Method for detecting human body posture change amplitude and method for evaluating posture richness

Abstract

The invention discloses a human body posture change amplitude detection method, a posture richness evaluation method, a device, equipment and a storage medium. The method for detecting the variation amplitude of the human body posture comprises the following steps: acquiring human body skeleton key point information of a target person of an initial image frame and a to-be-detected image frame, and extracting the variation amplitude of the human body posture based on preset to-be-extracted human body skeleton key points; respectively extracting corresponding human body skeleton key points as first and second human body key points according to the human body skeleton key point information of the initial image frame and the to-be-detected image frame; respectively calculating the area of a polygon defined by the first human body key point and the second human body key point to obtain a first area and a second area; according to the change degree of the first area and the second area, the change amplitude of the human body posture is obtained. The method is relatively simple, occupies less resources, is relatively sensitive, is suitable for the scene that the teacher takes a class, and can reflect the variation amplitude of the human body posture of the teacher in time.

Description

Technical Field

[0001] The present invention relates to the technical field of image processing, and more specifically, to a method for detecting a variation range of a human body posture, a method, a device, a equipment and a storage medium for evaluating posture richness. Background Art

[0002] In teaching activities, teachers are the soul of the teaching scene. The appeal of teachers' lectures directly affects the effect of teaching activities, and the rich teaching postures of teachers help to improve the appeal of teachers' lectures. Through rich and diverse teaching postures, teachers can stimulate students' interest in learning, help students understand knowledge from different perspectives, encourage students to participate in classroom discussions, enhance the interaction between teachers and students, thereby improving learning effects and making the classroom more lively and interesting.

[0003] The current posture richness evaluation methods are based on recognition based on preset postures, and then statistics are collected to obtain the final results. However, in actual teaching scenarios, the teacher's posture is ever-changing and has no fixed form, so it is difficult to detect all postures through preset posture recognition, resulting in statistical errors. In addition, the teacher's class is a dynamic process, and the rate and amplitude of change of posture are also aspects that need to be considered. Traditional evaluation methods do not take this aspect into account. Summary of the invention

[0004] In order to overcome the defects in the above-mentioned prior art that the amplitude of change of human head posture cannot be detected and the richness of posture cannot be evaluated by the amplitude of change, the present invention provides a method for detecting the amplitude of change of human body posture, a method, device, equipment and storage medium for evaluating posture richness. The technical solution adopted by the present invention is as follows.

[0005] In a first aspect, the present invention provides a method for detecting a change range of a human body posture, comprising:

[0006] Acquire the human skeleton key point information of the target person in the initial image frame, and based on the preset human skeleton key points to be extracted, extract the corresponding human skeleton key points as the first human skeleton key points according to the human skeleton key point information of the initial image frame;

[0007] Acquire the human skeleton key point information of the target person in the image frame to be detected, and based on the preset human skeleton key points to be extracted, extract the corresponding human skeleton key points as the second human skeleton key points according to the human skeleton key point information of the image frame to be detected;

[0008] Calculate the area of ​​the polygon enclosed by the first human body key points to obtain a first area;

[0009] Calculate the area of ​​the polygon enclosed by the second human body key points to obtain a second area;

[0010] The change amplitude of the human body posture is obtained according to the change degrees of the first area and the second area.

[0011] In one embodiment, the preset key points of the human skeleton to be extracted include: the top of the head, the fingertips of both hands, and the toes of both feet.

[0012] In one embodiment, it further includes:

[0013] Calculate the height of the target person according to the human skeleton key point information of the target person in the initial image frame and / or the human skeleton key point information of the target person in the image frame to be detected;

[0014] The process of obtaining the change amplitude of the human body posture according to the change degrees of the first area and the second area includes:

[0015] Based on the height of the target person and according to the degree of change of the first area and the second area, the change range of the human body posture is obtained.

[0016] In one implementation, the process of obtaining the change range of the human body posture based on the height of the target person and the degree of change between the first area and the second area includes:

[0017] According to the height of the target person and the first area, a first area per unit height is obtained;

[0018] According to the height of the target person and the second area, the second area per unit height is obtained;

[0019] The variation range of the human body posture is obtained according to the variation degree of the first area per unit height and the first area per unit height.

