Face recognition-based intelligent turn-back running evaluation method and system

Abstract

The invention discloses an intelligent turn-back running evaluation method and system based on face recognition. According to the method, firstly, intelligent acquisition devices are installed at the starting point and the ending point of a runway, and a high-resolution camera and an edge calculation module are used for carrying out real-time face snapshot and preprocessing on students; and carrying out face recognition by adopting a deep learning model, comparing a captured face image with a student face library, confirming the identity of the target to be detected, and associating with a running record. In the running process, the motion trail of the student is tracked in real time through the human body recognition technology, the turn-back action is accurately recognized, and the accuracy of turn-back point data is ensured. The problems of large manual timing error, difficulty in turning point monitoring, incomplete data recording and the like in a traditional turn-back running test are solved, and the automation degree and the data accuracy of the test are improved. Meanwhile, the system supports real-time data display and feedback, and provides a scientific basis for physical education and management.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a shuttle run intelligent evaluation method and system based on face recognition. Background Art

[0002] In campus physical education and physical tests, the shuttle run test (such as the 50-meter shuttle run) is an important physical fitness test item used to evaluate students' endurance, speed, and flexibility. However, the traditional shuttle run test method mainly relies on manual timing and manual recording, which has the following problems:

[0003] In traditional shuttle run tests, time is usually manually measured at the start and end points using a stopwatch. This method is not only inefficient, but also easily interfered with by human factors, such as differences in reaction time and timing errors, resulting in inaccurate test results. In particular, in the timing of the turning point, the error is more obvious because it is necessary to pay attention to the turning movements of multiple students at the same time.

[0004] In the 50-meter shuttle run test, monitoring the turning point is a key link. In traditional methods, the turning point is usually manually observed by the student to see whether the student has completed the turning action. This method is not only prone to errors, but also difficult to record the student's turning time in real time, resulting in incomplete data. Summary of the invention

[0005] Based on this, an embodiment of the present application provides an intelligent evaluation method and system for shuttle runs based on face recognition. This method uses intelligent collection equipment and face recognition technology to achieve accurate collection, real-time recording and efficient management of students' running data, and accurately identify whether the students have completed the shuttle action.

[0006] In a first aspect, a shuttle run intelligent evaluation method based on face recognition is provided, the method comprising:

[0007] Install intelligent acquisition equipment at the starting point and the end point of the runway, and use the intelligent acquisition equipment to capture facial images; wherein the intelligent acquisition equipment at least includes a high-resolution camera and an edge computing device, the high-resolution camera is used to capture the face, and the edge computing device is used to perform preliminary face detection and preprocessing;

[0008] Each facial image captured at the starting point is recognized using a deep learning model, and is compared one by one with a pre-stored student face database to determine whether the student corresponding to each facial image is the target to be tested. If the comparison is successful, the identity information of the successfully matched student is associated with the running record.

[0009] During the running process of the target, the return action of the student passing the starting point and the end point is recognized, and the running data of the target is collected; wherein the running data includes the running mileage, duration, number of return times and pace data;

[0010] The collected running data is processed and statistically analyzed in real time to generate intelligent evaluation results for the target to be tested.

[0011] Optionally, the return action of the students passing through the starting point and the end point is recognized, including:

[0012] Through the human body recognition function of the intelligent data collection equipment, the students' turn-around movements at the starting point and the end point are detected; the students' body contours and movement trajectories are tracked in real time to determine whether the students have completed the required turn-around movements at the turn-around points; only when it is confirmed that the students have completed the turn-around movements, the turn-around time will be recorded and included in the running data;

[0013] The accuracy of the turning action is verified by analyzing the student's body posture and movement direction at the turning point; among them, by detecting whether the student's turning angle at the turning point reaches the preset threshold, it is ensured that the student has indeed completed the turning action.

