An evaluation method and device for military training examination projects
By acquiring and processing human three-dimensional and motion posture data, and comparing them with a preset standard library, military training assessment results are optimized, solving the problem of low accuracy in assessment results and achieving higher assessment accuracy.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- HANGZHOU EBOYLAMP ELECTRONICS CO LTD
- Filing Date
- 2023-08-31
- Publication Date
- 2026-07-24
Smart Images
Figure CN117197889B_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of military training, and in particular to an evaluation method and apparatus for military training assessment projects. Background Technology
[0002] In military training, assessments are an extremely important part, and each assessment is crucial for every trainee. Military training assessments include, but are not limited to, obstacle courses and sit-ups. Current military training assessment methods primarily rely on manual labor or counting equipment to record the number of tests performed and the time taken, thereby determining the assessment results.
[0003] However, such assessment results often overlook the important factor of whether the trainees' training movements are standard, which can easily lead to a decrease in the accuracy of the assessment results. Summary of the Invention
[0004] This application aims to address the aforementioned problem of decreased accuracy in assessment results. Embodiments of this application provide an evaluation method and apparatus for military training assessment projects. The technical solution is as follows:
[0005] Firstly, embodiments of this specification provide an evaluation method for military training assessment projects, including:
[0006] Acquire the human body 3D data and motion posture data corresponding to the assessment items, and process the human body 3D data and motion posture data to obtain motion joint data;
[0007] Based on the comparison results between the joint motion data and the preset standard library, the pass data corresponding to the assessment items are obtained;
[0008] The assessment data is optimized based on the achievement data corresponding to the assessment items to obtain the target score.
[0009] In one alternative of the first aspect, the motion pose data includes at least two video files, each video file including at least two frames of images;
[0010] Human body 3D data and motion posture data are processed to obtain motion joint data, including:
[0011] Based on a preset spatial rectangular coordinate system, coordinate values are assigned to all joints in the three-dimensional human body data.
[0012] All joints are numbered based on the ascending order of values on at least two coordinate axes and the coordinates of all joints.
[0013] Perform grayscale processing on each image in each video file to obtain the corresponding image grayscale data;
[0014] Calculate the variance of grayscale data for each image, and use the image corresponding to the maximum variance as the target image frame of the corresponding video file;
[0015] Feature fusion processing is performed on the numbered human 3D data and each target image frame to obtain motion joint data.
[0016] In another alternative to the first aspect, feature fusion processing is performed on the numbered human 3D data and each target image frame to obtain motion joint data, including:
[0017] Each target image frame after fusion processing is input into a preset computational model to obtain each joint angle in each target image frame; wherein, the model is trained by sample image frames labeled with joint angles.
[0018] In another alternative to the first aspect, based on the comparison results between the motion joint data and the preset standard library, the compliance data corresponding to the assessment items are obtained, including:
[0019] The difference between the joint angles in each target image frame and the joint angles of the corresponding joints in the preset standard library is calculated, and the number of joints that fall within the preset error range is determined.
[0020] The number of target image frames with a number of joints greater than or equal to the qualified threshold is counted, and the number of target image frames is used as the qualified data.
[0021] In another alternative to the first aspect, the assessment data is optimized based on the achievement data corresponding to the assessment items to obtain the target score, including:
[0022] When the assessment item is a counting assessment item, determine whether the target data and the assessment data are consistent;
[0023] When the target achievement data and the assessment data are inconsistent, the target score is determined based on the target achievement data.
[0024] When the target data matches the assessment data, the target score is determined based on the assessment data.
[0025] In another alternative to the first aspect, the target score is determined based on the achievement data, including:
[0026] Calculate the ratio between the number of qualified data and the preset number of standards, and determine the target score by multiplying the ratio by the standard score corresponding to the assessment item.
[0027] In another alternative to the first aspect, optimizing the assessment data based on the achievement data corresponding to the assessment items to obtain the target score also includes:
[0028] When the assessment item is a timed assessment item, the number of unqualified items is determined based on the pass data and the number of target image frames corresponding to the assessment item.