[0020] In a second aspect, the present invention provides a method for evaluating posture richness, comprising:

[0021] Obtain the video of the teacher's class and take screenshots of the video at preset time intervals;

[0022] Calculate the change in the teacher's body posture between the initial image frame and each screenshot;

[0023] According to the variation of each teacher's body posture, the evaluation results of the richness of the teacher's teaching posture are obtained;

[0024] The process of calculating the change range of the teacher's human body posture between the initial image frame and each screenshot includes:

[0025] Using the method for detecting the amplitude of changes in human body posture described above, the amplitude of changes in the teacher's human body posture between the initial image frame and each screenshot is calculated. In the process of using the method for detecting the amplitude of changes in human body posture, the teacher is used as the target object, and the screenshot of the teacher's static standing posture is used as the initial image frame.

[0026] In one embodiment, the variation range of the teacher's body posture is the difference between the first area and the second area;

[0027] The process of obtaining the evaluation result of the richness of the teacher's teaching posture according to the variation range of each teacher's body posture includes:

[0028] The standard deviation was calculated based on the variation of each teacher’s body posture;

[0029] The evaluation result of the richness of the teacher's teaching posture is obtained based on the standard deviation.

[0030] In one embodiment, the variation range of the teacher's body posture is the difference between the first area and the second area;

[0031] The process of obtaining the evaluation result of the richness of the teacher's teaching posture according to the variation range of each teacher's body posture includes:

[0032] The standard deviation was calculated based on the variation of each teacher’s body posture;

[0033] According to the standard deviation, an evaluation result of the richness of the teacher's segmented teaching posture within each preset time period is obtained;

[0034] Based on the evaluation results of the richness of the teaching postures in each segment, the evaluation results of the richness of the teacher's teaching postures are obtained.

[0035] In a third aspect, the present invention provides a device for detecting a change range of a human body posture, comprising:

[0036] An acquisition module, used to acquire the human skeleton key point information of the target person in the initial image frame and the human skeleton key point information of the target person in the image frame to be detected;

[0037] An extraction module is used to extract the corresponding human skeleton key points as the first human skeleton key points according to the human skeleton key point information of the initial image frame based on the preset human skeleton key points to be extracted, and to extract the corresponding human skeleton key points as the second human skeleton key points according to the human skeleton key point information of the image frame to be detected;

[0038] A calculation module, used for calculating the area of ​​the polygon surrounded by the first human body key points to obtain a first area, and calculating the area of ​​the polygon surrounded by the second human body key points to obtain a second area;

[0039] The comparison module is used to obtain the change range of the human body posture according to the change degree of the first area and the second area.

[0040] In a fourth aspect, the present invention provides a device for evaluating posture richness, characterized in that it includes:

[0041] A receiving module is used to obtain the video of the teacher's class and take screenshots of the video at preset time intervals;

[0042] A processing module, for calculating the magnitude of changes in the teacher's body posture between the initial image frame and each screenshot;

[0043] An evaluation module is used to obtain evaluation results of the richness of the teacher's teaching postures according to the variation of each teacher's body posture;

[0044] The processing module performs a process of calculating the change range of the teacher's body posture between the initial image frame and each screenshot, including:

[0045] Using the device for detecting the amplitude of changes in human body posture described above, the amplitude of changes in the teacher's human body posture between the initial image frame and each screenshot is calculated, wherein, in the process of using the method for detecting the amplitude of changes in human body posture, the teacher is used as the target object, and the screenshot of the teacher's static standing posture is used as the initial image frame.

[0046] In a fifth aspect, the present invention provides a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements any of the above-mentioned methods when executing the program.

[0047] In a sixth aspect, the present invention provides a computer-readable storage medium having a computer program stored thereon, characterized in that when the program is executed by a processor, the method of any of the above-mentioned embodiments is implemented.

