Modeled camera layout method and system

Abstract

The invention relates to the technical field of monitoring layout, in particular to a modeling camera layout method and system. The method comprises the following steps: carrying out geometric topology analysis on a venue to obtain a venue functional region model; performing fluid mechanics simulation on the venue functional area model to obtain people flow density distribution characteristic data; performing risk grade division on the venue according to the people flow density distribution characteristic data to obtain a venue key area evaluation matrix; performing dynamic density field modeling on the venue based on the crowd density distribution characteristic data to obtain a crowd density field mathematical model; performing monitoring demand analysis on the venue according to the crowd density field mathematical model and the venue key area evaluation matrix to obtain a monitoring coverage scheme; and performing density equalization configuration on the cameras according to the monitoring coverage range scheme to obtain a camera distribution density scheme. According to the invention, the camera layout is optimized, the resource waste is avoided, and the monitoring continuity and no dead angle are ensured.

Description

Technical Field

[0001] The present invention relates to the technical field of monitoring layout, and particularly to a layout method and system for a modeled camera. Background Art

[0002] Existing camera layout methods often fail to fully consider the complexity and dynamic changes of the environment, resulting in unsatisfactory monitoring effects. Taking large stadiums as an example, these stadiums not only have a vast area but also a complex structure, including multiple entrances and exits, spectator stands, playing fields and other areas. In such a scenario, it is very difficult for traditional camera layout methods to achieve full coverage of all key areas. For example, in an international football match, the number of spectators can reach tens of thousands, and the mobility of the crowd is extremely high, which requires the camera to not only cover the spectator stands but also be able to monitor areas such as the perimeter of the field and entrances and exits. However, due to the limitations of the camera's viewing angle and monitoring range, there are often monitoring blind spots, especially in crowded areas such as exits and entrances. Once an emergency occurs in these places, it is very difficult for the monitoring system to capture key information in a timely manner, thus delaying the emergency response and handling. Summary of the Invention

[0003] Based on this, it is necessary for the present invention to provide a layout method and system for a modeled camera to solve at least one of the above technical problems.

[0004] To achieve the above object, a layout method for a modeled camera includes the following steps:

[0005] Step S1: Conduct a geometric topology analysis on the stadium to obtain a stadium functional area model; conduct a fluid dynamics simulation on the stadium functional area model to obtain crowd density distribution characteristic data; divide the stadium into risk levels according to the crowd density distribution characteristic data to obtain a stadium key area evaluation matrix;

[0006] Step S2: Based on the crowd density distribution characteristic data, conduct a dynamic density field modeling on the stadium to obtain a crowd density field mathematical model; conduct a monitoring requirement analysis on the stadium according to the crowd density field mathematical model and the stadium key area evaluation matrix to obtain a monitoring coverage plan; evenly allocate the density of cameras according to the monitoring coverage plan to obtain a camera distribution density plan;

[0007] Step S3: Divide the stadium into spaces according to the camera distribution density plan to obtain a stadium space segmentation network; conduct a field of view overlap degree evaluation on the cameras based on the stadium space segmentation network to obtain field of view coverage effect data;

[0008] Step S4: Identify dead angle areas from the field of view coverage effect data to obtain a stadium monitoring dead angle distribution map; conduct an optimization solution on the stadium monitoring dead angle distribution map to obtain a target collaborative coverage plan;

[0009] Step S5: Coordinately manage the camera group according to the target collaborative coverage scheme to obtain an intelligent monitoring network scheme.

[0010] The present invention accurately identifies the distribution of pedestrian flow density through geometric topology analysis and hydrodynamic simulation, improves the monitoring efficiency and coverage rate, and ensures that all key areas in a large stadium are effectively monitored. By dividing the risk levels of the stadium, the risk management ability is enhanced, resources can be deployed targeted, and emergencies can be prevented and responded to in advance. Through the evaluation of pedestrian flow density and key areas of the stadium, the density of cameras is evenly configured, the layout of cameras is optimized, resource waste is avoided, and the continuity and dead - free of monitoring are ensured. Through dynamic density field modeling and analysis of monitoring requirements, it can adapt to the dynamic changes of pedestrian flow in the stadium and adjust the monitoring strategy in real time. Through stadium space segmentation and evaluation of field - of - view overlap, the field - of - view coverage effect is further improved, monitoring blind spots are reduced, and the monitoring quality is improved. Through the identification and optimization of dead - end areas, it helps to discover and optimize monitoring dead - end areas, enhancing the integrity and reliability of the monitoring system. Finally, through the coordinated management of the camera group, an intelligent monitoring network scheme is constructed, which not only covers all key areas but also can intelligently respond to emergencies, improving the emergency response speed and processing efficiency. The present invention has strong adaptability, is applicable to different stadium structures and pedestrian flow characteristics, provides data - driven decision - making support, makes the monitoring layout more scientific and reasonable, and significantly improves the safety and emergency response ability of the stadium.

[0011] Preferably, the present invention also provides a layout system of model - based cameras for implementing the above - mentioned layout method of model - based cameras. The layout system of model - based cameras includes:

[0012] An area risk assessment module, which is used to perform geometric topology analysis on the stadium to obtain a stadium functional area model; perform hydrodynamic simulation on the stadium functional area model to obtain pedestrian flow density distribution characteristic data; divide the risk levels of the stadium according to the pedestrian flow density distribution characteristic data to obtain a stadium key area evaluation matrix;

[0013] A monitoring configuration analysis module, which is used to perform dynamic density field modeling on the stadium based on the pedestrian flow density distribution characteristic data to obtain a mathematical model of the crowd density field; perform monitoring requirement analysis on the stadium according to the mathematical model of the crowd density field and the stadium key area evaluation matrix to obtain a monitoring coverage range scheme; evenly configure the density of cameras according to the monitoring coverage range scheme to obtain a camera distribution density scheme;

[0014] A field - of - view evaluation module, which is used to divide the space of the stadium according to the camera distribution density scheme to obtain a stadium space segmentation network; perform field - of - view overlap evaluation on the cameras based on the stadium space segmentation network to obtain field - of - view coverage effect data;

[0015] An optimization coverage module is used to identify dead - angle areas from the field - of - view coverage effect data to obtain a distribution map of monitoring dead - angles in the venue; perform optimization and solution on the distribution map of monitoring dead - angles in the venue to obtain a target collaborative coverage plan.

[0016] A collaborative management module is used to collaboratively manage the camera group according to the target collaborative coverage plan to obtain an intelligent monitoring network plan.

[0017] Through the integrated modules, the present invention realizes automated risk assessment, improves the efficiency and accuracy of risk assessment; ensures the reasonable allocation and efficient utilization of monitoring resources through precise monitoring configuration; maximizes the field - of - view coverage effect through optimized space division, reduces monitoring blind spots; significantly improves the integrity and reliability of the monitoring system through intelligent identification and optimization of dead - angle areas; enhances the response speed and processing efficiency of the monitoring system through intelligent collaborative management, especially in emergency situations; the design of the entire system improves the safety and emergency handling capabilities of public places such as large stadiums. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Other features, objectives, and advantages of the present invention will become more apparent by reading the following detailed description with reference to the accompanying drawings:

[0019] Figure 1 Shows a schematic flow chart of the steps of a layout method for a modeled camera in an embodiment.

[0020] Figure 2 Shows a detailed schematic flow chart of step S2 in an embodiment.

[0021] Figure 3 Shows a detailed schematic flow chart of step S26 in an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0022] The following clearly and completely describes the technical method of the present invention with reference to the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of them. All other embodiments obtained by those skilled in the art within the scope of the present invention without creative efforts belong to the protection scope of the present invention.

[0023] In addition, the attached drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the drawings denote the same or similar parts, and thus repeated descriptions thereof will be omitted. Some of the block diagrams shown in the drawings are functional entities and do not necessarily correspond to physically or logically independent entities. The functional entities can be implemented in software form, or in one or more hardware modules or integrated circuits, or in different networks and / or processor methods and / or microcontroller methods.

[0024] It should be understood that although terms such as "first" and "second" may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, without departing from the scope of the exemplary embodiments, the first unit may be referred to as the second unit, and similarly the second unit may be referred to as the first unit. The term "and / or" used herein includes any and all combinations of one or more of the listed associated items.

[0025] To achieve the above object, please refer to Figures 1 to 3 , the present invention provides a layout method for a modeled camera, including the following steps:

[0026] Step S1: Perform geometric topology analysis on the venue to obtain a venue functional area model; perform hydrodynamic simulation on the venue functional area model to obtain crowd density distribution characteristic data; divide the risk level of the venue according to the crowd density distribution characteristic data to obtain a venue key area evaluation matrix;

[0027] Step S2: Perform dynamic density field modeling on the venue based on the crowd density distribution characteristic data to obtain a crowd density field mathematical model; analyze the monitoring requirements of the venue according to the crowd density field mathematical model and the venue key area evaluation matrix to obtain a monitoring coverage plan; perform density equalization configuration on the cameras according to the monitoring coverage plan to obtain a camera distribution density plan;

[0028] Step S3: Divide the space of the venue according to the camera distribution density plan to obtain a venue space segmentation network; evaluate the field of view overlap degree of the cameras based on the venue space segmentation network to obtain field of view coverage effect data;

[0029] Step S4: Identify dead corner areas from the field of view coverage effect data to obtain a venue monitoring dead corner distribution map; perform optimization solution on the venue monitoring dead corner distribution map to obtain a target collaborative coverage plan;

[0030] Step S5: Perform collaborative management on the camera groups according to the target collaborative coverage plan to obtain an intelligent monitoring network plan.

