Teaching project assessment system based on posture perception

Abstract

The invention relates to the technical field of machine vision, in particular to a teaching project assessment system based on posture perception, which comprises a video acquisition module; the data extraction module is used for extracting examination images and key examination video segments; the data processing module is used for acquiring the outline and key assessment action point positions of the assessed person and constructing lines of the key assessment action point positions; the evaluation module is used for judging whether the key evaluation point position posture of the examinee meets a preset standard or not, verifying whether the key evaluation point position posture of the examinee meets the preset standard or not, determining an optimization mode of a key evaluation action standard image, judging whether the key evaluation action posture process in the key evaluation video segment meets the preset standard or not, and if yes, judging whether the key evaluation action posture process meets the preset standard. The attitude analysis module is used for checking whether the key assessment action process meets a preset standard or not; comprising a first storage unit and a second storage unit, the intelligent analysis of the examination posture is realized, and the accuracy of the examination system is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of machine vision, and in particular to a teaching project assessment system based on posture perception. Background Art

[0002] Teaching project assessment refers to the process of comprehensively evaluating students' learning outcomes, skills mastery, project completion quality, teamwork and other aspects of their performance in a specific teaching project. This assessment not only focuses on students' understanding and mastery of knowledge points, but also emphasizes the evaluation of students' comprehensive qualities such as their ability to demonstrate in actual project operations, innovative thinking, problem-solving ability and teamwork.

[0003] Chinese patent publication number: CN116228012A, discloses a smart military sports assessment and training management system, including: identity acquisition module, knowledge guidance module, state monitoring module, motion recording module and processing module; wherein the identity acquisition module is used to obtain user identity information; the knowledge guidance module is used to match the corresponding assessment and training knowledge from the knowledge base according to the obtained user identity information, and display the assessment and training knowledge; the state monitoring module is used to collect the user's physical function data during the user's assessment and training; the motion recording module is used to collect the user's motion data for assessment and training, wherein the motion data includes video recording data and performance recording data; the processing module is used to analyze the user's assessment and training situation according to the acquired physical function data and motion data, and obtain the user's assessment and training analysis results. It can be seen that the above technical solution lacks the function of intelligent analysis and processing of assessment posture. Summary of the invention

[0004] To this end, the present invention provides a teaching project assessment system based on posture perception, so as to overcome the problem of lack of intelligent analysis and processing of assessment posture in the prior art.

[0005] To achieve the above object, the present invention provides a teaching project assessment system based on posture perception, comprising:

[0006] A video acquisition module, which includes a camera for acquiring the video to be assessed and a pre-storage unit for temporarily storing the acquired video to be assessed;

[0007] A data extraction module, which is connected to the video acquisition module, and is used to extract the assessment image in the video to be assessed according to the key assessment action, and to extract the key assessment video segment according to the assessment weight coefficient;

[0008] A data processing module, connected to the data extraction module, for obtaining the outline of the examinee in the assessment image, for obtaining key assessment action points according to the outline of the examinee, and for constructing key assessment action point lines according to the key assessment action points;

[0009] A posture analysis module, which is connected to the data processing module, determines whether the posture of the key assessment points of the assessee meets the preset standard based on the contour overlap, verifies whether the posture of the key assessment points of the assessee meets the preset standard based on the angle evaluation value, determines the optimization method of the key assessment action standard image based on the body posture ratio, determines whether the key assessment action posture process in the key assessment video segment meets the preset standard based on the key point motion trajectory overlap, and verifies whether the key assessment action process meets the preset standard based on the change time difference;

[0010] The data storage module is connected to the data extraction module and the posture analysis module, and includes a first storage unit and a second storage unit, wherein:

[0011] The first storage unit is used to store standard posture data, assessment standard video data, and the standard image data of the key assessment action, the outline of the standard person in the assessment standard video, the motion trajectory curve of the standard assessment action point, and the standard point line of the key assessment action;

[0012] The second storage unit is used to store the images and video segments extracted by the data extraction module, and to store the posture data analyzed by the posture analysis module.

[0013] Furthermore, in response to the assessment weight coefficient being greater than or equal to a preset coefficient, the data extraction module extracts the to-be-assessed video within a preset time period to generate a key assessment video segment.

[0014] Furthermore, the assessment weight coefficient is an average of the percentage of different pixels between two adjacent frames of the video within a preset time period.