[0029] The extra time is calculated based on the number of non-compliance items, and the target score is determined based on the extra time and the assessment data.
[0030] Secondly, embodiments of this application provide an evaluation device for military training assessment projects, comprising:
[0031] The first processing module is used to acquire the human body three-dimensional data and motion posture data corresponding to the assessment items, and to process the human body three-dimensional data and motion posture data to obtain motion joint data.
[0032] The second processing module is used to obtain the compliance data corresponding to the assessment items based on the comparison results between the motion joint data and the preset standard library.
[0033] The third processing module is used to optimize the assessment data based on the achievement data corresponding to the assessment items, so as to obtain the target score.
[0034] Thirdly, embodiments of this application provide an evaluation device for military training assessment projects, including a processor and a memory;
[0035] The processor is connected to the memory;
[0036] Memory, used to store executable program code;
[0037] The processor runs a program corresponding to the executable program code by reading the executable program code stored in the memory, so as to implement the evaluation method for military training assessment projects provided by the first aspect or any implementation of the first aspect of the embodiments of this application.
[0038] Fourthly, embodiments of this application provide a computer storage medium storing a computer program, which includes program instructions. When executed by a processor, the program instructions can implement the evaluation method for military training assessment projects provided by the first aspect or any implementation of the first aspect of this application.
[0039] The beneficial effects of the technical solutions provided in some embodiments of this specification include at least the following:
[0040] In the evaluation process of military training assessment projects, three-dimensional human body data and motion posture data corresponding to the assessment projects are acquired. This data is then processed to obtain joint data. Based on the comparison between the joint data and a preset standard library, qualifying data corresponding to the assessment projects is obtained. The assessment data is then optimized based on this qualifying data to arrive at the target score. By processing the three-dimensional human body data and recognizing human movements to obtain corresponding joint data, and using this joint data to measure the standardization of assessment movements, the standardization of movements is incorporated into the calculation of assessment scores, thereby reducing human error and improving the accuracy of military training assessment results. Attached Figure Description
[0041] To more clearly illustrate the technical solutions in the embodiments of this application, the accompanying drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.
[0042] Figure 1 A flowchart illustrating an overall evaluation method for military training assessment projects provided in this application embodiment;
[0043] Figure 2 A schematic diagram of the structure of an evaluation device for military training assessment projects provided in this application embodiment;
[0044] Figure 3 This is a schematic diagram of the structure of another evaluation device for military training assessment projects provided in the embodiments of this application. Detailed Implementation
[0045] The technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings.
[0046] In the following description, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance. The following description provides multiple embodiments of this application, which can be substituted or combined with each other. Therefore, this application can also be considered to include all possible combinations of the same and / or different embodiments described. Thus, if one embodiment includes features A, B, and C, and another embodiment includes features B and D, then this application should also be considered to include embodiments containing one or more other possible combinations of A, B, C, and D, even if such embodiments are not explicitly described in the following text.
[0047] The following description provides examples and does not limit the scope, applicability, or examples set forth in the claims. Changes may be made to the function and arrangement of the described elements without departing from the scope of this application. Various processes or components may be appropriately omitted, substituted, or added to the examples. For example, the described methods may be performed in a different order than described, and various steps may be added, omitted, or combined. Furthermore, features described with respect to some examples may be combined into other examples.
[0048] Please see Figure 1 , Figure 1 This paper presents an overall flowchart of an evaluation method for military training assessment projects provided in an embodiment of this application.
[0049] like Figure 1 As shown, the assessment method used for military training assessment projects may include at least the following steps:
[0050] Step 101: Obtain the human body 3D data and motion posture data corresponding to the assessment items, and process the human body 3D data and motion posture data to obtain motion joint data.
