An internet of things-based double-carbon target education scene integrated management system

Abstract

The application discloses a double-carbon target education scene integrated management system based on Internet of Things, relates to the technical field of integrated management, and comprises an image acquisition and contour processing module, a contour in-out analysis module, and a human body contour quantity statistics and prompting module.The image acquisition and contour processing module is used for real-time acquisition and processing to obtain contour data.The contour in-out analysis module is used for symbol change detection on the contour data to obtain a contour in signal or a contour out signal.The human body contour quantity statistics and prompting module is used for prompting the closing of indoor electrical equipment when there is only the last person or the same batch of people leaving in the indoor according to the contour in signal or the contour out signal.The application can accurately determine the entry and exit of personnel by three-dimensional coordinate system, barycentric coordinate symbol change, displacement vector analysis, and normal path screening combined with in-out threshold values, dynamically track the human body contour ID, predict the leaving personnel, and remind the closing when the indoor is about to be unoccupied and the equipment is turned on, so that energy waste is avoided, and the double-carbon target is implemented.

Description

Technical Field

[0001] This invention relates to the field of integrated management technology, specifically to an integrated management system for dual-carbon target education scenarios based on the Internet of Things. Background Technology

[0002] Promoting dual-carbon goals in the education sector and cultivating low-carbon awareness among young people through courses and practices to reserve talent for the future low-carbon economy is not only a necessary requirement for cultivating talents with green values ​​and sustainable development capabilities, but also a responsibility of the education system itself as a high-energy-consuming public institution to achieve energy conservation and emission reduction and play a demonstrative role. However, when teachers and students leave the classroom and forget to turn off the equipment, causing the equipment to continue to consume electricity, it not only wastes energy, but also violates the educational concept of dual-carbon goals. Summary of the Invention

[0003] Technical problems to be solved

[0004] To address the shortcomings of existing technologies, this invention provides an integrated management system for dual-carbon educational scenarios based on the Internet of Things. This system solves the problem of continuous power consumption caused by teachers and students leaving equipment on after leaving school, which not only wastes energy but also deviates from the educational practice and concept of dual-carbon goals.

[0005] Technical solution

[0006] To achieve the above objectives, the present invention is implemented through the following technical solution: an integrated management system for dual-carbon target education scenarios based on the Internet of Things, comprising the following specific modules: an image acquisition and contour processing module: acquiring and processing contour data in real time; a contour entry and exit analysis module: detecting symbol changes in the contour data to obtain contour entry signals or contour exit signals; and a human contour quantity statistics and prompting module: prompting the last person or the same group of people leaving the room to turn off indoor electrical equipment based on the contour entry signal or contour exit signal.

[0007] Further, the specific steps for obtaining the contour entry signal or contour exit signal are as follows: The contour data includes outdoor contours, indoor contours, and entrance / exit contours. A three-dimensional coordinate system is established with the center point of the entrance / exit contours as the origin. The positive direction of the entrance / exit contours pointing horizontally into the interior is set as the normal vector. A certain dimension of the three-dimensional coordinate system is parallel to the normal vector and is denoted as the x-axis. The three-dimensional coordinates within both the outdoor and indoor contours are averaged to obtain the centroid of each contour. The contour entry signal is obtained by observing the change in the sign of the centroid coordinates on the x-axis after the outdoor contour moves into the interior. Similarly, the contour exit signal can be obtained.

[0008] Furthermore, the specific method for obtaining the contour entry signal is as follows: Let the coordinate of the centroid of the outdoor contour on the x-axis be x1, and the coordinate of the centroid of the indoor contour on the x-axis be x2. According to the time series, when the product of x1 and x2 is less than zero, the contour entry signal is obtained. The dimension that is perpendicular to the normal vector is denoted as the y-axis. The displacement vector of the outdoor contour moving to the indoor area intersects with the y-axis to obtain the continuous contour entry signal.

[0009] Furthermore, the specific method for obtaining the continuous entry signal of the contour is as follows: In the time series, the displacement vector of the outdoor contour moving to the indoor contour intersects the y-axis, obtaining the intersection point P0. Let the centroid coordinates of the outdoor contour be P1(x1,y1,z1) and the centroid coordinates of the indoor contour be P2(x2,y2,z2), obtaining the displacement vector as follows: p0 = p1 + t × (p2 - p1), where p2 - p1 represents t represents starting from P1 in By calculating the movement ratio on the t, we establish a system of equations about t, such that t simultaneously satisfies x = 0 and z = 0, thus obtaining the continuous entry signal of the contour. The interval of the inlet and outlet contours on the y-axis is set as the entry and exit threshold. The displacement vector of the outdoor contour moving to the indoor area and passing through the entry and exit threshold is denoted as the normal continuous entry signal of the contour.

