AI smart campus-based campus area monitoring management method and system, terminal and medium

Abstract

The invention discloses a campus monitoring management method and system based on an AI smart campus, a terminal and a medium, and the method comprises the steps: dividing a campus region into a high people flow region and a low people flow region according to the people flow density, and arranging cameras and sensors according to the types of the regions, the monitoring range of each camera is set; performing feature extraction on the data of the camera and the sensor; inputting the extracted features into a recognition model, and recognizing abnormal behaviors; corresponding emergency measures are generated according to the recognition result; the campus area is divided into the high people flow area and the low people flow area, arrangement of the cameras and the sensors is optimized, feature extraction and behavior recognition are carried out on the collected data, real-time abnormal behavior detection and automatic emergency response are achieved, and the efficiency and accuracy of campus safety management are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of campus safety management, and in particular to a campus monitoring and management method, system, terminal and medium based on AI smart campus. Background Art

[0002] With the advancement of modern education informatization, the concept of smart campus has gradually become the mainstream trend of management in colleges and educational institutions. Smart campus has achieved intelligent upgrades in teaching, management, life and other aspects by integrating advanced technologies such as information technology, Internet of Things (IoT), cloud computing and artificial intelligence (AI). Among the many application scenarios of smart campus, campus monitoring and management plays a vital role. Traditional campus monitoring systems usually rely on fixed cameras and a single type of sensor to monitor campus security using image and data analysis. However, with the increasing diversity and complexity of campus activities, traditional monitoring methods are unable to cope with the real-time, accuracy and response efficiency. For example, in areas with high traffic density, the existing monitoring system is often unable to provide comprehensive coverage due to insufficient number of cameras or limited viewing angles; while in areas with low traffic density, excessive monitoring resource investment may cause resource waste. Therefore, how to better combine the dynamic changes in traffic density with the resource allocation of the monitoring system has become an urgent problem to be solved in the current smart campus monitoring and management system.

[0003] Although the existing AI-based campus monitoring system has made some progress in improving security and intelligent management, there are still obvious technical bottlenecks. First, the existing system's recognition model for abnormal behavior mostly uses a simple deep learning framework, and the recognition accuracy of complex behaviors is not high, especially in diversified scenarios. False alarms and missed alarms are more serious. Secondly, the existing technology lacks deep optimization at the feature extraction level and fails to fully utilize the complementarity of different features, resulting in insufficient generalization ability of the model and difficulty in adapting to complex dynamic environments. Summary of the invention

[0004] In order to overcome the defects in the above-mentioned prior art, the present invention provides a campus monitoring and management method based on AI smart campus, including: dividing the campus area into high-flow areas and low-flow areas according to the crowd density, arranging cameras and sensors according to the area type, and setting the monitoring range of each camera; extracting features from the camera and sensor data; inputting the extracted features into the recognition model to identify abnormal behavior; and generating corresponding emergency measures based on the recognition results.

[0005] As a preferred solution of the campus monitoring and management method based on AI smart campus described in the present invention, it includes: collecting daily traffic data of different areas in the campus through infrared sensors, analyzing the traffic density in different time periods according to the daily traffic data, marking high-traffic areas and low-traffic areas on the campus plan, and assigning a unique identifier to each area; installing traffic sensors in high-traffic areas to monitor the flow of people in real time, and installing door magnetic sensors or infrared sensors at the entrances of low-traffic areas to detect the switch status of doors and intrusion behaviors.

[0006] As a preferred solution of the campus monitoring and management method based on AI smart campus described in the present invention, it also includes preprocessing the data collected by the camera and sensor, including data enhancement, data smoothing and data synchronization, and feature extraction of the preprocessed camera and sensor data.

[0007] As a preferred solution of the campus monitoring and management method based on AI smart campus described in the present invention, feature extraction includes: converting camera data into an image matrix as a first modality input to Transformer; converting sensor data into a sensor matrix as a second modality input to Transformer; calculating the attention weights Attention (Q, K, V) of the image matrix and the sensor matrix;

[0008]

[0009] Where Q is the query vector generated by the image matrix, K is the key vector generated by the sensor matrix, and V S is the value vector generated by the sensor matrix, T is the transpose symbol, D K The dimension of the key vector generated for the sensor matrix, used to scale the dot product result;

[0010] Attention weights Attention(Q,K,V S ) performs weighted fusion and outputs the fusion feature F:

[0011] F = α·Attention(Q,K,V S )+β·Vs

[0012] Wherein, α and β are weighting parameters, α+β=1.

