Physical education method, device and equipment based on depth-of-field camera, storage medium and product

Abstract

The invention relates to the technical field of artificial intelligence, in particular to a physical education method and device based on a depth-of-field camera, equipment, a storage medium and a product. The method comprises the steps of obtaining motion image data of a student based on a depth-of-field camera; identifying the motion image data to obtain a motion posture of the student; constructing a 3D motion model based on the motion posture; comparing the 3D motion model with a preset standard motion posture; based on the comparison result, a physical education instruction scheme is generated, and the physical education teaching effect is improved.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a sports teaching method, device, equipment, storage medium and product based on a depth of field camera. Background Art

[0002] As the country continues to pay attention to the quality of education, the all-round development of students has become an important goal in the education system. In modern education, physical education is not only an important way to improve students' physical fitness, but also an important means to promote students' mental health, teamwork ability and personal quality. However, the traditional physical education teaching model faces many challenges, especially when facing individual differences among students, it is difficult for teachers to provide refined and personalized guidance for each student. Physical education usually involves multiple students participating at the same time, and it is difficult for teachers to accurately monitor the movement posture and movement quality of each student in real time, which makes it difficult for students' movement deviations to be discovered and corrected in time, affecting the overall effect of physical education. Therefore, how to improve the teaching effect of physical education has become a technical problem that needs to be solved urgently. Summary of the invention

[0003] The main purpose of this application is to provide a physical education teaching method, device, equipment, storage medium and product based on a depth of field camera, aiming to solve the technical problem of how to improve the teaching effect of physical education classes.

[0004] To achieve the above objectives, the present application provides a physical education teaching method based on a depth of field camera, the method comprising:

[0005] Acquire students' motion image data based on depth-of-field camera;

[0006] Recognizing the motion image data to obtain the student's motion posture;

[0007] Based on the motion posture, construct a 3D motion model;

[0008] Comparing the 3D motion model with a preset standard motion posture;

[0009] Based on the comparison results, a physical education teaching guidance plan is generated.

[0010] In one embodiment, after the step of generating a physical education teaching guidance program based on the comparison result, the following step is further included:

[0011] The motion image data of all students were summarized;

[0012] Generate an overall learning report based on the summary results;

[0013] Determine the mainstream exercise type based on the overall learning report and a preset ratio threshold;

[0014] A mainstream guidance plan is generated according to the mainstream motion type.

[0015] In one embodiment, the step of acquiring the student's motion image data based on the depth of field camera includes:

[0016] When the depth-of-field camera enters the working state, it is determined whether a student enters the camera range and starts to move;

[0017] If yes, control the depth-of-field camera to obtain the two-dimensional image data and spatial depth data of the student;

[0018] The motion image data is determined based on the two-dimensional image data and the spatial depth data.

[0019] In one embodiment, the step of identifying the motion image data to obtain the student's motion posture includes:

[0020] Performing denoising and image enhancement processing on the two-dimensional image data to obtain enhanced image data;

[0021] Performing correction processing on the spatial depth data to obtain corrected spatial data;

[0022] Based on a preset deep learning model, the enhanced image data and the corrected space data are identified to determine the student's movement posture.

[0023] In one embodiment, the step of constructing a 3D motion model based on the motion posture comprises:

[0024] Based on a preset posture recognition algorithm, extracting key points of the human body from the motion posture to obtain a plurality of key points of the human body;

[0025] Connect each key point of the human body to obtain a three-dimensional skeleton model;

[0026] Based on a preset smoothing algorithm, the three-dimensional skeleton model is optimized to obtain the 3D motion model.

[0027] In one embodiment, the step of comparing the 3D motion model with a preset standard motion posture comprises:

[0028] Determine the type of motion according to the 3D motion model;

[0029] According to the exercise type, determining a corresponding preset standard action posture;

[0030] The 3D motion model is matched and compared with the three-dimensional skeleton model of the preset standard action posture at key points.

[0031] In addition, to achieve the above purpose, the present application also proposes a physical education teaching device based on a depth of field camera, and the physical education teaching device based on a depth of field camera includes:

[0032] A data acquisition module, used for acquiring students' motion image data based on a depth-of-field camera;

[0033] A recognition module, used to recognize the motion image data to obtain the student's motion posture;

[0034] A model building module, used for building a 3D motion model based on the motion posture;

[0035] A comparison module, used for comparing the 3D motion model with a preset standard motion posture;

[0036] The target module is used to generate sports teaching guidance plans based on the comparison results.

[0037] In addition, to achieve the above-mentioned purpose, the present application also proposes a physical education teaching device based on a depth of field camera, the device comprising: a memory, a processor, and a physical education teaching program based on a depth of field camera stored on the memory and executable on the processor, the physical education teaching program based on the depth of field camera being configured to implement the steps of the physical education teaching method based on the depth of field camera as described above.

[0038] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, on which a physical education teaching program based on a depth of field camera is stored. When the physical education teaching program based on the depth of field camera is executed by a processor, the steps of the physical education teaching method based on the depth of field camera as described above are implemented.

[0039] In addition, to achieve the above-mentioned purpose, the present application also proposes a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the physical education teaching method based on a depth of field camera as described above.

[0040] This application obtains students' motion image data based on a depth of field camera; identifies the motion image data to obtain students' motion postures; constructs a 3D motion model based on the motion postures; compares the 3D motion model with preset standard action postures; and generates a physical education teaching guidance plan based on the comparison results. This application obtains students' motion image data through a depth of field camera, and identifies it, accurately captures students' motion postures, and ensures that the acquired motion information is highly accurate and real-time; then constructs a 3D motion model based on the motion posture, which can present students' actual motion status in three dimensions and fully reflect students' motion details; compares the generated 3D motion model with preset standard action postures, which can accurately analyze the differences between students' movements and standard movements, and identify deviations or errors in movements; finally, generates a personalized physical education teaching guidance plan based on the comparison results, provides specific improvement suggestions for students' movement problems, and can provide teachers with more targeted teaching assistance, so that students can correct movement deviations in a timely manner, thereby improving the effectiveness of physical education teaching. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 This is a flow chart of the first embodiment of the physical education teaching method based on a depth of field camera of the present application;

[0042] Figure 2 This is a schematic diagram of a sub-process in the second embodiment of the physical education teaching method based on a depth of field camera of this application;

[0043] Figure 3 This is a schematic diagram of a sub-process in the third embodiment of the physical education teaching method based on a depth of field camera of this application;

[0044] Figure 4 This is a schematic diagram of the module structure of a physical education teaching device based on a depth of field camera according to an embodiment of the present application;

[0045] Figure 5 This is a schematic diagram of the device structure of the hardware operating environment involved in the physical education teaching method based on a depth of field camera in an embodiment of the present application.