[0048] In the present invention, by obtaining the preset key points of the human skeleton to be extracted, and connecting these key points of the human skeleton to form a polygon, the area change degree of the polygon is calculated, so as to obtain the change amplitude of the human posture; then, based on the posture of the teacher standing still, the posture is compared with the standing posture, the change amplitude of the posture is compared, and then the evaluation result of the richness of the teacher's teaching posture is obtained. The present invention is relatively simple, occupies less resources, and is relatively sensitive. It is suitable for the scene of the teacher teaching, and can timely reflect the change amplitude of the teacher's human posture and the richness of the teacher's human posture. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] Figure 1 It is a flowchart of an implementation method of Example 1 of the present invention.

[0050] Figure 2 It is an area schematic diagram of an implementation method of Example 1 of the present invention.

[0051] Figure 3 It is a flow chart of an implementation method of Example 21 of the present invention.

[0052] Figure 4 It is a schematic diagram of the overall structure of an implementation method of Example 41 of the present invention.

[0053] Figure 5 It is a schematic diagram of the overall structure of another implementation method of Example 4 of the present invention. DETAILED DESCRIPTION

[0054] The exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. Although the exemplary embodiments of the present disclosure are shown in the accompanying drawings, it should be understood that the present disclosure can be implemented in various forms and should not be limited by the embodiments set forth herein. On the contrary, these embodiments are provided to enable a more thorough understanding of the present disclosure and to fully convey the scope of the present disclosure to those skilled in the art.

[0055] It should be noted that the terms "first\second\..." involved in the embodiments of the present invention are only used to distinguish similar objects, and do not represent a specific order for the objects. It is understandable that the specific order or sequence of "first\second\..." can be interchanged where permitted. It should be understood that the objects distinguished by "first\second\..." can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein.

[0056] Embodiment 1

[0057] See also Figure 1 , Figure 1 1 is a flow chart of a method for detecting the amplitude of a human body posture change provided in Embodiment 1 of the present invention, the method comprising step S110, step S120, step S130, step S140 and step S150. It should be noted that step S110, step S120, step S130, step S140 and step S150 are merely reference numerals for the purpose of clearly explaining the embodiment and the appendix. Figure 1 The corresponding relationship does not limit the order of the steps in this embodiment.

[0058] Step S110, obtaining the human skeleton key point information of the target person in the initial image frame, and based on the preset human skeleton key points to be extracted, extracting the corresponding human skeleton key points as the first human skeleton key points according to the human skeleton key point information of the initial image frame;

[0059] Step S120, obtaining the human skeleton key point information of the target person in the image frame to be detected, and based on the preset human skeleton key points to be extracted, extracting the corresponding human skeleton key points as the second human skeleton key points according to the human skeleton key point information of the image frame to be detected;

[0060] Step S130, calculating the area of ​​the polygon enclosed by the first human body key points to obtain a first area;

[0061] Step S140, calculating the area of ​​the polygon enclosed by the second human body key points to obtain a second area;

[0062] Step S150, obtaining a change range of the human body posture according to the change degree of the first area and the second area.

[0063] This method is applicable to a device for analyzing teaching videos. First, two image frames to be compared are obtained, wherein the initial image frame is an image frame used as a benchmark, and the image frame to be detected is an image frame used to determine the amplitude of changes in human posture. This method does not limit the relationship between the two image frames. For example, the initial image frame can be an image frame about a benchmark action, such as an image frame of a standing action, or, relative to the image frame to be detected, an image frame before it used to compare with the image frame to be detected.

[0064] Two image frames to be compared are obtained, and the human skeleton key point information of the target person in the two image frames is detected by using the human skeleton key point detection technology.

[0065] Human skeleton key point detection is an important technology in the field of computer vision. It involves identifying and locating the main joints and parts of the human body. These key points usually include the following parts: head, torso, shoulder, upper arm, forearm, hand, thigh, calf and foot. The algorithms for human skeleton key point detection are mainly divided into two categories: top-down method and bottom-up method. The top-down method first determines the approximate position of the human body through the target detection algorithm, and then detects the key points of each human body; while the bottom-up method first detects all the key points in the image, and then assigns the key points to different individuals through strategies such as clustering. In terms of algorithm implementation, there are many different methods, including deep learning-based methods such as recurrent neural network (RNN), convolutional neural network (CNN), graph convolutional network (GCN), Transformer and hybrid network. In addition, there are methods based on manual features, which can be further subdivided into geometric descriptors, dynamic descriptors and statistical descriptors according to different feature descriptors.