[0013] As a preferred solution of the campus monitoring and management method based on AI smart campus described in the present invention, wherein: the recognition model includes an input layer, a feature extraction layer, a feature fusion layer, and a prediction layer; the feature extraction layer includes a convolutional layer, a Dropout layer and a CSPDarknet53 network, the convolutional layer size is 3*3, and the number of channels is 64; the Dropout layer is arranged after the convolutional layer, the drop rate of the Dropout layer is 50%, and the CSPDarknet53 network is arranged after the Dropout layer; the feature fusion layer includes a path aggregation network and a feature pyramid network, and the feature pyramid network dynamically adjusts the fusion strategy of the path aggregation network according to the target size; the prediction layer includes a detection head and an IoU prediction head, the detection head includes a convolutional layer for bounding box regression and category prediction, and the IoU prediction head includes a convolutional layer for predicting the IoU value of each bounding box from the same feature map.

[0014] As a preferred solution of the campus monitoring and management method based on AI smart campus described in the present invention, it also includes: optimizing the recognition model through AdamW optimizer, setting the learning rate to 0.001, and stopping the training when the number of training iterations is greater than 500 and the accuracy of the recognition model is greater than the preset value.

[0015] As a preferred solution of the campus monitoring and management method based on AI smart campus described in the present invention, generating corresponding emergency measures includes: when the recognition result is abnormal, triggering an audible and visual alarm, displaying real-time video through the monitoring platform, and sending emergency notifications to relevant personnel.

[0016] The present invention also provides a campus monitoring and management system based on AI smart campus, which is used to implement the campus monitoring and management method based on AI smart campus as described in any of the above items. The campus monitoring and management system based on AI smart campus includes: a monitoring and acquisition module, which is configured to divide the campus area into high-flow areas and low-flow areas according to the crowd density, arrange cameras and sensors according to the area type, and set the monitoring range of each camera; a feature extraction module, which is configured to perform feature extraction on camera and sensor data; a recognition module, which is configured to input the extracted features into a recognition model to identify abnormal behavior; and an early warning module, which is configured to generate corresponding emergency measures based on the recognition results.

[0017] The present invention also provides a terminal device, comprising:

[0018] one or more processors;

[0019] A memory, coupled to the processor, for storing one or more programs;

[0020] When the one or more programs are executed by the one or more processors, the one or more processors implement the campus monitoring and management method based on AI smart campus as described in any of the above items.

[0021] The present invention also provides a computer-readable storage medium on which a computer program is stored, and the computer program is executed by a processor to implement the campus monitoring and management method based on AI smart campus as described in any of the above items.

[0022] Beneficial effects of the present invention: The present invention divides the campus area into high-flow areas and low-flow areas, optimizes the layout of cameras and sensors, and performs feature extraction and behavior recognition on the collected data to achieve real-time abnormal behavior detection and automated emergency response, thereby improving the efficiency and accuracy of campus safety management. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following briefly introduces the drawings required for describing the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative labor. Among them:

[0024] Figure 1 This is a flow chart of the campus monitoring and management method based on AI smart campus described in the first embodiment of the present invention. DETAILED DESCRIPTION

[0025] In order to make the above-mentioned purposes, features and advantages of the present invention more obvious and easy to understand, the specific implementation methods of the present invention are described in detail below in conjunction with the drawings of the specification. Obviously, the described embodiments are part of the embodiments of the present invention, but not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary persons in the art without creative work should fall within the scope of protection of the present invention.

[0026] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0027] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive with other embodiments.

[0028] The present invention is described in detail with reference to schematic diagrams. When describing the embodiments of the present invention, for the sake of convenience, the cross-sectional diagrams showing the device structure will not be partially enlarged according to the general scale, and the schematic diagrams are only examples, which should not limit the scope of protection of the present invention. In addition, in actual production, the three-dimensional dimensions of length, width and depth should be included.