[0015] Furthermore, in response to the number of assessment images contained in a single key assessment video segment being less than a preset number, the data processing module corrects the extraction duration of the assessment video segment and completes the extraction of the key assessment video segment.

[0016] Furthermore, the posture analysis module determines whether the posture of the key assessment point of the assessee meets the preset standard based on the contour overlap, wherein:

[0017] If the contour overlap is less than the first preset contour overlap, the posture analysis module determines that the posture of the key assessment point of the examinee does not meet the preset standard, and the reason for not meeting the preset standard is that the action execution of the examinee does not meet the standard;

[0018] If the contour overlap is greater than or equal to the first preset contour overlap and less than the second preset contour overlap, the posture analysis module determines that the posture of the key assessment point of the examinee meets the preset standard, and verifies whether the posture of the key assessment point of the examinee meets the preset standard according to the angle evaluation value;

[0019] If the contour overlap is greater than or equal to the second preset contour overlap, the posture analysis module determines that the posture of the key assessment point of the assessee meets the preset standard, and stores the assessment image in the second storage unit.

[0020] Furthermore, the posture analysis module verifies whether the posture of the key assessment point of the assessee meets the preset standard based on the angle evaluation value, wherein:

[0021] If the angle evaluation value is less than the preset angle evaluation value, the posture analysis module determines that the posture of the key assessment point of the assessee meets the preset standard, stores the assessment image in the second storage unit, and determines the optimization method of the key assessment action standard image according to the posture ratio;

[0022] If the angle evaluation value is greater than or equal to the preset angle evaluation value, the posture analysis module determines that the posture of the key assessment point of the examinee does not meet the preset standard, and the reason for not meeting the preset standard is that the action execution of the examinee does not meet the standard;

[0023] The angle evaluation value is determined according to the angle between the key assessment action point line and the key assessment action standard point line;

[0024] The posture ratio is determined by the posture data of the examinee and the posture information in the assessment standard video.

[0025] Furthermore, the posture analysis module determines an optimization method for the key assessment action standard image based on the posture ratio, wherein:

[0026] If the posture ratio is less than the preset posture ratio, the posture analysis module enlarges the standard image of the key assessment action;

[0027] If the posture ratio is greater than or equal to the preset posture ratio, the posture analysis module will reduce the key assessment action standard image.

[0028] Furthermore, the reduction range of the key assessment action standard diagram is positively correlated with the posture adjustment difference; the posture adjustment difference is the difference between the posture ratio and the preset posture ratio.

[0029] Furthermore, the posture analysis module determines whether the key assessment action posture process in the key assessment video segment meets the preset standard based on the overlap of the key point motion trajectory, wherein:

[0030] If the overlap of the key point motion trajectories is less than the preset trajectory overlap, the posture analysis module determines that the key assessment action posture process in the key assessment video segment does not meet the preset standard and removes it from the second storage unit;

[0031] If the overlap of the key point motion trajectories is greater than or equal to the preset trajectory overlap, the posture analysis module determines that the key assessment action posture process in the key assessment video segment meets the preset standard and checks whether the key assessment action process in the key assessment video segment meets the preset standard according to the change time difference;

[0032] The change duration difference is the difference between the change duration of the key assessment action point and the preset standard change duration.

[0033] Furthermore, the posture analysis module verifies whether the key assessment action process meets the preset standard based on the change time difference, wherein:

[0034] If the change duration difference is less than the preset duration difference, the posture analysis module determines that the key assessment action process meets the preset standard and completes the assessment according to the current parameters;

[0035] If the change duration difference is greater than or equal to the preset duration difference, the posture analysis module determines that the key assessment action process does not meet the preset standard and removes the key assessment video segment.

[0036] Compared with the prior art, the beneficial effects of the present invention are as follows: the present invention sets a video acquisition module, a data extraction module, a data processing module, for determining whether the posture of the key assessment point meets the preset standard based on the contour coincidence, for verifying whether the posture of the key assessment point meets the preset standard based on the angle evaluation value, for determining the optimization strategy of the second assessment image based on the body posture ratio, for determining whether the key assessment action posture process in the key assessment video segment meets the preset standard based on the coincidence of the key point motion trajectory, for verifying whether the key assessment action process meets the preset standard based on the change time difference, and a posture analysis module, and a data storage module, thereby realizing efficient and accurate analysis of the assessment video.

