Classroom teacher attendance checking method, device and equipment and storage medium

Abstract

The invention discloses a classroom teacher attendance checking method, device and equipment and a storage medium. The method comprises the following steps: acquiring course information of a current course; when the trigger time point is started, an attendance camera for teacher attendance is triggered and started for the first time; after the attendance camera is triggered and started for the first time, judging whether a face matched with the face information of the course teacher exists in the captured classroom class picture or not; if yes, the attendance time is obtained, the attendance time is compared with the class time specified by the class schedule, and whether the teacher is punctual or late is judged; when a preset duration before the course ending time point is reached, triggering and starting an attendance camera for teacher attendance for the second time; after the attendance camera is triggered and started for the second time, judging whether a face matched with the face information of the course teacher exists in the captured classroom class picture or not; and if matching and continuing until the end of the classroom, judging that the teacher normally finishes teaching. According to the invention, the attendance condition can be automatically and accurately identified.

Description

Technical Field

[0001] This invention relates to the field of video image processing technology, and more specifically, to a method, apparatus, device, and storage medium for classroom teacher attendance tracking. Background Technology

[0002] In school teaching, attendance data is very important to both students and teachers, serving as a crucial basis for evaluating them.

[0003] In existing technologies, for monitoring teacher attendance, image acquisition devices are typically deployed in each classroom to capture images of the classroom. When monitoring personnel need to monitor teacher A's attendance, they must first locate the classroom where teacher A is currently teaching and retrieve the corresponding classroom's surveillance footage. Then, they need to determine if a teacher appears in the footage; if a teacher is present, they must further verify that the teacher's identity is indeed teacher A before attendance monitoring can be completed.

[0004] However, existing manual monitoring methods for teacher attendance have several shortcomings: First, the process is cumbersome and requires manual operation by monitoring personnel; second, due to blind spots in the video or the randomness of image capture, the retrieved footage may lack teacher images, leading to misjudgments; third, when the equipment's resolution is insufficient, the image needs to be enlarged to identify the teacher. Furthermore, this solution requires monitoring personnel to know each teacher and be familiar with their course schedules to accurately identify the student, which is not only difficult to implement and places high demands on personnel, but also makes it difficult to balance accuracy and efficiency in monitoring. Summary of the Invention

[0005] To overcome at least one of the defects described in the prior art, the present invention provides a method, apparatus, device, and storage medium for classroom teacher attendance. The technical solution adopted by the present invention is as follows.

[0006] In a first aspect, the present invention provides a method for classroom teacher attendance tracking, comprising:

[0007] Obtain the course information for the current course, including: course start time, course end time, and the facial information of the course instructor;

[0008] At the activation trigger time, the attendance camera used for teacher attendance is activated for the first time; wherein, the activation trigger time is determined based on the start time of the current course, and the activation trigger time is no later than the start time of the course;

[0009] After the attendance camera is triggered for the first time, it captures classroom scenes at a preset first frequency and uses face detection and recognition algorithms to analyze the captured classroom scenes in real time to determine whether there are faces in the captured classroom scenes that match the facial information of the course instructor.

[0010] When a face matching the course instructor's facial information is detected in the classroom video, the attendance time is obtained. The attendance time is then compared with the class time specified in the timetable to determine whether the instructor is on time or late.

[0011] When the preset time before the end of the course is reached, the attendance camera used for teacher attendance will be activated for the second time.

[0012] After the attendance camera is triggered for the second time, it captures classroom dismissal footage at a preset second frequency and uses face detection and recognition algorithms to analyze the captured classroom dismissal footage in real time to determine whether there is a face in the captured classroom class footage that matches the face information of the course instructor.

[0013] If a face matching the teacher's facial information is detected in the classroom dismissal screen and this match continues until the end of the class, it is determined that the teacher has successfully completed the lesson.

[0014] In one implementation, the method for taking classroom attendance further includes:

[0015] In addition to determining whether a teacher is punctual or late, the system also records the timestamp of the attendance time and the corresponding teacher's photo.

[0016] In one implementation, the method for taking classroom attendance further includes:

[0017] If no face matching the course instructor's facial information is detected from the start time to the end time of the course, it is determined that the instructor is absent.