[0029] At the same time, in the description of the present invention, it should be noted that the directions or positional relationships indicated by the terms "upper, lower, inner and outer" are based on the directions or positional relationships shown in the drawings, and are only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific direction, be constructed and operated in a specific direction, and therefore cannot be understood as limiting the present invention. In addition, the terms "first, second or third" are only used for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0030] In the present invention, unless otherwise clearly specified and limited, the terms "install, connect, connect" should be understood in a broad sense, for example: it can be a fixed connection, a detachable connection or an integral connection; it can also be a mechanical connection, an electrical connection or a direct connection, or it can be indirectly connected through an intermediate medium, or it can be the internal communication of two components. For ordinary technicians in this field, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0031] Example 1

[0032] Reference Figure 1 , which is the first embodiment of the present invention, and provides a campus monitoring and management method based on AI smart campus, including:

[0033] S1: Divide the campus area into high-flow area and low-flow area according to the flow density, arrange cameras and sensors according to the area type, and set the monitoring range of each camera.

[0034] The infrared sensor collects daily flow data of people in different areas of the campus and analyzes the density of people in different time periods based on the daily flow data. For example, the density in classrooms is high during class time, while the corridors have less traffic at noon and after school.

[0035] Mark high-traffic areas (such as classrooms, cafeterias, and main corridors, which require more intensive surveillance coverage) and low-traffic areas (such as administrative offices and storage rooms, which can be equipped with fewer surveillance facilities) on the campus floor plan and assign a unique identifier to each area.

[0036] Install crowd sensors in high-flow areas to monitor the flow of people in real time, and install door magnetic sensors or infrared sensors at the entrances of low-flow areas to detect the door's open and close status and intrusion behavior. That is, high-flow areas are equipped with high-resolution cameras and sensors to ensure that the details of the activities can be clearly captured, and multiple cameras are set up to cover the entire area. For example, in the cafeteria, cameras are installed at the entrance, exit and main dining area to ensure that every corner is within the monitoring range. In the classroom corridor, cameras are installed to cover the entire corridor and sensors are set up to detect peak traffic; low-flow areas are equipped with standard-resolution cameras and basic sensors to reduce the number of equipment to reduce costs. For example, in the storage room, a camera is installed to cover the entire area and combined with a basic infrared sensor to detect abnormal activities.

[0037] Furthermore, set the monitoring range of each camera, adjust the angle and focal length of the camera in the high-traffic area, and ensure that there are no blind spots in the entire area. For example, the camera in the cafeteria can cover from the entrance to each dining area, ensuring that key areas such as food collection and seating areas are within the monitoring range. Adjust the camera in the low-traffic area to cover the entire storage room area. There is no need for too much detail, just to ensure that abnormal situations can be detected.

[0038] S2: Perform feature extraction on camera and sensor data.

[0039] Before feature extraction, the data collected by cameras and sensors (people flow data, behavior data) needs to be preprocessed to improve data availability and processing efficiency.

[0040] Preprocessing includes data enhancement, data smoothing and data synchronization, and feature extraction is performed on the preprocessed camera and sensor data.

[0041] Data enhancement: Adjust the images captured by the camera, such as brightness, contrast, clarity, etc. to improve image quality; use interpolation methods to fill in missing sensor data points to improve the continuity and integrity of sensor data.

[0042] Data smoothing: Applying a Gaussian filter reduces random fluctuations in sensor data to more accurately reflect actual trends.

[0043] Data synchronization: Align the data from the camera and the sensor in time.

[0044] Furthermore, feature extraction is performed on the preprocessed camera and sensor data. The steps are as follows:

[0045] (1) Convert the camera data into an image matrix as the first modality input to the Transformer;

[0046] (2) Convert the sensor data into a sensor matrix as the second modality input to the Transformer;

[0047] (3) Calculate the attention weights of the image matrix and the sensor matrix Attention (Q, K, V S );

[0048]

[0049] Where Q is the query vector generated by the image matrix, K is the key vector generated by the sensor matrix, and V S is the value vector generated by the sensor matrix, T is the transpose symbol, D K The dimension of the key vector generated for the sensor matrix, used to scale the dot product result;

[0050] (4) Attention weights Attention(Q,K,V S ) performs weighted fusion and outputs the fusion feature F:

[0051] F = α·Attention(Q,K,V S )+β·Vs

[0052] Wherein, α and β are weighting parameters, α+β=1.