[0037] Furthermore, the present invention realizes intelligent extraction of the video to be assessed by setting a data extraction module to extract key assessment video segments of the preset duration in response to the assessment weight coefficient being greater than or equal to a preset coefficient.

[0038] Furthermore, the present invention improves the accuracy of extracting the key assessment video by setting a data processing module to correct the extraction duration of the key assessment video segment based on the number of the assessment images under the first preset condition.

[0039] Furthermore, the present invention improves the assessment efficiency by setting a posture analysis module to determine whether the posture of the key assessment point meets the preset standard based on the contour coincidence.

[0040] Furthermore, the present invention improves the objectivity of the posture assessment movement by setting a posture analysis module to verify whether the posture of the key assessment point meets the preset standard based on the angle evaluation value.

[0041] Furthermore, the present invention improves the accuracy of the assessment system by setting a posture analysis module to determine the optimization strategy of the second assessment image based on the posture ratio.

[0042] Furthermore, the present invention realizes precise control of the adjustment of the key assessment action standard diagram by setting a positive correlation between the reduction range of the key assessment action standard diagram and the difference between the posture ratio and the preset posture ratio.

[0043] Furthermore, the present invention improves the automation level of the assessment system by setting a posture analysis module to determine whether the key assessment action posture process in the key assessment video segment meets the preset standards based on the overlap of the key point motion trajectory. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Figure 1 It is a structural diagram of a teaching project assessment system based on posture perception according to an embodiment of the present invention;

[0045] Figure 2 A flowchart of correcting the extraction duration of the key assessment video segment according to an embodiment of the present invention;

[0046] Figure 3 This is a flow chart of an embodiment of the present invention for determining whether the posture of a key assessment point meets a preset standard;

[0047] Figure 4 The present invention is a flowchart of an embodiment of the present invention for determining whether the posture of a key assessment point meets a preset standard. DETAILED DESCRIPTION

[0048] In order to make the objects and advantages of the present invention more clearly understood, the present invention is further described below in conjunction with embodiments; it should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0049] It should be pointed out that the data in this embodiment are obtained by comprehensive analysis and evaluation of the historical detection data of the central control processor in the three months before the current detection and the corresponding historical detection results. Those skilled in the art can understand that the system of the present invention can determine the above-mentioned single parameter by selecting the highest proportion of the value as the preset standard parameter according to the data distribution, using weighted summation to use the obtained value as the preset standard parameter, substituting each historical data into a specific formula and using the value obtained by the formula as the preset standard parameter or other selection methods, as long as the system of the present invention can clearly define the different specific situations in the single judgment process through the obtained values.

[0050] The preferred embodiments of the present invention are described below with reference to the accompanying drawings. It should be understood by those skilled in the art that these embodiments are only used to explain the technical principles of the present invention and are not intended to limit the protection scope of the present invention.

[0051] See also Figure 1 , Figure 2 , Figure 3 as well as Figure 4 As shown, they are respectively a structural schematic diagram of a teaching project assessment system based on posture perception according to an embodiment of the present invention; a flowchart of correcting the extraction time of the key assessment video segment according to an embodiment of the present invention; a flowchart of determining whether the posture of a key assessment point meets the preset standard according to an embodiment of the present invention; a flowchart of determining whether the posture of a key assessment point meets the preset standard according to an embodiment of the present invention;

[0052] The embodiment of the present invention provides a teaching project assessment system based on posture perception, including:

[0053] A video acquisition module, which includes a camera for acquiring the video to be assessed and a pre-storage unit for temporarily storing the acquired video to be assessed;

[0054] A data extraction module, which is connected to the video acquisition module, and is used to extract the assessment image in the video to be assessed according to the key assessment action, and to extract the key assessment video segment according to the assessment weight coefficient;

[0055] A data processing module, which is connected to the data extraction module, and is used to obtain the outline of the examinee in the examination image, obtain key examination action points, and construct key examination action point lines;

[0056] A posture analysis module, which is connected to the data processing module, determines whether the posture of the key assessment points of the assessee meets the preset standard based on the contour overlap, verifies whether the posture of the key assessment points of the assessee meets the preset standard based on the angle evaluation value, determines the optimization method of the key assessment action standard image based on the body posture ratio, determines whether the key assessment action posture process in the key assessment video segment meets the preset standard based on the key point motion trajectory overlap, and verifies whether the key assessment action process meets the preset standard based on the change time difference;

[0057] The data storage module is connected to the data extraction module and the posture analysis module, and includes a first storage unit and a second storage unit, wherein:

[0058] The first storage unit is used to store standard posture data, assessment standard video data, and the standard image data of the key assessment action, standard assessment action point motion trajectory curves, and key assessment action standard point lines;

[0059] The second storage unit is used to store the images and video segments extracted by the data extraction module, and to store the posture data analyzed by the posture analysis module.