[0051] In this embodiment, the evaluation method for military training assessment items can be, but is not limited to, applied to a control terminal. This control terminal can connect to multiple electronic devices to obtain data sent by these devices. These electronic devices include, but are not limited to, motion-sensing devices, camera devices, and devices for acquiring user information. It is understood that by incorporating the standardization of movements as a reference point during the military training assessment process, the control terminal can reduce the influence of human factors on assessment results, thereby improving the accuracy of the military training assessment results. The military training assessment items include, but are not limited to, long-distance running, push-ups, pull-ups, sit-ups, obstacle courses, static shooting, dynamic shooting, and multi-target shooting.
[0052] Specifically, motion-sensing devices can acquire 3D human body data of trainees participating in the assessment, and camera devices can acquire data on the trainees' movement postures during the assessment process. The 3D human body data will differ between different trainees.
[0053] It is understandable that the three-dimensional human body data collected by the motion sensing device includes at least the three-dimensional data of the 20 joints of the human body, and the motion posture data includes at least the information such as the body posture, direction of movement, and degree of bending of body parts of the trainee recorded by the camera device and processed by human motion recognition during the assessment process.
[0054] Furthermore, by processing the trainee's 3D human body data and motion posture data, such as through feature stitching, feature weighting, feature fusion, and multimodal learning, the trainee's joint motion information during the assessment process can be obtained.
[0055] As an optional embodiment of this application, the motion posture data includes at least two video files, and each video file includes at least two frames of images;
[0056] Human body 3D data and motion posture data are processed to obtain motion joint data, including:
[0057] Based on a preset spatial rectangular coordinate system, coordinate values are assigned to all joints in the three-dimensional human body data.
[0058] All joints are numbered based on the ascending order of values on at least two coordinate axes and the coordinates of all joints.
[0059] Perform grayscale processing on each image in each video file to obtain the corresponding image grayscale data;
[0060] Calculate the variance of grayscale data for each image, and use the image corresponding to the maximum variance as the target image frame of the corresponding video file;
[0061] Feature fusion processing is performed on the numbered human 3D data and each target image frame to obtain motion joint data.
[0062] Specifically, by using a pre-defined Cartesian coordinate system, or a three-dimensional coordinate space, the three-dimensional data of the 20 joints of the human body can be placed into this coordinate space to measure the joint coordinates of each joint. This Cartesian coordinate system contains three axes: the x-axis, the y-axis, and the z-axis.
[0063] Next, the joints can be arranged in ascending order based on the x-axis values of each measured joint coordinate. For joints with the same x-axis value, they are then arranged in ascending order based on the y-axis value; for joints with the same x-axis and y-axis values, they are arranged in ascending order based on the z-axis value. After arranging the joints, they can be numbered sequentially. It is important to note that the numbering method described above is based on the numbering method for identical joints in a pre-defined standard library.
[0064] Simultaneously, image processing software can be used to convert each image in each video file of the motion posture data to grayscale to obtain the grayscale data of that image. The grayscale data of this image includes the grayscale value of each pixel in the image. Next, the variance of the grayscale data for each image is calculated. Specifically, the calculation method is as follows: first, calculate the average grayscale value of all pixels in the grayscale data; then, calculate the square of the difference between the grayscale value of each pixel and the average value; finally, divide by the number of pixels in the grayscale data to obtain the variance of the grayscale data for that image. The specific calculation formula is:
[0065]
[0066]
[0067] Where, x i Let be the gray value of the i-th pixel in the image, n be the number of pixels in the gray data of the image, i be a counting parameter, μ be the average gray value of all pixels in the image, and D(x) be the variance of the gray data of the image.
[0068] Next, the image with the largest variance in grayscale data from the video file of the motion pose data is selected as the corresponding target image frame. It is worth noting that the method of selecting the target image frame can be, but is not limited to, the method of selecting by variance. Alternatively, the grayscale values of the two pixels in the horizontal right neighborhood of each pixel can be subtracted, multiplied, and then accumulated to calculate the square of the difference between the grayscale values of the two adjacent pixels. The image sharpness is then determined based on the value of the square, and the sharpest image is selected as the target image frame.