[0010] Furthermore, the specific method for obtaining the normal continuous entry signal of the contour is as follows: Based on experiments, the lower limit of the entry / exit threshold is set to y. 下 The upper limit of the entry and exit threshold is y. 上 Then, based on the condition that the displacement vector of the outdoor contour moving to the indoor area intersects the y-axis in the time series, the coordinate range of the intersection point P0 on the y-axis is within the range of y... 下 With y 上 Between these points, a normal, continuous entry signal for the contour is obtained.

[0011] Furthermore, in the human body contour quantity statistics and prompting module, if a normal and continuous entry signal of the contour is collected, it is recorded as the target contour entering. The target contour entering is detected by the human body contour detection model. If the target contour entering is detected as a human body contour, an ID is added to the human body contour, and the number of indoor IDs is counted. If the number of indoor IDs is greater than or equal to one, the on / off status of indoor electrical equipment is monitored. If the target contour entering is not a human body contour, no operation is performed.

[0012] Furthermore, in the human body contour quantity statistics and prompting module, similarly, if a normal continuous outgoing contour signal is collected, it is recorded as the outgoing target contour. If the outgoing target contour has an ID, this ID is deleted, and the number of indoor IDs is updated. It also predicts whether the subsequent outgoing target contours have IDs. If the outgoing target contours are predicted to have IDs, this ID is pre-deleted, and the number of indoor IDs is pre-updated until the predicted number of indoor IDs is equal to zero and the indoor electrical equipment is in the on state. Then, a reminder is issued to the indoor area. If the predicted and detected outgoing target contours have no IDs or the indoor electrical equipment is in the off state, no operation is performed.

[0013] Furthermore, the specific steps for predicting the exit target contour are as follows: An experimentally determined distance threshold is established to trigger the prediction of whether the subsequent exit target contour possesses an ID, denoted as the exit distance threshold. The displacement vector of this exit target contour is denoted as... Based on experiments, a threshold value was set for the displacement vector from the target contour to the inlet / outlet, denoted as the direction threshold. Any displacement vector within this direction threshold is denoted as... Through the and Cosine similarity calculation is performed. If the cosine similarity is equal to one, then the target outline is predicted if the target outline is within the exit distance threshold and the cosine similarity is equal to one.

[0014] Furthermore, the specific method for achieving a cosine similarity of one is as follows: Where 1 represents a cosine similarity of one. This represents the displacement vector that delineates the target contour. This represents any displacement vector within a direction threshold. express The model, express The model.

[0015] Further, the specific steps for predicting that the number of indoor IDs is equal to zero are as follows: When the exit target contour is detected to be a human contour, continue to detect the exit interval time for human contours that simultaneously satisfy the exit target contour being within the exit distance threshold and having a cosine similarity of one. Obtain the exit interval time between the previous human contour and the next human contour, and record it as the interval time. Experimentally, set the same batch of time thresholds. If the interval time is within the same batch of time thresholds, then when pre-updating the number of indoor IDs, subtract the number of the corresponding human contours in one go. If the interval time is not within the same batch of time thresholds, then when pre-updating the number of indoor IDs, subtract the number of human contours in one go, and pre-update the number of indoor IDs in all cases. Continue in this manner until the number of predicted indoor IDs is equal to zero.

[0016] Beneficial effects

[0017] Compared with the prior art, the embodiments of the present invention have at least the following advantages or beneficial effects:

[0018] 1. By analyzing the three-dimensional coordinate system, the change of the center of gravity coordinate sign, and the displacement vector, combined with the entry and exit threshold, normal paths are screened to eliminate interference and ensure the accuracy and reliability of personnel entry and exit status judgment.

[0019] 2. By dynamically tracking human contour IDs and combining distance, direction thresholds, and time intervals to predict people going out, educational scenario reminders are issued when only one person or a group of people are about to leave the room and the device is turned on, thus avoiding energy waste and achieving dual carbon goals.

[0020] Of course, any product implementing this invention does not necessarily need to achieve all of the advantages described above at the same time. Attached Figure Description

[0021] Figure 1 This invention presents a structural diagram of an integrated management system for dual-carbon target education scenarios based on the Internet of Things. Detailed Implementation

[0022] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0023] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the terms "comprising," "including," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus.