[0053] Preferably, the Transformer model can effectively capture long-term dependencies and complex feature interactions, and is particularly suitable for processing multimodal data.

[0054] S3: Input the extracted features into the recognition model to identify abnormal behaviors.

[0055] The recognition model includes input layer, feature extraction layer, feature fusion layer, and prediction layer;

[0056] The feature extraction layer includes convolution layer, Dropout layer and CSPDarknet53 network. The size of the convolution layer is 3*3 and the number of channels is 64. The Dropout layer is set after the convolution layer. The dropout rate of the Dropout layer is 50%. The CSPDarknet53 network is set after the Dropout layer.

[0057] The feature fusion layer includes a path aggregation network and a feature pyramid network. The path aggregation network is used to enhance feature fusion, especially for the scale invariance problem in target detection. It uses different levels of features in the feature pyramid structure and aggregates feature information layer by layer to improve the model's ability to recognize targets of different scales. The feature pyramid network dynamically adjusts the fusion strategy of the path aggregation network according to the target size.

[0058] The prediction layer includes a detection head and an IoU prediction head. The detection head includes a convolutional layer for bounding box regression and category prediction. The IoU prediction head includes a convolutional layer for predicting the IoU value of each bounding box from the same feature map. The IoU value indicates the degree of overlap between the predicted box and the true box, which helps to improve the non-maximum suppression (NMS) step in post-processing.

[0059] The recognition model is trained using the AdamW optimizer to optimize the training process of the Transformer model. The learning rate is set to 0.001, and the training is stopped when the number of training iterations is greater than 500 and the accuracy of the recognition model is greater than the preset value.

[0060] S4: Generate corresponding emergency measures based on the identification results.

[0061] When the recognition result is abnormal, an audible and visual alarm is triggered, and real-time video is displayed through the monitoring platform, sending emergency notifications to relevant personnel.

[0062] Example 2

[0063] The present invention provides a campus monitoring and management system based on AI smart campus, which is used to implement the steps of the campus monitoring and management method based on AI smart campus in any of the above embodiments. The campus monitoring and management system based on AI smart campus includes:

[0064] The monitoring and acquisition module is configured to divide the campus area into high-flow area and low-flow area according to the flow density, arrange cameras and sensors according to the area type, and set the monitoring range of each camera;

[0065] A feature extraction module configured to perform feature extraction on camera and sensor data;

[0066] A recognition module is configured to input the extracted features into a recognition model to identify abnormal behaviors;

[0067] The early warning module is configured to execute corresponding emergency measures generated according to the recognition results.

[0068] Example 3

[0069] This embodiment provides a terminal device, including:

[0070] one or more processors;

[0071] A memory, coupled to the processor, for storing one or more programs;

[0072] When the one or more programs are executed by the one or more processors, the one or more processors implement the campus monitoring and management method based on AI smart campus as described above.

[0073] The processor is used to control the overall operation of the terminal device to complete all or part of the steps of the above-mentioned campus monitoring and management method based on AI smart campus. The memory is used to store various types of data to support the operation of the terminal device, which data may include, for example, instructions for any application or method used to operate on the terminal device, and application-related data. The memory can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (Static Random Access Memory, referred to as SRAM), electrically erasable programmable read-only memory (Electrically Erasable Programmable Read-Only Memory, referred to as EEPROM), erasable programmable read-only memory (Erasable Programmable Read-Only Memory, referred to as EPROM), programmable read-only memory (Programmable Read-Only Memory, referred to as PROM), read-only memory (Read-Only Memory, referred to as ROM), magnetic memory, flash memory, disk or optical disk.

[0074] The terminal device can be implemented by one or more application-specific integrated circuits (Application Specific1n Integrated Circuit, ASC), digital signal processors (Digital Signal Processor, DSP), digital signal processing devices (Digital Signal Processing Device, DSPD), programmable logic devices (Programmable Logic Device, PLD), field programmable gate arrays (Field Programmable Gate Array, FPGA), controllers, microcontrollers, microprocessors or other electronic components, and is used to execute the campus monitoring and management method based on AI smart campus as described in any of the above embodiments, and achieve the same technical effect as the above method.