[0014] Optionally, the method further comprises:

[0015] When it is detected that the student's behavior at the turning point does not meet the preset turning-back action standards, it is marked as abnormal and an alarm is triggered to notify the on-site staff to conduct a manual review; the student ID, turning-back time, and human posture information of the abnormal turning-back are also recorded;

[0016] After each test, the turnaround point data is automatically calibrated and verified, and the turnaround data deviation caused by equipment error or environmental interference is corrected by comparing the snapshot images of the students at the starting and ending points and combining them with the motion trajectory data provided by the human body recognition module.

[0017] Optionally, intelligent data collection equipment is installed at the start and end of the runway, and also includes:

[0018] Set the effective capture time. When the smart acquisition device is running, it will obtain the current time in real time and compare it with the set effective capture time. The smart acquisition device will start the capture process only when you enter the running area within the effective capture time.

[0019] Set a minimum number of captured photos. During the capture process, the intelligent collection device will count the photos captured by each student. When processing the captured data, it will check whether the number of captured photos of each student reaches the set minimum threshold. Only when the number of captured photos reaches or exceeds the set minimum number, the student's running data will be counted and recorded in the database.

[0020] Optionally, the edge computing device performs preliminary face detection and preprocessing, including:

[0021] After capturing an image through a high-resolution camera, the NPU algorithm is used to identify the face area in the image and determine its position and size;

[0022] The detected face image is preprocessed, including grayscale, normalization, cropping and enhancement operations, to optimize image quality and remove background information, and a valid face image is determined based on the tilt angle of the face.

[0023] Optionally, each captured facial image is subjected to facial recognition using a deep learning model, specifically including:

[0024] Analyze the captured facial images using a pre-trained deep learning model, where the deep learning model can detect 150 facial key points and locate the key points of the face, eyes, eyebrows, lips, and nose;

[0025] At the same time, it can accurately locate single and multiple faces, and use the face angle judgment function to analyze the faces in the picture at various posture angles, and obtain valid data based on the face space posture angle reference.

[0026] In the second aspect, a shuttle run intelligent evaluation system based on face recognition is provided, the system comprising:

[0027] A collection module, including installing intelligent collection equipment at the start and end of the runway, and capturing facial images through the intelligent collection equipment; wherein the intelligent collection equipment at least includes a high-resolution camera and an edge computing device, the high-resolution camera is used to realize face capture, and the edge computing device is used to perform preliminary face detection and preprocessing;

[0028] The recognition module is used to perform face recognition on each face image captured at the starting point using a deep learning model, and compare it one by one with the pre-stored student face database to determine whether the student corresponding to each face image is the target to be tested. If the comparison is successful, the identity information of the successfully matched student is associated with the running record;

[0029] A processing module is used to identify the turning motion of the student passing the starting point and the end point during the running process of the target to be tested, and collect the running data of the target to be tested; wherein the running data includes running mileage, duration, number of turnings and pace data;

[0030] The generation module is used to perform real-time processing and statistical analysis on the collected running data to generate intelligent evaluation results for the target to be tested.

[0031] In a third aspect, an electronic device is provided, including a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, the intelligent evaluation method for shuttle runs described in any one of the first aspects is implemented.

[0032] In a fourth aspect, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the shuttle run intelligent evaluation method described in any one of the first aspects is implemented.

[0033] In a fifth aspect, a computer program product is provided, including a computer program / instruction, which, when executed by a processor, implements the shuttle run intelligent evaluation method described in any one of the first aspects.

[0034] The beneficial effects brought by the technical solution provided by the embodiment of the present application include at least:

[0035] (1) By displaying students’ running data, daily rankings, and weekly rankings in real time, students’ competitive awareness and enthusiasm for sports are stimulated. Personalized exercise suggestions and real-time feedback mechanisms further enhance students’ sense of participation, encourage them to actively participate in physical exercise, and improve their physical fitness.

[0036] (2) Automatically collect, process and analyze running data, generate intelligent evaluation results, and provide scientific management basis for teachers and administrators. It reduces the workload of manual statistics and management, improves management efficiency and data accuracy, and enables schools to formulate physical education teaching plans and evaluate students' sports performance more scientifically. BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the implementation methods of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for the implementation methods or the description of the prior art. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other implementation drawings can be derived from the provided drawings without creative work.