[0069] After selecting target image frames, feature fusion processing can be performed on the numbered human 3D data and each target image frame. This involves mapping the joint numbers in the human 3D data to each target image frame, thus obtaining motion joint data based on the target image frames labeled with joint numbers. It is understood that the mapping method can be, but is not limited to: obtaining the relative position information of 20 joints in the target image frame using human recognition technology and camera equipment; then combining this relative position information with the coordinates of 20 joints in the human 3D data to determine the corresponding joint in each target image frame and apply the same numbering processing, thereby mapping the joint numbers in the human 3D data to each target image frame. Subsequently, based on the numbering mapping relationship and other information, the motion joint data of the trainee during the assessment process can be obtained.
[0070] As another optional embodiment of this application, feature fusion processing is performed on the numbered human three-dimensional data and each target image frame to obtain motion joint data, including:
[0071] Each target image frame after fusion processing is input into a preset computational model to obtain each joint angle in each target image frame; wherein, the model is trained by sample image frames labeled with joint angles.
[0072] Specifically, a computational model can be trained using a large number of sample image frames labeled with joint angle information. This model can obtain the joint angles of 20 joints in each target image frame by using information such as joint length, joint connection method, and joint number in each fused target image frame.
[0073] It is worth noting that the methods for obtaining the joint numbers and corresponding joint angles of the 20 joints of the trainee during the assessment process include, but are not limited to, the methods described above. Alternatively, the joint numbers and corresponding joint angles of the 20 joints of the trainee during the assessment process can be obtained through a multimodal data fusion algorithm and a multi-channel convolutional neural network model. This application embodiment is not limited to this method.
[0074] Step 102: Based on the comparison results between the motion joint data and the preset standard library, obtain the standard data corresponding to the assessment items.
[0075] Specifically, by comparing the joint number and joint angle in the motion joint data with the joint angle of the same joint number in the preset standard library, the numerical relationship between the two can be used to determine whether the trainee's movements in the corresponding assessment item are standardized and whether they have reached the qualified standard.
[0076] As another optional embodiment of this application, based on the comparison results between the motion joint data and the preset standard library, the compliance data corresponding to the assessment items is obtained, including:
[0077] The difference between the joint angles in each target image frame and the joint angles of the corresponding joints in the preset standard library is calculated, and the number of joints that fall within the preset error range is determined.
[0078] The number of target image frames with a number of joints greater than or equal to the qualified threshold is counted, and the number of target image frames is used as the qualified data.
[0079] Specifically, based on the joint angles of 20 joints in each target image frame, the joint angle data of the corresponding joints (i.e., joints with the same number) are found in a preset standard library, and this data is compared with the joint angle data of the same joint in the target image frame to calculate the difference between the two. When the difference is within a preset error range, the joint is considered a qualified joint, and the number of qualified joints in the target image frame is counted.
[0080] The following table illustrates the comparison of joint angle data and the process for determining whether the difference falls within the error range:
[0081]
[0082] As shown in the table above, when the difference between the actual joint angle calculated by the preset model and the standard joint angle in the preset standard library is within the preset error range, the joint is considered a qualified joint; otherwise, it is considered an unqualified joint.
[0083] Furthermore, based on the number of qualified joints counted in the target image frame, the relationship between the number of qualified joints and the qualification threshold is determined, and the number of target image frames with a number of qualified joints greater than or equal to the qualification threshold is counted. The qualification threshold can be, but is not limited to, a preset threshold of not less than 15. For example, when the qualification threshold is 17, if 17 or more of the 20 joints in the target image frame are qualified, then that target image frame is counted. After the number of such target image frames in each group of motion joint data is counted, this statistical data is used as the corresponding compliance data.
[0084] Step 103: Optimize the assessment data based on the achievement data corresponding to the assessment items to obtain the target score.
[0085] Specifically, the manually recorded assessment data can be optimized based on the pass / fail data corresponding to the assessment items. By incorporating the standardization of actions during the assessment process as a reference, unqualified assessment data can be filtered out to obtain more accurate assessment results.
