A campus personnel gathering detection system based on radar wave technology

Abstract

The present invention discloses a campus personnel gathering detection system based on radar wave technology, which relates to the field of campus safety management technology. The system includes the following components: a radar wave detection module: a high-precision, multi-band radar wave sensor is used to continuously scan various areas in the campus, and real-time data on personnel distribution, movement speed and direction are obtained. The present invention automatically generates the optimal evacuation path and plan through an intelligent analysis and processing unit when an early warning is triggered. The evacuation guidance information is released through multiple channels such as the campus broadcasting system, mobile phone APP, and electronic display screens, providing teachers and students with clear and intuitive evacuation guidance. During the evacuation process, the system can also dynamically adjust the evacuation guidance information according to real-time personnel flow and on-site feedback to ensure the safety and order of the evacuation process. This intelligent evacuation guidance mechanism not only improves the evacuation efficiency, but also reduces the risk of safety accidents caused by panic or chaos.

Description

Technical Field

[0001] The present invention relates to the technical field of campus safety management, and in particular to a campus personnel gathering detection system based on radar wave technology. Background Art

[0002] In contemporary society, with the vigorous development of education and the improvement of the popularity of higher education, the scale of campuses has continued to expand and the number of teachers and students has increased dramatically. Although this trend has promoted academic exchanges and knowledge dissemination, it has also brought unprecedented challenges to campus safety management. Especially during holidays, large-scale events or emergencies, the phenomenon of people gathering on campus is particularly prominent. Once improperly managed, it is very easy to cause stampedes, congestion problems and other safety hazards, seriously threatening the lives and property of teachers and students.

[0003] Traditional methods of monitoring gatherings of people mainly include video surveillance systems and manual patrols. Although video surveillance systems can intuitively display the on-site situation, they have many shortcomings: First, video data is easily affected by changes in light, obstructions, and bad weather factors, which greatly reduces the monitoring effect. Second, video surveillance involves the collection and processing of a large amount of personal information, which poses a high risk of privacy leakage and can easily lead to dissatisfaction among teachers and students and legal disputes. Finally, video surveillance systems rely on manual monitoring and judgment, which is not only inefficient but also prone to missing warning opportunities due to human negligence.

[0004] Based on the above problems, it is necessary to optimize the existing means of monitoring crowd gatherings, use radar wave detection technology to realize real-time monitoring of crowd gatherings on campus, and integrate advanced artificial intelligence algorithms to conduct in-depth analysis and processing of the collected data, automatically identify and evaluate the density of crowd gatherings, and automatically trigger the early warning mechanism and evacuation guidance information release platform when necessary. Therefore, it is of great significance to develop a campus crowd gathering detection system based on radar wave technology that can comprehensively realize the above characteristics. Summary of the Invention

[0005] The purpose of this invention is to make up for the shortcomings of the existing technology and provide a campus crowd gathering detection system based on radar wave technology. It can realize real-time monitoring and analysis of the crowd gathering situation on campus by combining high-precision, multi-band radar wave sensors and advanced artificial intelligence algorithms, automatically trigger the early warning mechanism, and provide efficient and accurate evacuation guidance to prevent stampedes and other safety hazards.

[0006] In order to solve the above technical problems, the present invention provides the following technical solutions: a school area crowd gathering detection system based on radar wave technology, the system includes the following components:

[0007] Radar wave detection module: uses high-precision, multi-band radar wave sensors to continuously scan various areas within the campus and obtain real-time data on personnel distribution, movement speed, and direction;

[0008] Intelligent analysis and processing unit: Integrates artificial intelligence algorithms, including but not limited to deep learning, machine learning, and data mining technologies, to process and analyze data collected by the radar wave detection module in real time, automatically identifying and assessing the density of crowds and determining whether there are safety hazards;

[0009] Early warning trigger module: If the analysis results show that the density of people gathering in a certain area exceeds the preset safety threshold, an early warning signal will be automatically triggered, including but not limited to sound and light alarms, SMS notifications, and email alerts, so that relevant management personnel and security personnel can obtain warning information immediately;

[0010] Evacuation guidance information release platform: Combining multiple channels such as the campus broadcast system, mobile phone apps, and electronic display screens, it automatically generates and releases detailed evacuation guidance information based on the specific conditions of the warning area, including evacuation routes, emergency exit locations, and precautions, to guide teachers and students to evacuate in an orderly manner and avoid stampede safety accidents;

[0011] Self-learning and optimization module: The system has self-learning capabilities, can continuously accumulate historical data, optimize algorithm models, improve the accuracy of warnings and the effectiveness of evacuation guidance, and support remote configuration and updates, facilitating flexible adjustments based on the actual situation on campus.