[0018] In one implementation, the method for taking classroom attendance further includes:

[0019] If no face can be identified that matches the course instructor's facial information, or if a face is identified that matches the course instructor's facial information but cannot be identified until the end of class, the teacher is deemed to have left early.

[0020] In one implementation, the method for taking classroom attendance further includes:

[0021] While initially identifying teachers leaving early, the system also recorded the corresponding timestamps and images of the classroom after class.

[0022] In one implementation, before the process of obtaining the course information of the current course, the method further includes:

[0023] Determine the end time of the course;

[0024] The process of determining the end time of the course includes:

[0025] Get class schedule information;

[0026] Determine whether the current course is a regular course or a combined consecutive course based on the timetable information;

[0027] If the current course is a regular class period, the end time of the current class period shall be taken as the end time of the course.

[0028] When the current course is an integrated consecutive class, the end time of the last class in the integrated consecutive class is taken as the end time of the course.

[0029] In one implementation, the integrated consecutive class types include: a first type and a second type, wherein the number of consecutive classes in the first type is greater than the number of consecutive classes in the second type;

[0030] The process of determining the end time of the course also includes:

[0031] When the current course is an integrated consecutive class, read the class information corresponding to the class that ends with the first type;

[0032] Determine whether the lesson information matches the course information of the current course;

[0033] If a match is found, the end time of the corresponding lesson will be used as the end time of the last lesson in the integrated consecutive lessons.

[0034] If they do not match, the end time of the lesson corresponding to the end of the second type will be used as the end time of the last lesson of the integrated consecutive lessons.

[0035] Secondly, the present invention provides a device for taking classroom teacher attendance, comprising:

[0036] The acquisition module is used to acquire course information for the current course, wherein the course information includes: course start time, course end time, and facial information of the course instructor;

[0037] The startup module is used to trigger the startup of the attendance camera used for teacher attendance for the first time at the startup trigger time point; wherein, the startup trigger time point is determined based on the start time point of the current course, and the startup trigger time point is no later than the course start time point;

[0038] The analysis module is used to capture classroom scenes at a preset first frequency after the attendance camera is first triggered and started. It uses face detection and recognition algorithms to analyze the captured classroom scenes in real time and determine whether there are faces in the captured classroom scenes that match the face information of the course instructor.

[0039] The judgment module is used to determine the attendance time when a face matching the face information of the course instructor is detected in the classroom screen. The attendance time is then compared with the class time specified in the timetable to determine whether the teacher is on time or late.

[0040] The startup module is also used to trigger the attendance camera for teacher attendance a second time when a preset time before the end of the course is reached.

[0041] The analysis module is also used to capture classroom dismissal scenes at a preset second frequency after the attendance camera is triggered for the second time, and to analyze the captured classroom dismissal scenes in real time using face detection and recognition algorithms to determine whether there are faces in the captured classroom teaching scenes that match the face information of the course instructor.

[0042] The determination module is also used to determine that the teacher has completed the teaching normally when it is determined that there is a face matching the face information of the course instructor in the classroom dismissal screen and the face can continue until the end of the class.

[0043] Thirdly, the present invention provides a computer device including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the program to implement the method of any of the above embodiments.

[0044] Fourthly, the present invention provides a computer-readable storage medium having a computer program stored thereon, characterized in that the program, when executed by a processor, implements the method of any of the above embodiments.

[0045] This invention consists of two stages: class attendance recognition and get out of class dismissal attendance recognition. The class attendance recognition stage determines whether the teacher is on time or late, and the get out of class dismissal attendance recognition stage determines whether the teacher leaves early. Both stages use facial recognition to ensure that the system can accurately identify which teacher is in the classroom, avoiding misidentification of other people (such as other teachers, teaching assistants, and students) as the instructor. This automates the attendance process without manual intervention, saving manpower and avoiding human error. Attached Figure Description

[0046] Figure 1 This is a schematic diagram of the overall process of one embodiment of the present invention.

[0047] Figure 2 This is the course schedule of Embodiment 1 of the present invention.

[0048] Figure 3 This is a schematic diagram of the overall structure of Embodiment 2 of the present invention. Detailed Implementation

[0049] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0050] It should be noted that the terms "first, second, ..." used in the embodiments of the present invention are merely used to distinguish similar objects and do not represent a specific ordering of objects. It is understood that "first, second, ..." can be interchanged in a specific order or sequence where permissible. It should be understood that the objects distinguished by "first, second, ..." can be interchanged where appropriate so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein.