[0038] Figure 1 A flowchart of the steps of a shuttle run intelligent evaluation method based on face recognition provided in an embodiment of the present application;

[0039] Figure 2 A block diagram of a shuttle run intelligent evaluation system based on face recognition provided in an embodiment of the present application;

[0040] Figure 3 A schematic diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0041] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the accompanying drawings and embodiments. 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.

[0042] In the description of the present invention, the terms "comprises", "has" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may also include other steps or units that are not explicitly listed but are inherent to these processes, methods, products or apparatuses, or steps or units added based on further optimization schemes conceived by the present invention.

[0043] Please refer to Figure 1 , which shows a flow chart of a shuttle run intelligent evaluation method based on face recognition provided by an embodiment of the present application, which may include the following steps:

[0044] S1, install intelligent collection equipment at the starting point and the end point of the runway, and capture facial images through the intelligent collection equipment.

[0045] Among them, the intelligent collection equipment includes at least a high-resolution camera and an edge computing device. The high-resolution camera is used to capture faces, and the edge computing device is used to perform preliminary face detection and preprocessing.

[0046] In this step, smart acquisition devices are installed at the starting and ending points of the school playground runway. These devices include high-resolution cameras and built-in edge computing modules. The high-resolution camera is used to capture facial images in real time to ensure image clarity and quality, which can meet the needs of face recognition. The playground runway can be a 50-meter or 100-meter runway. At the same time, the starting and ending points are also the turning points in this embodiment. The smart acquisition devices are connected via a gigabit wired network to ensure the stability and real-time performance of data transmission.

[0047] The edge computing module is responsible for the preliminary processing of the captured facial images, including face detection, image preprocessing (such as grayscale, normalization, cropping and enhancement), and face angle judgment, reducing the amount of data transmission and improving the system response speed.

[0048] When students enter the running area, the intelligent acquisition device automatically starts the capture process, captures the students' facial images, and performs preliminary processing to prepare for subsequent facial recognition.

[0049] In an optional embodiment of the present application, an effective capture time is set. When the intelligent acquisition device is running, it will obtain the current time in real time and compare it with the set effective capture time. When entering the running area within the effective capture time, the intelligent acquisition device will start the capture process;

[0050] Set a minimum number of captured photos. During the capture process, the intelligent collection device will count the photos captured by each student. When processing the captured data, it will check whether the number of captured photos of each student reaches the set minimum threshold. Only when the number of captured photos reaches or exceeds the set minimum number, the student's running data will be counted and recorded in the database.

[0051] S2, using a deep learning model to perform face recognition on each face image captured at the starting point, and comparing them one by one with the pre-stored student face database to determine whether the student corresponding to each face image is the target to be tested. If the comparison is successful, the identity information of the successfully matched student will be associated with this running record.

[0052] In this step, the intelligent acquisition device transmits the preliminarily processed facial image to the back-end system through the network.

[0053] The face recognition engine in the back-end system uses a deep learning model to perform high-precision recognition of captured facial images.

[0054] This deep learning model is based on large-scale data training and can detect 150 key points, accurately locate facial features (such as eyebrows, eyes, nose, lips, cheeks, etc.) and contours, and support recognition of single and multiple faces.

[0055] The system makes angle judgments on facial images and combines them with the spatial posture angle reference of the face to enhance the accuracy and robustness of recognition.

[0056] During the recognition process, the system will compare the captured facial image with the pre-stored student face database one by one to determine whether the student is a student of this school (i.e., the target to be tested).

[0057] If the match is successful, the system will associate the student's identity information with the running record, providing a basis for subsequent data statistics and analysis.

[0058] S3, when the target is running, the turning motion of the student passing the starting point and the end point is recognized, and the running data of the target is collected.