[0012] Furthermore, the radar wave detection module deploys high-precision, multi-band radar wave sensors in key areas of the campus, initializes the configuration of the radar sensors, including setting the scanning frequency, detection range, and data processing parameters, and adjusts them according to the specific environment and needs of the campus. The radar sensors continuously scan the designated area and collect raw data on personnel distribution, movement speed and direction. The collected data is transmitted to the intelligent analysis and processing unit via wireless or wired means. The intelligent analysis and processing unit pre-processes the collected raw data, including denoising, filtering, and calibration steps, to improve the quality and accuracy of the data.

[0013] Furthermore, the intelligent analysis and processing unit receives data from the radar wave detection module, and performs preliminary data verification and synchronization processing, and uses image processing or signal processing algorithms to extract characteristic information related to personnel gathering from the pre-processed data, including the number and density of personnel. The integrated artificial intelligence algorithm conducts in-depth analysis of the extracted characteristic information to evaluate the severity of personnel gathering and potential safety risks. Based on the analysis results, the intelligent analysis and processing unit determines whether it is necessary to trigger the early warning mechanism. When the density of personnel gathering in a certain area exceeds the preset safety threshold, the early warning process is entered.

[0014] Furthermore, the intelligent analysis and processing unit uses a density estimation algorithm based on an image processing algorithm to extract feature information related to personnel gathering from the preprocessed data. The algorithm formula is: Density Estimate = f (Extracted Features, Model Parameters), where f represents the density estimation model, ExtractedFeatures represents the features extracted from the preprocessed data, and Model Parameters represents the parameters of the model.

[0015] Furthermore, the intelligent analysis and processing unit uses a support vector machine algorithm to evaluate the severity of the gathering of people and the potential safety risks, and the calculation formula is: Where N is the number of training samples, x i is the feature vector of the i-th sample, y i is the label of the i-th sample, K(x i ,x j ) is the kernel function used to calculate the similarity between samples, C is the regularization parameter used to control overfitting, α i It is a Lagrange multiplier, which uses the trained support vector machine model to perform real-time classification or regression on the extracted feature information to evaluate the current density of personnel gathering and the level of safety risk.

[0016] Furthermore, when the early warning trigger module determines that an early warning needs to be triggered, the intelligent analysis and processing unit immediately generates an early warning signal, including an audible and visual alarm signal, a text message notification, and an email alert, and sends the early warning signal to the terminal devices of relevant management personnel and security personnel, as well as the campus broadcasting system and the public release platform of the electronic display screen. Personnel receiving the early warning signal must immediately confirm and take corresponding response measures, including going to the site to check and activating the emergency plan.

[0017] Furthermore, the evacuation guidance information release platform automatically generates the optimal evacuation path and plan based on the specific conditions of the warning area through the intelligent analysis and processing unit, and releases the evacuation guidance information through multiple channels such as the campus broadcasting system, mobile phone APP, and electronic display screens. The information content includes detailed guidance on evacuation routes, safety exit locations, and precautions. During the evacuation process, the intelligent analysis and processing unit can dynamically adjust the evacuation guidance information based on real-time personnel flow and on-site feedback.

[0018] Furthermore, the evacuation guidance information release platform uses the Dijkstra algorithm to automatically generate the optimal evacuation path. Based on the campus map, real-time personnel distribution, safety exit locations, and obstacle distribution information, the optimal evacuation path from the current location to the nearest safety exit is automatically generated. The calculation formula is: The calculation of the evacuation path P can be expressed as the problem of finding the optimal path from the starting node S to the safety exit node T: Where P represents the optimal path to be found, S and T are the starting and ending nodes of the path respectively, all paths fromstot represents all possible paths from node S to node T, (e) represents the edge in the path, ∑ e∈p w(e) represents the sum of the weights of all edges on path P.