[0046] The realization of the purpose, functional features and advantages of this application will be further explained in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0047] It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0048] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0049] It should be noted that as the country continues to pay attention to the quality of education, the all-round development of students has become an important goal in the education system. In modern education, physical education is not only an important way to improve students' physical fitness, but also an important means to promote students' mental health, teamwork ability and personal quality. However, the traditional physical education teaching model faces many challenges, especially when facing individual differences among students, it is difficult for teachers to provide refined and personalized guidance for each student. Physical education usually involves multiple students participating at the same time, and it is difficult for teachers to accurately monitor the movement posture and movement quality of each student in real time, which makes it difficult for students' movement deviations to be discovered and corrected in time, affecting the overall effect of physical education. Therefore, how to improve the teaching effect of physical education has become a technical problem that needs to be solved urgently.

[0050] The main solution of this application is: to obtain students' motion image data based on a depth of field camera; to identify the motion image data to obtain students' motion postures; to construct a 3D motion model based on the motion postures; to compare the 3D motion model with preset standard motion postures; and to generate a physical education teaching guidance plan based on the comparison results.

[0051] This application obtains students' motion image data through a depth-of-field camera, identifies it, and accurately captures students' motion postures, ensuring that the acquired motion information is of high precision and real-time; then, a 3D motion model is constructed based on the motion posture, which can present the students' actual motion state in three dimensions and fully reflect the students' motion details; the generated 3D motion model is compared with the preset standard motion posture, which can accurately analyze the difference between the students' movements and the standard movements, and identify deviations or errors in the movements; finally, a personalized physical education teaching guidance plan is generated based on the comparison results, and specific improvement suggestions are provided for students' movement problems, which can provide teachers with more targeted teaching assistance, enable students to correct movement deviations in a timely manner, and improve the effectiveness of physical education teaching.

[0052] It should be noted that the execution subject of the method of this embodiment can be a computing service device with data processing, network communication and program running functions, or it can be the above-mentioned sports teaching equipment based on depth of field camera with the same or similar functions. This embodiment and the following embodiments will be described by taking the sports teaching equipment based on depth of field camera as an example.

[0053] Based on this, the first embodiment of the physical education teaching method based on the depth of field camera of this application is proposed, please refer to Figure 1 , Figure 1 This is a flow chart of the first embodiment of the physical education teaching method based on a depth of field camera of the present application.

[0054] In this embodiment, the method includes the following steps:

[0055] S1: Acquire students’ motion image data based on the depth-of-field camera;

[0056] It should be noted that the depth of field camera is a special camera device that can not only capture traditional two-dimensional images, but also capture the depth information of each pixel, that is, the distance from the object to the camera. Through this depth data, the depth of field camera can accurately perceive the position and shape of objects in three-dimensional space. This makes it very suitable for application scenarios that need to capture precise movements and postures, such as physical education, motion analysis, etc. Motion image data refers to a sequence of images containing dynamic information captured by a camera. Especially in physical education, these image data represent the postures and movements of various parts of the body of students during exercise. These data usually include two-dimensional images and depth information provided by the depth of field camera.

[0057] Specifically, a depth-of-field camera is installed in the sports venue to cover the students' sports area. When a student enters the camera's monitoring range and starts sports activities, the camera automatically starts collecting motion image data. Multiple images are taken per second to ensure that continuous motion details are captured. The depth-of-field camera can not only collect traditional two-dimensional image data, but also simultaneously obtain the depth information of each pixel point to record the student's position and motion trajectory in three-dimensional space. The captured image data includes multi-dimensional information such as the student's motion posture, speed, direction, etc. in the venue.

[0058] Furthermore, the collected image data is transmitted to the terminal server in real time through the network for processing. The motion image data received by the server undergoes preliminary processing, such as denoising and distortion correction, to ensure the accuracy and clarity of the data. At the same time, the system will identify the position and outline of the students based on the image and depth data, thus providing a basis for subsequent posture analysis and three-dimensional modeling. Through this step, the system can comprehensively record the students' movement details, laying a solid foundation for further movement analysis and teaching guidance.

[0059] By using a depth-of-field camera to obtain students' motion image data, the system can accurately record students' motion status in three-dimensional space, capturing not only the two-dimensional surface information of the action, but also the depth data, which makes the analysis of students' movements more comprehensive and three-dimensional. Compared with traditional cameras that can only record flat images, depth-of-field cameras can accurately restore students' motion postures by obtaining depth information, making subsequent posture analysis more accurate. In addition, the data collected and transmitted in real time can provide instant feedback during the teaching process, providing teachers and students with high-precision movement guidance, ensuring that students can correct wrong movements in a timely manner during the learning process, and improving the efficiency and accuracy of physical education teaching.

[0060] S2: Recognize the motion image data to obtain the student's motion posture;

[0061] It should be noted that sports posture refers to the physical state of students at a certain moment during physical activities, usually represented by multiple key points (such as the coordinates of the head, shoulders, knees, elbows, etc.), through which the student's body posture and movement changes can be determined.