[0031] In this embodiment, first, 3D laser scanning technology is used to perform geometric topology analysis on the venue to generate point cloud data of the venue. Using Autodesk Revit software, a 3D model of the venue is created based on the point cloud data, and different functional areas are divided, such as the auditorium, the competition venue, and the entrances and exits, etc., to form a venue functional area model. Next, computational fluid dynamics software, such as ANSYS Fluent, is used to perform fluid mechanics simulation on the venue functional area model. By simulating crowd flow, characteristic data of the crowd density distribution is obtained, and these data show the crowd density in different areas of the venue. Using Python and the machine learning library Scikit-learn, the venue is classified according to the characteristic data of the crowd density distribution, high-risk areas are identified, and an evaluation matrix of the key areas of the venue is constructed. This matrix can determine which areas require more monitoring resources. Based on the characteristic data of the crowd density distribution, MATLAB is used to perform dynamic density field modeling to establish a mathematical model of the crowd density field. Combining with the evaluation matrix of the key areas of the venue, the monitoring requirements are analyzed to determine the monitoring coverage plan. Then, using monitoring layout planning software, such as Milestone System Designer, the cameras are evenly configured according to the monitoring coverage plan to ensure that the key areas are fully covered while avoiding waste of resources, and a camera distribution density plan is obtained. According to the camera distribution density plan, Revit is used again to divide the space of the venue to obtain a venue space segmentation network. Then, a PTZ (Pan-Tilt-Zoom) camera simulation software is used to simulate the camera field of view, evaluate the field of view overlap, and obtain field of view coverage effect data. Using GIS software, such as ArcGIS, dead angle areas are identified from the field of view coverage effect data to obtain a venue monitoring dead angle distribution map. Through spatial analysis tools, the monitoring dead angles are optimized to obtain a target collaborative coverage plan. Finally, using a network management system, such as Cisco DNA Center, the camera groups are collaboratively managed according to the target collaborative coverage plan. The network parameters of the cameras are configured to implement an intelligent monitoring network plan to ensure the efficient operation and real-time response of the monitoring system.

[0032] Preferably, step S1 includes the following steps:

[0033] Step S11: Perform multi-angle point cloud acquisition on the venue to obtain the original venue point cloud data, and denoise the original venue point cloud data to obtain the denoised venue point cloud data;

[0034] Specifically, 5 3D laser scanners can be deployed at different locations in the venue, and each scanner can cover a part of the venue area. These scanners rotate 360 degrees omnidirectionally, capture the three-dimensional geometric information of the venue, and generate the original venue point cloud data. This data contains the X, Y, and Z coordinates of each point in the venue, as well as the reflection intensity and color information. After the acquisition is completed, professional point cloud processing software, such as CloudCompare or PCL (Point Cloud Library), is used to denoise the original point cloud data. The denoising process includes removing outliers, smoothing, and filtering. For example, a filter is set to identify points whose distance from surrounding points exceeds a certain threshold as noise and remove them from the dataset. Finally, the denoised venue point cloud data is obtained.

[0035] Step S12: Perform topological feature encoding on the denoised venue point cloud data to obtain the venue spatial semantic encoding data, and perform 3D modeling on the venue based on the venue spatial semantic encoding data to obtain the venue point cloud model;

[0036] Specifically, software tools such as GIS (Geographic Information System) software can be used for topological feature encoding, such as ArcGIS or QGIS. Perform topological feature encoding on each point in the denoised venue point cloud data, which involves identifying the connection relationships between points, such as adjacency and intersection. Through this encoding, the point cloud data can be converted into the venue's spatial semantic encoding data, which contains not only geometric information but also spatial relationship information. Use 3D modeling software, such as Autodesk Revit or SketchUp, to perform 3D modeling on the venue based on the spatial semantic encoding data. During the modeling process, first create the basic structure of the venue, such as walls, columns, and roofs. According to the geometric information in the point cloud data, adjust the dimensions and positions of these structures to ensure that they match the geometric shape of the actual venue. Interior facilities of the venue, such as seats, walkways, and stairs, can also be added. Through adjustment and optimization, the venue point cloud model is finally obtained.

[0037] Step S13: Perform surface reconstruction on the venue point cloud model to obtain the venue reconstructed point cloud model, and extract surface features from the venue reconstructed point cloud model to obtain the venue surface geometric feature data;

[0038] Specifically, 3D reconstruction software such as MeshLab or Agisoft Metashape can be used to process the venue point cloud model. In MeshLab, its surface reconstruction tool is utilized. By selecting the dense areas in the point cloud and applying the Poisson reconstruction algorithm, a reconstructed venue point cloud model is generated. Feature extraction tools are used to identify and quantify the surface geometric features of the reconstructed venue point cloud model. This includes extracting edges, corners, and regions, as well as calculating their geometric properties such as curvature, normal vectors, and distances. For example, an edge detection algorithm is used to identify the edges of walls and columns in the venue model, and then the lengths and directions of these edges are calculated. For corners, the RANSAC (Random Sample Consensus) algorithm is used to identify the intersection points of lines and planes in the point cloud, and the exact positions and angles of these corners are calculated.

[0039] Step S14: Calculate the spatial connectivity of the venue based on the venue surface geometric feature data to obtain a venue topological relationship graph;

[0040] Specifically, computational geometry software such as CGAL (Computational Geometry Algorithms Library) can be used to analyze the geometric feature data of the venue and calculate the spatial connectivity. The 3D model of the venue is imported into CGAL, and its data structures and algorithms are used to identify the holes, channels, and regions in the model. The concepts of graph theory are used to represent the spatial structure of the venue, where nodes represent the intersection points or turning points in space, and edges represent the paths or corridors connecting these points. For example, all the entrances and exits in the venue are identified, and the shortest paths between them are calculated. In this way, a venue topological relationship graph can be constructed, which shows the connectivity of all the spaces in the venue, including which regions are interconnected and the strength of their connections. GIS software can also be used to assist in the analysis, combining the topological relationship graph with the geographical information of the venue to further analyze the potential paths of people flow and logistics. Finally, a detailed venue topological relationship graph is obtained, which not only shows the physical structure of the venue but also reveals the logical relationships between the spaces.

[0041] Step S15: Divide the venue into structural zones according to the venue topological relationship graph to obtain venue functional area partition data, and divide the venue point cloud model according to the venue functional area partition data to obtain a venue functional area model;

[0042] Specifically, building information modeling (BIM) software, such as Autodesk Revit, can be used to import and analyze the venue topology diagram. Revit allows different functional areas to be defined based on the connectivity and spatial relationships in the topology diagram. For example, the venue is divided into the following functional areas: the auditorium area, the playing field area, the entrance / exit area, the lounge area, and the emergency evacuation area. In Revit, a separate model group is created for each area, and the corresponding parts in the point cloud model are assigned to these groups. The boundaries of these areas are determined by identifying key nodes in the topology diagram, such as the intersections of corridors, the locations of stairs, and obvious spatial partitions. The three-dimensional modeling tools in Revit are used to refine the boundaries of these areas. For example, a virtual wall is created between the auditorium area and the playing field area to clearly define these two areas. Models of doors and passages can also be added in the entrance / exit area to reflect the actual flow of people. After these operations are completed, each area is color-coded. Finally, the data of these functional areas is exported as a new point cloud model file, which contains the detailed division of each functional area in the venue.

[0043] Step S16: Conduct a hydrodynamic simulation on the venue functional area model to obtain the characteristic data of the crowd density distribution, and divide the risk levels of the venue based on the characteristic data of the crowd density distribution to obtain the venue key area evaluation matrix.

[0044] Specifically, for the detailed implementation process of this embodiment, please refer to the sub-steps of Step S16.

[0045] The present invention improves the data quality through multi-angle point cloud acquisition and denoising processing. The generation of topological feature coding and spatial semantic coding enhances the understanding of the venue space structure. The capture of the subtle geometric features of the venue is achieved through three-dimensional modeling and surface reconstruction. The generation of the venue topology diagram enables accurate calculation of spatial connectivity and understanding of the patterns of people flow and aggregation. The effective division of different functional areas of the venue is realized through structural zoning and the generation of the functional area model, providing an accurate area division for obtaining the characteristic data of the crowd density distribution. The accuracy of the crowd flow simulation is improved through hydrodynamic simulation, which helps to predict the crowd density distribution and identify high-risk areas. The scientific nature of the risk assessment is enhanced through the risk level division based on the characteristic data of the crowd density distribution, which helps to identify and prevent potential safety problems in advance. The key areas are accurately identified through the generation of the venue key area evaluation matrix, ensuring the concentrated investment of monitoring resources in the key areas.

[0046] Preferably, Step S16 includes the following steps:

[0047] Step S161: Conduct a time-series tracking of the number of people in the venue to obtain the extreme value data of the number of people in the venue;

[0048] Specifically, a high-precision pedestrian flow counting system can be installed at the main entrance of the venue. This system includes infrared sensors, pressure sensors, and video surveillance cameras, which are integrated into a pedestrian flow counting device, such as Axis People Counter. During the implementation process, first configure the infrared sensors and pressure sensors to detect the pedestrian flow passing through the entrance. When someone passes through the entrance, these sensors can sense the change and trigger the counting. On large event or competition days, monitor the pedestrian flow counting system in real time and record the number of people entering every hour or even every minute. In this way, the changing trend of the pedestrian flow can be tracked, and peak hours of the pedestrian flow can be identified, such as the 30 minutes before the start and the 30 minutes after the end. The lowest point of the pedestrian flow can also be recorded, such as the halftime period during the competition. Identify the extreme values of the pedestrian flow, including key data points such as the maximum pedestrian flow within a single hour, the maximum pedestrian flow in a single day, and the maximum pedestrian flow in history.

[0049] Step S162: Extract spatial parameters from the venue functional area model to obtain the venue structure feature library;

[0050] Specifically, 3D modeling software, such as SketchUp or AutoCAD, can be used to process and analyze the venue's functional area model. In these software, measure and record parameters such as the size, shape, and location of each functional area. For example, measure the length and width of each row of seats in the auditorium area, record the position of each seat, and calculate the total area of each area. The width and height of the entrances and their distances from the main activity areas can also be extracted from the model. The width and length of the passageways and the different areas they connect can also be measured. Use spatial analysis tools, such as buffer analysis and network analysis tools in GIS software, to further extract and analyze these spatial parameters. For example, create a buffer for each entrance to determine its influence range and analyze the accessibility between different areas. Through these analyses, the venue structure feature library is finally obtained, which contains the spatial parameters of each functional area and structure in the venue.