[0051] Example 1

[0052] Please see Figure 1 , Figure 1 This is a flowchart illustrating a method for classroom teacher attendance according to Embodiment 1 of the present invention. The method includes steps S110, S120, S130, S140, S150, S160, and S170. It should be noted that steps S110, S120, S130, S140, S150, S160, and S170 are merely reference numerals used to clearly explain the embodiment and the accompanying drawings. Figure 1 The correspondence is not intended to limit the order of steps in this embodiment.

[0053] Step S110: Obtain the course information of the current course, wherein the course information includes: course start time, course end time, and the facial information of the course instructor;

[0054] Step S120: At the start trigger time point, the attendance camera used for teacher attendance is triggered for the first time; wherein, the start trigger time point is determined according to the start time point of the current course, and the start trigger time point is not later than the start time point of the course;

[0055] Step S130: After the attendance camera is triggered and started for the first time, it captures classroom teaching scenes at a preset first frequency, and uses face detection and recognition algorithms to analyze the captured classroom teaching scenes in real time to determine whether there are faces in the captured classroom teaching scenes that match the face information of the course instructor.

[0056] Step S140: When it is determined that there is a face in the classroom teaching screen that matches the face information of the course instructor, the attendance time is obtained, and the attendance time is compared with the class time specified in the timetable to determine whether the teacher is on time or late.

[0057] Step S150: When the preset time before the end of the course is reached, the attendance camera used for teacher attendance is activated for the second time.

[0058] Step S160: After the attendance camera is triggered for the second time, it captures the classroom dismissal scene at a preset second frequency, and uses face detection and recognition algorithms to analyze the captured classroom dismissal scene in real time to determine whether there is a face in the captured classroom dismissal scene that matches the face information of the course instructor.

[0059] Step S170: When it is determined that there is a face in the classroom dismissal screen that matches the face information of the course instructor, and this face information continues until the end of the class, it is determined that the instructor has completed the teaching normally.

[0060] Based on the pre-imported electronic timetable, the system can determine the start and end times of each class, as well as the instructor for each class. By linking the instructors to a teacher facial recognition database, the system can obtain the facial information of the instructors for each class. Specifically, a teacher facial recognition database can be pre-built before linking. The process of building the database can include: collecting frontal facial photos or video clips of all instructors in the school, extracting facial features using image processing and artificial intelligence technologies, binding these features with the teacher's identity information, and storing them in the system's database to form the teacher facial recognition database. In addition, the system needs to regularly update or supplement the facial information of newly hired teachers. Step S110 obtains, for example, the course information of the current course obtained through the above method.

[0061] In addition, for classroom scenarios, teachers usually arrive at the classroom before the start time of the class. Therefore, a start-up trigger time can be determined before the start time of the class. When the start-up trigger time is reached, the attendance camera used for teacher attendance will be activated to immediately record the teacher's attendance.

[0062] It should be noted that this method does not restrict the selection of attendance cameras used for teacher attendance. They can be dedicated attendance cameras or other camera equipment, such as panoramic cameras or close-up cameras for teachers.

[0063] In one implementation, the start-up trigger time point is the start-up time point of the classroom recording and broadcasting device.

[0064] As mentioned earlier, this start time must be earlier than or synchronized with the teacher's class time to ensure effective attendance verification. For recording equipment, since it is inherently linked to the class schedule and will also be activated, its start time is the most natural and reliable.

[0065] Step S130 is the core of the attendance tracking process. After the attendance camera is activated, the system continuously captures classroom footage at a preset first frequency. This preset first frequency is typically set to a relatively high frequency. Then, face detection and recognition algorithms are used to analyze the footage in real time. During the analysis, the captured faces are compared with the obtained facial information of the course instructors to determine if the instructors' faces are present. This step involves real-time monitoring of the classroom to ensure that teacher attendance is captured as soon as possible.

[0066] During the judgment process in step S130, once a face matching the teacher's face database is detected, the process proceeds to step S140, where the moment a matching face is detected is defined as the teacher's attendance time. The system compares the recorded attendance time with the class time specified in the timetable to determine whether the teacher is punctual or late, thus obtaining the teacher's attendance result.