[0062] Specifically, the acquired motion image data is processed through the AI ​​posture recognition algorithm. The image data is input into the posture recognition module, and firstly performs pre-processing operations such as denoising and background removal to extract the motion contour of the student. Subsequently, the system uses a deep learning model to identify the key points of the student's body, such as the head, shoulders, elbows, knees, ankles, etc. The recognition of this key point usually relies on a pre-trained neural network model, which can learn how to identify different limb parts from a large amount of motion posture data.

[0063] Furthermore, by combining the relative position and depth data of these key points, the student's two-dimensional and three-dimensional motion postures are constructed. Each key point is assigned a corresponding spatial coordinate, and the system uses these coordinates to determine the student's limb movement. For example, the relative position of the shoulder and elbow can be used to determine the extension state of the arm, while the relationship between the knee and ankle can be used to determine the degree of bending of the leg. The whole process is carried out in real time, ensuring that the system can dynamically capture the student's posture changes during exercise.

[0064] By using AI recognition technology to process motion image data, the system can accurately capture students' movement postures and identify the status of various parts of the limbs. This not only enables teachers to fully understand students' posture performance during exercise, but also provides high-precision data support for subsequent motion analysis and feedback. Compared with traditional manual observation or two-dimensional camera capture, this posture recognition based on deep learning can greatly improve the accuracy and efficiency of recognition, especially in complex movements, the system can identify subtle differences in limbs. In addition, the recognition process can be carried out in real time, ensuring immediate feedback in teaching, allowing students to correct their movements in time during exercise, improving the effectiveness of teaching and the quality of personalized guidance.

[0065] S3: constructing a 3D motion model based on the motion posture;

[0066] It should be noted that the 3D motion model is a three-dimensional structure constructed using the three-dimensional spatial coordinate information extracted from the motion posture, which reflects the posture and movement trajectory of the students during the motion process. Through these models, the precise details of the motion can be analyzed and the teaching feedback can be further optimized.

[0067] Specifically, the three-dimensional coordinate information of each key point of the student's body is obtained from the motion posture data extracted in the previous step. These key points represent the positions of the student's limbs, such as the head, shoulders, elbows, knees, etc., which together constitute the student's posture in space. Each key point is given an accurate three-dimensional coordinate, including X, Y (plane coordinates) and Z (depth coordinates), through the depth information captured by the depth-of-field camera, which provides basic data for subsequent three-dimensional modeling.

[0068] Furthermore, by connecting these three-dimensional coordinate points, a three-dimensional skeleton model of the student is generated. This skeleton model is not only a representation of the student's static posture, but can also dynamically reflect the changes in the student's limbs during exercise. The system constructs a complete motion trajectory through continuous posture data, which records every detail of the student's movement, such as the curvature of the legs and the swing amplitude of the arms. Through such three-dimensional modeling, the system can fully present the student's movement status in three-dimensional space, providing more accurate and comprehensive movement information than two-dimensional images.

[0069] By constructing a 3D motion model, the system can more accurately capture the student's movement details and posture changes. Compared with traditional two-dimensional images or data based only on plane coordinates, the three-dimensional motion model can more comprehensively reflect the student's actual movement trajectory. The three-dimensional model can accurately display the student's positional relationship in space, such as the bending angle of the limbs, the relative position of the upper and lower limbs, etc., helping the system and teachers to better analyze the standardization and continuity of the movement. In addition, this 3D model-based analysis can be used to identify subtle errors in movement and provide targeted improvement suggestions, thereby greatly improving the accuracy and effectiveness of physical education teaching, allowing students to receive personalized feedback and guidance during exercise.

[0070] S4: comparing the 3D motion model with a preset standard motion posture;

[0071] It should be noted that the 3D motion model refers to a three-dimensional model constructed based on the student's motion posture, which reflects the position, posture and motion trajectory of each key point of the student's body during the exercise. The preset standard action posture refers to the standard motion posture model used as a reference and comparison in physical education. This model is usually provided by a professional coach or an authoritative sports manual, which defines the correct motion posture and its key point coordinates. By comparing the position and angle of the student's 3D motion model with the key points of the standard action posture, the deviation of the student's movement can be analyzed and the errors or non-standard parts in the movement can be identified.

[0072] Specifically, the student's 3D motion model is matched with a preset standard action posture model. The system calls the corresponding standard posture model from the standard posture library according to different sports. The model contains a set of correct key point positions and angles, representing the standard motion posture. The system compares the student's 3D motion model with each key point of the standard model one by one. The key points include the head, shoulders, elbows, knees, ankles and other major parts of the body. By calculating the coordinate difference of each key point in three-dimensional space, the system can determine the deviation between the student's action and the standard action.

[0073] Furthermore, the position deviation of each key point is analyzed, and the angle changes between each limb, such as the degree of bending of the elbow and knee joints, are calculated to further determine whether the student's posture meets the standard. For example, the system can judge whether the arm is extended in place by the angle between the elbow and the shoulder, or judge whether the squat depth meets the requirements by the angle between the knee and the ankle joint. Based on these comparison results, the system can identify the specific movement deviations of the students and record these deviations for subsequent feedback and adjustment.

[0074] By comparing the 3D motion model with the preset standard movement posture, the system can accurately analyze the student's movement deviation and help teachers and students quickly identify deficiencies in the movement. This three-dimensional comparison method can provide more comprehensive and accurate feedback than two-dimensional plane comparison, especially in complex movement postures such as bending, rotation and stretching. The system can identify whether each of the student's limb movements is in place and provide more detailed feedback by analyzing the angle changes between the limbs. This comparison can not only improve the accuracy of teaching, but also help students achieve standard postures by gradually adjusting their movements, thereby improving sports skills and promoting the personalization of physical education and maximizing the effect.

[0075] S5: Generate a physical education teaching guidance plan based on the comparison results.

[0076] It should be noted that the comparison results refer to the analysis data obtained by comparing the student's 3D motion model with the preset standard action posture. These data include the student's movement deviation, key point position error, joint angle difference, etc., which are used to evaluate the gap between the student's actual sports performance and the standard movement. The sports teaching guidance plan refers to the personalized feedback and guidance suggestions generated based on the comparison results to help students correct movement errors and improve sports performance. The plan usually includes targeted improvement measures and training plans to improve students' sports skills.