[0051] Step S163: Based on the venue structure feature library, construct a crowd flow simulation grid for the venue to obtain the venue flow domain division grid;

[0052] Specifically, simulation software such as AnyLogic or MATSim can be used. These software can handle complex human flow dynamics and simulate crowd behavior. Detailed spatial parameters of the venue are extracted from the venue structure feature library, including the dimensions of each area, the width and length of the passageways, the locations of the entrances and exits, etc. Taking a specific example, assume there is a stadium. According to the information in the venue structure feature library, the stadium is divided into multiple grid cells. Each grid cell represents a specific area, such as the spectator stands, walkways, entrances, and exits. Software like AutoCAD or GIS is used to accurately draw these grids and ensure that the dimensions and locations of each grid cell match the actual venue. In the simulation software, specific attributes are assigned to each grid cell, such as capacity, passing speed, and pedestrian flow. For example, the grid cells of the walkways are set to allow fast flow, while the grid cells of the spectator stands are set to move at a low speed. The connection relationships between the grid cells can also be set according to the structural features of the venue, such as the locations of the emergency exits. In this way, the grid division of the venue flow domain can be obtained.

[0053] Step S164: Set boundary conditions for the grid division of the venue flow domain according to the extreme value data of the venue pedestrian flow to obtain the initial parameters of the venue flow field;

[0054] Specifically, computational fluid dynamics simulation software such as ANSYS Fluent or OpenFOAM can be used. These software can handle the simulation of the human flow as a fluid and accurately set the boundary conditions. Assume that the extreme value data of the venue pedestrian flow at different time periods are obtained from step S161. According to these data, boundary conditions are set for each entrance and exit of the grid division of the venue flow domain. For example, according to the maximum pedestrian flow data 30 minutes before the start, the grid cells of the main entrance are set with the boundary condition of allowing 3000 people to enter per hour. According to the minimum pedestrian flow data during the dispersal, the grid cells of the exit are set with the boundary condition of allowing 1000 people to leave per hour. Special situations inside the venue can also be considered, such as the flow speed and direction of the crowd during an emergency evacuation. According to safety regulations and historical data, specific boundary conditions are set for the grid cells of the emergency exits. For example, in an emergency, each grid cell of the emergency exits must be able to evacuate 500 people within 5 minutes. Through the setting of these boundary conditions, the initial parameters of the venue flow field can be obtained.

[0055] Step S165: Perform numerical simulation calculations on the initial parameters of the venue flow field to obtain the crowd flow field distribution data, and extract the dynamic characteristics of the crowd flow field distribution data to obtain the crowd density distribution characteristic data;

[0056] Specifically, computational fluid dynamics (CFD) software, such as ANSYS Fluent or CFX, can be used to perform these calculations. First, according to the boundary conditions set in step S164, the initial parameters of the venue flow field are input into the simulation software. These parameters include the pedestrian flow velocity, direction, and density of each grid cell. During the simulation, physical models of crowd movement, such as the social force model or the hydrodynamic model, are applied to simulate the behavior of the crowd. For example, a model based on the Navier-Stokes equations is used, which takes into account the inertia of the crowd, the repulsive force between them, and the attraction of the environment. Through these models, the pedestrian flow density and velocity of each grid cell at different time points are calculated. After the simulation is completed, distribution data of the crowd flow field are obtained, including the pedestrian flow density and velocity of each grid cell at different time points. To extract the dynamic characteristics of these data, data post-processing tools, such as Tecplot or Paraview, are used to visualize and analyze the simulation results. The peak areas of pedestrian flow density, flow bottlenecks, and high-flow areas are identified, and this information is correlated with time to obtain the characteristics of the change in pedestrian flow density over time. Through these analyses, characteristic data of the pedestrian flow density distribution are finally obtained, which reflect the changes in pedestrian flow density in different areas of the venue at different time periods.

[0057] Step S166: Perform threshold segmentation on the characteristic data of the pedestrian flow density distribution to obtain the venue crowd density level zoning;

[0058] Specifically, the characteristic data of the pedestrian flow density distribution can be imported into GIS software, and thresholds are created according to the numerical range of the pedestrian flow density. For example, the pedestrian flow density is divided into four levels: low (0 - 10 people per square meter), medium (11 - 20 people per square meter), high (21 - 30 people per square meter), and very high (more than 30 people per square meter). Using the classification tool in the GIS software, the grid cells of the venue are divided into different density level areas according to these thresholds. Each area will be assigned a specific color or symbol. In this way, the venue crowd density level zoning is finally obtained, which shows the pedestrian flow density levels in different areas of the venue.

[0059] Step S167: Assign risk weights to the venue crowd density level zoning to obtain the venue key area evaluation matrix.

[0060] Specifically, risk assessment software such as @RISK or Crystal Ball can be used in combination with the analysis tools in GIS software to perform risk weight allocation. Based on the results of the zoning by pedestrian flow density level, determine the risk weight for each zone. Consider multiple factors, including pedestrian flow density, the function of the area (such as exits, entrances, emergency evacuation areas), historical safety incident records, and the physical characteristics of the area (such as narrow passages or stairs). For example, assign higher risk weights to areas with very high pedestrian flow density, especially emergency evacuation areas and narrow passages, because these areas are more prone to congestion and safety accidents in case of emergencies. Use Excel or a professional decision support system to construct an evaluation matrix for the key areas of the venue. In this matrix, each row represents a zone, and each column represents a risk factor. Assign a weight to each risk factor for each zone, and these weights are based on expert opinions, historical data, and simulation results. For example, assign a higher risk weight to the "emergency evacuation capacity" factor in areas with high pedestrian flow density, and a lower risk weight to the same factor in areas with low pedestrian flow density. Calculate the overall risk score for each zone, which is obtained by weighted summation of the weights of each risk factor. Finally, obtain an evaluation matrix for the key areas of the venue, which includes the overall risk score for each zone.

[0061] The present invention improves the dynamic monitoring ability of pedestrian flow through the time series tracking of pedestrian flow volume, providing real-time data support for pedestrian flow management and safety monitoring. Extracting spatial parameters lays a foundation for in-depth analysis of the venue structure characteristics and the establishment of a structure feature library. Constructing a pedestrian flow simulation grid makes the pedestrian flow simulation more accurate and can simulate the flow of pedestrian flow in the venue. Using the extreme value data of pedestrian flow volume is used to scientifically set the boundary conditions of the flow domain division grid to ensure the scientificity and accuracy of the simulation calculation. Numerical simulation calculation and dynamic feature extraction provide the distribution data of the crowd flow field and accurately simulate the dynamic of pedestrian flow. The application of threshold segmentation realizes the hierarchical management of pedestrian flow density, facilitating targeted monitoring. Through risk weight allocation, the risk levels of each area in the venue can be refined and evaluated, providing guidance for safety monitoring and emergency response.

[0062] Preferably, step S2 includes the following steps:

[0063] Step S21: Identify the spatio-temporal sequence of the pedestrian flow density distribution characteristics data to obtain the crowd density change characteristics data;

[0064] Specifically, data analysis tools such as the Python environment combined with the Pandas library and the Scikit-learn library can be used to process and analyze the data on the distribution characteristics of pedestrian flow density. First, extract the data on the distribution characteristics of pedestrian flow density within the past month from the database. These data are collected by multiple sensors in the venue at different times and locations. The dataset contains information such as the ID of each sensor, the number of people detected, the detection time, and the date. Use the Pandas library to load these data into a DataFrame, convert the timestamp to the DateTime format of Pandas, and set it as the index of the DataFrame. This can obtain a time series data framework that contains the pedestrian flow density data of each sensor changing over time. Use the time series analysis tools in the Scikit-learn library to analyze these data. First, use the Fourier transform to identify the periodic patterns in the data, such as daily and weekly cycles, which helps to understand the daily changes in pedestrian flow density and the weekend effect. Apply the ARIMA model to predict the short-term change trend of pedestrian flow density, which helps to predict the peak of pedestrian flow within a specific time period. Use the K-means clustering algorithm to perform clustering analysis on the sensor data. Classify the sensors into several groups according to the similarity of pedestrian flow density. Each group represents an area with similar pedestrian flow density in the venue. By analyzing the time series of these groups, the common characteristics of the change in pedestrian flow density can be identified, such as the phenomenon of pedestrian aggregation in a specific area during a specific time period. Finally, obtain the data on the change characteristics of crowd density, which includes not only the time change trend of pedestrian flow density but also the spatial distribution characteristics.

[0065] Step S22: Based on the data on the change characteristics of crowd density, perform Markov state transition modeling to obtain a crowd density dynamic evolution model;

[0066] Specifically, statistical modeling software such as R or the Statsmodels library in Python can be used to build a Markov model. Divide the data on the change characteristics of crowd density into different states, such as low density, medium density, and high density. Use the Hidden Markov Model (HMM) to model the transition probabilities between these states. For example, it is found that before the start of the game, the probability of the pedestrian flow density transitioning from the low-density state to the high-density state increases significantly. Use the maximum likelihood estimation method to estimate the state transition probabilities, and use the Viterbi algorithm to determine the state sequence at each time point. Through these analyses, a crowd density dynamic evolution model can be obtained, which can predict the state changes of crowd density at different time periods.

[0067] Step S23: Perform a partial differential equation parameterization description on the crowd density dynamic evolution model to obtain data on the crowd density field expression, and perform an analytical solution on the data on the crowd density field expression to obtain a crowd density field mathematical model;

[0068] Specifically, mathematical modeling software such as the PDE Toolbox of MATLAB or COMSOL Multiphysics can be used to perform parametric description of partial differential equations. First, based on the state transition probabilities and state durations of the Markov model obtained in step S22, a continuous time-space population density model (population density dynamic evolution model) is established. Assume that the change of population density over time and space can be described by a partial differential equation, such as a convection-diffusion equation, which takes into account the flow and diffusion effects of the population. Using the parameter estimation function in the PDE Toolbox, the state transition probabilities and durations of the Markov model are input as parameters into the PDE. For example, the state transition probability is used as the coefficient of the convection term, and the state duration is used as the coefficient of the diffusion term. These parameters are calibrated to ensure that the solution of the PDE model matches the actual observed data. A numerical solver such as the finite element method (FEM) is used to solve these PDEs. In MATLAB or COMSOL, the type, boundary conditions, and initial conditions of the PDE are defined, and then the solver is run to obtain the expression data of the population density field. These data provide a mathematical description indicating the population density at different time and space positions. Finally, a mathematical model of the population density field is obtained, which can predict the distribution of population density under different conditions.