[0059] In this step, the return action of the students who have passed the starting point and the end point is recognized, including:

[0060] Through the human body recognition function of the intelligent data collection device, the student's turn-around action at the starting point and the end point is detected. The student's body contour and movement trajectory are tracked in real time to determine whether the student has completed the required turn-around action at the turn-around point; only when it is confirmed that the student has completed the turn-around action, the turn-around time will be recorded and included in the running data;

[0061] The accuracy of the turnaround action is verified by analyzing the student's posture and movement direction at the turning point. In particular, by detecting whether the student's turning angle at the turning point reaches the preset threshold, it is ensured that the student has indeed completed the turnaround action.

[0062] The method also includes:

[0063] When it is detected that the student's behavior at the turning point does not meet the preset turning action standards, the turning is marked as abnormal, and an alarm is triggered to notify the on-site staff to conduct a manual review; the student ID, turning time, and human posture information of the abnormal turning are also recorded;

[0064] After each test, the turnaround point data is automatically calibrated and verified, and the turnaround data deviation caused by equipment error or environmental interference is corrected by comparing the snapshot images of the students at the starting and ending points and combining them with the motion trajectory data provided by the human body recognition module.

[0065] Among them, running data includes running mileage, duration, number of turns and pace data.

[0066] In this step, while the target (confirmed student) is running, the intelligent data collection device continuously captures the face of the student passing the monitoring point. The system confirms whether the captured student is the target through face comparison to ensure the accuracy of the data. After each successful capture, the system records the time when the student passes the turning point and calculates the running mileage, duration, pace and other data according to the time sequence.

[0067] The running mileage is calculated by calculating the total path length after the students have made several turns; the running time is calculated by recording the difference between the time when the students start running and the time when they end running; and the pace is calculated by dividing the running mileage by the running time.

[0068] The system transmits the collected running data to the back-end system in real time for storage and further processing.

[0069] In an optional embodiment of the present application, human body recognition is also included:

[0070] When the target is running, the intelligent data acquisition device not only captures the face, but also starts the body recognition function at the same time. Body recognition technology can detect a single or multiple people in the picture, track the people, and feedback the relative position of the people in the picture.

[0071] The human body recognition algorithm can detect the student's body outline in real time and track it. Even when the face is partially blocked (such as wearing a hat, mask, etc.) or the face cannot be captured clearly due to angle problems, the human body recognition technology can still confirm the student's identity and location through the body outline and movement trajectory.

[0072] Human body recognition technology can provide information about the relative position of the human body in the image, helping the system to more accurately determine whether students have passed through monitoring points and their specific positions during running.

[0073] During the face capture process, human body recognition technology can assist in confirming whether the captured face belongs to a student who is running, avoiding data errors caused by mistakenly capturing other non-running people.

[0074] In a scenario where multiple people are running, human body recognition technology can distinguish different students and ensure that each student's running data is accurately collected. Even if there is overlap between students or the queues are tight, human body recognition technology can still accurately distinguish them through body contours and movement trajectories.

[0075] The location information provided by human body recognition technology can more accurately calculate the student's running mileage and pace. For example, the system can more accurately estimate the running path and speed based on the movement trajectory of the human body between monitoring points.

[0076] During running, human body recognition technology can provide real-time feedback on students' exercise status, helping the system to adjust data collection strategies in a timely manner to ensure the accuracy and completeness of the data.

[0077] S4, performs real-time processing and statistical analysis on the collected running data to generate intelligent evaluation results of the target to be tested.

[0078] In this step, the back-end system processes the received running data in real time, including data cleaning, verification and integration, to ensure the accuracy and completeness of the data.

[0079] The system performs statistical analysis on the running data of each target to be tested and calculates basic statistical indicators such as total mileage, total time, and average pace.

[0080] Based on the statistical results, daily and weekly rankings for the entire school are generated to display the students' rankings and encourage students to actively participate in running exercises.

[0081] The system also performs personalized analysis, such as exercise trend analysis and exercise suggestion generation, to provide targeted exercise guidance for each student.

[0082] Ultimately, the system generates intelligent evaluation results, including students' running data, ranking information, sports trend analysis, and personalized recommendations.