[0077] Specifically, after the comparison results are generated, the system will analyze the errors of each key point and the student's overall athletic performance to generate a detailed physical education teaching guidance plan. First, the system will determine the student's specific movement problems based on the position differences and angle deviations of each key point. For example, if the student's arms are not raised to the height required by the standard movement, the system will point out the deviation of the movement and its specific direction of improvement. Similarly, if the student's knees are not bent enough when squatting, the system will also give relevant correction suggestions.

[0078] Furthermore, a personalized physical education guidance plan is generated based on these analysis data, which includes specific improvement suggestions, training points and goals. For example, the system may suggest that students focus on raising their arms or bending their knees in subsequent exercises, and provide step-by-step improvement measures. In addition, the system may also recommend students to perform additional training movements to help strengthen specific muscle groups or improve the flexibility of movements. The plan can be pushed to students and teachers in digital form to ensure that students can make adjustments based on these feedbacks in their daily training, and teachers can also use this information to optimize the teaching process and provide more targeted guidance.

[0079] By generating personalized sports teaching guidance plans based on the comparison results, the system can effectively help students optimize their individual movement deviations and thus improve their sports performance. Unlike traditional unified teaching methods, this data-driven personalized guidance ensures that each student can get feedback and training plans that meet their needs, truly realizing teaching students in accordance with their aptitude. Students can adjust their movements based on the detailed suggestions in the plan, and teachers can also understand the progress and shortcomings of each student through the analysis results of the plan, and further optimize the teaching content. Ultimately, this intelligent teaching guidance plan can greatly improve the accuracy and effectiveness of physical education, helping students master standard movements faster and more effectively, and improve their sports skills.

[0080] This embodiment obtains the student's motion image data based on a depth of field camera; identifies the motion image data to obtain the student's motion posture; constructs a 3D motion model based on the motion posture; compares the 3D motion model with the preset standard action posture; and generates a physical education teaching guidance plan based on the comparison results. This embodiment obtains the student's motion image data through a depth of field camera, and identifies it, accurately captures the student's motion posture, and ensures that the acquired motion information has high precision and real-time performance; then constructs a 3D motion model based on the motion posture, which can present the student's actual motion state in three dimensions and fully reflect the student's motion details; compares the generated 3D motion model with the preset standard action posture, which can accurately analyze the difference between the student's motion and the standard motion, and identify the deviation or error in the motion; finally, generates a personalized physical education teaching guidance plan based on the comparison results, provides specific improvement suggestions for the student's motion problems, and can provide teachers with more targeted teaching assistance, so that students can correct their motion deviations in time, thereby improving the effect of physical education teaching.

[0081] Based on the above-mentioned first embodiment, a second embodiment of the physical education teaching method based on a depth of field camera of the present application is proposed.

[0082] In this embodiment, after step S5, the method further includes:

[0083] S5a: Summarize the motion image data of all students;

[0084] S5b: Generate an overall learning report based on the summary results;

[0085] S5c: determining the mainstream exercise type based on the overall learning report and a preset ratio threshold;

[0086] S5d: Generate a mainstream guidance plan according to the mainstream motion type.

[0087] It should be noted that aggregation refers to integrating and counting the motion image data of multiple students to extract the overall motion performance and characteristic data of the group. The overall learning report refers to a report generated after analyzing the motion image data of all students, reflecting the overall motion level, common problems and performance trends of the class or group. The preset ratio threshold refers to the standard value used to determine the mainstream degree of a certain type of motion in a group. The system determines whether a certain type of motion is representative in the student group based on the threshold. Mainstream motion type refers to the most common or most in need of focused guidance in the student group based on the results of data analysis. The mainstream guidance plan is a teaching guidance plan generated based on the mainstream motion type, which is used to provide unified guidance suggestions and training plans for common motion problems or common motion types in the group.

[0088] Specifically, the motion image data of all students are summarized. The summary process includes statistics on each student's motion posture, action performance, key point error, and angle deviation. The system will process this data and extract the overall motion performance and common problems of the class or group. Through data summary, the system can fully understand the overall motion level of students in the class, discover common problems, and the types of motion that are prevalent in the group.

[0089] Furthermore, based on the aggregated data results, the system generates an overall learning report. The report lists in detail the average performance of the group, the success and error rates of various types of sports movements, common posture deviations and problems in limb movements. The system also classifies and screens the types of movement of all students based on a preset ratio threshold to determine the mainstream movement type in the group. For example, if more than a certain proportion of students show a large deviation in a certain sport or the movement frequently appears in classroom training, the system will determine it as a mainstream movement type. Based on the analysis results of the mainstream movement type, a mainstream guidance plan is generated. The plan proposes specific improvement suggestions and training plans for the common movement problems of most students in the group. The plan not only includes general movement correction suggestions, but may also come with video demonstrations, common error analysis and training focus to help teachers provide concentrated guidance on common problems in the group in class. At the same time, the mainstream guidance plan can also provide students with a unified self-training plan to help them improve their performance in this type of movement.

[0090] By summarizing and analyzing the motion image data of all students, the system can fully understand the overall sports level and common problems of the class or group, thereby providing important decision-making basis for physical education. The overall learning report generated based on data can help teachers fully grasp the sports characteristics and common problems of the student group, so that teachers can adjust teaching strategies more targeted. In addition, by determining the mainstream sports types, the system can provide a unified mainstream guidance plan for the common sports problems in the group. This not only simplifies the teaching process, but also improves the efficiency of group training and ensures that every student can receive effective guidance. At the same time, the mainstream guidance plan can also optimize the allocation of teaching resources, helping teachers to focus on solving common problems of most students, thereby greatly improving the quality and effectiveness of physical education.

[0091] See also Figure 2 , Figure 2 This is a schematic diagram of a sub-process in the second embodiment of the physical education teaching method based on a depth of field camera of this application.