[0086] As another optional embodiment of this application, the assessment data is optimized based on the achievement data corresponding to the assessment items to obtain the target score, including:
[0087] When the assessment item is a counting assessment item, determine whether the target data and the assessment data are consistent;
[0088] When the target achievement data and the assessment data are inconsistent, the target score is determined based on the target achievement data.
[0089] When the target data matches the assessment data, the target score is determined based on the assessment data.
[0090] Specifically, when the assessment item is a counting-based assessment item, such as push-ups, pull-ups, and sit-ups, the statistically obtained pass data is compared with the manually recorded assessment data. If the two values are inconsistent, it indicates that the manually recorded assessment data is inaccurate, and the pass data can be used to calculate the assessment score; if the two values are consistent, it indicates that the manually recorded assessment data is correct, and the manually recorded assessment data can be used to calculate the assessment score.
[0091] As another optional embodiment of this application, determining the target score based on the achievement data includes:
[0092] Calculate the ratio between the number of qualified data and the preset number of standards, and determine the target score by multiplying the ratio by the standard score corresponding to the assessment item.
[0093] Specifically, when using benchmark data to calculate assessment scores, the ratio between the benchmark data and the preset number of standards can be calculated first. The preset number of standards can be the number of assessments required to achieve a full score for the assessment item corresponding to the benchmark data. Then, this ratio can be multiplied by the full score value for that assessment item to obtain the accurate assessment score.
[0094] As another optional embodiment of this application, optimizing the assessment data based on the achievement data corresponding to the assessment items to obtain the target score further includes:
[0095] When the assessment item is a timed assessment item, the number of unqualified items is determined based on the pass data and the number of target image frames corresponding to the assessment item.
[0096] The extra time is calculated based on the number of non-compliance items, and the target score is determined based on the extra time and the assessment data.
[0097] Specifically, when the assessment item is a timed assessment item, such as long-distance running or obstacle course running, the number of non-standard movements, i.e., the number of failures, can be calculated first based on the assessment data corresponding to the assessment item and the number of target image frames. Then, the additional time can be calculated according to a custom conversion rule, which includes, but is not limited to, adding three seconds to the additional time for each failure. After calculating the additional time, the additional time can be summed with the assessment time to obtain accurate assessment data. The accurate assessment data can be further calculated using custom scoring rules for timed assessment items to arrive at the final assessment score. Custom scoring rules for timed assessment items include, but are not limited to, a custom score calculation table containing the assessment time range for each timed assessment item and the corresponding score for each range. For example, in a long-distance running event, a score of 100 points is awarded for a time within 3 minutes, 80 points for a time exceeding 3 minutes but not exceeding 4 minutes, 70 points for a time exceeding 4 minutes but not exceeding 5 minutes, 60 points for a time exceeding 5 minutes but not exceeding 6 minutes, and 0 points for a time exceeding 6 minutes.
[0098] Please see Figure 2 , Figure 2 A schematic diagram of the structure of an evaluation device for military training assessment projects provided in an embodiment of this application is shown.
[0099] like Figure 2 As shown, the evaluation device for military training assessment projects may include at least a first processing module 201, a second processing module 202, and a third processing module 203, wherein:
[0100] The first processing module 201 is used to acquire human three-dimensional data and motion posture data corresponding to the assessment items, and to process the human three-dimensional data and motion posture data to obtain motion joint data.
[0101] The second processing module 202 is used to obtain the compliance data corresponding to the assessment items based on the comparison results between the motion joint data and the preset standard library.
[0102] The third processing module 203 is used to optimize the assessment data based on the achievement data corresponding to the assessment items to obtain the target score.
[0103] In some possible embodiments, the motion pose data includes at least two video files, each video file including at least two frames of images;
[0104] The first processing module 201 is specifically used for:
[0105] Human body 3D data and motion posture data are processed to obtain motion joint data, including:
[0106] Based on a preset spatial rectangular coordinate system, coordinate values are assigned to all joints in the three-dimensional human body data.