[0067] In one implementation, the method for taking classroom attendance by teachers further includes:

[0068] In addition to determining whether a teacher is punctual or late, the system also records the timestamp of the attendance time and the corresponding teacher's photo.

[0069] This method records the timestamp of attendance time and the corresponding teacher's photo, and archives the information in a timely manner to provide an accurate basis for subsequent punctuality assessment.

[0070] In one implementation, step S141 is also included.

[0071] Step S141: If no face matching the course instructor's facial information is detected from the start trigger time to the course end time, it is determined that the instructor is absent.

[0072] If no teacher's face is recognized from the start of attendance to the end of class, it can be determined that the teacher has not been in the classroom. Therefore, the system determines that the teacher is absent and will continue to record this status until the class ends naturally.

[0073] Steps S120 to S140 are the first trigger to start the attendance camera, which is used to determine whether the teacher has arrived at the classroom. However, even if the teacher has arrived at the classroom, there is a possibility that they may leave early, so a second trigger is needed to start the attendance camera to determine whether the teacher has left early.

[0074] Specifically, in step S150, the system presets a certain number of minutes before the end time of each class, for example, 5 minutes before the end time, and then triggers the recognition function of the attendance camera used for teacher attendance for the second time.

[0075] The real-time monitoring process in step S160 is similar to that in step S130. After the attendance camera is started for the second time, the system continues to capture classroom images at a preset second frequency. The preset second frequency is generally a relatively high frequency, which can be the same as or different from the first frequency.

[0076] The judgment method in step S170 differs slightly from that in step S140. Since step S170 determines whether the teacher left early, i.e., whether the teacher left before the end of get out of class, this judgment process in step S170 must continue until the end of the class. In other words, the real-time monitoring process in step S160 must continue until the end of the class, and the judgment process in step S170 must also continue until the end of the class. If a face matching the course instructor's facial information is consistently obtained throughout this process, then it can be determined that the teacher completed the lesson normally and did not leave early.

[0077] In one implementation, the method for taking attendance by classroom teachers further includes step S171.

[0078] Step S171: If no face is found that matches the face information of the course instructor, or if a face is found that matches the face information of the course instructor but cannot be used until the end of class, it is determined that the teacher has left early.

[0079] Step S171 is a supplement to step S170. If no face is detected, or the face disappears before the end of class, it can be determined that the teacher left early.

[0080] In one implementation, the method for taking classroom attendance by teachers further includes:

[0081] While initially identifying teachers leaving early, the system also recorded the corresponding timestamps and images of the classroom after class.

[0082] In this method, the timestamp of the early departure time and the corresponding classroom dismissal screen are recorded. As mentioned above, steps S160 and S170 are a continuous determination process. Therefore, in this embodiment, only the record of the first determination is recorded, and then the information is archived in a timely manner to provide an accurate basis for subsequent timeliness determination.

[0083] This method consists of two stages: class attendance recognition and get out of class dismissal attendance recognition. The class attendance recognition stage determines whether the teacher is on time or late, and the get out of class dismissal attendance recognition stage determines whether the teacher leaves early. Both stages use facial recognition to ensure that the system can accurately identify which teacher is in the classroom, avoiding misidentification of other people (such as other teachers, teaching assistants, and students) as the instructor. This automates the attendance process without manual intervention, saving manpower and avoiding human error.

[0084] In one implementation, before the process of obtaining the course information of the current course, the method further includes:

[0085] Determine the end time of the course;

[0086] The process of determining the end time of the course includes steps S210, S220, S230 and S240.

[0087] Step S210: Obtain the class schedule information;

[0088] Step S220: Determine whether the current course is a regular course or an integrated consecutive course based on the timetable information;

[0089] Step S230: If the current course is a regular class period, the end time of the current class period shall be taken as the end time of the course.

[0090] Step S240: When the current course is an integrated consecutive class, the end time of the last class of the integrated consecutive class is taken as the end time of the course.