[0092] like Figure 2 As shown, in this embodiment, step S1 includes:

[0093] S11: When the depth-of-field camera enters the working state, determining whether a student enters the camera range and starts to move;

[0094] S12: If yes, control the depth-of-field camera to obtain the two-dimensional image data and spatial depth data of the student;

[0095] S13: Determine the motion image data according to the two-dimensional image data and the spatial depth data.

[0096] It should be noted that two-dimensional image data refers to the plane image data captured by the camera, which records the surface information of the object (such as color, shape, texture, etc.), but does not contain the distance information from the object to the camera. Spatial depth data is the distance information between the object and the camera generated by the depth of field camera. It captures the depth of each pixel through the sensor, thereby helping the system to generate a three-dimensional model. Motion image data includes the comprehensive results of two-dimensional image data and spatial depth data, reflecting the movement trajectory and posture information of students in three-dimensional space.

[0097] Specifically, when the depth-of-field camera enters the working state, the system uses the built-in dynamic detection mechanism to monitor the working range of the camera in real time to determine whether any students enter the camera's field of view and start moving. This determination is usually made through an algorithm that analyzes the images captured by the camera. If an object is detected moving in the image and the movement conforms to human characteristics (such as size, shape, etc.), it is determined that a student has entered the monitoring area and started moving. The system will further confirm whether the student's movements conform to the expected sports behavior (such as running, jumping, etc.) through analysis of depth data and motion trajectories.

[0098] Furthermore, once it is confirmed that the student has entered the monitoring range and started to move, the system controls the depth of field camera to start the image acquisition program to obtain the student's two-dimensional image data and spatial depth data. The two-dimensional image data contains the student's appearance information, such as the body outline, clothing, etc., while the spatial depth data is used to record the distance from each part to the camera. By combining these two types of data, the system can construct a three-dimensional model of the student and accurately record its movement trajectory in space. These data are then integrated into motion image data as the basis for subsequent posture recognition, 3D modeling and motion analysis.

[0099] By controlling the depth-of-field camera to collect data when students enter the camera range and start moving, the system can ensure that images are captured only when necessary, saving resources and improving the efficiency of data processing. Combining two-dimensional images and spatial depth data, the system can accurately capture the student's movement posture in three-dimensional space, not only obtaining motion information on the plane, but also analyzing subtle differences in depth. This combination greatly improves the detection accuracy of the system, ensuring that in the subsequent motion recognition and feedback process, analysis can be based on accurate three-dimensional data. This method also helps to capture students' movements in real time, ensuring that instant feedback is provided during teaching, thereby effectively improving the quality of physical education and the effectiveness of personalized guidance.

[0100] This embodiment obtains the student's motion image data based on a depth of field camera; identifies the motion image data to obtain the student's motion posture; constructs a 3D motion model based on the motion posture; compares the 3D motion model with the preset standard action posture; and generates a physical education teaching guidance plan based on the comparison results. This embodiment obtains the student's motion image data through a depth of field camera, and identifies it, accurately captures the student's motion posture, and ensures that the acquired motion information has high precision and real-time performance; then constructs a 3D motion model based on the motion posture, which can present the student's actual motion state in three dimensions and fully reflect the student's motion details; compares the generated 3D motion model with the preset standard action posture, which can accurately analyze the difference between the student's motion and the standard motion, and identify the deviation or error in the motion; finally, generates a personalized physical education teaching guidance plan based on the comparison results, provides specific improvement suggestions for the student's motion problems, and can provide teachers with more targeted teaching assistance, so that students can correct their motion deviations in time, thereby improving the effect of physical education teaching.

[0101] Based on the above second embodiment, a third embodiment of the physical education teaching method based on a depth of field camera is proposed. Figure 3 , Figure 3 This is a schematic diagram of a sub-process in the third embodiment of the physical education teaching method based on a depth of field camera of this application.

[0102] In this embodiment, step S2 includes:

[0103] S21: performing denoising and image enhancement processing on the two-dimensional image data to obtain enhanced image data;

[0104] S22: performing correction processing on the spatial depth data to obtain corrected spatial data;

[0105] S23: Based on a preset deep learning model, the enhanced image data and the corrected space data are identified to determine the student's movement posture.

[0106] It should be noted that denoising refers to removing interfering information or noise from image data to improve the quality of the image and make subsequent processing more accurate. Image enhancement processing refers to improving the contrast and brightness of the image through algorithms, enhancing image details, making the image information clearer, and thus improving the recognition accuracy of the system. Spatial depth data correction refers to calibrating and correcting the depth data collected by the depth of field camera to eliminate errors caused by external factors (such as angle, light, etc.) and make the depth information more accurate. The deep learning model is a machine learning algorithm based on a neural network. It can automatically identify and extract features in images through a large amount of training data, and is used for complex tasks such as posture recognition.

[0107] Specifically, the two-dimensional image data obtained from the depth of field camera is subjected to denoising and image enhancement processing. The purpose of denoising is to reduce the degradation of image quality caused by ambient light, noise or other external interference to ensure that the image is clearer. The system will use filtering algorithms (such as Gaussian filtering) to remove noise in the image. At the same time, image enhancement processing will optimize parameters such as image contrast and brightness to ensure that the body contours and movement details of the students in the image are more prominent. After denoising and enhancement processing, higher quality enhanced image data is obtained, providing better quality input data for subsequent recognition algorithms.

[0108] Furthermore, the captured spatial depth data is corrected. Due to factors such as the camera's shooting angle, lighting conditions, and distance, the depth data initially acquired may have errors or distortions. The correction process eliminates these deviations by analyzing the camera's viewing angle and the actual spatial position of the object, making the depth value of each pixel more accurate, thereby generating corrected spatial data. After this processing, the system can more accurately understand the student's position and posture in three-dimensional space, providing a basis for subsequent 3D posture recognition. The processed enhanced image data and corrected spatial data are recognized based on a preset deep learning model. The deep learning model has been trained with a large amount of posture data in advance and can identify key points of the student's body, such as the head, shoulders, elbows, knees, ankles, etc. The model reconstructs the student's three-dimensional motion posture by analyzing the position and relative angle of these key points, and determines whether its motion meets the expected standards. The model can automatically identify and track the student's posture changes in complex motion scenes and generate corresponding three-dimensional posture models.