[0107] All joints are numbered based on the ascending order of values on at least two coordinate axes and the coordinates of all joints.
[0108] Perform grayscale processing on each image in each video file to obtain the corresponding image grayscale data;
[0109] Calculate the variance of grayscale data for each image, and use the image corresponding to the maximum variance as the target image frame of the corresponding video file;
[0110] Feature fusion processing is performed on the numbered human 3D data and each target image frame to obtain motion joint data.
[0111] In some possible embodiments, feature fusion processing is performed on the numbered human 3D data and each target image frame to obtain motion joint data, including:
[0112] The first processing module 201 is specifically used for:
[0113] Each target image frame after fusion processing is input into a preset computational model to obtain each joint angle in each target image frame; wherein, the model is trained by sample image frames labeled with joint angles.
[0114] In some possible embodiments, based on the comparison results between motion joint data and a preset standard library, the compliance data corresponding to the assessment items is obtained, including:
[0115] The second processing module 202 is specifically used for:
[0116] The difference between the joint angles in each target image frame and the joint angles of the corresponding joints in the preset standard library is calculated, and the number of joints that fall within the preset error range is determined.
[0117] The number of target image frames with a number of joints greater than or equal to the qualified threshold is counted, and the number of target image frames is used as the qualified data.
[0118] In some possible embodiments, the assessment data is optimized based on the achievement data corresponding to the assessment items to obtain the target score, including:
[0119] The third processing module 203 is specifically used for:
[0120] When the assessment item is a counting assessment item, determine whether the target data and the assessment data are consistent;
[0121] When the target achievement data and the assessment data are inconsistent, the target score is determined based on the target achievement data.
[0122] When the target data matches the assessment data, the target score is determined based on the assessment data.
[0123] In some possible embodiments, the target score is determined based on the achievement data, including:
[0124] The third processing module 203 is specifically used for:
[0125] Calculate the ratio between the number of qualified data and the preset number of standards, and determine the target score by multiplying the ratio by the standard score corresponding to the assessment item.
[0126] In some possible embodiments, optimizing the assessment data based on the achievement data corresponding to the assessment items to obtain the target score further includes:
[0127] The third processing module 203 is specifically used for:
[0128] When the assessment item is a timed assessment item, the number of unqualified items is determined based on the pass data and the number of target image frames corresponding to the assessment item.
[0129] The extra time is calculated based on the number of non-compliance items, and the target score is determined based on the extra time and the assessment data.
[0130] Please see Figure 3 , Figure 3 This paper shows a schematic diagram of the structure of another evaluation device for military training assessment projects provided in an embodiment of this application.
[0131] like Figure 3 As shown, the evaluation device 300 for military training assessment projects may include at least one processor 301, at least one network interface 304, user interface 303, memory 305, and at least one communication bus 302.
[0132] The communication bus 302 can be used to realize the connection and communication of the above components.
[0133] The user interface 303 may include buttons, and the optional user interface may also include a standard wired interface or a wireless interface.
[0134] The network interface 304 may include, but is not limited to, Bluetooth modules, NFC modules, Wi-Fi modules, etc.
[0135] The processor 301 may include one or more processing cores. The processor 301 connects to various parts of the evaluation device 300 for military training and assessment projects using various interfaces and lines. It executes various functions and processes data of the evaluation device 300 by running or executing instructions, programs, code sets, or instruction sets stored in the memory 305, and by calling data stored in the memory 305. Optionally, the processor 301 may be implemented using at least one hardware form of DSP, FPGA, or PLA. The processor 301 may integrate one or more of the following: CPU, GPU, and modem. The CPU primarily handles the operating system, user interface, and applications; the GPU is responsible for rendering and drawing the content to be displayed on the screen; and the modem handles wireless communication. It is understood that the modem may also not be integrated into the processor 301 and may be implemented as a separate chip.