[0019] Furthermore, the self-learning and optimization module continuously accumulates historical data through the system, including the gathering of people, evacuation effect, and response time of each warning event, and uses the accumulated data to train and optimize the artificial intelligence algorithm model to improve the accuracy of warnings and the effectiveness of evacuation guidance, including adjusting model parameters and improving algorithm structure, while supporting remote configuration and updating of the system.

[0020] Furthermore, the self-learning and optimization module uses the Newton method to optimize the artificial intelligence algorithm model. Specifically, the model parameter θ0 is initialized and the parameters of the optimization algorithm are set. In each iteration, the data collected by the radar wave detection module is used as input to calculate the current model parameter θ t The objective function J(θ t ) and the Hessian matrix H t , according to Newton's method or its approximate algorithm, calculate the update direction and update the model parameters θ t+1 ,Right now The system automatically adjusts the parameters of the artificial intelligence algorithm model by continuously accumulating historical data and using the above training and optimization process.

[0021] Compared with the existing technology, this campus crowd gathering detection system based on radar wave technology has the following beneficial effects:

[0022] 1. The present invention uses integrated radar wave technology to monitor the gathering of people on campus in real time, and immediately triggers an early warning signal when abnormal gatherings or potential dangers are detected. This intelligent early warning mechanism greatly shortens the time from abnormal detection to early warning issuance, and improves the response speed of the early warning. At the same time, based on big data analysis and optimization of artificial intelligence algorithm models, the system can more accurately judge the necessity of early warning, reduce false alarms and missed alarms, and ensure the accuracy and reliability of early warning information.

[0023] 2. The present invention automatically generates the optimal evacuation path and plan through an intelligent analysis and processing unit when an early warning is triggered. Evacuation guidance information is released through multiple channels such as the campus broadcast system, mobile phone APP, and electronic display screens, providing teachers and students with clear and intuitive evacuation guidance. During the evacuation process, the system can also dynamically adjust the evacuation guidance information based on real-time personnel flow and on-site feedback to ensure a safe and orderly evacuation process. This intelligent evacuation guidance mechanism not only improves evacuation efficiency, but also reduces the risk of safety accidents caused by panic or chaos.

[0024] Other advantages, objects and features of the present invention will be described in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be learned from the practice of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0025] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0026] Figure 1 This is a process operation diagram of a campus crowd gathering detection system based on radar wave technology.

[0027] Figure 2 This is a flow chart of a campus personnel gathering detection system based on radar wave technology. DETAILED DESCRIPTION

[0028] The following is a clear and complete description of the technical solutions in the embodiments of the present invention. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of the present invention.

[0029] Example 1

[0030] This embodiment describes in detail the implementation process of the intelligent early warning function in the campus crowd gathering detection system based on radar wave technology. By deploying high-precision, multi-band radar wave sensors and combining them with the artificial intelligence algorithm of the intelligent analysis and processing unit, real-time monitoring and assessment of the crowd gathering situation in various areas of the campus are achieved, and an early warning signal is automatically triggered when the preset safety threshold is exceeded to ensure campus safety.

[0031] High-precision, multi-band radar wave sensors are deployed in key areas of the campus, including teaching buildings, playgrounds, and cafeterias. The radar sensors are initialized and configured, including setting the scanning frequency, detection range, and data processing parameters to adapt to the specific environment and needs of the campus. This ensures that the radar sensors continuously scan the designated area, collect raw data on personnel distribution, movement speed, and direction, and transmit it to the intelligent analysis and processing unit via wireless or wired methods.

[0032] The intelligent analysis and processing unit receives data from the radar wave detection module, performs preliminary data verification and synchronization processing to ensure data integrity and consistency, and uses signal processing algorithms to pre-process the data through denoising, filtering, and calibration to improve data quality and accuracy. A density estimation algorithm based on an image processing algorithm is used to extract feature information related to human gathering from the pre-processed data. The algorithm formula is: Density Estimate = f(Extracted Features, Model Parameters), where f represents the density estimation model, Extracted Features represents the features extracted from the pre-processed data, and Model Parameters represents the parameters of the model. The support vector machine algorithm is used to evaluate the severity of human gathering and the potential safety risks. The calculation formula is: Where N is the number of training samples, x i is the feature vector of the i-th sample, y i is the label of the i-th sample, K(x i ,x j ) is the kernel function used to calculate the similarity between samples, C is the regularization parameter used to control overfitting, α i It is a Lagrange multiplier, which uses the trained support vector machine model to perform real-time classification or regression on the extracted feature information to evaluate the current density of personnel gathering and the level of safety risk.