[0075] Example 4

[0076] This embodiment provides a computer-readable storage medium, and when the program instructions are executed by the processor, the steps of the campus monitoring and management method based on AI smart campus as described in any of the above embodiments are implemented. For example, the computer-readable storage medium can be the above-mentioned memory including program instructions, and the above-mentioned program instructions can be executed by the processor of the terminal device to complete the campus monitoring and management method based on AI smart campus as described in any of the above embodiments, and achieve the same technical effect as the above method.

[0077] It should be appreciated that embodiments of the present invention may be implemented or enforced by computer hardware, a combination of hardware and software, or by computer instructions stored in a non-transitory computer-readable memory. The method may be implemented in a computer program using standard programming techniques - including a non-transitory computer-readable storage medium configured with a computer program, wherein the storage medium so configured causes the computer to operate in a specific and predefined manner - according to the methods and drawings described in the specific embodiments. Each program may be implemented in a high-level procedural or object-oriented programming language to communicate with a computer system. However, if desired, the program may be implemented in an assembly or machine language. In any case, the language may be a compiled or interpreted language. In addition, the program may be run on a programmed ASIC for this purpose.

[0078] Furthermore, the operations of the processes described herein may be performed in any suitable order unless otherwise indicated herein or otherwise clearly contradicted by context. The processes described herein (or variations and / or combinations thereof) may be performed under the control of one or more computer systems configured with executable instructions, and may be implemented as code (e.g., executable instructions, one or more computer programs, or one or more applications) that is executed collectively on one or more processors, by hardware, or a combination thereof. The computer program includes a plurality of instructions that may be executed by one or more processors.

[0079] Further, the method can be implemented in any type of computing platform that is operably connected to a suitable computer, including but not limited to a personal computer, a minicomputer, a mainframe, a workstation, a network or distributed computing environment, a separate or integrated computer platform, or in communication with a charged particle tool or other imaging device, etc. Aspects of the present invention can be implemented in machine-readable code stored on a non-transitory storage medium or device, whether removable or integrated into a computing platform, such as a hard disk, an optical read and / or write storage medium, a RAM, a ROM, etc., so that it can be read by a programmable computer, and when the storage medium or device is read by the computer, it can be used to configure and operate the computer to perform the process described herein. In addition, the machine-readable code, or part thereof, can be transmitted via a wired or wireless network. When such media includes instructions or programs that implement the steps described above in conjunction with a microprocessor or other data processor, the invention described herein includes these and other different types of non-transitory computer-readable storage media. When programmed according to the methods and techniques described in the present invention, the present invention also includes the computer itself. The computer program can be applied to input data to perform the functions described herein, thereby converting the input data to generate output data stored in a non-volatile memory. The output information can also be applied to one or more output devices such as a display. In a preferred embodiment of the present invention, the converted data represents a physical and tangible object, including a specific visual depiction of the physical and tangible object produced on a display.

[0080] As used in this application, the terms "component", "module", "system", etc. are intended to refer to a computer-related entity, which can be hardware, firmware, a combination of hardware and software, software, or software in operation. For example, a component can be, but is not limited to: a process running on a processor, a processor, an object, an executable file, a thread in execution, a program, and / or a computer. As an example, an application running on a computing device and the computing device can both be components. One or more components can exist in a process and / or thread in execution, and a component can be located in a computer and / or distributed between two or more computers. In addition, these components can be executed from various computer-readable media having various data structures thereon. These components can communicate in a local and / or remote process manner, such as according to a signal having one or more data packets (e.g., data from a component that interacts with another component in a local system, a distributed system, and / or interacts with other systems in a signal manner through a network such as the Internet).

[0081] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention rather than to limit it. Although the present invention has been described in detail with reference to the preferred embodiments, those skilled in the art should understand that the technical solutions of the present invention may be modified or replaced by equivalents without departing from the spirit and scope of the technical solutions of the present invention, which should all be included in the scope of the claims of the present invention.