[0024] like Figure 1 As shown, this embodiment of the invention provides an integrated management system for dual-carbon target education scenarios based on the Internet of Things, comprising the following specific modules:

[0025] Image Acquisition and Contour Processing Module: This module acquires image data in real time via cameras positioned both indoors and outdoors. Based on IoT technology, it interconnects and collaboratively calibrates indoor and outdoor image data. Multi-source image data is then stitched together using image registration and fusion algorithms, such as the SIFT algorithm. Filtering and noise reduction are applied to improve image quality. Image contour segmentation and motion tracking algorithms are used to process the data. Contour segmentation algorithms, such as the Sobel algorithm, are used to segment human figures or objects in the image data. Motion tracking algorithms, such as the Lucas-Kanade optical flow method, are used to track the motion of human figures or objects in the image data, resulting in contour data. This contour data includes outdoor contours, indoor contours, and entrance / exit contours. Outdoor contours are moved indoors to become indoor contours, and indoor contours are moved outdoors to become outdoor contours. Entrance / exit contours are denoted as entrances / exits.

[0026] Contour Entry / Exit Analysis Module: A three-dimensional coordinate system is established with the center point of the entrance / exit as the origin, comprising x, y, and z axes. The positive horizontal direction pointing inwards from the entrance / exit is defined as the normal vector. A dimension of the three-dimensional coordinate system parallel to the normal vector is denoted as the x-axis. The 3D coordinates of both the outdoor and indoor contours are averaged to obtain the centroid of each contour. Since the sign of the centroid's x-axis coordinate changes after the outdoor contour moves indoors, the change in the sign of the centroid's x-axis coordinate after the outdoor contour moves indoors is used to obtain the contour entry signal. The dimension perpendicular to the normal vector is denoted as the y-axis. The displacement vector of the outdoor contour moving into the interior intersects with the y-axis to obtain a continuous entry signal. This prevents camera malfunctions from causing the outdoor contour to suddenly appear indoors and become the indoor contour. The interval between the entrance and exit on the y-axis is set as the entry and exit threshold. The displacement vector of the outdoor contour moving into the interior and passing through the entry and exit threshold is recorded as the normal continuous entry signal of the contour. This prevents the outdoor contour from entering the interior through abnormal entrances and exits and being detected by the system. Abnormal entrances and exits refer to entrances and exits other than doors to prevent situations other than dual-carbon target education from misleading the system. Similarly, the displacement vector of the indoor contour moving into the exterior and passing through the entry and exit threshold is recorded as the normal continuous exit signal of the contour.

[0027] The specific method for obtaining the contour entry signal is as follows:

[0028] Let x1 be the coordinate of the centroid of the outdoor profile on the x-axis and x2 be the coordinate of the centroid of the indoor profile on the x-axis. Since the center point of the entrance and exit is taken as the origin, x1 and x2 have opposite signs. Therefore, according to the time series, the product of x1 and x2 is less than zero, and the profile entry signal is obtained.

[0029] The specific method for obtaining the continuous entry signal of the contour is as follows:

[0030] Since one of the properties of vectors is continuity, the displacement vector of the outdoor contour moving to the indoor contour in the time series intersects the y-axis, resulting in an intersection point P0. Let the centroid coordinates of the outdoor contour be P1(x1,y1,z1) and the centroid coordinates of the indoor contour be P2(x2,y2,z2). Therefore, the displacement vector is... The intersection point P0 represents the point where, starting from P1, ... The shift ratio is p0 = p1 + t × (p2 - p1), where p2 - p1 represents t represents starting from P1 in The movement ratio t ranges from zero to one. Since the intersection point P0 is 0 on both the x-axis and z-axis, a system of equations is established for t, such that t simultaneously satisfies x = 0 and z = 0. That is, it satisfies that the displacement vector of the outdoor contour moving to the indoor area under the time series intersects the y-axis, thus obtaining the continuous entry signal of the contour.

[0031] The specific method for obtaining the normal continuous entry signal of the contour is as follows:

[0032] Based on experiments, the lower limit of the entry and exit threshold is set to y. 下 The upper limit of the entry and exit threshold is y. 上 Then, based on the condition that the displacement vector of the outdoor contour moving to the indoor area intersects the y-axis in the time series, the coordinate range of the intersection point P0 on the y-axis is within the range of y... 下 With y 上 Between these points, a normal, continuous entry signal for the contour is obtained.