[0060] Specifically, the key assessment action points are, for example, the centers of human joints in the outline of the person being assessed, and the key assessment action point lines are the connecting lines of the assessment action points.

[0061] Specifically, the data extraction module determines whether the video to be assessed within a preset time period is the key assessment video segment based on the assessment weight coefficient, wherein:

[0062] If the assessment weight coefficient is less than the preset coefficient, the data extraction module determines that the video to be assessed within the preset time period is not the key assessment video segment and removes the assessment video segment;

[0063] If the assessment weight coefficient is greater than or equal to the preset coefficient, the data extraction module determines that the video to be assessed within the preset time period is the key assessment video segment and extracts and stores it in the second storage unit;

[0064] Among them, the preset time period is set to 5s, and the preset coefficient is set to 0.34.

[0065] Specifically, the assessment weight coefficient is calculated by the following formula:

[0066]

[0067] In the formula, A represents the assessment weight coefficient, g(j) represents the ratio of the number of different pixels between two adjacent frames of the jth frame to the total number of pixels in a single frame, where j = 1, 2...m-1, m represents the total number of frames in the video segment within the preset time period,

[0068] The number of different pixels between two adjacent frames is calculated using GIMP software.

[0069] Specifically, the data processing module corrects the extraction time of the single key assessment video segment based on the number of assessment images contained in the single key assessment video segment, wherein:

[0070] If the number of assessment images contained in the single key assessment video segment is less than the preset number of 7, the data processing module corrects the extraction time of the single key assessment video segment;

[0071] Specifically, the increase in the extraction time of a single key assessment video segment is positively correlated with the difference in the number of images, wherein the difference in the number of images is the difference between the preset number and the number of assessment images contained in the single key assessment video segment. For example, the increase in the extraction time of a single key assessment video segment is set to △B, and the difference in the number of images is set to △λ, then △B=μ×△λ, μ is the time adjustment coefficient, and μ is set to 1.06. It can be understood that the larger the difference in the number of images, the greater the increase in the extraction time of the single key assessment video segment.

[0072] If the number of assessment images contained in the single key assessment video segment is greater than or equal to the preset number of 7, the data processing module completes data processing according to the current extraction duration.

[0073] Specifically, the posture analysis module determines whether the posture of the key assessment point of the examinee meets the preset standard based on the contour overlap, wherein:

[0074] If the contour overlap is less than the first preset contour overlap 0.75, the posture analysis module determines that the posture of the key assessment point of the examinee does not meet the preset standard, and the reason for not meeting the preset standard is that the action execution of the examinee does not meet the standard;

[0075] If the contour overlap is greater than or equal to the first preset contour overlap and less than the second preset contour overlap of 0.93, the posture analysis module determines that the posture of the key assessment point of the examinee meets the preset standard and verifies whether the posture of the key assessment point of the examinee meets the preset standard according to the angle evaluation value;

[0076] If the contour overlap is greater than or equal to the second preset contour overlap, the posture analysis module determines that the posture of the key assessment point of the assessee meets the preset standard, and stores the assessment image in the second storage unit;

[0077] The contour overlap is calculated by the following formula:

[0078]

[0079] In the formula, O represents the degree of contour overlap; Sc represents the area of ​​contour overlap; S0 represents the area of ​​the contour area of ​​the standard person in the assessment standard video; S1 represents the area of ​​the contour area of ​​the person being assessed in the assessment image.

[0080] Specifically, the posture analysis module verifies whether the posture of the key assessment point meets the preset standard based on the angle evaluation value, wherein:

[0081] If the angle evaluation value is less than the preset angle evaluation value of 5.2°, the posture analysis module determines that the posture of the key assessment point of the assessee meets the preset standard, and stores the assessment image in the second storage unit, and determines the optimization method of the key assessment action standard image according to the posture ratio;

[0082] If the angle evaluation value is greater than or equal to the preset angle evaluation value, the posture analysis module determines that the posture of the key assessment point of the examinee does not meet the preset standard, and the reason for not meeting the preset standard is that the action execution of the examinee does not meet the standard;

[0083] The angle evaluation value is the average value of the angles between each key assessment action point line and the corresponding key assessment action standard point line.