[0069] Step S24: Construct constraint conditions for the mathematical model of the population density field to obtain data for describing the monitoring coverage optimization problem;

[0070] Specifically, optimization software such as CPLEX or Gurobi, and mathematical modeling tools such as AMPL or the SciPy library of Python can be used to construct constraint conditions. First, the objective function and constraint conditions of the monitoring coverage optimization problem are defined. The objective function is to minimize the area of the monitoring blind area or maximize the coverage rate of key areas. The constraint conditions include the field of view angle limit of the camera, installation location limit, and budget limit. The optimization module in the SciPy library is used to define these constraint conditions and apply them to the mathematical model of the population density field. For example, the field of view angle limit of the camera is used as a constraint condition to ensure that the coverage area of each camera matches the high population density area. GIS software can also be used to analyze the geographical information of the venue and incorporate geographical constraint conditions such as the positions of walls and obstacles into the optimization problem. Finally, data for describing the monitoring coverage optimization problem is obtained.

[0071] Step S25: Solve the data for describing the monitoring coverage optimization problem using the variational method to obtain the monitoring coverage range function, and perform gradient projection optimization on the monitoring coverage range function to obtain data for the locally optimal coverage solution;

[0072] Specifically, mathematical modeling and optimization software, such as MATLAB or the CVXPY library in Python, can be used to solve the variational method. First, define the monitoring coverage function, which is a function representing the relationship between the camera coverage area and the mathematical model of the crowd density field. Use the variational method to solve the optimal solution of this function. The variational method involves finding a function that can minimize or maximize a functional, which is an integral of the function. In this case, the functional is the integral of the product of the monitoring coverage and the crowd density field. Use the numerical optimization tools in MATLAB or Python to solve this variational problem. For example, in Python, use the CVXPY library to define this functional and use its built-in solver to find the optimal solution. This solver is based on algorithms such as gradient descent or Newton's method. Perform gradient projection optimization on the monitoring coverage function. Gradient projection is an optimization algorithm that finds the optimal solution by moving along the opposite direction of the gradient of the objective function and projecting back into the feasible region at each step. Use the optimization tools in MATLAB or Python to implement the gradient projection algorithm. In each iteration, calculate the gradient of the monitoring coverage function and update the solution along the opposite direction of the gradient. Project the updated solution back into the feasible region, which is defined by the physical limitations of the camera and the geometric constraints of the venue. This process is repeated until convergence to a local optimal solution. Finally, obtain the local optimal coverage solution data.

[0073] Step S26: Perform global constraint reconstruction on the local optimal coverage solution data according to the venue key area evaluation matrix to obtain the monitoring coverage scheme; perform density equalization configuration on the cameras according to the monitoring coverage scheme to obtain the camera distribution density scheme.

[0074] Specifically, for the detailed implementation process of this embodiment, please refer to the sub-steps of step S26.

[0075] The present invention captures the variation characteristics of crowd density over time and space, providing detailed dynamic data for crowd flow management and monitoring. Enhances the system's ability to predict the dynamic evolution of crowd density through Markov state transition modeling. Provides a mathematical model through parametric description and analytical solution of partial differential equations. Makes the monitoring coverage optimization problem more scientific and accurate by constructing constraint conditions, clarifying the goals and limitations for solving the optimal monitoring coverage range. Improves the utilization efficiency and coverage effect of monitoring resources and solves the local optimal coverage solution through the application of the variational method and gradient projection optimization. Ensures that the monitoring coverage scheme not only considers the local optimum but also meets the global security requirements through global constraint reconstruction according to the venue key area evaluation matrix. Makes the camera distribution more reasonable through the density equalization configuration method, ensuring full coverage of key areas while avoiding resource waste. The optimized monitoring coverage scheme helps to detect and respond to potential security risks in a timely manner, reduce the probability of accidents, and improve the rapid accuracy of emergency response.

[0076] Preferably, step S26 includes the following steps:

[0077] Step S261: Normalize the feature weights of the venue key area evaluation matrix to obtain a standardized coverage weight factor;

[0078] Specifically, data processing software such as Excel or the Pandas library in Python can be used to process the venue key area evaluation matrix. First, extract the risk scores of each area from the venue key area evaluation matrix. These scores include multiple factors such as pedestrian flow density, emergency evacuation ability, and historical safety event records. The goal is to convert these risk scores of different magnitudes and units into comparable standardized coverage weight factors. Use the min-max normalization method, which is a common feature scaling technique, to transform the original data into the range of [0,1]. In this way, a normalized value is calculated for each risk factor in each area, and then these values are aggregated to obtain the standardized coverage weight factor for each area.

[0079] Step S262: Reconstruct the semantic constraints of the local optimal coverage solution data according to the standardized coverage weight factor to obtain sensitivity area mapping data;

[0080] Specifically, GIS software such as ArcGIS or QGIS, and optimization tools such as the SciPy library in Python can be used to perform semantic constraint reconstruction. First, use the standardized coverage weight factor as the input, combined with the geographical information of the venue and the camera layout data. The goal is to adjust the local optimal coverage solution to ensure that high-risk areas (i.e., areas with high standardized coverage weight factors) receive more monitoring resources. Use the optimization module in the SciPy library to define an optimization problem, where the objective function is to maximize the coverage of high-risk areas. Add semantic constraints to ensure that the camera layout not only considers the coverage range but also the risk weight of the area. For example, set a constraint such that each high-risk area is covered by at least one camera, and the weighted sum of the coverage ranges of these cameras is maximized. Use GIS software to visualize these constraints and apply them to the local optimal coverage solution data. Adjust the position and orientation of the cameras to meet these semantic constraints while trying to maintain the optimization of the coverage range. In this way, sensitivity area mapping data is finally obtained, which indicates the monitoring sensitivity and priority of each area.

[0081] Step S263: Identify the spatial topological constraints of the venue point cloud model to obtain the venue topological constraint mapping set;

[0082] Specifically, 3D modeling and analysis software such as Autodesk Revit or Rhinoceros can be used, combined with professional topology analysis tools such as TopoShape or through the Shapely library in Python to identify spatial topology constraints. First, import the venue point cloud model into Revit or Rhinoceros, and use the topology analysis functions of these software to identify structural features in the model, such as walls, columns, stairs, and passages. Mark these features and record their spatial positions and the connection relationships between them. Use the Shapely library in Python for more detailed topology constraint analysis. For example, calculate the intersection points between walls, determine the centerlines of passages, and identify the exact positions of entrances and exits. This information is used to construct a set of topology constraint mappings that includes the spatial positions and topological relationships of all key structures in the venue. Finally, export these topology constraint mappings as a dataset. This dataset assigns a unique identifier to each structural feature and details their spatial attributes and topological connections.

[0083] Step S264: Perform entropy reduction optimization on the locally optimal coverage solution data according to the sensitivity area mapping data and the venue topology constraint mapping set to obtain a monitoring coverage range plan;

[0084] Specifically, optimization software such as MATLAB or the SciPy library in Python can be used, combined with GIS software to perform entropy reduction optimization. First, merge the sensitivity area mapping data and the venue topology constraint mapping set into a unified data framework. Use optimization algorithms in the SciPy library, such as linear programming or dynamic programming, to adjust the locally optimal coverage solution to meet these constraint conditions. For example, there is a highly sensitive area, such as the VIP entrance, which needs to be completely covered by at least one camera. Use the information in the topology constraint mapping set to ensure that the camera layout does not violate physical limitations, such as cameras cannot be installed inside the wall. Adjust the positions of the cameras according to the sensitivity area mapping data to maximize the coverage of the highly sensitive area. Use entropy reduction optimization to measure the uniformity and coverage efficiency of the camera layout. The goal of entropy reduction optimization is to reduce the uncertainty and randomness of the camera layout while increasing the deterministic coverage of key areas. By adjusting the positions and directions of the cameras, minimize the entropy value to obtain a more optimized monitoring coverage range plan. Finally, use GIS software to visualize this optimized monitoring coverage range plan.

[0085] Step S265: Use the preset regional importance weight index to perform sensitivity clustering on the monitoring coverage range plan to obtain a hierarchical weighted monitoring priority sequence;

[0086] Specifically, data science and machine learning tools such as the Scikit-learn library in Python can be used to perform sensitivity clustering. First, define a set of regional importance weight metrics, which include pedestrian flow density, historical safety event frequency, and the functional importance of the region (such as VIP areas, exits, entrances, etc.). Assign a weight to each metric, and these weights are derived based on expert opinions and historical data analysis. Use the K-means clustering algorithm in the Scikit-learn library to perform sensitivity clustering on different regions of the venue. Calculate a comprehensive sensitivity score for each region according to the preset weight metrics, and use this score as the basis for clustering. For example, divide the venue into regions with high, medium, and low sensitivity levels. During the clustering process, adjust the parameters of the clustering algorithm, such as the number of clusters (K value) and distance metric, to ensure the rationality and accuracy of the clustering results. After clustering, finally obtain a hierarchical weighted monitoring priority sequence, which indicates the monitoring importance of different regions. Regions with high sensitivity will be given a higher monitoring priority to ensure that these regions are covered by denser monitoring.

[0087] Step S266: Based on the venue topology constraint mapping set and the hierarchical weighted monitoring priority sequence, perform density equalization configuration on the venue to obtain a camera distribution density plan.