[0066] In step S110 and step S120, the human skeleton key point information of the two image frames to be compared is obtained respectively, and the corresponding human skeleton key points are extracted based on the preset human skeleton key points to be extracted. For example, the preset human skeleton key points to be extracted are the top of the head, the fingertips of both hands, and the toes of both feet. Then, according to the human skeleton key point information of the initial image frame, these five human skeleton key points are extracted and used as the first human skeleton key points, and according to the human skeleton key point information of the image frame to be detected, these five human skeleton key points are extracted and used as the second human skeleton key points.

[0067] In step S130, all the first human body key points are connected to form a polygon, and the area of ​​the polygon is calculated to obtain the first area. Figure 2 As shown, Figure 2 This is the example of the preset key points of the human skeleton to be extracted as the top of the head, the fingertips of both hands and the toes of both feet. Figure 2 The five points are connected to obtain a pentagon, and then the area of ​​the pentagon is calculated and used as the first area. Similarly, step S140 uses the same processing method to obtain the second area.

[0068] The most common posture changes that teachers make during teaching are hand or leg posture changes. Figure 2 It can be seen that the change in the posture of the hand or leg will cause the area of ​​the pentagon to change, and the more obvious the posture change, the greater the change in area. Based on the above principle, the application compares the degree of change of the first area and the second area, and draws a conclusion on the change range of the human body posture by observing the degree of change. For example, subtract or divide the two area values, and obtain the degree of change of the area through the result of the subtraction or division, so as to further draw a conclusion on the change range of the human body posture.

[0069] It should be noted here that step S150 can draw a conclusion on the change range of the human body posture based on the degree of change of the first area and the second area. What is intended here is to use the first and second areas as two factors to judge the change range of the human body posture. In this application, there is no restriction on whether to add other factors on the basis of these two factors. Technical personnel in this field can add other factors according to actual conditions to achieve the best effect of the judgment conclusion.

[0070] In addition, the amplitude of the change may be the difference or ratio between two values, which is not limited by asymmetry in the present method.

[0071] In this method, the preset human skeleton key points to be extracted are obtained, and these human skeleton key points are connected to form a polygon, and the degree of area change of the polygon is calculated, so as to obtain the change range of human posture. This method is relatively simple, occupies less resources, and is relatively sensitive. It is suitable for the scene of teachers teaching, and can timely reflect the change range of teachers' human posture.

[0072] In one embodiment, the preset key points of the human skeleton to be extracted include: the top of the head, the fingertips of both hands, and the toes of both feet.

[0073] In one implementation, the method for detecting the amplitude of a human body posture change further includes: step S160.

[0074] Step S160, calculating the height of the target person according to the human skeleton key point information of the target person in the initial image frame and / or the human skeleton key point information of the target person in the image frame to be detected;

[0075] The process of step S150 includes: step S151.

[0076] Step S151, based on the height of the target person and according to the degree of change of the first area and the second area, the change range of the human body posture is obtained.

[0077] Everyone's height is different. In actual experience, even if a tall person has a small movement range, the area change range is relatively large. For this reason, the present application performs standardization processing by the individual's height, thereby obtaining a more reliable change range of the human body posture. For example, the first area of ​​the initial image frame is A0, the second area of ​​the image frame to be detected is Ai, and the height of the target person obtained in step S160 is H, and the standardized area change degree S'=(Ai-A0) / H is obtained.

[0078] It should be noted that the height of the target person in step S160 can be calculated based on the initial image frame only, or based on the image frame to be detected only, or can be obtained by sorting out the calculation results of the initial image frame and the image frame to be detected. In addition, the unit and ratio of the height of the target person here only need to be adapted to the calculation process of the first and second areas.