Claims

1. A campus monitoring and management method based on AI smart campus, characterized in that: include: Divide the campus area into high-flow areas and low-flow areas according to the flow density, arrange cameras and sensors according to the area type, and set the monitoring range of each camera; Perform feature extraction on camera and sensor data; The extracted features are input into the recognition model to identify abnormal behaviors; Generate corresponding emergency measures based on the identification results.

2. The campus monitoring and management method based on AI smart campus according to claim 1, characterized in that: include: The infrared sensor collects daily traffic data from different areas of the campus. Based on the daily traffic data, the density of traffic in different time periods is analyzed, and high and low traffic areas are marked on the campus floor plan, and a unique identifier is assigned to each area. Install crowd flow sensors in high-flow areas to monitor the flow of people in real time, and install door magnetic sensors or infrared sensors at the doors of low-flow areas to detect the door's open and close status and intrusion behavior.

3. The campus monitoring and management method based on AI smart campus according to claim 2 is characterized in that: It also includes preprocessing of data collected by cameras and sensors, including data enhancement, data smoothing and data synchronization, and feature extraction of preprocessed camera and sensor data.

4. The campus monitoring and management method based on AI smart campus according to claim 3 is characterized in that: Feature extraction includes: Convert the camera data into an image matrix and input it into the Transformer as the first modality. Convert sensor data into sensor matrix and input it into Transformer as the second modality; Calculate the attention weights of the image matrix and the sensor matrix Attention (Q, K, V S ); Where Q is the query vector generated by the image matrix, K is the key vector generated by the sensor matrix, and V S is the value vector generated by the sensor matrix, T is the transpose symbol, D K The dimension of the key vector generated for the sensor matrix, used to scale the dot product result; Attention weights Attention(Q,K,V S ) performs weighted fusion and outputs fusion feature F: F=α·Attention(Q,K,V S )+β·Vs Wherein, α and β are weighting parameters, α+β=1.

5. The campus monitoring and management method based on AI smart campus according to claim 4 is characterized in that: The recognition model includes input layer, feature extraction layer, feature fusion layer, and prediction layer; The feature extraction layer includes a convolution layer, a Dropout layer and a CSPDarknet53 network. The size of the convolution layer is 3*3 and the number of channels is 64. The Dropout layer is arranged after the convolution layer, the dropout rate of the Dropout layer is 50%, and the CSPDarknet53 network is arranged after the Dropout layer. The feature fusion layer includes a path aggregation network and a feature pyramid network. The feature pyramid network dynamically adjusts the fusion strategy of the path aggregation network according to the target size. The prediction layer includes a detection head and an IoU prediction head, wherein the detection head includes a convolutional layer for bounding box regression and category prediction, and the IoU prediction head includes a convolutional layer for predicting the IoU value of each bounding box from the same feature map.

6. The campus monitoring and management method based on AI smart campus according to claim 5, characterized in that: Also includes: The recognition model is optimized and trained by the AdamW optimizer, and the learning rate is set to 0.

001. The training is stopped when the number of training iterations is greater than 500 and the accuracy of the recognition model is greater than a preset value.

7. The campus monitoring and management method based on AI smart campus according to claim 6 is characterized in that: Generate corresponding emergency measures including: When the recognition result is abnormal, an audible and visual alarm is triggered, and real-time video is displayed through the monitoring platform, sending emergency notifications to relevant personnel.

8. A campus monitoring and management system based on AI smart campus, used to implement the campus monitoring and management method based on AI smart campus according to any one of claims 1 to 7, the campus monitoring and management system based on AI smart campus comprising: The monitoring and acquisition module is configured to divide the campus area into high-flow area and low-flow area according to the flow density, arrange cameras and sensors according to the area type, and set the monitoring range of each camera; A feature extraction module configured to perform feature extraction on camera and sensor data; A recognition module is configured to input the extracted features into a recognition model to identify abnormal behaviors; The early warning module is configured to execute corresponding emergency measures generated according to the recognition results.

9. A terminal device, characterized in that: include: one or more processors; A memory, coupled to the processor, for storing one or more programs; When the one or more programs are executed by the one or more processors, the one or more processors implement the campus monitoring and management method based on AI smart campus as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: The computer program is executed by the processor to implement the campus monitoring and management method based on AI smart campus as described in any one of claims 1 to 7.

Images