[0109] By denoising and enhancing the two-dimensional image data, the system can significantly improve the image quality, making subsequent posture recognition more accurate and reliable. Clear image data reduces recognition errors caused by noise or blur, thereby improving the recognition accuracy of the system. On the other hand, the correction of spatial depth data can eliminate errors in the camera capture process, ensure the accuracy of the depth information of each pixel, and enhance the system's perception of postures in three-dimensional space. Based on the deep learning model to recognize the enhanced image data and the corrected spatial data, the system can automatically and accurately capture the students' movement postures without manual intervention. This method not only improves the recognition efficiency, but also effectively copes with complex sports scenes and ensures the high accuracy of the recognition results. This posture recognition method that combines image enhancement, depth data correction and deep learning can help teachers and students better understand posture deviations in sports and provide accurate feedback, thereby improving the personalization and scientific nature of physical education.

[0110] Based on the above second embodiment, in this embodiment, step S3 includes:

[0111] S31: extracting key points of the human body from the motion posture based on a preset posture recognition algorithm to obtain a plurality of key points of the human body;

[0112] S32: Connecting key points of the human body to obtain a three-dimensional skeleton model;

[0113] S33: Based on a preset smoothing algorithm, the three-dimensional skeleton model is optimized to obtain the 3D motion model.

[0114] It should be noted that the posture recognition algorithm is an algorithm used to automatically identify and extract human posture. By analyzing the human features in the image or video, the key points of various parts of the human body (such as the head, shoulders, elbows, knees, etc.) are extracted to construct a human posture model. The key points of the human body represent the points of various joints and important positions of the human body, such as the head, shoulders, elbows, knees, ankles, etc. The position information of the key points can reflect the posture and movement state of the human body. The three-dimensional skeleton model is a structure composed of the key points of the human body in three-dimensional space, showing the three-dimensional expression of the human body posture. By connecting the key points, the movement trajectory and posture of the human body can be presented. The smoothing algorithm is an algorithm used to eliminate noise and data fluctuations to ensure that the change process of the human body posture is smoother. This algorithm eliminates abnormal data or irregular changes generated during motion capture by optimizing the skeleton model.

[0115] Specifically, the preset posture recognition algorithm is used to process the student's motion image data and extract multiple key points of the human body. The algorithm can automatically identify the various joints of the human body based on image data and depth data, such as the head, shoulders, elbows, knees, ankles and other key points. Each key point has a three-dimensional coordinate, indicating the specific position of the point in space. Through the extraction of these key points, the system can accurately identify the student's current motion posture. This step ensures that the system can accurately capture the structural information of the human body from the original data and form a preliminary posture model.

[0116] Further, these extracted key points are connected to form a complete three-dimensional skeleton model. The connection between each key point reflects the relative position and movement relationship of each part of the human body. For example, the line between the shoulder and the elbow represents the posture of the arm, and the line between the knee and the ankle reflects the degree of bending of the leg. Through these connections, the system generates a three-dimensional skeleton model that can reflect the overall movement state of the student. The skeleton model shows the whole body structure of the student during exercise, and can intuitively reflect the position and posture of each limb in space. Finally, based on the preset smoothing algorithm, the system optimizes the generated three-dimensional skeleton model. Since momentary posture jitter, noise or abnormal data may occur during the data acquisition process, the role of the smoothing algorithm is to eliminate these irregular changes and ensure that the change process of the motion posture is more natural and coherent. The smoothing algorithm processes the motion data of each frame, smoothes the motion trajectory of the key points, makes the three-dimensional skeleton model more accurate and coherent, and thus generates an optimized 3D motion model. This model can not only accurately reflect the student's motion posture, but also reduce the interference caused by data fluctuations, making subsequent posture analysis more reliable.

[0117] By using the preset posture recognition algorithm, the system can automatically identify the key points of the human body, accurately capture the students' movement postures, and build a three-dimensional skeleton model based on these key points. Compared with traditional two-dimensional posture recognition, the three-dimensional skeleton model can more comprehensively reflect the actual movement state of the human body and provide more three-dimensional and intuitive movement data. This process ensures that the system can comprehensively analyze the movement posture of each student, providing an accurate basis for subsequent teaching feedback. In addition, the application of the smoothing algorithm further improves the accuracy and consistency of the three-dimensional skeleton model, eliminating the fluctuations and jitters that may exist during the data collection process. By optimizing the skeleton model, the system generates a more accurate 3D motion model, which not only improves the accuracy of motion analysis, but also enhances the consistency of the model, ensuring that the system can make more accurate judgments on students' movements. Finally, the optimized 3D motion model can provide teachers and students with clearer movement feedback, improving the personalization and scientific nature of physical education.

[0118] Based on the above second embodiment, in this embodiment, step S4 includes:

[0119] S41: Determine the motion type according to the 3D motion model;

[0120] S42: Determine a corresponding preset standard action posture according to the exercise type;

[0121] S43: performing key point matching and comparison between the 3D motion model and the three-dimensional skeleton model of the preset standard action posture.

[0122] It should be noted that the type of sport refers to the specific sport or type of action that the student is performing, such as running, jumping, weightlifting, kicking a ball, etc. Each type of sport corresponds to a set of standard action postures. The preset standard action posture refers to a standard posture model pre-defined for a specific sport type, usually provided by a professional coach or sports guide, which contains the ideal movement posture and the three-dimensional coordinates of its key points for comparative analysis. Key point matching refers to the comparison and analysis of postures by matching the key points of the human body in the 3D motion model with the key points of the preset standard action posture one by one to ensure that the positions of the two are aligned in space. Comparison refers to the position and angle comparison of the three-dimensional skeleton key points of the student's 3D motion model and the standard posture model, analyzing the deviation of the student's movement and determining the gap with the standard movement.