[0091] like Figure 2 As shown, Figure 2 This is a course schedule. The schedule includes regular classes (one class period) and multi-session classes (several consecutive classes). For regular classes, attendance can be checked class by class; however, checking attendance class by class for multi-session classes is too cumbersome. In this case, we can directly check whether the teacher left early at the end of the last class of the multi-session class. Accordingly, in this implementation, the end time of the last class of the multi-session class is used as the course end time, thus only one early departure needs to be checked, saving resources.

[0092] In one implementation, the integrated consecutive class types include: a first type and a second type, wherein the number of consecutive classes in the first type is greater than the number of consecutive classes in the second type;

[0093] The process of determining the end time of the course also includes steps S250 and S260.

[0094] Step S250: When the current course is an integrated consecutive class, read the class information corresponding to the class that ends with the first type;

[0095] Step S260: Determine whether the lesson information matches the course information of the current course;

[0096] If a match is found, the end time of the corresponding lesson will be used as the end time of the last lesson in the integrated consecutive lessons.

[0097] If they do not match, the end time of the lesson corresponding to the end of the second type will be used as the end time of the last lesson of the integrated consecutive lessons.

[0098] like Figure 2 As shown in the course schedule, there are two types of integrated courses: one with 4 lessons per session (second column from the right in the figure) and one with 6 lessons per session (first column from the right in the figure). In this implementation, the one with 6 lessons per session is the first type, and the one with 4 lessons per session is the second type.

[0099] In this embodiment, it is first determined whether it is a first-type course. Therefore, in step S250, it is assumed that the course ends with a first-type course, and the lesson information of the corresponding lesson is read. Figure 2 In this example, assuming a class consists of 6 periods, the lesson information for the sixth period is retrieved. After retrieval, step S260 makes a judgment. Continuing with the example above, if the conclusion is that the sixth period is the same as the current course, then it can be determined as the first type; otherwise, it is the second type.

[0100] In real-world scenarios, the course information obtained in step S110 is often only the information for the current lesson. Furthermore, integrated consecutive lessons frequently include two types, making it difficult to determine the type of integrated consecutive lesson even after step S220. However, after processing by this embodiment, the type of integrated consecutive lesson can be determined. Once the result is determined, the end time of the corresponding lesson can be calculated, thus enabling early departure to be detected only once for an integrated course.

[0101] Example 2

[0102] Corresponding to the method in Example 1, such as Figure 3 As shown, the present invention also provides a classroom facial recognition attendance device 3, comprising: an acquisition module 310, a startup module 320, an analysis module 330, and a judgment module 340.

[0103] The acquisition module 310 is used to acquire course information of the current course, wherein the course information includes: course start time, course end time, and facial information of the course instructor;

[0104] The startup module 320 is used to trigger the startup of the attendance camera used for teacher attendance for the first time at the startup trigger time point; wherein, the startup trigger time point is determined according to the start time point of the current course, and the startup trigger time point is not later than the start time point of the course;

[0105] The analysis module 330 is used to capture classroom teaching scenes at a preset first frequency after the attendance camera is first triggered and started, and to analyze the captured classroom teaching scenes in real time using face detection and recognition algorithms to determine whether there are faces in the captured classroom teaching scenes that match the face information of the course instructor.

[0106] The judgment module 340 is used to determine the attendance time when it determines that there is a face in the classroom teaching screen that matches the face information of the course instructor. It then compares the attendance time with the class time specified in the timetable to determine whether the teacher is on time or late.

[0107] The startup module is also used to trigger the attendance camera for teacher attendance a second time when a preset time before the end of the course is reached.

[0108] The analysis module is also used to capture classroom dismissal scenes at a preset second frequency after the attendance camera is triggered for the second time, and to analyze the captured classroom dismissal scenes in real time using face detection and recognition algorithms to determine whether there are faces in the captured classroom teaching scenes that match the face information of the course instructor.

[0109] The determination module is also used to determine that the teacher has completed the teaching normally when it is determined that there is a face matching the face information of the course instructor in the classroom dismissal screen and the face can continue until the end of the class.

[0110] In one implementation, the determination module is also used to record the timestamp of the attendance time and the corresponding teacher photo while determining whether the teacher is on time or late.

[0111] In one implementation, the determination module is further configured to determine that the teacher is absent if no face matching the teacher's facial information is detected from the start trigger time to the end time of the course.