[0088] Specifically, GIS software such as ArcGIS and optimization tools such as the PuLP library in Python can be used to perform density equalization configuration. First, merge the hierarchical weighted monitoring priority sequence with the venue topology constraint mapping set to form a comprehensive data set. Use ArcGIS to visualize this data and determine the physical limitations and monitoring requirements of each region. Use the PuLP library to define a linear programming problem, with the goal of minimizing the monitoring blind spots while considering the cost and installation limitations of the cameras. Define a decision variable for each region, representing the number of cameras in that region, and set the constraint conditions according to the sensitivity level and topology constraints of the region. For example, require that there is at least one camera in high-sensitivity regions, while low-sensitivity regions can share cameras. By solving this linear programming problem, a camera distribution density plan can be obtained, which details the number and location of cameras in each region.

[0089] The present invention enhances the fairness of weight processing through feature weight normalization, ensuring the rationality of monitoring resource allocation. It enhances the semantic rationality of the coverage solution through semantic constraint reconstruction, making it more in line with actual monitoring requirements. It provides key spatial information for the monitoring layout by effectively utilizing the spatial topology, optimizing the monitoring coverage range, and improving the monitoring efficiency and quality. It enhances the sensitivity recognition of the monitoring scheme through sensitivity clustering, providing a basis for formulating monitoring priorities. Through the implementation of a hierarchical weighted monitoring priority sequence, differential monitoring can be carried out according to the importance of regions, giving priority to ensuring the safety of key regions. Through the density balance configuration based on the venue topology constraint and the monitoring priority sequence, refined management of the camera layout is achieved, ensuring full coverage of key regions.

[0090] Preferably, step S3 includes the following steps:

[0091] Step S31: Parse the key nodes of the venue point cloud model according to the camera distribution density scheme to obtain the venue space semantic seed point set;

[0092] Specifically, 3D modeling software such as Autodesk 3ds Max or professional point cloud processing software such as CloudCompare can be used to perform the key node parsing. First, import the camera distribution density scheme into 3ds Max, which contains the positions and coverage ranges of each camera. Use the grid tool in 3ds Max to identify the key nodes in the venue point cloud model, which are the installation positions of the cameras or the central points of densely populated areas. Use the point cloud screening function of CloudCompare to extract these key nodes to form the venue space semantic seed point set. For example, select the points located at the center of high pedestrian density areas or those near the venue entrances and exits. Ensure that the distribution of these seed point sets in space is uniform and covers all important monitoring areas within the venue. The selection of these seed point sets takes into account the field of view and coverage range of the cameras to ensure that the final monitoring layout can meet the monitoring requirements.

[0093] Step S32: Perform topological connection on the venue space semantic seed point set to obtain the initial triangular grid of the venue space, and perform regional segmentation on the initial triangular grid of the venue space to obtain the venue space partition grid;

[0094] Specifically, 3D modeling and mesh generation software, such as MeshLab or Salome, can be used to perform topological connection. First, import the set of semantic seed points of the venue space into MeshLab. Use the triangulation tool in MeshLab to perform topological connection on these seed points and generate an initial triangular mesh. This mesh captures the main structural features of the venue space, such as walls, passages, and open areas. Use the mesh segmentation tool in Salome to perform regional segmentation on the initial triangular mesh. Define the segmentation rules according to the functional areas of the venue and the camera distribution density scheme. For example, divide the auditorium area, the competition venue, and the entrance and exit areas into different meshes, with each mesh corresponding to a specific functional area. Ensure that each segmented mesh contains sufficient details. These partitioned meshes will be used to guide the specific installation positions and directions of the cameras to achieve the best monitoring effect. Through these operations, the partitioned mesh of the venue space is finally obtained.

[0095] Step S33: Optimize the boundary morphology of the partitioned mesh of the venue space to obtain the venue space segmentation network;

[0096] Specifically, computer-aided design (CAD) software, such as AutoCAD, or geographic information system (GIS) software, such as ArcGIS, can be used to perform boundary morphology optimization. First, import the data of the partitioned mesh of the venue space into AutoCAD. Use the drawing and editing tools in AutoCAD to adjust the mesh boundaries to make them more conform to the actual structure of the venue. For example, if there are deviations between the mesh boundaries and the actual positions of the walls or passages, manually adjust these boundaries. Use the geoprocessing tools in ArcGIS to optimize the morphology of the mesh. Apply spatial analysis tools, such as buffer analysis and overlay analysis, to identify and solve problems such as overlapping or gaps between meshes. For example, it is found that the boundaries of two adjacent meshes overlap, or the boundary of a mesh extends beyond the actual boundary of the venue. Adjust these boundaries to ensure that each mesh is independent and completely contained within the venue. Through these operations, the venue space segmentation network is finally obtained, and this network accurately reflects the internal structure of the venue.

[0097] Step S34: Based on the camera distribution density scheme and the venue space segmentation network, perform geometric constraint modeling on the camera field of view angle to obtain the venue monitoring field of view cone model;

[0098] Specifically, 3D modeling software such as SketchUp or professional geometric modeling software such as SolidWorks can be used to perform geometric constraint modeling. Import the data of the venue space segmentation network and the camera distribution density scheme into SketchUp. Use the modeling tools in SketchUp to create a 3D model of the camera and place it at the predetermined installation location. Use the geometric constraint function in SolidWorks to define the geometric constraints of the camera's field of view angle. Set the geometric shape of the field of view cone according to the technical parameters of the camera, such as the field of view angle and focal length. For example, if a camera has a field of view angle of 90 degrees, create a cone centered on the camera with an opening angle of 90 degrees in SolidWorks. Ensure that the field of view cone model of each camera matches the venue space segmentation network, which means that the boundary of the field of view cone has no conflict with the walls and other structures of the venue. Adjust the position and orientation of the camera to ensure that the field of view cone completely covers its corresponding monitoring area and does not overlap with the field of view cones of other cameras. Through these operations, a venue monitoring field of view cone model can be obtained, which details the monitoring range and angle of each camera.

[0099] Step S35: Perform spatial cross-identification on the cameras based on the venue monitoring field of view cone model to obtain the camera field of view overlap matrix;

[0100] Specifically, 3D modeling and analysis software such as Revit or 3ds Max can be combined with mathematical calculation software such as MATLAB to perform spatial cross-identification. First, import the venue monitoring field of view cone model into Revit, which contains the field of view angle and position information of each camera. Use the 3D analysis tool in Revit to simulate the field of view cone of each camera and compare it with the field of view cones of other cameras. Use MATLAB for mathematical calculations and write scripts to calculate the intersection of each pair of field of view cones. Define a function to calculate the overlap degree of two field of view cones, which calculates the intersection area based on the spatial position and angle of the two cones. For each pair of cameras in the venue, calculate their field of view overlap degree and store it in a matrix, that is, the camera field of view overlap matrix.

[0101] Step S36: Perform occlusion suppression identification on the overlapping area according to the camera field of view overlap matrix to obtain the effective coverage map of the monitoring field of view;

[0102] Specifically, GIS software such as ArcGIS and image processing software such as Adobe Photoshop or GIMP can be used to perform occlusion suppression recognition tasks. First, import the camera field of view overlap matrix into ArcGIS. Use the spatial analysis tools in ArcGIS to identify those areas with highly overlapping fields of view and mark these areas as potential occlusion areas. For example, if the field of view overlap of two cameras exceeds a certain threshold, it is considered that there is an occlusion between these two fields of view. Use Photoshop or GIMP to process the images of these overlapping areas. Simulate the actual coverage of the camera field of view by adjusting the transparency or using layer masks. For example, overlay the images of the fields of view of two cameras and intuitively display their overlap and occlusion by adjusting the transparency. Through these operations, finally obtain an effective coverage map of the monitoring field of view, which details the actual coverage areas of each camera, including those occluded areas.

[0103] Step S37: Quantitatively evaluate the coverage rate of the effective coverage map of the monitoring field of view to obtain field of view coverage effect data.

[0104] Specifically, GIS software such as ArcGIS or QGIS and data analysis tools such as the Geopandas library in Python can be used to perform the coverage rate quantitative evaluation. First, import the effective coverage map of the monitoring field of view into ArcGIS. This coverage map contains the field of view areas and potential occlusion areas of each camera. Use the spatial analysis tools in ArcGIS, such as Viewshed Analysis and Overlay Analysis, to quantify the coverage of each area. Use the Geopandas library in Python to process and analyze this spatial data. Write scripts to calculate the coverage area of each area and compare it with the total area of the venue to calculate the coverage rate. For example, calculate the area of the field of view area of each camera and divide it by the total area of the venue to obtain the coverage rate percentage of each area. Further analyze this data to identify areas with a coverage rate lower than expected. For example, if the coverage rate of a certain area is lower than the set threshold, mark it as an area that requires additional cameras or adjustment of the positions of existing cameras. Finally, obtain the field of view coverage effect data, which includes the coverage rate of each area, a list of areas with a coverage rate lower than the threshold, and suggestions for optimizing the positions of cameras.

[0105] Through spatial semantic analysis, the present invention efficiently constructs a venue space grid, optimizes the space grid to fit the actual structure of the venue, accurately models the camera field of view angle, effectively identifies the field of view overlap and occlusion areas, and realizes the quantitative evaluation of the monitoring coverage rate. The present invention not only optimizes the camera layout, ensures the efficient use of monitoring resources, but also improves the coverage quality of the monitoring system and reduces the monitoring blind spots.

[0106] Preferably, step S4 includes the following steps:

[0107] Step S41: Perform spherical coordinate transformation on the camera field of view based on the field of view coverage effect data to obtain a camera panoramic spherical projection model;

[0108] Specifically, 3D graphics processing software such as Blender and mathematical calculation software such as MATLAB can be used to perform spherical coordinate transformation. First, import the field of view coverage effect data into Blender. These data include the position, field of view angle, and coverage area of each camera. Use the camera object in Blender to simulate the field of view of each camera and set the corresponding field of view angle parameters. Use MATLAB to calculate the spherical coordinate transformation. Write a script to convert the field of view of each camera from the Cartesian coordinate system to the spherical coordinate system. In this process, define the center of the sphere (i.e., the camera position), and calculate the longitude and latitude coordinates of each field of view boundary point on the sphere. For example, for a camera with a field of view angle of 90 degrees, calculate the spherical coordinates of all points on its field of view boundary and generate a corresponding spherical model in MATLAB. Through these operations, a camera panoramic spherical projection model can be obtained, which accurately describes the distribution of the field of view of each camera on the sphere.

