[0106] An action parameter determination unit, used to determine whether the action parameter matches the reference standard action parameter in the evaluation parameter;

[0107] A matching degree judgment unit is used to indicate the preparation action standard of the person under test if a match is found, and to start the physical test assessment, and to judge the matching degree of the action parameters with the process standard action parameters in the assessment parameters in the time period between the action parameters matching the next benchmark standard action parameters;

[0108] The evaluation unit is used to indicate that the action standard is met and the accuracy is increased by one if the matching degree between the action parameter and the process standard action parameter is equal to or higher than the preset matching degree.

[0109] In order to conduct targeted physical assessment according to different test subjects, thereby improving the applicability of physical assessment, it also includes:

[0110] A facial feature information acquisition module is used to obtain facial feature information of the tested person according to the divided different parts;

[0111] A matching module is used to match the facial feature information with the information in the personnel database to obtain matching personnel evaluation parameters;

[0112] In this case, the action parameter judgment unit is specifically used to judge whether the action parameter matches the reference standard action parameter in the evaluation parameter of the matching person.

[0113] Specifically, the matching degree includes at least: the difference between the action parameter and the process standard action parameter and / or the matching time between the action parameter and the process standard action parameter.

[0114] Technical Effects

[0115] 1. The implementation of the evaluation method and system provided by the embodiments of the present invention is mainly based on the depth information collected by the depth camera, and uses relevant algorithms to convert it into connection information of key points of the human body that can be used for evaluation work. Then, the combined change relationship of the spatial distance and angle of these point information within a specific time interval is used to achieve the purpose of physical fitness test evaluation, thereby solving the technical problems existing in the prior art.

[0116] 2. Obtain the facial feature information of the person under test based on the different divided parts; match the facial feature information with the information in the personnel database to obtain the matching personnel evaluation parameters; determine whether the motion parameters match the benchmark standard motion parameters in the matching personnel evaluation parameters, so that targeted physical test evaluation can be carried out according to different persons under test, thereby improving the applicability of physical test evaluation.

[0117] In summary, the evaluation method and system provided by the embodiment of the present invention are rich in evaluation content. Only one machine is needed to cope with various physical fitness test items such as sit-ups, pull-ups, push-ups, etc. The evaluation method is scientific, and the precise point cloud algorithm is used to accurately judge the standard degree and quantity of each tested action. The evaluation efficiency is high, and accurate physical fitness evaluation can be performed on multiple personnel at the same time. No additional preparation time is required when switching personnel. It has strong portability and endurance. For outdoor scenes, it can achieve 5-minute rapid deployment and finishing and a whole day of off-power use. It supports complete offline usage scenarios and can be used normally in remote scenes or scenes with high confidentiality requirements. The main physical fitness test method has been successfully transformed into a physical fitness test product. The purpose of the product is to serve the physical fitness test assessment of the military, schools and other institutions. It uses intelligent machine vision to replace the previous manual counting evaluation methods that are highly subjective, inefficient, and uncomfortable, so that the entire physical fitness test process is more fair, reasonable, and efficient. Specific products such as Fig.15 , Fig.16 and Fig.17 shown.

[0118] Those skilled in the art will appreciate that embodiments of the present invention may be provided as methods, systems, or computer program products. Therefore, the present invention may take the form of a complete hardware embodiment, a complete software embodiment, or an embodiment combining software and hardware. Moreover, the present invention 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 code.

[0119] The present invention is described with reference to flowcharts and / or block diagrams of methods, devices (systems), and computer program products according to embodiments of the present invention. It should be understood that each process and / or block in the flowchart and / or block diagram, as well as the combination of processes and / or blocks 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 produce 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.

[0120] 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.

[0121] 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.

[0122] Although the preferred embodiments of the present invention have been described, those skilled in the art may make other changes and modifications to these embodiments once they have learned the basic creative concept. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments and all changes and modifications that fall within the scope of the present invention.

[0123] Obviously, those skilled in the art can make various changes and modifications to the present invention without departing from the spirit and scope of the present invention. Thus, if these modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include these modifications and variations.

Claims

1. A method for automatic assessment of physical fitness test based on a single camera device, characterized in that: include: Get the status parameters of the camera device; Matching the state parameter with a preset state parameter to obtain an evaluation parameter corresponding to the matching result; Obtaining motion parameters of the person under test; The action parameters are matched with the evaluation parameters to obtain an evaluation result.

2. The method according to claim 1, characterized in that The step of obtaining the motion parameters of the tested person includes: Acquire a point cloud image of the area of ​​the tested person; the point cloud image includes: the distance between each pixel point in the image and the camera device; Dividing different parts of the person under test according to the distance between each pixel point in the point cloud image and the camera device; The motion parameters of the tested person are obtained according to the divided different parts.

3. The method according to claim 2, characterized in that The step of matching the action parameter with the evaluation parameter to obtain an evaluation result includes: Determining whether the action parameters match the benchmark standard action parameters in the evaluation parameters; If there is a match, determining the degree of match between the action parameter and the process standard action parameter in the evaluation parameter during the time period between the action parameter matching the next benchmark standard action parameter; If the matching degree between the action parameter and the process standard action parameter is equal to or higher than the preset matching degree, the accuracy is increased by one.

4. The method according to claim 3, characterized in that Also includes: Obtaining facial feature information of the tested person according to the divided different parts; Matching the facial feature information with information in a personnel database to obtain matching personnel assessment parameters; The determining whether the action parameter matches the reference standard action parameter in the evaluation parameter includes: Determine whether the action parameters match the benchmark standard action parameters in the evaluation parameters of the matching person.

5. The method according to claim 3, characterized in that The matching degree includes at least: a difference between the action parameter and the process standard action parameter and / or a matching time between the action parameter and the process standard action parameter.

6. A physical fitness test automatic assessment system based on a single camera device, characterized in that: include: A status parameter acquisition module is used to obtain the status parameters of the camera device; An evaluation parameter acquisition module, used to match the state parameter with a preset state parameter to obtain an evaluation parameter corresponding to the matching result; An action parameter acquisition module is used to obtain the action parameters of the person under test; The evaluation module is used to match the action parameters with the evaluation parameters to obtain an evaluation result.

7. The system according to claim 6, characterized in that The action parameter acquisition module includes: A point cloud image acquisition unit is used to acquire a point cloud image of the area of ​​the person under test; the point cloud image includes: the distance between each pixel point in the image and the camera device; A part division unit, used for dividing different parts of the tested person according to the distance between each pixel point in the point cloud image and the camera device; The motion parameter acquisition unit is used to obtain the motion parameters of the tested person according to the divided different parts.

8. The system according to claim 7, characterized in that The evaluation module comprises: an action parameter determination unit, configured to determine whether the action parameter matches a reference standard action parameter in the evaluation parameter; a matching degree judgment unit, for judging the matching degree of the action parameter with the process standard action parameter in the evaluation parameter within a time period between the action parameter matching with the next benchmark standard action parameter, if a match is found; An evaluation unit is used to increase the accuracy by one if the matching degree between the action parameter and the process standard action parameter is equal to or higher than a preset matching degree.

9. The system according to claim 8, characterized in that Also includes: A facial feature information acquisition module, used to obtain facial feature information of the tested person according to the divided different parts; A matching module, used to match the facial feature information with the information in the personnel database to obtain matching personnel assessment parameters; The action parameter judgment unit is specifically used to judge whether the action parameter matches the benchmark standard action parameter in the evaluation parameter of the matching person.

10. The system according to claim 8, characterized in that The matching degree includes at least: a difference between the action parameter and the process standard action parameter and / or a matching time between the action parameter and the process standard action parameter.