[0033] When the density of people gathering in a certain area exceeds the preset safety threshold ρ threshold When an emergency occurs, the intelligent analysis and processing unit immediately generates an early warning signal, which includes an audible and visual alarm signal, SMS notification, and email alert. The early warning signal is released through multiple channels such as the campus broadcasting system and electronic display screens. The triggering logic of the early warning signal is expressed as follows: The terminal devices of relevant management personnel and security personnel will receive early warning signals and need to immediately confirm and take corresponding response measures, including visiting the site and activating emergency plans.

[0034] In summary, through the implementation of this embodiment, the gathering of people on campus can be monitored in real time and effectively warned, which significantly improves the level of campus safety management and reduces the safety hazards caused by the gathering of people. The system continuously optimizes the algorithm model to improve the accuracy of warnings and the effectiveness of evacuation guidance, providing strong technical support for campus safety.

[0035] Example 2

[0036] This embodiment elaborates on the implementation details of an evacuation guidance information release platform in a campus crowd gathering detection system based on radar wave technology. The platform is designed to quickly generate optimal evacuation routes and plans after intelligent early warnings are triggered, and accurately convey evacuation guidance information through multiple channels to ensure that teachers and students can evacuate quickly and orderly in emergency situations, effectively avoiding stampede safety accidents.

[0037] For early warning triggering and response, let D i is the density of people gathering in area i, T is the preset safety threshold, when the intelligent analysis and processing unit detects D i >T, the early warning signal is triggered and the evacuation guidance information release process is immediately started.

[0038] The generation of evacuation paths and plans involves complex terrain and crowd flow analysis. This can be achieved by using the shortest path algorithm in graph theory, namely the Dijkstra algorithm, combined with campus map data. Let G(V,E) be the graph representation of the campus map, where V is the node set (representing buildings and road intersections), E is the edge set (representing paths), and w(e) is the weight of edge e (which can represent distance, time, or a comprehensive risk indicator). The calculation of the evacuation path P can be expressed as finding the optimal path from the starting node S to the safe exit node T: Where P represents the optimal path to be found, S and T are the starting and ending nodes of the path respectively, all paths fromstot represents all possible paths from node S to node T, (e) represents the edge in the path, ∑ e∈p w(e) represents the sum of the weights of all edges on path P.

[0039] Evacuation guidance information is released through multiple channels such as the campus broadcasting system, mobile phone apps, and electronic display screens. The published content includes but is not limited to: evacuation route description, emergency exit locations, and precautions. During the evacuation process, the system uses real-time data to dynamically adjust the evacuation guidance information. Let F(t) be the real-time feedback data at time t, and the dynamic adjustment can be expressed as: Here, f(F(t),p) is the additional risk assessment of path P based on real-time feedback data, and λ is the adjustment factor. Management and security personnel act quickly according to the evacuation guidance information. At the same time, the system collects real-time data and feedback from teachers and students during the evacuation process. After the evacuation, an effect evaluation is conducted to optimize the algorithm and parameters and improve system performance. The evaluation indicators include evacuation time, casualty rate, and teacher and student satisfaction.

[0040] In summary, through the implementation of this embodiment, when the campus faces safety hazards caused by the gathering of people, it can quickly generate and publish evacuation guidance information based on radar wave technology and intelligent algorithms, which significantly improves evacuation efficiency and safety, reduces the risk of stampede accidents, and provides strong technical support for campus emergency management.