[0109] Step S42: Perform panoramic mapping calculation on the camera field of view based on the camera panoramic spherical projection model to obtain a venue monitoring panoramic coverage map;

[0110] Specifically, panoramic image processing software such as PTGui and GIS software such as ArcGIS can be used to perform panoramic mapping calculations. First, import the camera panoramic spherical projection model into PTGui. Use the spherical panoramic stitching function of PTGui to stitch the field-of-view images of each camera into a complete panoramic image. During this process, adjust the stitching parameters of the images, such as control points and projection types. Import the stitched panoramic image into ArcGIS and use its spatial analysis tools to calculate the panoramic coverage map. According to the spherical coordinates of the field of view of each camera, determine its coverage area in the panoramic image, and calculate the intersection and union of these areas. For example, calculate the total coverage area of all camera fields of view and the overlapping areas between these fields of view. Through these operations, a panoramic coverage map of the venue monitoring can be obtained, which details the total coverage of all cameras in the venue, including the coverage area and monitoring blind spots.

[0111] Step S43: Extract extreme value features from the panoramic coverage map of the venue monitoring to obtain a set of extreme value boundary points of the field of view, and perform a field-of-view geometric constraint mapping on the venue space based on the set of extreme value boundary points of the field of view to obtain field-of-view critical area mapping data;

[0112] Specifically, image processing software such as Adobe Photoshop and GIS software such as ArcGIS can be used to perform extreme value feature extraction. First, import the panoramic coverage map of the venue monitoring into Photoshop. Use the image analysis tools of Photoshop to identify the extreme value features in the image, such as extreme changes in brightness, color, or texture, which indicate the boundaries or special areas of the field of view. Import this set of extreme value feature points into ArcGIS and use the spatial analysis tools of ArcGIS to perform a field-of-view geometric constraint mapping on the venue space. By calculating the relative positions of these sets of extreme value boundary points and the venue geometric structure, determine the critical areas of the field of view. For example, it is found that some sets of extreme value boundary points coincide with the entrances and exits or emergency evacuation routes of the venue, and these areas need special attention. Through these operations, finally obtain the field-of-view critical area mapping data, which details the key monitoring areas in the venue.

[0113] Step S44: Perform blind spot semantic recognition on the venue space according to the field-of-view critical area mapping data to obtain a monitoring dead spot location table, and perform spatial clustering on the monitoring dead spot location table to obtain a distribution map of the monitoring dead spots in the venue;

[0114] Specifically, GIS software such as QGIS and data science tools such as the Scikit-learn library in Python can be used to perform blind area semantic recognition. First, import the field of view critical area mapping data into QGIS. Use QGIS's spatial query tool to identify the monitoring blind areas within these critical areas. For example, it is found that certain areas are not covered due to the limitations of the camera's field of view, and these areas are marked as monitoring dead zones. Use the Scikit-learn library in Python to perform spatial clustering analysis on the monitoring dead zone location table. Apply the K-means clustering algorithm to group these monitoring dead zones, and each group represents a specific monitoring blind area. Set the clustering parameters such as the number of clusters and distance metric according to the location, size, and importance of the dead zones. Through these operations, a distribution map of the monitoring dead zones in the venue can be obtained, which details the locations and distributions of all monitoring blind areas within the venue.

[0115] Step S45: Optimize and solve the distribution map of the monitoring dead zones in the venue to obtain the target collaborative coverage plan.

[0116] Specifically, for the detailed implementation process of this embodiment, please refer to the sub-steps of step S45.

[0117] The present invention realizes a panoramic monitoring view through spherical coordinate transformation and panoramic mapping calculation, provides a broader monitoring view, and enhances the view and function of the monitoring system. By extracting extreme value features to identify the set of field of view boundary points, the identification and optimization of monitoring blind areas are optimized. By obtaining the field of view critical area mapping data, the blind areas in the venue space are effectively identified, the monitoring coverage rate is increased, and the monitoring blind areas are reduced. By managing the monitoring dead zone locations through spatial clustering, a distribution map of the monitoring dead zones is generated. Through the target collaborative coverage plan obtained from the optimization and solution process, the reasonable allocation and efficient utilization of monitoring resources are realized, and the overall performance of the monitoring system is improved.

[0118] Preferably, step S45 includes the following steps:

[0119] Step S451: Construct an objective function for the distribution map of the monitoring dead zones in the venue to obtain a set of target collaborative coverage constraint conditions;

[0120] Specifically, mathematical modeling and optimization software, such as MATLAB or the PuLP library in Python, can be used to perform the construction of the objective function. First, import the data of the distribution map of blind spots in the venue monitoring into MATLAB. Use the optimization toolbox of MATLAB to define an objective function that aims to minimize the total area of blind spots while maximizing the coverage efficiency of cameras. Considering the installation cost, maintenance cost, and coverage effect of cameras, these factors are used as parameters of the objective function. Define a series of constraint conditions, including the field of view angle of cameras, installation location restrictions, and areas that must be covered. For example, it is stipulated that each camera must cover at least a certain area of high-risk areas, and the total installation cost of all cameras shall not exceed the budget. Through these operations, a set of objective collaborative coverage constraint conditions is finally obtained, and this set of conditions contains the mathematical expressions of all camera layout optimization problems.

[0121] Step S452: Perform topological feature mapping on the set of objective collaborative coverage constraint conditions to obtain a constraint space connectivity graph, and perform random walk dimensionality reduction on the feasible solution search space in the constraint space connectivity graph to obtain a set of candidate solution search subspaces;

[0122] Specifically, topological analysis software, such as TopoSimplify, and data science tools, such as the NetworkX library in Python, can be used to perform topological feature mapping. First, import the set of objective collaborative coverage constraint conditions into TopoSimplify. Use the topological analysis tool of TopoSimplify to identify the connected areas in the venue and map these areas into the constraint space connectivity graph. This graph shows the connectivity between various areas in the venue and their relationship with the camera coverage range. Use the NetworkX library in Python to process this connectivity graph and apply the random walk algorithm for dimensionality reduction. Randomly select nodes (representing potential camera positions) in this graph and simulate the random walk process to explore feasible camera layout schemes. Through this method, the search space can be reduced from the entire venue space to a smaller set of candidate solution search subspaces, and this set of subspaces contains all camera layout schemes. Through these operations, a set of candidate solution search subspaces is finally obtained, and this set of subspaces significantly reduces the number of camera layout schemes that need to be considered while retaining the possibility of the optimal solution.

[0123] Step S453: Perform a global optimal solution search on the set of candidate solution search subspaces to obtain a set of candidate solutions for objective collaborative coverage;

[0124] Specifically, mathematical optimization software such as CPLEX or Gurobi can be used to perform the global optimal solution search. First, all camera layout schemes in the candidate solution search subspace set are imported into CPLEX. The optimization algorithm of CPLEX is used to evaluate the coverage effect and cost - effectiveness of each scheme. Define an objective function that aims to maximize the monitoring coverage rate and reduce costs, while taking into account the field - of - view overlap and dead - angle areas of the cameras. Set a series of constraints, including the installation positions of the cameras, the field - of - view angles, and the key areas that must be covered. CPLEX uses its built - in algorithms such as the branch - and - bound method or the cutting - plane method to search for the global optimal solution. During the search process, CPLEX evaluates each candidate solution and compares it with the objective function and constraints to determine its advantages and disadvantages. Finally, CPLEX returns a set of candidate solutions that provide the best monitoring coverage effect while satisfying all the constraints. Through these operations, the target collaborative coverage candidate solution set is finally obtained, and this solution set contains all potential optimal camera layout schemes.

[0125] Step S454: Perform Pareto - optimal evaluation and screening on the target collaborative coverage candidate solution set to obtain the target collaborative coverage selected solution set;

[0126] Specifically, multi - objective optimization tools such as the Pareto Frontier toolbox in MATLAB or the Pyomo library in Python can be used to perform Pareto - optimal evaluation and screening. First, the target collaborative coverage candidate solution set is imported into MATLAB, and its Pareto Frontier toolbox is used to evaluate the multi - objective performance of each solution. Define two main objectives: maximize the monitoring coverage rate and minimize the cost. For each candidate solution, calculate its performance on these two objectives and compare them on the Pareto front. Use MATLAB's graphical tools to visualize these solutions and identify the Pareto - optimal solutions. These solutions provide the best trade - off between the two objectives, that is, no other solution can improve one objective without sacrificing the other. Use the Pyomo library to further screen these Pareto - optimal solutions. Define an optimization model that includes the objective functions of the monitoring coverage rate and cost, as well as the relevant constraints. Use the solver of Pyomo to evaluate each Pareto - optimal solution and select those that are the most feasible and effective in practical applications. Through these operations, the target collaborative coverage selected solution set is finally obtained, and this solution set contains the optimal camera layout schemes that have the greatest potential to achieve the monitoring objectives.

[0127] Step S455: Perform the final configuration on the target collaborative coverage selected solution set to obtain the target collaborative coverage scheme.

[0128] Specifically, project management and decision support software, such as Microsoft Project, or professional decision analysis software, such as Decision Lens, can be used to perform the final configuration. First, import the target collaborative coverage selected solution set into Microsoft Project. This solution set contains camera layout plans that have been screened through Pareto optimality assessment, and each plan has different monitoring coverage rates and cost-effectiveness. Use the resource planning and scheduling functions of Microsoft Project to evaluate the implementation feasibility of each plan. Consider factors such as the installation time of the cameras, the maintenance cycle, and the coordination with other venue facilities. For example, it is found that a certain plan requires camera installation on the game day, which will affect the normal operation of the venue, so the plan needs to be adjusted to avoid such conflicts. Use the decision analysis tools of Decision Lens to comprehensively evaluate each plan. Invite venue managers, security experts, and financial staff to form a decision-making team. According to the professional knowledge and experience of their respective technical staff, score and discuss the advantages and disadvantages of each plan. Use the weighted scoring card and decision tree tools of Decision Lens to integrate the opinions of the team and identify the final optimal plan. This plan takes into account cost-effectiveness and implementation feasibility while meeting the monitoring coverage requirements. Through these operations, the target collaborative coverage plan is finally obtained, which details the installation location, field of view angle, and expected monitoring effect of each camera.