[0084] Specifically, the body posture ratio is calculated by the following formula:

[0085]

[0086] In the formula, I represents the body shape ratio, and the unit is kg / m 2 ; W represents the weight of the person being assessed, in kg; H represents the height of the person being assessed, in m.

[0087] Specifically, the posture analysis module determines the optimization method of the key assessment action standard image based on the posture ratio, wherein:

[0088] If the posture ratio is less than the preset posture ratio of 24.67, the posture analysis module enlarges the standard image of the key assessment action;

[0089] If the posture ratio is greater than or equal to the preset posture ratio, the posture analysis module will reduce the key assessment action standard image.

[0090] Specifically, the reduction range of the key assessment action standard diagram is positively correlated with the posture adjustment difference; the posture adjustment difference is the difference between the posture ratio and the preset posture ratio. It can be understood that the larger the posture adjustment difference, the larger the reduction range of the key assessment action standard diagram.

[0091] Specifically, the posture analysis module determines whether the key assessment action posture process in the key assessment video segment meets the preset standard based on the overlap of the key point motion trajectory, wherein:

[0092] If the overlap of the key point motion trajectory is less than the preset trajectory overlap of 71.36%, the posture analysis module determines that the key assessment action posture process in the key assessment video segment does not meet the preset standard and removes it from the second storage unit;

[0093] If the overlap of the key point motion trajectories is greater than or equal to the preset trajectory overlap, the posture analysis module determines that the key assessment action posture process in the key assessment video segment meets the preset standard and checks whether the key assessment action process in the key assessment video segment meets the preset standard according to the change time difference;

[0094] The key point motion trajectory overlap degree is the overlap ratio between the key assessment action point motion trajectory curve of the assessee and the standard assessment action point motion trajectory curve.

[0095] Specifically, the change duration difference is the absolute value of the difference between the change duration of the key assessment action point and the preset standard change duration, wherein the preset standard change duration is the duration from the start to the end of the key assessment action, which can be obtained based on the execution duration of the corresponding standard assessment action point motion trajectory curve, for example 3s.

[0096] Specifically, the posture analysis module verifies whether the key assessment action process meets the preset standard based on the change time difference, wherein:

[0097] If the change duration difference is less than the preset duration difference of 0.67s, the posture analysis module determines that the key assessment action process meets the preset standard and completes the assessment according to the current parameters;

[0098] If the change duration difference is greater than or equal to the preset duration difference of 0.67s, the posture analysis module determines that the key assessment action process does not meet the preset standard and removes the key assessment video segment.

[0099] So far, the technical solutions of the present invention have been described in conjunction with the preferred embodiments shown in the accompanying drawings. However, it is easy for those skilled in the art to understand that the protection scope of the present invention is obviously not limited to these specific embodiments. Without departing from the principle of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after these changes or substitutions will fall within the protection scope of the present invention.

[0100] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A teaching project assessment system based on posture perception, characterized in that: include: A video acquisition module, which includes a camera for acquiring the video to be assessed and a pre-storage unit for temporarily storing the acquired video to be assessed; A data extraction module, which is connected to the video acquisition module, and is used to extract the assessment image in the video to be assessed according to the key assessment action, and to extract the key assessment video segment according to the assessment weight coefficient; A data processing module, connected to the data extraction module, for obtaining the outline of the examinee in the assessment image, for obtaining key assessment action points according to the outline of the examinee, and for constructing key assessment action point lines according to the key assessment action points; A posture analysis module, which is connected to the data processing module, determines whether the posture of the key assessment points of the assessee meets the preset standard based on the contour overlap, verifies whether the posture of the key assessment points of the assessee meets the preset standard based on the angle evaluation value, determines the optimization method of the key assessment action standard image based on the body posture ratio, determines whether the key assessment action posture process in the key assessment video segment meets the preset standard based on the key point motion trajectory overlap, and verifies whether the key assessment action process meets the preset standard based on the change time difference; The data storage module is connected to the data extraction module and the posture analysis module, and includes a first storage unit and a second storage unit, wherein: The first storage unit is used to store standard posture data, assessment standard video data, and key assessment action standard image data, the outline of the standard person in the assessment standard video, the motion trajectory curve of the standard assessment action point, and the key assessment action standard point line; The second storage unit is used to store the images and video segments extracted by the data extraction module, and to store the posture data analyzed by the posture analysis module.