[0123] Specifically, the student's movement type is determined based on his or her 3D movement model. The 3D movement model has captured the student's movement posture and its movement trajectory in three-dimensional space. The system determines the student's current movement type by analyzing the characteristics of the model (such as movement amplitude, movement pattern, and the changing rules of key points, etc.). For example, the system may recognize that the student is kicking a ball by detecting features such as leg extension and body rotation; or determine that it is a throwing motion by bending and swinging the upper limbs. Each type of movement has specific characteristics, and the system will classify and identify it based on these characteristics.

[0124] Furthermore, according to the identified movement type, the corresponding standard movement posture is selected from the preset standard movement posture library. Each movement type corresponds to a set of standard posture models, which are pre-established through demonstrations by professionals or movement standard manuals, and contain the ideal position of each key point in the three-dimensional space during the movement. For example, the standard movement model of running will show the standard angle of leg swing, the swing amplitude of the arms, etc. After the system calls the corresponding standard posture, it is ready to compare the student's 3D movement model with the standard posture.

[0125] Finally, the key points of the student's 3D motion model are matched and compared with the preset standard action postures. Key point matching refers to the one-to-one correspondence between the key points in the student's three-dimensional skeleton model (such as shoulders, elbows, knees, etc.) and the corresponding key points in the standard action model. By matching these key points, the system can compare the coordinate differences between the two in three-dimensional space. After the matching is completed, the system will analyze the position error of each key point and its corresponding angle deviation, and then determine the gap between the student's movement and the standard movement. For example, the system will determine whether the student's arms are stretched in place, whether the legs are bent according to the standard, etc. Based on these differences, the system will generate a detailed comparison report to guide students to improve their movements.

[0126] By determining the type of exercise based on the 3D motion model, the system can automatically identify the sports that students are doing, ensuring that subsequent action comparisons and feedback are accurate. The process of automatically identifying the type of exercise reduces manual intervention, allowing the system to efficiently handle different sports scenes and projects. At the same time, the system automatically selects the corresponding standard action posture according to the type of exercise, which ensures the scientificity and pertinence of the comparison process. Different sports have their own specific standard postures, and the system can perform personalized comparisons and analyses based on the actual sports situation of each student. The 3D motion model is matched and compared with the preset standard action postures at key points, so that the system can accurately analyze the deviations and non-standard aspects of the students' movements. Key point matching can ensure the accuracy of the comparison, and through the coordinate difference and angle error analysis in three-dimensional space, the system can provide students with detailed action feedback. This comparison based on three-dimensional data not only improves the accuracy of action analysis, but also helps students intuitively understand the gap between themselves and standard actions, and then improve their sports skills in a more targeted manner. This process greatly improves the personalization and scientificity of physical education, helping students to quickly correct wrong actions and improve their sports performance.

[0127] This embodiment obtains the student's motion image data based on a depth of field camera; identifies the motion image data to obtain the student's motion posture; constructs a 3D motion model based on the motion posture; compares the 3D motion model with the preset standard action posture; and generates a physical education teaching guidance plan based on the comparison results. This embodiment obtains the student's motion image data through a depth of field camera, and identifies it, accurately captures the student's motion posture, and ensures that the acquired motion information has high precision and real-time performance; then constructs a 3D motion model based on the motion posture, which can present the student's actual motion state in three dimensions and fully reflect the student's motion details; compares the generated 3D motion model with the preset standard action posture, which can accurately analyze the difference between the student's motion and the standard motion, and identify the deviation or error in the motion; finally, generates a personalized physical education teaching guidance plan based on the comparison results, provides specific improvement suggestions for the student's motion problems, and can provide teachers with more targeted teaching assistance, so that students can correct their motion deviations in time, thereby improving the effect of physical education teaching.

[0128] The present application also provides a physical education teaching device based on a depth of field camera. Figure 4 , Figure 4 This is a schematic diagram of the module structure of a physical education teaching device based on a depth of field camera according to an embodiment of the present application. The physical education teaching device based on a depth of field camera includes:

[0129] A data acquisition module 401 is used to acquire the student's motion image data based on a depth-of-field camera;

[0130] The recognition module 402 is used to recognize the motion image data to obtain the student's motion posture;

[0131] A model building module 403 is used to build a 3D motion model based on the motion posture;

[0132] A comparison module 404 is used to compare the 3D motion model with a preset standard motion posture;

[0133] The target module 405 is used to generate a physical education teaching guidance plan based on the comparison results.

[0134] The physical education teaching device based on a depth of field camera provided in the embodiment of the present application adopts the physical education teaching method based on a depth of field camera in the above embodiment, which can solve the technical problem of how to improve the teaching effect of physical education classes. Compared with the prior art, the beneficial effects of the physical education teaching device based on a depth of field camera provided in the embodiment of the present application are the same as the beneficial effects of the physical education teaching method based on a depth of field camera provided in the above embodiment, and the other technical features of the physical education teaching device based on a depth of field camera are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0135] The present application provides a physical education teaching device based on a depth of field camera, and the physical education teaching device based on a depth of field camera includes: at least one processor; and a memory connected to the at least one processor in communication; wherein the memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the physical education teaching method based on the depth of field camera in the above-mentioned embodiment.

[0136] Reference below Figure 5 , which shows a schematic diagram of the structure of a physical education teaching device based on a depth of field camera suitable for implementing the embodiment of the present application. The physical education teaching device based on a depth of field camera in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 5 The physical education teaching equipment based on the depth of field camera shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0137] like Figure 5As shown, the physical education teaching equipment based on the depth of field camera may include a processing device 1001 (such as a central processing unit, a graphics processor, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 to the random access memory (RAM: Random Access Memory) 1004. In RAM1004, various programs and data required for the operation of the physical education teaching equipment based on the depth of field camera are also stored. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. The input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the physical education teaching device based on the depth of field camera to communicate wirelessly or wired with other devices to exchange data. Although the figure shows a physical education teaching device based on a depth of field camera with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.