[0041] Example 3

[0042] The steps of the system based on Example 1 and Example 2 are as follows:

[0043] (1) System deployment and initialization: Install high-precision, multi-band radar wave sensors in selected key areas on campus to ensure comprehensive coverage without blind spots. Connect the radar wave detection module to the intelligent analysis and processing unit, initialize the system hardware and software, configure the parameters of the early warning trigger mechanism, including the preset safety threshold, alarm mode, and list of recipients, and integrate the campus broadcast system, mobile phone APP, and electronic display screen evacuation guidance information release platform to ensure that information can be accurately and quickly conveyed to teachers and students;

[0044] (2) Data collection and real-time monitoring: The radar wave detection module is activated to continuously scan various areas within the campus to obtain real-time data on personnel distribution, movement speed, and direction. The data is transmitted to the intelligent analysis and processing unit via wired or wireless means for preliminary processing and storage;

[0045] (3) Intelligent analysis and early warning triggering: The intelligent analysis and processing unit uses an integrated artificial intelligence algorithm to process and analyze the data collected by the radar wave detection module in real time, automatically identifying and evaluating the density of people gathering in each area, and comparing it with the preset safety threshold. Once it is found that the density of people gathering in a certain area exceeds the safety threshold, the early warning mechanism is immediately triggered, sounding an audible and visual alarm, and notifying relevant management personnel and security personnel via SMS and email;

[0046] (4) Evacuation guidance information release: Based on the specific situation of the warning area, the evacuation guidance information release platform automatically generates detailed evacuation guidance information, including evacuation routes, safety exit locations, and precautions. Emergency evacuation broadcasts are played through the campus broadcasting system, and evacuation guidance information is released on mobile phone apps and electronic display screens to ensure that teachers and students can obtain and understand evacuation instructions in a timely manner.

[0047] (5) Evacuation execution and feedback: Teachers and students evacuate to safe areas in an orderly manner according to evacuation guidance information. The system records data of the evacuation process, including evacuation time and personnel flow, to provide a basis for subsequent analysis and optimization. Management personnel and security personnel adjust the evacuation plan according to actual conditions to ensure the safety and efficiency of the evacuation process;

[0048] (6) Self-learning and optimization: The system continuously accumulates historical data and optimizes the model through self-learning algorithms to improve the accuracy of warnings and the effectiveness of evacuation guidance. It also supports remote configuration and updates, and can be flexibly adjusted according to the actual situation of the campus and seasonal changes to ensure the adaptability and reliability of the system.

[0049] (7) Regular maintenance and inspection: Regularly inspect and maintain the radar wave sensor, intelligent analysis and processing unit, and information release platform to ensure their normal operation and data accuracy, conduct performance evaluation of the system, and perform corresponding optimization and upgrades based on the evaluation results.

[0050] It will be apparent to those skilled in the art that the present invention is not limited to the details of the exemplary embodiments described above and that the invention can be embodied in other specific forms without departing from the spirit or essential characteristics of the invention. Therefore, the embodiments should be considered in all respects as illustrative and non-restrictive, and the scope of the invention is defined by the appended claims, not the foregoing description, and all variations within the meaning and range of equivalents of the claims are intended to be included therein. Any reference sign in a claim should not be construed as limiting the claim to which it relates.

Claims

1. A campus personnel gathering detection system based on radar wave technology, characterized in that: The system consists of the following components: Radar wave detection module: uses high-precision, multi-band radar wave sensors to continuously scan various areas on campus and obtain real-time data on personnel distribution, movement speed and direction; Intelligent analysis and processing unit: integrated artificial intelligence algorithms, including deep learning, machine learning and data mining technology, receive data from the radar wave detection module, and perform preliminary data verification and synchronization processing, extract characteristic information related to personnel gathering from the pre-processed data, including the number and density of personnel, and the integrated artificial intelligence algorithm conducts in-depth analysis of the extracted characteristic information to evaluate the severity of personnel gathering and potential safety risks. The calculation formula is: ,in, is the number of training samples, is the feature vector of the i-th sample, is the label of the i-th sample, is the kernel function, which is used to calculate the similarity between samples. is a regularization parameter used to control overfitting, It is a Lagrange multiplier. It uses the trained support vector machine model to perform real-time classification or regression on the extracted feature information to evaluate the current density of personnel gathering and the safety risk level. Based on the analysis results, the intelligent analysis and processing unit determines whether it is necessary to trigger the early warning mechanism. When the density of personnel gathering in a certain area exceeds the preset safety threshold, the early warning process is entered; Early warning trigger module: When the analysis results show that the density of people gathering in a certain area exceeds the preset safety threshold, an early warning signal is automatically triggered, including sound and light alarms, SMS notifications, and email alerts, so that relevant managers and security personnel can obtain warning information in the first place; Evacuation guidance information release platform: Combined with multiple channels such as campus broadcasting system, mobile phone APP, and electronic display screen, it automatically generates and releases detailed evacuation guidance information according to the specific situation of the warning area, including evacuation routes, safety exit locations and precautions, to guide teachers and students to evacuate in an orderly manner and avoid stampede safety accidents; Self-learning and optimization module: The system has self-learning capabilities, can continuously accumulate historical data, optimize algorithm models, improve the accuracy of warnings and the effectiveness of evacuation guidance, and at the same time, supports remote configuration and updates, facilitating flexible adjustments based on the actual situation on campus.