[0033] Human Contour Count and Alert Module: If a normal, continuous entry signal is collected, indicating that an outdoor contour has entered the interior and become an indoor contour, it is recorded as an entering target contour. The module then uses a human contour detection model, such as the YOLO model, to detect whether the entering target contour is a human contour. If a human contour is detected, an ID is added to that contour to determine its uniqueness, and the number of indoor IDs is counted. If the number of indoor IDs is greater than or equal to one, the on / off status of indoor electrical equipment is monitored. If an object contour is detected, no action is taken. If a normal, continuous exit signal is collected, it is recorded as an exiting target contour. If an exit... If the target outline has an ID, delete that ID and update the number of indoor IDs. Predict whether subsequent exit target outlines will have IDs. If the exit target outline is predicted to have an ID, delete that ID and continue to update the number of indoor IDs until the predicted number of indoor IDs equals zero and indoor electrical equipment is on. Then, issue a reminder to the last remaining person or group of people about to leave, reminding them to turn off the equipment. This reminder is an educational scenario, teaching teachers and students to remember to turn off indoor electrical equipment when leaving the classroom to avoid continuous power consumption, thus preventing energy waste and violating the educational philosophy of dual-carbon goals. If the predicted and detected exit target outlines have no IDs or indoor electrical equipment is off, no action is taken.

[0034] The specific steps for predicting the outline of the target are as follows:

[0035] Experimentally, a distance threshold was established to predict whether the target contour to be exited possesses an ID. This threshold is denoted as the exit distance threshold. It indicates that if the distance from the current position of the human contour to the entrance / exit is within the exit distance threshold, triggering the prediction. The displacement vector of this exit target contour is denoted as... Based on experiments, a threshold value was set for the displacement vector from the target contour to the inlet / outlet, denoted as the direction threshold. Any displacement vector within this direction threshold is denoted as... Through the and Cosine similarity calculation is performed. If the cosine similarity is equal to one, then the target outline is predicted if the target outline is within the exit distance threshold and the cosine similarity is equal to one.

[0036] The specific method for achieving a cosine similarity of one is as follows:

[0037]

[0038] Where 1 represents a cosine similarity of one. This represents the displacement vector that delineates the target contour. This represents any displacement vector within a direction threshold. express The model, express The model.

[0039] The specific steps to predict that the number of indoor IDs is zero are as follows:

[0040] When the detected target contour is a human body contour, the exit interval time is detected for human body contours that simultaneously meet the exit distance threshold and have a cosine similarity of 1. The exit interval time between the previous human body contour and the next human body contour is obtained and recorded as the interval time. Experiments show that if the interval time is within the same time threshold, it means that the human body contours are in the same batch. When pre-updating the number of indoor IDs, the number of corresponding human body contours is subtracted at one time. If the interval time is not within the same time threshold, when pre-updating the number of indoor IDs, the number of human body contours is subtracted at one time, and the number of indoor IDs is pre-updated in all cases. This process continues until the predicted number of indoor IDs is equal to zero. However, at this time, the actual number of indoor IDs is either one or N, where N represents the human body contours that exited together in the same batch.

[0041] The preferred embodiments of the present invention disclosed above are merely illustrative of the invention. These preferred embodiments do not exhaustively describe all details, nor do they limit the invention to the specific implementations described. Clearly, many modifications and variations can be made based on the content of this specification. This specification selects and specifically describes these embodiments to better explain the principles and practical applications of the invention, thereby enabling those skilled in the art to better understand and utilize the invention. The invention is limited only by the claims and their full scope and equivalents.

Claims

1. An integrated management system for dual-carbon target education scenarios based on the Internet of Things, characterized in that: Includes the following specific modules: Image acquisition and contour processing module: used to acquire and process contour data in real time; Contour entry / exit analysis module: used to detect sign changes in contour data to obtain contour entry signals or contour exit signals; Human silhouette count and prompt module: used to prompt the indoor electrical equipment to turn off when only the last person or the same group of people leaving the room is left, based on the silhouette entry signal or silhouette exit signal; The specific steps for obtaining the contour entry signal or contour exit signal are as follows: The contour data includes outdoor contours, indoor contours, and entrance / exit contours. A three-dimensional coordinate system is established with the center point of the entrance / exit contours as the origin. The positive direction of the entrance / exit contours pointing horizontally into the interior is defined as the normal vector. A certain dimension of the three-dimensional coordinate system is parallel to the normal vector and is denoted as the x-axis. The three-dimensional coordinates within both the outdoor and indoor contours are averaged to obtain the centroid of each contour. The change in the sign of the centroid coordinate on the x-axis after the outdoor contour moves into the interior is used to obtain the contour entry signal. The change in the sign of the centroid coordinate on the x-axis after the indoor contour moves into the outdoor is used to obtain the contour exit signal. The specific method for obtaining the contour entry signal is as follows: Let the centroid of the outdoor outline lie on the x-axis at coordinates of... The centroid of the interior outline is located at the x-axis coordinate of... Based on the time series, and When the product is less than zero, the contour entry signal is obtained. The dimension that is horizontal and perpendicular to the normal vector is denoted as the y-axis. The displacement vector of the outdoor contour moving to the indoor area intersects with the y-axis, and the contour continuous entry signal is obtained. The specific method for obtaining the continuous contour entry signal is as follows: The displacement vector of the outdoor contour moving to the indoor area in the time series intersects the y-axis, yielding the intersection point. Let the coordinates of the centroid of the outdoor outline be... The centroid coordinates of the interior outline are The displacement vector is obtained as , ,in express , Indicates from Departure The movement ratio on, establish about The system of equations makes Simultaneously satisfying x=0 and z=0, a continuous entry signal for the contour is obtained. The interval of the inlet and outlet contours on the y-axis is set as the entry and exit threshold. The displacement vector of the outdoor contour moving to the indoor area and passing through the entry and exit threshold is recorded as the normal continuous entry signal for the contour.