[0136] The memory 305 may include RAM or ROM. Optionally, the memory 305 may include a non-transitory computer-readable medium. The memory 305 may be used to store instructions, programs, code, code sets, or instruction sets. The memory 305 may include a program storage area and a data storage area, wherein the program storage area may store instructions for implementing an operating system, instructions for at least one function (such as touch function, sound playback function, image playback function, etc.), instructions for implementing the above-described method embodiments, etc.; the data storage area may store data involved in the above-described method embodiments, etc. Optionally, the memory 305 may also be at least one storage device located remotely from the aforementioned processor 301. Figure 3 As shown, the memory 305, which serves as a computer storage medium, may include an operating system, a network communication module, a user interface module, and an evaluation application for military training and assessment projects.
[0137] Specifically, processor 301 can be used to call the evaluation application for military training assessment projects stored in memory 305, and specifically perform the following operations:
[0138] Acquire the human body 3D data and motion posture data corresponding to the assessment items, and process the human body 3D data and motion posture data to obtain motion joint data;
[0139] Based on the comparison results between the joint motion data and the preset standard library, the pass data corresponding to the assessment items are obtained;
[0140] The assessment data is optimized based on the achievement data corresponding to the assessment items to obtain the target score.
[0141] This application also provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the steps of the above-described method. The computer-readable storage medium may include, but is not limited to, any type of disk, including floppy disks, optical disks, DVDs, CD-ROMs, microdrives, as well as magneto-optical disks, ROMs, RAMs, EPROMs, EEPROMs, DRAMs, VRAMs, flash memory devices, magnetic cards or optical cards, nanosystems (including molecular memory ICs), or any type of medium or device suitable for storing instructions and / or data.
[0142] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.
[0143] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the relevant descriptions in other embodiments.
[0144] In the several embodiments provided in this application, it should be understood that the disclosed apparatus can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some service interface; the indirect coupling or communication connection between apparatuses or units may be electrical or other forms.
[0145] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.
[0146] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.
[0147] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage device (CMD). Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned memory includes various media capable of storing program code, such as USB flash drives, read-only memory (ROM), random access memory (RAM), portable hard drives, magnetic disks, or optical disks.
[0148] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing related hardware. The program can be stored in a computer-readable storage medium, which may include: a flash drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, etc.
[0149] The above are merely exemplary embodiments of this disclosure and should not be construed as limiting the scope of this disclosure. Any equivalent changes and modifications made in accordance with the teachings of this disclosure shall still fall within the scope of this disclosure. Those skilled in the art will readily conceive of embodiments of this disclosure upon considering the specification and practicing the disclosure herein. This application is intended to cover any variations, uses, or adaptations of this disclosure that follow the general principles of this disclosure and include common knowledge or customary techniques in the art not described herein. The specification and embodiments are to be considered exemplary only, and the scope and spirit of this disclosure are defined by the claims.
Claims
1. An evaluation method for military training assessment projects, characterized in that, include: Acquire the human body 3D data and motion posture data corresponding to the assessment items, and process the human body 3D data and motion posture data to obtain motion joint data; Based on the comparison results between the joint motion data and the preset standard library, the pass data corresponding to the assessment items are obtained; The assessment data is optimized based on the pass data corresponding to the assessment items to obtain the target score; The motion posture data includes at least two video files, and each video file includes at least two frames of images; The process of processing the human body's three-dimensional data and motion posture data to obtain motion joint data includes: Based on a preset spatial rectangular coordinate system, coordinate values are assigned to all joints in the human body three-dimensional data. All joints are numbered based on the ascending order of values of any at least two coordinate axes and the coordinates of all joints. Each image in each video file is converted to grayscale to obtain the corresponding image grayscale data; Calculate the variance of each image grayscale data, and take the image corresponding to the maximum variance as the target image frame of the corresponding video file; The numbered human body 3D data and each target image frame are subjected to feature fusion processing to obtain motion joint data; The step of performing feature fusion processing on the numbered human body 3D data and each target image frame to obtain motion joint data includes: Each of the target image frames after fusion processing is input into a preset calculation model to obtain each joint angle in each target image frame; wherein, the model is trained by sample image frames labeled with the joint angles; The comparison results between the motion joint data and the preset standard library yield the qualification data corresponding to the assessment items, including: The difference between the joint angle in each target image frame and the joint angle of the corresponding joint in the preset standard library is calculated, and the number of joints that fall within the preset error range is determined. The number of target image frames with a joint count greater than or equal to the qualified threshold is counted, and the number of target image frames is used as the qualified data; The optimization of the assessment data based on the achievement data corresponding to the assessment items to obtain the target score includes: When the assessment item is a counting assessment item, determine whether the pass data is consistent with the assessment data; When the achievement data is inconsistent with the assessment data, the target score is determined based on the achievement data; When the achievement data matches the assessment data, the target score is determined based on the assessment data; Determining the target score based on the attainment data includes: The ratio between the qualified data and the preset number of standards is calculated, and the target score is determined by multiplying the ratio by the standard score corresponding to the assessment item.