[0138] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0139] The physical education teaching equipment based on the depth of field camera provided by the present application adopts the physical education teaching method based on the depth of field camera in the above-mentioned embodiment, which can solve the technical problem of how to improve the teaching effect of physical education classes. Compared with the prior art, the beneficial effects of the physical education teaching equipment based on the depth of field camera provided by the present application are the same as the beneficial effects of the physical education teaching method based on the depth of field camera provided by the above-mentioned embodiment, and the other technical features of the physical education teaching equipment based on the depth of field camera are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0140] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0141] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0142] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the physical education teaching method based on a depth of field camera in the above-mentioned embodiment.

[0143] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above. The computer-readable storage medium may be included in the physical education teaching device based on the depth of field camera; or may exist independently without being assembled into the physical education teaching device based on the depth of field camera.

[0144] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the physical education teaching device based on the depth of field camera, the physical education teaching device based on the depth of field camera: obtains the student's motion image data based on the depth of field camera; identifies the motion image data to obtain the student's motion posture; constructs a 3D motion model based on the motion posture; compares the 3D motion model with the preset standard action posture; and generates a physical education teaching guidance plan based on the comparison result. The computer program code for performing the operation of the present application can be written in one or more programming languages ​​or a combination thereof. The programming language includes an object-oriented programming language such as Java, Smalltalk, C++, and also includes a conventional procedural programming language such as "C" language or similar programming language. The program code can be executed completely on the user's computer, partially on the user's computer, as an independent software package, partially on the user's computer and partially on a remote computer, or completely on a remote computer or server. In the case of a remote computer, the remote computer can be connected to the user's computer through any type of network, including a Local Area Network (LAN) or a Wide Area Network (WAN), or it can be connected to an external computer (for example, through the Internet using an Internet service provider).

[0145] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0146] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0147] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned physical education teaching method based on a depth of field camera, and can solve the technical problem of how to improve the teaching effect of physical education classes. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the physical education teaching method based on a depth of field camera provided in the above-mentioned embodiment, and will not be repeated here.

[0148] An embodiment of the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned physical education teaching method based on a depth of field camera.

[0149] The computer program product provided in this application can solve the technical problem of how to improve the teaching effect of physical education. Compared with the prior art, the beneficial effects of the computer program product provided in the embodiment of this application are the same as the beneficial effects of the physical education teaching method based on the depth of field camera provided in the above embodiment, which will not be repeated here.

[0150] The above are only preferred embodiments of the present application, and are not intended to limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made using the contents of the present application specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent processing scope of the present application.

Claims

1. A physical education teaching method based on a depth of field camera, characterized in that: The method comprises: Acquire students' motion image data based on depth-of-field camera; Recognizing the motion image data to obtain the student's motion posture; Based on the motion posture, construct a 3D motion model; Comparing the 3D motion model with a preset standard motion posture; Based on the comparison results, a physical education teaching guidance plan is generated.

2. The method according to claim 1, characterized in that After the step of generating a physical education teaching guidance program based on the comparison results, the method further includes: The motion image data of all students were summarized; Generate an overall learning report based on the summary results; Determine the mainstream exercise type based on the overall learning report and a preset ratio threshold; A mainstream guidance plan is generated according to the mainstream motion type.

3. The method according to claim 1, characterized in that The step of acquiring the student's motion image data based on the depth-of-field camera includes: When the depth-of-field camera enters the working state, it is determined whether a student enters the camera range and starts to move; If yes, control the depth-of-field camera to obtain the two-dimensional image data and spatial depth data of the student; The motion image data is determined based on the two-dimensional image data and the spatial depth data.

4. The method according to claim 3, characterized in that The step of identifying the motion image data to obtain the student's motion posture comprises: Performing denoising and image enhancement processing on the two-dimensional image data to obtain enhanced image data; Performing correction processing on the spatial depth data to obtain corrected spatial data; Based on a preset deep learning model, the enhanced image data and the corrected space data are identified to determine the student's movement posture.

5. The method according to claim 1, characterized in that The step of constructing a 3D motion model based on the motion posture comprises: Based on a preset posture recognition algorithm, extracting key points of the human body from the motion posture to obtain a plurality of key points of the human body; Connect each key point of the human body to obtain a three-dimensional skeleton model; Based on a preset smoothing algorithm, the three-dimensional skeleton model is optimized to obtain the 3D motion model.

6. The method according to claim 1, characterized in that The step of comparing the 3D motion model with a preset standard motion posture comprises: Determine the type of motion according to the 3D motion model; According to the exercise type, determining a corresponding preset standard action posture; The 3D motion model is matched and compared with the three-dimensional skeleton model of the preset standard action posture at key points.

7. A physical education teaching device based on a depth of field camera, characterized in that: The device comprises: A data acquisition module, used for acquiring students' motion image data based on a depth-of-field camera; A recognition module, used to recognize the motion image data to obtain the student's motion posture; A model building module, used for building a 3D motion model based on the motion posture; A comparison module, used for comparing the 3D motion model with a preset standard motion posture; The target module is used to generate sports teaching guidance plans based on the comparison results.

8. A computer device, characterized in that: The device includes: a memory, a processor, and a physical education teaching program based on a depth of field camera stored in the memory and executable on the processor, wherein the physical education teaching program based on the depth of field camera is configured to implement the steps of the physical education teaching method based on the depth of field camera as described in any one of claims 1 to 6.

9. A storage medium, characterized in that: The storage medium stores a physical education teaching program based on a depth of field camera. When the physical education teaching program based on a depth of field camera is executed by a processor, the steps of the physical education teaching method based on a depth of field camera as described in any one of claims 1 to 6 are implemented.

10. A computer program product, characterized in that The computer program product comprises a computer program, and when the computer program is executed by a processor, the steps of the physical education teaching method based on a depth of field camera as described in any one of claims 1 to 6 are implemented.

Images