2. The IoT-based dual-carbon target education scenario integrated management system according to claim 1, characterized in that: The specific method for obtaining the normal continuous entry signal of the contour is as follows: Based on experiments, the lower limit of the entry and exit threshold is set as follows: The upper limit of the entry and exit threshold is Then, based on the condition that the displacement vector of the outdoor contour moving to the indoor area intersects the y-axis in the time series, the intersection point... Within the coordinate range of the y-axis and Between these points, a normal, continuous entry signal for the contour is obtained.

3. The IoT-based dual-carbon target education scenario integrated management system according to any one of claims 1-2, characterized in that: In the human body contour quantity statistics and prompting module, if a normal and continuous entry signal of the contour is collected, it is recorded as the target contour entering. The target contour entering is detected by the human body contour detection model. If the target contour entering is detected as a human body contour, an ID is added to the human body contour, and the number of indoor IDs is counted. If the number of indoor IDs is greater than or equal to one, the on / off status of indoor electrical equipment is monitored. If the target contour entering is not a human body contour, no operation is performed.

4. The IoT-based dual-carbon target education scenario integrated management system according to any one of claims 1-2, characterized in that: In the human body contour quantity statistics and prompting module, if a normal continuous outgoing contour signal is collected, it is recorded as an outgoing target contour. If an outgoing target contour has an ID, the ID is deleted and the number of indoor IDs is updated. It also predicts whether subsequent outgoing target contours have IDs. If an outgoing target contour is predicted to have an ID, the ID is pre-deleted and the number of indoor IDs is pre-updated until the predicted number of indoor IDs is equal to zero and the indoor electrical equipment is in the on state. Then, a reminder is issued to the indoor area. If the predicted and detected outgoing target contours have no IDs or the indoor electrical equipment is in the off state, no operation is performed.

5. The IoT-based dual-carbon target education scenario integrated management system according to claim 4, characterized in that: The specific steps for predicting the target contour are as follows: Experimentally, a distance threshold was established to trigger prediction of whether the target contour to be exited possesses an ID, denoted as the exit distance threshold. The displacement vector of this exit target contour is denoted as... Through experiments, a threshold value was set for the displacement vector from the target contour to the inlet / outlet, denoted as the direction threshold. Any displacement vector within this direction threshold is denoted as... Through the and Cosine similarity calculation is performed. If the cosine similarity is equal to one, then the target outline is predicted if the target outline is within the exit distance threshold and the cosine similarity is equal to one.

6. The IoT-based dual-carbon target education scenario integrated management system according to claim 5, characterized in that: The specific method for achieving a cosine similarity of one is as follows: ； in, This indicates that the cosine similarity is equal to one. This represents the displacement vector that delineates the target contour. This represents any displacement vector within a direction threshold. express The model, express The model.

7. The IoT-based dual-carbon target education scenario integrated management system according to claim 4, characterized in that: The specific steps to predict that the number of indoor IDs is equal to zero are as follows: When the detected target contour is a human body contour, the exit interval time is detected for human body contours that simultaneously satisfy the exit distance threshold and have a cosine similarity of 1. The exit interval time between the previous human body contour and the next human body contour is obtained and recorded as the interval time. Experiments show that if the interval time is within the same batch of time thresholds, the number of corresponding human body contours is subtracted when the number of indoor IDs is pre-updated. If the interval time is not within the same batch of time thresholds, the number of human body contours is subtracted by 1 when the number of indoor IDs is pre-updated, and the number of indoor IDs is pre-updated in all cases. This process continues until the number of predicted indoor IDs is equal to zero.

Images