[0129] The present invention enhances the recognition ability of monitoring blind spots by constructing an objective function and performing topological feature mapping. By utilizing random walk dimensionality reduction, the solution search efficiency is improved, and the problem dimension is reduced. By combining global optimal solution search and Pareto optimality assessment screening, the quality of candidate solutions is optimized, and better solutions are screened out. By evaluating the quality of solutions from multiple dimensions through Pareto optimality assessment screening, the rationality of monitoring resource allocation is improved, and the allocation of monitoring resources is optimized. The target collaborative coverage plan for the final configuration comprehensively considers various factors, realizes the optimization of monitoring coverage, and improves the overall performance and efficiency of the monitoring system.

[0130] Preferably, step S5 includes the following steps:

[0131] Step S51: Deploy a camera monitoring system for the venue according to the target collaborative coverage plan, and construct a distributed network for the camera monitoring system to obtain a monitoring data transmission architecture;

[0132] Specifically, network design and deployment tools such as Cisco Packet Tracer or Huawei's eSight network management system can be used to perform the deployment of the camera monitoring system. First, take the camera positions and quantities determined in the target collaborative coverage plan as basic data and import them into Cisco Packet Tracer. Simulate the network layout of the venue, including the positions of cameras, the placement of network switches, and the routing paths of optical fibers or cables. Ensure that each camera is connected to the network and that the network architecture can support the transmission of high-definition video streams. Use the eSight network management system to configure the actual network devices such as cameras, switches, and routers. Assign a unique IP address to each camera and set network parameters such as subnet mask and default gateway. Ensure that the network bandwidth is sufficient to support all cameras being online simultaneously and consider future expansion. Through these operations, a monitoring data transmission architecture is finally obtained, which details how the cameras are connected to the network and how data flows in the network.

[0133] Step S52: Design the communication protocol for the cameras based on the monitoring data transmission architecture to obtain the venue monitoring network control plan;

[0134] Specifically, communication protocol analysis tools such as Wireshark and network configuration tools such as Cisco's IOS command-line interface (CLI) can be used to perform the communication protocol design. First, analyze the monitoring data transmission architecture to determine the communication protocols to be used. Select protocols suitable for video stream transmission, such as H.264 or H.265 encoding protocols, and protocols suitable for network communication, such as TCP / IP or UDP. Use Wireshark to capture and analyze the data packets in the network to ensure that the selected protocols can stably transmit data in the network. Adjust protocol parameters such as transmission rate and buffer size to optimize the quality and latency of the video stream. Use Cisco's IOS CLI to configure network devices such as cameras and switches to support the selected communication protocols. Set QoS (Quality of Service) rules to ensure the priority transmission of video stream data and reduce the impact of network congestion. Through these operations, a venue monitoring network control plan is finally obtained, which details how the cameras transmit data through the network and how to manage and control these data streams.

[0135] Step S53: Allocate bandwidth for the venue monitoring network control plan to obtain the monitoring network resource scheduling strategy;

[0136] Specifically, network management software such as SolarWinds Network Performance Monitor or PRTG Network Monitor can be used to perform bandwidth allocation. First, analyze the data transmission requirements of all cameras in the venue, including the video resolution, frame rate, and encoding format. Determine the amount of data generated by each camera and predict the total data traffic during peak hours. Use SolarWinds Network Performance Monitor to monitor the bandwidth usage of the existing network, identify bottlenecks and idle resources. Based on the monitoring data and predicted traffic requirements, allocate bandwidth to each camera or camera group. For example, allocate more bandwidth to cameras in high-risk areas to ensure the video stream quality in critical areas. Set QoS rules to prioritize the video stream transmission of critical cameras and allocate appropriate bandwidth to cameras in non-critical areas. Through these operations, a monitoring network resource scheduling strategy is finally obtained, which details how to reasonably allocate network resources.

[0137] Step S54: Perform regional management division on the camera groups according to the monitoring network resource scheduling strategy to obtain a camera group control unit;

[0138] Specifically, network configuration and management tools such as Cisco's DNA Center or ArubaCentral can be used to perform regional management division. First, divide the venue into multiple management regions according to the physical layout of the venue and the coverage area of the cameras. For example, divide the venue into an entrance area, a spectator area, a playing area, and a logistics area. Use Cisco's DNA Center to configure the network parameters and security policies for each region. Set independent SSIDs and VLANs for the camera groups in each region to isolate traffic and improve security. Configure different bandwidth limits and QoS policies for each region to meet the monitoring requirements of different regions. Use Aruba Central to monitor and manage the camera groups in each region. Set automated fault detection and recovery policies to ensure that the monitoring of relevant regions is not interrupted in case of equipment failure or network problems. Through these operations, a camera group control unit is finally obtained, which details how the cameras in each region are managed and controlled.

[0139] Step S55: Based on the camera group control unit, make collaborative decisions on the camera monitoring system to obtain a venue monitoring management strategy set;

[0140] Specifically, an intelligent monitoring and management system, such as Genetec Security Center or Verint Video Intelligence, can be used to perform collaborative decision-making. First, import the data of the camera group control unit into Genetec Security Center. This unit contains the camera configurations and network parameters for each area. Use the collaborative decision-making tool of Genetec Security Center to analyze the data streams and monitoring coverage of each camera group in the venue. Set a series of collaborative decision-making rules. For example, when the crowd density in a certain area exceeds a preset threshold, the system will automatically adjust the monitoring parameters of the cameras in that area, such as increasing the frame rate or adjusting the focal length, to obtain a clearer monitoring image. At the same time, the monitoring priority of this area will be increased, and the camera resources in other areas will be mobilized to provide additional monitoring support. Use the video analysis tool of Verint Video Intelligence to implement these collaborative decisions. For example, use the behavior analysis function to identify abnormal behaviors, such as crowd gathering or rapid movement, and then automatically adjust the monitoring strategies of relevant cameras to respond to these situations. Through these operations, a venue monitoring management strategy set is finally obtained, which details how to adjust the monitoring strategies of cameras according to real-time monitoring data and preset rules.

[0141] Step S56: Perform consistency maintenance on the venue monitoring management strategy set to obtain an intelligent monitoring network plan.

[0142] Specifically, network management and configuration tools, such as Ansible or Puppet, and monitoring and analysis tools, such as Nagios or Zabbix, can be used to perform consistency maintenance. First, import the venue monitoring management strategy set into Ansible. Use the automation script function of Ansible to ensure that all cameras and network devices are configured and updated according to the requirements of the strategy set. For example, write an Ansible playbook to automatically update the firmware of the cameras, configure network parameters, and assign IP addresses. Use Nagios to monitor the performance and health status of the entire monitoring network. Set a series of monitoring metrics, such as CPU usage, memory usage, network latency, and packet loss rate, and set thresholds for each metric. When any metric exceeds the threshold, Nagios will automatically issue an alarm and trigger preset response measures, such as restarting the device or reallocating network resources. Through these operations, an intelligent monitoring network plan is finally obtained.

[0143] The present invention provides a stable architecture for monitoring data transmission through a distributed network, ensuring efficient data transmission and processing. Through the optimized design of the communication protocol, the reliability and efficiency of communication between cameras are improved. By implementing bandwidth allocation and resource scheduling strategies, the use of network resources is intelligently optimized, enhancing network performance and user experience. Through the implementation of regional management division, the management of camera groups is realized, enhancing the flexibility and response speed of the monitoring system. Through the collaborative decision-making based on the camera group control unit, the monitoring management efficiency and effect are improved, and the optimal allocation of monitoring resources is achieved. By maintaining the consistency of the monitoring management strategy set, the stability and reliability of the system are enhanced, and the risk resistance ability is improved.

[0144] Preferably, the present invention further provides a layout system for modeled cameras, which is used to execute the layout method for modeled cameras as described above. The layout system for modeled cameras includes:

[0145] A regional risk assessment module, which is used to perform geometric topology analysis on the venue to obtain a venue functional area model; perform hydrodynamic simulation on the venue functional area model to obtain crowd density distribution characteristic data; divide the risk level of the venue according to the crowd density distribution characteristic data to obtain a venue key area evaluation matrix;

[0146] A monitoring configuration analysis module, which is used to perform dynamic density field modeling on the venue based on the crowd density distribution characteristic data to obtain a mathematical model of the crowd density field; perform monitoring requirement analysis on the venue according to the mathematical model of the crowd density field and the venue key area evaluation matrix to obtain a monitoring coverage plan; perform density balanced configuration on the cameras according to the monitoring coverage plan to obtain a camera distribution density plan;

[0147] A field of view evaluation module, which is used to perform spatial division on the venue according to the camera distribution density plan to obtain a venue spatial segmentation network; perform field of view overlap degree evaluation on the cameras based on the venue spatial segmentation network to obtain field of view coverage effect data;

[0148] An optimization coverage module, which is used to identify dead corner areas from the field of view coverage effect data to obtain a venue monitoring dead corner distribution map; perform optimization solution on the venue monitoring dead corner distribution map to obtain a target collaborative coverage plan;

[0149] A collaborative management module, which is used to perform collaborative management on the camera group according to the target collaborative coverage plan to obtain an intelligent monitoring network plan.

[0150] Therefore, from any perspective, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, it is intended to encompass all changes falling within the meaning and scope of the equivalent elements of the application documents within the present invention.

[0151] The above are only specific embodiments of the present invention, enabling those skilled in the art to understand or implement the present invention. Various modifications to these embodiments will be obvious to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to these embodiments shown herein, but rather to the broadest scope consistent with the principles and novel features invented herein.