[0112] In one implementation, the determination module is further configured to determine that the teacher has left early if it is determined that no face matches the facial information of the course instructor, or if a face matches the facial information of the course instructor but cannot be maintained until the end of the class.

[0113] In one implementation, the determination module is also used to record the corresponding timestamp and the corresponding classroom dismissal screen when it first determines that a teacher has left early.

[0114] In one embodiment, the classroom facial recognition attendance device further includes:

[0115] The time determination module is used to determine the end time of the course;

[0116] The process of determining the end time of the course includes:

[0117] Get class schedule information;

[0118] Determine whether the current course is a regular course or a combined consecutive course based on the timetable information;

[0119] If the current course is a regular class period, the end time of the current class period shall be taken as the end time of the course.

[0120] When the current course is an integrated consecutive class, the end time of the last class in the integrated consecutive class is taken as the end time of the course.

[0121] In one implementation, the integrated consecutive class types include: a first type and a second type, wherein the number of consecutive classes in the first type is greater than the number of consecutive classes in the second type;

[0122] The process of determining the end time of the course also includes:

[0123] When the current course is an integrated consecutive class, read the class information corresponding to the class that ends with the first type;

[0124] Determine whether the lesson information matches the course information of the current course;

[0125] If a match is found, the end time of the corresponding lesson will be used as the end time of the last lesson in the integrated consecutive lessons.

[0126] If they do not match, the end time of the lesson corresponding to the end of the second type will be used as the end time of the last lesson of the integrated consecutive lessons.

[0127] This device consists of two stages: class attendance recognition and get out of class dismissal attendance recognition. The class attendance recognition stage determines whether the teacher is on time or late, and the get out of class dismissal attendance recognition stage determines whether the teacher leaves early. Both stages use facial recognition to ensure that the system can accurately identify which teacher is in the classroom, avoiding misidentification of other people (such as other teachers, teaching assistants, and students) as the instructor. This automates the attendance process without manual intervention, saving manpower and avoiding human error.

[0128] Example 3

[0129] This invention also provides a storage medium storing computer instructions that, when executed by a processor, implement the classroom teacher attendance method of any of the above embodiments.

[0130] Those skilled in the art will understand that all or part of the steps of the above method embodiments can be implemented by hardware related to program instructions. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it performs the steps of the above method embodiments. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, random access memory (RAM), read-only memory (ROM), magnetic disks, or optical disks.

[0131] Alternatively, if the integrated units of this invention are implemented as software functional modules and sold or used as independent products, they can also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of this invention, or the parts that contribute to related technologies, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, terminal, or network device, etc.) to execute all or part of the methods of the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as mobile storage devices, RAM, ROM, magnetic disks, or optical disks.

[0132] Corresponding to the computer storage medium described above, one embodiment also provides a computer device, which includes a memory, an encoder, and a computer program stored in the memory and executable on the encoder, wherein the encoder executes the program to implement any of the classroom teacher attendance methods described in the above embodiments.

[0133] The aforementioned computer equipment consists of two stages: class attendance recognition and get out of class dismissal attendance recognition. The class attendance recognition stage determines whether the teacher is on time or late, and the get out of class dismissal attendance recognition stage determines whether the teacher leaves early. Both stages use facial recognition to ensure that the system can accurately identify which teacher is in the classroom, avoiding misidentification of other people (such as other teachers, teaching assistants, and students) as the instructor. This automates the attendance process without manual intervention, saving manpower and preventing human error.

[0134] The technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above 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.

[0135] Obviously, the above embodiments of the present invention are merely examples for clearly illustrating the present invention, and are not intended to limit the implementation of the present invention. Those skilled in the art can make other variations or modifications based on the above description. It is neither necessary nor possible to exhaustively describe all embodiments here. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention should be included within the scope of protection of the claims of the present invention.