[0079] This is Figure 2 The key points of the human skeleton are extracted in the example. The pentagon formed by these points can better reflect the range of changes in the teacher's movements.

[0080] In one implementation, the process of step S151 includes: step S210, step S220, and step S230.

[0081] Step S210, obtaining a first area per unit height according to the height of the target person and the first area;

[0082] Step S220, obtaining a second area per unit height according to the height of the target person and the second area;

[0083] Step S230, obtaining a change range of the human body posture according to the first area per unit height and the degree of change of the first area per unit height.

[0084] As mentioned above, the height of an individual is standardized to obtain a more reliable range of change in human posture. The present embodiment calculates the first area and the second area per unit height, respectively. For example, in the previous example, let Ai'=Ai / H, let A0'=A0 / H, and then compare Ai' and A0' to obtain the degree of change.

[0085] Embodiment 2

[0086] See also Figure 3 , Figure 3 1 is a flow chart of a method for evaluating the richness of posture provided in the second embodiment of the present invention, the method comprising step S310, step S320 and step S330. It should be noted that step S310, step S320 and step S330 are only reference numerals for clarifying the embodiment and the appendix. Figure 3 The corresponding relationship does not limit the order of the steps in this embodiment.

[0087] Step S310, obtaining a video of the teacher's class, and taking screenshots of the video at preset time intervals;

[0088] Step S320, calculating the change range of the teacher's body posture between the initial image frame and each screenshot;

[0089] Step S330, obtaining an evaluation result of the richness of the teacher's teaching posture according to the change range of each teacher's body posture;

[0090] The process of step S320 includes: step S321.

[0091] Step S321, using the method for detecting the amplitude of changes in human body posture described in Example 1, calculate the amplitude of changes in the teacher's human body posture between the initial image frame and each screenshot, wherein, in the process of using the method for detecting the amplitude of changes in human body posture, the teacher is used as the target object, and the screenshot of the teacher's static standing posture is used as the initial image frame.

[0092] The method for evaluating the richness of posture in this embodiment is based on the posture of the teacher standing still, comparing it with the standing posture, comparing the change range of the posture, and then obtaining the evaluation result of the richness of the teacher's teaching posture. Then, the area of ​​the teacher's standing still posture is recorded as the reference area, and then the pentagonal area of ​​each screenshot is calculated and compared with the reference area to obtain a series of differences, and the richness of the teacher's teaching posture is judged by these differences. This method is relatively simple, occupies fewer resources, and is relatively sensitive. It is suitable for the scene of the teacher teaching, and can timely reflect the richness of the teacher's human body posture.

[0093] In one embodiment, the variation range of the teacher's body posture is the difference between the first area and the second area;

[0094] The process of step S330 includes: step S331 and step S332.

[0095] Step S331, calculating the standard deviation according to the variation of each teacher's body posture;

[0096] Step S332, obtaining an evaluation result of the richness of the teacher's teaching posture according to the standard deviation.

[0097] If the teacher has rich movements and uses a variety of body languages, the standard deviation will be larger. If the standard deviation is within the preset standard deviation threshold, it can be considered that the teacher's teaching posture is relatively rich.

[0098] In one embodiment, the variation range of the teacher's body posture is the difference between the first area and the second area;

[0099] The process of step S330 includes: step S333, step S334, and step S335.

[0100] Step S333, calculating the standard deviation according to the variation of each teacher's body posture;

[0101] Step S334, obtaining an evaluation result of the richness of the teacher's segmented teaching postures within each preset time period according to the standard deviation;

[0102] Step S335, obtaining the evaluation result of the richness of the teacher's teaching posture according to the evaluation result of the richness of the teaching posture of each segment.

[0103] This implementation is similar to the previous implementation in terms of the basic idea, but based on the fact that teaching is a dynamic process, the results obtained by analyzing each period of time will be more accurate. Therefore, in this implementation, the video is divided into several segments of preset duration (such as 10 seconds, half a minute, one minute, etc.), and each video is analyzed. The evaluation results of the richness of the teacher's teaching posture in each video are analyzed, and then the overall evaluation results of the richness of the teacher's teaching posture are summarized.