2. The method according to claim 1, characterized in that, The step of optimizing the assessment data based on the achievement data corresponding to the assessment items to obtain the target score also includes: When the assessment item is a timed assessment item, the number of unqualified items is determined based on the pass data and the number of target image frames corresponding to the assessment item. The additional time is calculated based on the number of non-compliance items, and the target score is determined based on the additional time and the assessment data.
3. An evaluation device for military training assessment projects, characterized in that, include: The first processing module is used to acquire human three-dimensional data and motion posture data corresponding to the assessment items, and to process the human three-dimensional data and motion posture data to obtain motion joint data. The second processing module is used to obtain the pass data corresponding to the assessment item based on the comparison results between the motion joint data and the preset standard library. The third processing module is used to optimize the assessment data based on the pass data corresponding to the assessment items to obtain the target score; The motion posture data includes at least two video files, and each video file includes at least two frames of images; The process of processing the human body's three-dimensional data and motion posture data to obtain motion joint data includes: Based on a preset spatial rectangular coordinate system, coordinate values are assigned to all joints in the human body three-dimensional data. All joints are numbered based on the ascending order of values of any at least two coordinate axes and the coordinates of all joints. Each image in each video file is converted to grayscale to obtain the corresponding image grayscale data; Calculate the variance of each image grayscale data, and take the image corresponding to the maximum variance as the target image frame of the corresponding video file; The numbered human body 3D data and each target image frame are subjected to feature fusion processing to obtain motion joint data; The step of performing feature fusion processing on the numbered human body 3D data and each target image frame to obtain motion joint data includes: Each of the target image frames after fusion processing is input into a preset calculation model to obtain each joint angle in each target image frame; wherein, the model is trained by sample image frames labeled with the joint angles; The comparison results between the motion joint data and the preset standard library yield the qualification data corresponding to the assessment items, including: The difference between the joint angle in each target image frame and the joint angle of the corresponding joint in the preset standard library is calculated, and the number of joints that fall within the preset error range is determined. The number of target image frames with a joint count greater than or equal to the qualified threshold is counted, and the number of target image frames is used as the qualified data; The optimization of the assessment data based on the achievement data corresponding to the assessment items to obtain the target score includes: When the assessment item is a counting assessment item, determine whether the pass data is consistent with the assessment data; When the achievement data is inconsistent with the assessment data, the target score is determined based on the achievement data; When the achievement data matches the assessment data, the target score is determined based on the assessment data; Determining the target score based on the attainment data includes: The ratio between the qualified data and the preset number of standards is calculated, and the target score is determined by multiplying the ratio by the standard score corresponding to the assessment item.
4. An evaluation device for military training assessment projects, characterized in that, Including the processor and memory; The processor is connected to the memory; The memory is used to store executable program code; The processor runs a program corresponding to the executable program code stored in the memory to perform the steps of the method as described in any one of claims 1-2.
5. A computer-readable storage medium having a computer program stored thereon, characterized in that, The computer-readable storage medium stores instructions that, when executed on a computer or processor, cause the computer or processor to perform the steps of the method as described in any one of claims 1-2.