[0083] The intelligent evaluation results are displayed to students and administrators in real time through a user-friendly interface (such as a large sunlight screen), and can also be sent to relevant personnel in the form of electronic reports, providing a scientific basis for the school's physical education and management. The user-friendly interface supports a variety of interactive methods, and displays running student information and the school's daily / weekly leaderboard; the running student information includes the student's head portrait and today's running mileage, and the school's daily / weekly leaderboard includes the student's name, class, total running mileage, and total duration information for each day / week.

[0084] Please refer to Figure 2 , which shows a block diagram of a shuttle run intelligent evaluation system based on face recognition provided by an embodiment of the present application. Figure 2 As shown, the system may include:

[0085] A collection module, including installing intelligent collection equipment at the start and end of the runway, and capturing facial images through the intelligent collection equipment; wherein the intelligent collection equipment at least includes a high-resolution camera and an edge computing device, the high-resolution camera is used to realize face capture, and the edge computing device is used to perform preliminary face detection and preprocessing;

[0086] The recognition module is used to perform face recognition on each face image captured at the starting point using a deep learning model, and compare it one by one with the pre-stored student face database to determine whether the student corresponding to each face image is the target to be tested. If the comparison is successful, the identity information of the successfully matched student is associated with the running record;

[0087] A processing module is used to identify the turning motion of the student passing the starting point and the end point during the running process of the target to be tested, and collect the running data of the target to be tested; wherein the running data includes running mileage, duration, number of turnings and pace data;

[0088] The generation module is used to perform real-time processing and statistical analysis on the collected running data to generate intelligent evaluation results for the target to be tested.

[0089] For the specific definition of the shuttle run intelligent evaluation system based on face recognition, please refer to the definition of the shuttle run intelligent evaluation method based on face recognition in the above text, which will not be repeated here. Each module in the above-mentioned shuttle run intelligent evaluation system based on face recognition can be implemented in whole or in part by software, hardware and a combination thereof. The above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory in the computer device in the form of software, so that the processor can call and execute the operations corresponding to the above modules.

[0090] In one embodiment, an electronic device is provided. The electronic device may be a computer, and its internal structure diagram may be as follows: Figure 3 As shown. The electronic device includes a processor, a memory and a network interface connected via a system bus. The processor of the device is used to provide computing and control capabilities. The memory of the device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used for intelligent evaluation data of shuttle runs based on face recognition. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a method for intelligent evaluation of shuttle runs based on face recognition is implemented.

[0091] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a part of the structure related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine certain components, or have a different arrangement of components.

[0092] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored, which involves all or part of the processes in the above-mentioned embodiment method.

[0093] In one embodiment, a computer program product is also provided, including a computer program / instruction, which involves all or part of the process in the above embodiment method.

[0094] Those of ordinary skill in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing related hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in M ​​forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (SyMchliMk) DRAM (SLDRAM), memory bus (RaMbus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), etc.

[0095] 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.

[0096] The above-described embodiments only express several implementation methods of the present application, and the descriptions thereof are relatively specific and detailed, but they cannot be construed as limiting the scope of the patent application. It should be pointed out that, for a person of ordinary skill in the art, several variations and improvements can be made without departing from the concept of the present application, and these all belong to the protection scope of the present application. Therefore, the protection scope of the patent application shall be subject to the attached claims.

Claims

1. A shuttle run intelligent evaluation method based on face recognition, characterized in that: The method comprises: Install intelligent acquisition equipment at the starting point and the end point of the runway, and use the intelligent acquisition equipment to capture facial images; wherein the intelligent acquisition equipment at least includes a high-resolution camera and an edge computing device, the high-resolution camera is used to capture the face, and the edge computing device is used to perform preliminary face detection and preprocessing; Each facial image captured at the starting point is recognized using a deep learning model, and is compared one by one with a pre-stored student face database to determine whether the student corresponding to each facial image is the target to be tested. If the comparison is successful, the identity information of the successfully matched student is associated with the running record. During the running process of the target, the return action of the student passing the starting point and the end point is recognized, and the running data of the target is collected; wherein the running data includes the running mileage, duration, number of return times and pace data; The collected running data is processed and statistically analyzed in real time to generate intelligent evaluation results for the target to be tested.