[0104] Embodiment 3

[0105] Corresponding to the method of embodiment 1, as Figure 4 As shown, the present invention also provides a device for detecting the amplitude of changes in human body posture, including: an acquisition module 410, an extraction module 420, a calculation module 430 and a comparison module 440.

[0106] An acquisition module 410 is used to acquire the human skeleton key point information of the target person in the initial image frame and the human skeleton key point information of the target person in the image frame to be detected;

[0107] An extraction module 420 is used to extract the corresponding human skeleton key points as first human skeleton key points based on the preset human skeleton key points to be extracted according to the human skeleton key point information of the initial image frame, and to extract the corresponding human skeleton key points as second human skeleton key points according to the human skeleton key point information of the image frame to be detected;

[0108] A calculation module 430, configured to calculate the area of ​​the polygon enclosed by the first human body key points to obtain a first area, and calculate the area of ​​the polygon enclosed by the second human body key points to obtain a second area;

[0109] The comparison module 440 is used to obtain a change range of the human body posture according to the change degree of the first area and the second area.

[0110] In one embodiment, the preset key points of the human skeleton to be extracted include: the top of the head, the fingertips of both hands, and the toes of both feet.

[0111] In one embodiment, the extraction module is further used to calculate the height of the target person based on the human skeleton key point information of the target person in the initial image frame and / or the human skeleton key point information of the target person in the image frame to be detected;

[0112] The comparison module performs the process of obtaining the change range of the human body posture according to the change degree of the first area and the second area, including:

[0113] Based on the height of the target person and according to the degree of change of the first area and the second area, the change range of the human body posture is obtained.

[0114] In one embodiment, the preset key points of the human skeleton to be extracted include: the top of the head, the fingertips of both hands, and the toes of both feet;

[0115] The comparison module performs the process of obtaining the change range of the human body posture based on the height of the target person and the change degree of the first area and the second area, including:

[0116] According to the height of the target person and the first area, a first area per unit height is obtained;

[0117] According to the height of the target person and the second area, the second area per unit height is obtained;

[0118] The variation range of the human body posture is obtained according to the variation degree of the first area per unit height and the first area per unit height.

[0119] Corresponding to the method of the second embodiment, as Figure 5 As shown, the present invention also provides a device for evaluating posture richness, including: a receiving module 510, a processing module 520 and an evaluating module 530.

[0120] The receiving module 510 is used to obtain the video of the teacher's class and take screenshots of the video at a preset time interval;

[0121] Processing module 520, for calculating the change range of the teacher's body posture between the initial image frame and each screenshot;

[0122] Evaluation module 530, used to obtain evaluation results of the richness of the teacher's teaching posture according to the change range of each teacher's body posture;

[0123] The processing module performs a process of calculating the change range of the teacher's human body posture between the initial image frame and each screenshot, including:

[0124] Using the device for detecting the amplitude of changes in human body posture described in the aforementioned embodiment, the amplitude of changes in the teacher's human body posture between the initial image frame and each screenshot is calculated, wherein, in the process of using the method for detecting the amplitude of changes in human body posture, the teacher is used as the target object, and the screenshot of the teacher's static standing posture is used as the initial image frame.

[0125] In one embodiment, the variation range of the teacher's body posture is the difference between the first area and the second area;

[0126] The evaluation module executes the process of obtaining the evaluation result of the richness of the teacher's teaching posture according to the change range of each teacher's human body posture, including:

[0127] The standard deviation was calculated based on the variation of each teacher’s body posture;

[0128] The evaluation result of the richness of the teacher's teaching posture is obtained based on the standard deviation.