2. A teaching project assessment system based on posture perception according to claim 1, characterized in that: In response to the assessment weight coefficient being greater than or equal to a preset coefficient, the data extraction module extracts the to-be-assessed video within a preset time period to generate a key assessment video segment.

3. A teaching project assessment system based on posture perception according to claim 2, characterized in that: The assessment weight coefficient is the average of the percentage of different pixels between two adjacent frames of the video within a preset time period.

4. A teaching project assessment system based on posture perception according to claim 3, characterized in that: In response to the fact that the number of assessment images contained in a single key assessment video segment is less than a preset number, the data processing module corrects the extraction duration of the assessment video segment and completes the extraction of the key assessment video segment.

5. A teaching project assessment system based on posture perception according to claim 4, characterized in that: The posture analysis module determines whether the posture of the key assessment point of the examinee meets the preset standard based on the contour overlap, wherein: If the contour overlap is less than the first preset contour overlap, the posture analysis module determines that the posture of the key assessment point of the examinee does not meet the preset standard, and the reason for not meeting the preset standard is that the action execution of the examinee does not meet the standard; If the contour overlap is greater than or equal to the first preset contour overlap and less than the second preset contour overlap, the posture analysis module determines that the posture of the key assessment point of the examinee meets the preset standard, and verifies whether the posture of the key assessment point of the examinee meets the preset standard according to the angle evaluation value; If the contour overlap is greater than or equal to the second preset contour overlap, the posture analysis module determines that the posture of the key assessment point of the assessee meets the preset standard, and stores the assessment image in the second storage unit.

6. A teaching project assessment system based on posture perception according to claim 5, characterized in that: The posture analysis module verifies whether the posture of the key assessment point of the assessee meets the preset standard based on the angle evaluation value, wherein: If the angle evaluation value is less than the preset angle evaluation value, the posture analysis module determines that the posture of the key assessment point of the assessee meets the preset standard, stores the assessment image in the second storage unit, and determines the optimization method of the key assessment action standard image according to the posture ratio; If the angle evaluation value is greater than or equal to the preset angle evaluation value, the posture analysis module determines that the posture of the key assessment point of the examinee does not meet the preset standard, and the reason for not meeting the preset standard is that the action execution of the examinee does not meet the standard; The angle evaluation value is determined according to the angle between the key assessment action point line and the key assessment action standard point line; The posture ratio is determined by the posture data of the examinee and the posture information in the assessment standard video.

7. A teaching project assessment system based on posture perception according to claim 6, characterized in that: The posture analysis module determines the optimization method of the key assessment action standard image based on the posture ratio, wherein: If the posture ratio is less than the preset posture ratio, the posture analysis module enlarges the standard image of the key assessment action; If the posture ratio is greater than or equal to the preset posture ratio, the posture analysis module will reduce the key assessment action standard image.

8. The teaching project assessment system based on posture perception according to claim 7 is characterized in that: The reduction range of the key assessment action standard diagram is positively correlated with the posture adjustment difference; the posture adjustment difference is the difference between the posture ratio and the preset posture ratio.

9. The teaching project assessment system based on posture perception according to claim 8 is characterized in that: The posture analysis module determines whether the key assessment action posture process in the key assessment video segment meets the preset standard based on the overlap of the key point motion trajectory, wherein: If the overlap of the key point motion trajectories is less than the preset trajectory overlap, the posture analysis module determines that the key assessment action posture process in the key assessment video segment does not meet the preset standard and removes it from the second storage unit; If the overlap of the key point motion trajectories is greater than or equal to the preset trajectory overlap, the posture analysis module determines that the key assessment action posture process in the key assessment video segment meets the preset standard and checks whether the key assessment action process in the key assessment video segment meets the preset standard according to the change time difference; The change duration difference is the difference between the change duration of the key assessment action point and the preset standard change duration.

10. A teaching project assessment system based on posture perception according to claim 9, characterized in that: The posture analysis module verifies whether the key assessment action process meets the preset standard based on the change time difference, wherein: If the change duration difference is less than the preset duration difference, the posture analysis module determines that the key assessment action process meets the preset standard and completes the assessment according to the current parameters; If the change duration difference is greater than or equal to the preset duration difference, the posture analysis module determines that the key assessment action process does not meet the preset standard and removes the key assessment video segment.

Images