Claims

1. A modeled camera layout method, characterized in that: The following steps are involved: Step S1: Perform geometric topological analysis on the venue to obtain a functional area model of the venue; perform fluid mechanics simulation on the functional area model of the venue to obtain characteristic data of crowd density distribution; classify the venue into risk levels according to the characteristic data of crowd density distribution to obtain a key area assessment matrix of the venue; Step S2: Based on the crowd density distribution characteristic data, a dynamic density field model is constructed for the venue to obtain a crowd density field mathematical model; based on the crowd density field mathematical model and the venue key area evaluation matrix, a monitoring demand analysis is conducted on the venue to obtain a monitoring coverage plan; based on the monitoring coverage plan, cameras are density-balancedly configured to obtain a camera distribution density plan; Step S3: spatially divide the venue according to the camera distribution density plan to obtain a venue space segmentation network; evaluate the field of view overlap of the cameras based on the venue space segmentation network to obtain field of view coverage effect data; Step S4: identify blind spots in the field of view coverage effect data to obtain a blind spot distribution map for venue monitoring; optimize and solve the blind spot distribution map for venue monitoring to obtain a target collaborative coverage solution; Step S5: Coordinate management of camera groups according to the target collaborative coverage plan to obtain an intelligent monitoring network solution.

2. The layout method of the modeled cameras according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: performing multi-angle point cloud acquisition on the venue to obtain original venue point cloud data, and denoising the original venue point cloud data to obtain denoised venue point cloud data; Step S12: topological feature encoding is performed on the denoised venue point cloud data to obtain venue space semantic encoding data, and three-dimensional modeling of the venue is performed based on the venue space semantic encoding data to obtain a venue point cloud model; Step S13: performing surface reconstruction on the venue point cloud model to obtain a reconstructed venue point cloud model, and performing surface feature extraction on the venue reconstructed point cloud model to obtain venue surface geometric feature data; Step S14: Calculate the spatial connectivity of the venue based on the surface geometric feature data of the venue to obtain a topological relationship diagram of the venue; Step S15: Structurally partitioning the venue according to the venue topological relationship diagram to obtain venue functional area partition data, and partitioning the venue point cloud model according to the venue functional area partition data to obtain the venue functional area model; Step S16: Perform fluid mechanics simulation on the functional area model of the venue to obtain characteristic data of crowd density distribution, and classify the venue into risk levels based on the characteristic data of crowd density distribution to obtain an assessment matrix for key areas of the venue.

3. The layout method of the modeled cameras according to claim 2, characterized in that: Step S16 includes the following steps: Step S161: Track the flow of people in the venue in time series to obtain the extreme value data of the flow of people in the venue; Step S162: extracting spatial parameters of the venue functional area model to obtain a venue structure feature library; Step S163: constructing a crowd flow simulation grid for the venue based on the venue structure feature library to obtain a venue flow domain division grid; Step S164: setting boundary conditions for the grids of the flow domain of the venue according to the extreme value data of the venue passenger flow, and obtaining the initial parameters of the flow field of the venue; Step S165: performing numerical simulation calculation on the initial parameters of the flow field of the venue to obtain crowd flow field distribution data, and performing dynamic feature extraction on the crowd flow field distribution data to obtain crowd flow density distribution feature data; Step S166: performing threshold segmentation on the crowd density distribution characteristic data to obtain crowd density level partitions of the venue; Step S167: Allocate risk weights to the crowd density level zones of the venue to obtain a venue key area assessment matrix.

4. The method for layout of modeled cameras according to claim 1, characterized in that: Step S2 includes the following steps: Step S21: performing spatiotemporal sequence recognition on the crowd density distribution characteristic data to obtain crowd density change characteristic data; Step S22: Performing Markov state transition modeling based on the crowd density change characteristic data to obtain a crowd density dynamic evolution model; Step S23: performing a partial differential equation parameter description on the crowd density dynamic evolution model to obtain crowd density field expression data, and performing analytical solution on the crowd density field expression data to obtain a crowd density field mathematical model; Step S24: construct constraint conditions for the mathematical model of the crowd density field to obtain monitoring coverage optimization problem description data; Step S25: performing a variational method to solve the monitoring coverage optimization problem description data to obtain a monitoring coverage function, and performing gradient projection optimization on the monitoring coverage function to obtain local optimal coverage solution data; Step S26: Perform global constraint reconstruction on the local optimal coverage solution data according to the venue key area evaluation matrix to obtain a monitoring coverage plan; perform density-balanced configuration of cameras according to the monitoring coverage plan to obtain a camera distribution density plan.

5. The method for arranging modeled cameras according to claim 4, characterized in that: Step S26 includes the following steps: Step S261: normalizing the feature weights of the venue key area evaluation matrix to obtain a standardized coverage weight factor; Step S262: reconstructing the local optimal coverage solution data with semantic constraints according to the standardized coverage weight factor to obtain sensitive area mapping data; Step S263: performing spatial topological constraint identification on the venue point cloud model to obtain a venue topological constraint mapping set; Step S264: performing entropy reduction optimization on the local optimal coverage solution data according to the sensitive area mapping data and the venue topology constraint mapping set to obtain a monitoring coverage solution; Step S265: using the preset regional importance weight index to perform sensitivity clustering on the monitoring coverage scheme to obtain a hierarchical weighted monitoring priority sequence; Step S266: Based on the venue topology constraint mapping set and the hierarchical weighted monitoring priority sequence, the venue is density-balancedly configured to obtain a camera distribution density plan.

6. The method for layout of modeled cameras according to claim 1, characterized in that: Step S3 includes the following steps: Step S31: parsing the key nodes of the venue point cloud model according to the camera distribution density scheme to obtain the venue space semantic seed point set; Step S32: topologically connect the venue space semantic seed point set to obtain the venue space initial triangular mesh, and segment the venue space initial triangular mesh into regions to obtain the venue space partition grid; Step S33: Optimizing the boundary morphology of the venue space partition grid to obtain the venue space segmentation network; Step S34: geometrically constraining the camera field of view angles based on the camera distribution density scheme and the venue space segmentation network to obtain a venue monitoring field of view cone model; Step S35: performing spatial cross-recognition on the cameras based on the venue monitoring field of view cone model to obtain a camera field of view overlap matrix; Step S36: performing occlusion suppression identification on the overlapping area according to the camera field of view overlap matrix to obtain an effective coverage map of the monitoring field of view; Step S37: Perform a quantitative evaluation of the coverage rate of the monitoring field of view effective coverage map to obtain field of view coverage effect data.

7. The method for layout of modeled cameras according to claim 1, characterized in that: Step S4 includes the following steps: Step S41: performing spherical coordinate transformation on the camera field of view based on the field of view coverage effect data to obtain a camera panoramic spherical projection model; Step S42: performing panoramic mapping calculation on the camera field of view based on the camera panoramic spherical projection model to obtain a panoramic coverage map of the venue monitoring; Step S43: extracting extreme value features from the panoramic coverage map of the venue monitoring to obtain a set of extreme value boundary points of the field of view, and performing field of view geometric constraint mapping on the venue space based on the set of extreme value boundary points of the field of view to obtain field of view critical area mapping data; Step S44: performing blind spot semantic recognition on the venue space according to the field of view critical area mapping data to obtain a monitoring blind spot position table, and performing spatial clustering on the monitoring blind spot position table to obtain a venue monitoring blind spot distribution map; Step S45: Optimize and solve the venue monitoring blind spot distribution map to obtain a target collaborative coverage solution.

8. The method for arranging modeled cameras according to claim 7, characterized in that: Step S45 includes the following steps: Step S451: constructing an objective function for the venue monitoring blind spot distribution map to obtain a target collaborative coverage constraint condition set; Step S452: topological feature mapping is performed on the target collaborative coverage constraint condition set to obtain a constraint space connectivity graph, and random walk dimensionality reduction is performed on the feasible solution search space in the constraint space connectivity graph to obtain a candidate solution search subspace set; Step S453: performing a global optimal solution search on the candidate solution search subspace set to obtain a target collaborative coverage candidate solution set; Step S454: Perform Pareto optimal evaluation and screening on the target collaborative coverage candidate solution set to obtain the target collaborative coverage selected solution set; Step S455: finally configure the target collaborative coverage selected solution set to obtain the target collaborative coverage solution.

9. The method for layout of modeled cameras according to claim 1, characterized in that: Step S5 includes the following steps: Step S51: deploying a camera monitoring system for the venue according to the target collaborative coverage plan, and constructing a distributed network for the camera monitoring system to obtain a monitoring data transmission architecture; Step S52: Designing a communication protocol for the camera based on the monitoring data transmission architecture to obtain a venue monitoring network control solution; Step S53: Allocate bandwidth for the venue monitoring network control solution to obtain a monitoring network resource scheduling strategy; Step S54: performing regional management division on the camera group according to the monitoring network resource scheduling strategy to obtain a camera group control unit; Step S55: performing collaborative decision-making on the camera monitoring system based on the camera group control unit to obtain a venue monitoring management strategy set; Step S56: Maintain the consistency of the venue monitoring management strategy set to obtain an intelligent monitoring network solution.

10. A modeled camera layout system, characterized in that: The method for executing the layout of the modeled camera according to claim 1, wherein the layout system of the modeled camera comprises: The regional risk assessment module is used to perform geometric topological analysis on the venue to obtain the venue's functional area model; perform fluid mechanics simulation on the venue's functional area model to obtain crowd density distribution characteristic data; classify the venue into risk levels based on the crowd density distribution characteristic data to obtain the venue's key area assessment matrix; The monitoring configuration analysis module is used to model the dynamic density field of the venue based on the crowd density distribution characteristic data to obtain the crowd density field mathematical model; analyze the monitoring needs of the venue according to the crowd density field mathematical model and the venue key area evaluation matrix to obtain the monitoring coverage plan; and perform density balancing configuration of cameras according to the monitoring coverage plan to obtain the camera distribution density plan; The field of view evaluation module is used to divide the venue into spaces according to the camera distribution density plan to obtain the venue space segmentation network; based on the venue space segmentation network, the camera field of view overlap is evaluated to obtain the field of view coverage effect data; The coverage optimization module is used to identify blind spots in the field of view coverage effect data and obtain a blind spot distribution map for venue monitoring; the blind spot distribution map for venue monitoring is optimized and solved to obtain a target collaborative coverage solution; The collaborative management module is used to collaboratively manage the camera group according to the target collaborative coverage plan to obtain an intelligent monitoring network solution.

Images