[0129] In one embodiment, the variation range of the teacher's body posture is the difference between the first area and the second area;

[0130] The evaluation module executes the process of obtaining the evaluation result of the richness of the teacher's teaching posture according to the change range of each teacher's human body posture, including:

[0131] The standard deviation was calculated based on the variation of each teacher’s body posture;

[0132] According to the standard deviation, an evaluation result of the richness of the teacher's segmented teaching posture within each preset time period is obtained;

[0133] Based on the evaluation results of the richness of the teaching postures in each segment, the evaluation results of the richness of the teacher's teaching postures are obtained.

[0134] In this device, the teacher's static standing posture is compared with the standing posture, the change range of the posture is compared, and then the evaluation result of the richness of the teacher's teaching posture is obtained. This device is relatively simple, occupies less resources, and is relatively sensitive. It is suitable for the scene of teachers teaching, and can timely reflect the richness of the teacher's human body posture.

[0135] Embodiment 4

[0136] An embodiment of the present invention further provides a storage medium on which computer instructions are stored. When the instructions are executed by a processor, the method for detecting the amplitude of changes in human body posture and / or the method for evaluating posture richness of any of the above embodiments is implemented.

[0137] Those skilled in the art can understand that: all or part of the steps of implementing the above method embodiments can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above method embodiments; and the aforementioned storage medium includes: mobile storage devices, random access memories (RAM), read-only memories (ROM), magnetic disks or optical disks, etc., various media that can store program codes.

[0138] Alternatively, if the above-mentioned integrated unit of the present invention is implemented in the form of a software function module and sold or used as an independent product, it can also be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the embodiment of the present invention can be essentially or partly reflected in the form of a software product that contributes to the relevant technology. The computer software product is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, terminal, or network device, etc.) to execute all or part of the methods of each embodiment of the present invention. The aforementioned storage medium includes: various media that can store program codes, such as mobile storage devices, RAM, ROM, magnetic disks or optical disks.

[0139] Corresponding to the above-mentioned computer storage medium, in one embodiment, a computer device is also provided, which includes a memory, an encoder, and a computer program stored in the memory and runnable on the encoder, wherein when the encoder executes the program, it implements any one of the methods for detecting the amplitude of human body posture change and / or the method for posture richness evaluation in the above-mentioned embodiments.

[0140] The above computer device obtains the preset key points of the human skeleton to be extracted, connects these key points of the human skeleton to form a polygon, calculates the degree of change of the area of ​​the polygon, and thus obtains the change range of the human posture; then, based on the teacher's static standing posture, it compares the standing posture, compares the change range of the posture, and then obtains the evaluation result of the richness of the teacher's teaching posture. The above computer device is relatively simple, occupies less resources, and is relatively sensitive. It is suitable for the scene of the teacher teaching, and can timely reflect the change range of the teacher's human posture and the richness of the teacher's human posture.

[0141] The technical features of the above-described embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above-described embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

[0142] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the embodiments of the present invention. For those skilled in the art, other different forms of changes or modifications can be made based on the above description. It is not necessary and impossible to list all the embodiments here. Any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the protection scope of the claims of the present invention.

Claims

1. A method for detecting the amplitude of a human body posture change, characterized in that: include: Acquire the human skeleton key point information of the target person in the initial image frame, and based on the preset human skeleton key points to be extracted, extract the corresponding human skeleton key points as the first human skeleton key points according to the human skeleton key point information of the initial image frame; Acquire the human skeleton key point information of the target person in the image frame to be detected, and based on the preset human skeleton key points to be extracted, extract the corresponding human skeleton key points as the second human skeleton key points according to the human skeleton key point information of the image frame to be detected; Calculate the area of ​​the polygon enclosed by the first human body key points to obtain a first area; Calculate the area of ​​the polygon enclosed by the second human body key points to obtain a second area; The change amplitude of the human body posture is obtained according to the change degrees of the first area and the second area.

2. The method for detecting the variation of human posture according to claim 1, characterized in that: The preset key points of the human skeleton to be extracted include: the top of the head, the fingertips of both hands, and the toes of both feet.

3. The method for detecting the variation of human posture according to claim 1 or 2, characterized in that: Also includes: Calculate the height of the target person according to the human skeleton key point information of the target person in the initial image frame and / or the human skeleton key point information of the target person in the image frame to be detected; The process of obtaining the change amplitude of the human body posture according to the change degrees of the first area and the second area includes: Based on the height of the target person and according to the degree of change of the first area and the second area, the change range of the human body posture is obtained.