Claims

1. A method for taking classroom teacher attendance, characterized in that, include: Obtain the course information for the current course, including: course start time, course end time, and the facial information of the course instructor; At the activation trigger time, the attendance camera used for teacher attendance is activated for the first time; wherein, the activation trigger time is determined based on the start time of the current course, and the activation trigger time is no later than the start time of the course; After the attendance camera is triggered for the first time, it captures classroom scenes at a preset first frequency and uses face detection and recognition algorithms to analyze the captured classroom scenes in real time to determine whether there are faces in the captured classroom scenes that match the facial information of the course instructor. When a face matching the course instructor's facial information is detected in the classroom video, the attendance time is obtained. The attendance time is then compared with the class time specified in the timetable to determine whether the instructor is on time or late. When the preset time before the end of the course is reached, the attendance camera used for teacher attendance will be activated for the second time. After the attendance camera is triggered for the second time, it captures classroom dismissal footage at a preset second frequency and uses face detection and recognition algorithms to analyze the captured classroom dismissal footage in real time to determine whether there is a face in the captured classroom class footage that matches the face information of the course instructor. If a face matching the teacher's facial information is detected in the classroom dismissal screen and this match continues until the end of the class, it is determined that the teacher has successfully completed the lesson.

2. The method for taking classroom teacher attendance according to claim 1, characterized in that, Also includes: In addition to determining whether a teacher is punctual or late, the system also records the timestamp of the attendance time and the corresponding teacher's photo.

3. The method for taking classroom teacher attendance according to claim 1, characterized in that, Also includes: If no face matching the course instructor's facial information is detected from the start time to the end time of the course, it is determined that the instructor is absent.

4. The method for classroom teacher attendance according to claim 1, characterized in that, Also includes: If no face can be identified that matches the course instructor's facial information, or if a face is identified that matches the course instructor's facial information but cannot be identified until the end of class, the teacher is deemed to have left early.

5. The method for classroom teacher attendance according to claim 4, characterized in that, Also includes: While initially identifying teachers leaving early, the system also recorded the corresponding timestamps and images of the classroom after class.

6. The method for taking classroom teacher attendance according to claim 1, characterized in that, Before the process of obtaining the course information of the current course, it also includes: Determine the end time of the course; The process of determining the end time of the course includes: Get class schedule information; Determine whether the current course is a regular course or a combined consecutive course based on the timetable information; If the current course is a regular class period, the end time of the current class period shall be taken as the end time of the course. When the current course is an integrated consecutive class, the end time of the last class in the integrated consecutive class is taken as the end time of the course.

7. The method for classroom teacher attendance according to claim 6, characterized in that, The integrated consecutive class types include: a first type and a second type, wherein the number of consecutive classes in the first type is greater than the number of consecutive classes in the second type; The process of determining the end time of the course also includes: When the current course is an integrated consecutive class, read the class information corresponding to the class that ends with the first type; Determine whether the lesson information matches the course information of the current course; If a match is found, the end time of the corresponding lesson will be used as the end time of the last lesson in the integrated consecutive lessons. If they do not match, the end time of the lesson corresponding to the end of the second type will be used as the end time of the last lesson of the integrated consecutive lessons.

8. A device for taking classroom teacher attendance, characterized in that, include: The acquisition module is used to acquire course information for the current course, wherein the course information includes: course start time, course end time, and facial information of the course instructor; The startup module is used to trigger the startup of the attendance camera used for teacher attendance for the first time at the startup trigger time point; wherein, the startup trigger time point is determined based on the start time point of the current course, and the startup trigger time point is no later than the course start time point; The analysis module is used to capture classroom scenes at a preset first frequency after the attendance camera is first triggered and started. It uses face detection and recognition algorithms to analyze the captured classroom scenes in real time and determine whether there are faces in the captured classroom scenes that match the face information of the course instructor. The judgment module is used to determine the attendance time when a face matching the face information of the course instructor is detected in the classroom screen. The attendance time is then compared with the class time specified in the timetable to determine whether the teacher is on time or late. The startup module is also used to trigger the attendance camera for teacher attendance a second time when a preset time before the end of the course is reached. The analysis module is also used to capture classroom dismissal scenes at a preset second frequency after the attendance camera is triggered for the second time, and to analyze the captured classroom dismissal scenes in real time using face detection and recognition algorithms to determine whether there are faces in the captured classroom teaching scenes that match the face information of the course instructor. The determination module is also used to determine that the teacher has completed the teaching normally when it is determined that there is a face matching the face information of the course instructor in the classroom dismissal screen and the face can continue until the end of the class.

9. A computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the program, it implements the method as described in any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the method as described in any one of claims 1-7.

Images