2. According to the radar wave technology-based campus personnel gathering detection system of claim 1, it is characterized in that: The radar wave detection module deploys high-precision, multi-band radar wave sensors in key areas of the campus, and initializes the configuration of the radar sensors, including setting the scanning frequency, detection range, and data processing parameters, and adjusts them according to the specific environment and needs of the campus. The radar sensor continuously scans the designated area and collects raw data on personnel distribution, movement speed, and direction. The collected data is transmitted to the intelligent analysis and processing unit via wireless or wired means. The intelligent analysis and processing unit pre-processes the collected raw data, including denoising, filtering, and calibration steps, to improve the quality and accuracy of the data.

3. According to the radar wave technology-based campus personnel gathering detection system of claim 1, it is characterized in that: The intelligent analysis and processing unit uses a density estimation algorithm based on an image processing algorithm to extract feature information related to personnel gathering from the preprocessed data. The algorithm formula is: ,in, represents the density estimation model, represents the features extracted from the preprocessed data, Represents the parameters of the model.

4. According to claim 1, a campus personnel gathering detection system based on radar wave technology is characterized in that: When the early warning trigger module determines that an early warning needs to be triggered, the intelligent analysis and processing unit immediately generates an early warning signal, including an audible and visual alarm signal, a text message notification, and an email alert, and sends the early warning signal to the terminal devices of relevant managers and security personnel, as well as the campus broadcasting system and the public publishing platform of the electronic display screen. Personnel receiving the early warning signal must immediately confirm and take corresponding response measures, including visiting the site and initiating emergency plans.

5. According to the radar wave technology-based campus personnel gathering detection system of claim 1, it is characterized in that: The evacuation guidance information release platform automatically generates the optimal evacuation path and plan based on the specific situation of the warning area through the intelligent analysis and processing unit, and releases the evacuation guidance information through multiple channels such as the campus broadcasting system, mobile phone APP, and electronic display screens. The information content includes detailed guidance on evacuation routes, safety exit locations, and precautions. During the evacuation process, the intelligent analysis and processing unit can dynamically adjust the evacuation guidance information based on real-time personnel flow and on-site feedback.

6. According to claim 5, a campus personnel gathering detection system based on radar wave technology is characterized in that ,The evacuation guidance information release platform uses the Dijkstra algorithm to automatically generate the optimal evacuation path. According to the campus map, real-time personnel distribution, safety exit location and obstacle distribution information, it automatically generates the optimal evacuation path from the current location to the nearest safety exit. The calculation formula is: evacuation path The computational expression of is to find the optimal path from the starting node S to the safe exit node T: ,in, represents the optimal path to be found, S and T are the starting node and the ending node of the path respectively. represents all possible paths from node S to node T, represents the edges in the path, Indicates the path The sum of the weights of all edges on .

7. According to claim 1, a campus personnel gathering detection system based on radar wave technology is characterized in that ,The self-learning and optimization module continuously accumulates historical data through the system, including the gathering of people, evacuation effect, and response time of each warning event, and uses the accumulated data to train and optimize the artificial ,intelligence algorithm model to improve the accuracy of warning and the effectiveness of evacuation guidance, including adjusting the model parameters, improving the algorithm structure, and supporting remote configuration and updating of the system.

8. The campus personnel gathering detection system based on radar wave technology according to claim 1 is characterized in that ,The self-learning and optimization module uses Newton’s method to optimize the artificial intelligence algorithm model. Specifically, the model parameters are initialized and set the parameters of the optimization algorithm. In each iteration, the data collected by the radar wave detection module is used as input to calculate the current model parameters. The objective function under Gradient and The system automatically adjusts the parameters of the artificial intelligence algorithm model by continuously accumulating historical data and using the above training and optimization process.

Images