4. The method for detecting the variation range of human posture according to claim 3, characterized in that: The process of obtaining the change range of the human body posture based on the height of the target person and the change degree of the first area and the second area includes: According to the height of the target person and the first area, a first area per unit height is obtained; According to the height of the target person and the second area, the second area per unit height is obtained; The variation range of the human body posture is obtained according to the variation degree of the first area per unit height and the first area per unit height.

5. A method for evaluating posture richness, characterized in that: include: Obtain the video of the teacher's class and take screenshots of the video at preset time intervals; Calculate the change in the teacher's body posture between the initial image frame and each screenshot; According to the variation of each teacher's body posture, the evaluation results of the richness of the teacher's teaching posture are obtained; The process of calculating the change range of the teacher's human body posture between the initial image frame and each screenshot includes: Use the method for detecting the amplitude of changes in human body posture as described in any one of claims 1 to 4 to calculate the amplitude of changes in the teacher's human body posture between the initial image frame and each screenshot, wherein, in the process of using the method for detecting the amplitude of changes in human body posture, the teacher is used as the target object, and the screenshot of the teacher's static standing posture is used as the initial image frame.

6. The method for posture richness assessment according to claim 5, characterized in that: The variation range of the teacher's body posture is the difference between the first area and the second area; The process of obtaining the evaluation result of the richness of the teacher's teaching posture according to the variation range of each teacher's body posture includes: The standard deviation was calculated based on the variation of each teacher’s body posture; The evaluation result of the richness of the teacher's teaching posture is obtained based on the standard deviation.

7. The method for posture richness assessment according to claim 5, characterized in that: The variation range of the teacher's body posture is the difference between the first area and the second area; The process of obtaining the evaluation result of the richness of the teacher's teaching posture according to the variation range of each teacher's body posture includes: The standard deviation was calculated based on the variation of each teacher’s body posture; According to the standard deviation, an evaluation result of the richness of the teacher's segmented teaching posture within each preset time period is obtained; Based on the evaluation results of the richness of the teaching postures in each segment, the evaluation results of the richness of the teacher's teaching postures are obtained.

8. A device for detecting the amplitude of changes in human body posture, characterized in that: include: An acquisition module, used to acquire the human skeleton key point information of the target person in the initial image frame and the human skeleton key point information of the target person in the image frame to be detected; An extraction module is used to extract the corresponding human skeleton key points as the first human skeleton key points according to the human skeleton key point information of the initial image frame based on the preset human skeleton key points to be extracted, and to extract the corresponding human skeleton key points as the second human skeleton key points according to the human skeleton key point information of the image frame to be detected; A calculation module, used for calculating the area of ​​the polygon surrounded by the first human body key points to obtain a first area, and calculating the area of ​​the polygon surrounded by the second human body key points to obtain a second area; The comparison module is used to obtain the change range of the human body posture according to the change degree of the first area and the second area.

9. A device for evaluating posture richness, characterized in that: include: A receiving module is used to obtain the video of the teacher's class and take screenshots of the video at preset time intervals; A processing module, for calculating the magnitude of changes in the teacher's body posture between the initial image frame and each screenshot; An evaluation module is used to obtain evaluation results of the richness of the teacher's teaching postures according to the variation of each teacher's body posture; The processing module performs a process of calculating the change range of the teacher's body posture between the initial image frame and each screenshot, including: Use the device for detecting the amplitude of changes in human body posture as described in claim 8 to calculate the amplitude of changes in the teacher's human body posture between the initial image frame and each screenshot, wherein, in the process of using the method for detecting the amplitude of changes in human body posture, the teacher is used as the target object, and the screenshot of the teacher's static standing posture is used as the initial image frame.

10. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the program, the method according to any one of claims 1 to 7 is implemented.

11. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the program is executed by a processor, the method according to any one of claims 1 to 7 is implemented.

Images