2. The shuttle run intelligent evaluation method according to claim 1, characterized in that: Recognize the return movement of students who pass the starting point and the end point, including: Through the human body recognition function of the intelligent data collection equipment, the students' turn-around movements at the starting point and the end point are detected; the students' body contours and movement trajectories are tracked in real time to determine whether the students have completed the required turn-around movements at the turn-around points; only when it is confirmed that the students have completed the turn-around movements, the turn-around time will be recorded and included in the running data; The accuracy of the turning action is verified by analyzing the student's body posture and movement direction at the turning point; among them, by detecting whether the student's turning angle at the turning point reaches the preset threshold, it is ensured that the student has indeed completed the turning action.

3. The shuttle run intelligent evaluation method according to claim 2, characterized in that: The method further comprises: When it is detected that the student's behavior at the turning point does not meet the preset turning-back action standards, it is marked as abnormal and an alarm is triggered to notify the on-site staff to conduct a manual review; the student ID, turning-back time, and human posture information of the abnormal turning-back are also recorded; After each test, the turnaround point data is automatically calibrated and verified, and the turnaround data deviation caused by equipment error or environmental interference is corrected by comparing the snapshot images of the students at the starting and ending points and combining them with the motion trajectory data provided by the human body recognition module.

4. The shuttle run intelligent evaluation method according to claim 1, characterized in that: Install intelligent data collection equipment at the start and end of the runway, including: Set the effective capture time. When the smart acquisition device is running, it will obtain the current time in real time and compare it with the set effective capture time. The smart acquisition device will start the capture process only when you enter the running area within the effective capture time. Set a minimum number of captured photos. During the capture process, the intelligent collection device will count the photos captured by each student. When processing the captured data, it will check whether the number of captured photos of each student reaches the set minimum threshold. Only when the number of captured photos reaches or exceeds the set minimum number, the student's running data will be counted and recorded in the database.

5. The shuttle run intelligent evaluation method according to claim 1, characterized in that: The edge computing device performs preliminary face detection and preprocessing, including: After capturing an image through a high-resolution camera, the NPU algorithm is used to identify the face area in the image and determine its position and size; The detected face image is preprocessed, including grayscale, normalization, cropping and enhancement operations, to optimize image quality and remove background information, and a valid face image is determined based on the tilt angle of the face.

6. The shuttle run intelligent evaluation method according to claim 1, characterized in that: Each captured facial image is used for face recognition using a deep learning model, including: Analyze the captured facial images using a pre-trained deep learning model, where the deep learning model can detect 150 facial key points and locate the key points of the face, eyes, eyebrows, lips, and nose; At the same time, it can accurately locate single and multiple faces, and use the face angle judgment function to analyze the faces in the picture at various posture angles, and obtain valid data based on the face space posture angle reference.

7. An intelligent evaluation system for shuttle run based on face recognition, characterized in that: The system comprises: A collection module, including installing intelligent collection equipment at the start and end of the runway, and capturing facial images through the intelligent collection equipment; wherein the intelligent collection equipment at least includes a high-resolution camera and an edge computing device, the high-resolution camera is used to realize face capture, and the edge computing device is used to perform preliminary face detection and preprocessing; The recognition module is used to perform face recognition on each face image captured at the starting point using a deep learning model, and compare it one by one with the pre-stored student face database to determine whether the student corresponding to each face image is the target to be tested. If the comparison is successful, the identity information of the successfully matched student is associated with the running record; A processing module is used to identify the turning motion of the student passing the starting point and the end point during the running process of the target to be tested, and collect the running data of the target to be tested; wherein the running data includes running mileage, duration, number of turnings and pace data; The generation module is used to perform real-time processing and statistical analysis on the collected running data to generate intelligent evaluation results for the target to be tested.

8. An electronic device, characterized in that: The method comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 6 are implemented.

9. A computer-readable storage medium, characterized in that: A computer program is stored thereon, and when the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

10. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 6 are implemented.

Images