Modeled camera layout method and system

Abstract

The invention relates to the technical field of camera layout, in particular to a modeling camera layout method and system. The method comprises the following steps: acquiring three-dimensional geometric scanning data and dynamic object data of a monitoring space; performing light field space modeling on the monitoring space according to the three-dimensional geometric scanning data to obtain space light field distribution data; performing light tracing analysis on the spatial light field distribution data according to the dynamic object data to obtain light propagation characteristic data; performing effective coverage analysis based on a light intensity threshold value and a field angle range on the monitoring area by using the light propagation characteristic data so as to obtain area coverage characteristic data; and performing adaptive optimization calculation on the initial layout of the camera through the area coverage feature data and pre-acquired environment parameter data to obtain camera layout parameter data. By introducing the four-dimensional light field function, the propagation characteristics of the light in the space can be comprehensively described, so that the coverage analysis is more accurate.

Description

Technical Field

[0001] The present invention relates to the field of camera layout technology, and in particular to a modeled camera layout method and system. Background Art

[0002] Camera layout is a key link in the design of security monitoring systems. Reasonable layout can ensure comprehensive coverage of the monitoring area, improve monitoring effects and optimize costs. It is necessary to identify key areas that need to be monitored, such as entrances, exits, corridors, parking lots, cash registers, stairwells, elevators, cargo loading and unloading areas, etc. Determine the priority of monitoring according to the importance of the scene, personnel mobility and risk level. For example, high-risk places such as banks and jewelry stores require more intensive camera layout. When arranging cameras, adjust their angles to ensure that there are no obvious blind spots in the monitoring picture. The viewing angles of multiple cameras should have a certain overlap to ensure seamless coverage of key areas. The installation height and inclination of the camera will also affect the monitoring effect. It should usually be installed at a higher position to avoid being blocked and have a larger field of view.

[0003] However, the current modeling camera layout methods often have the following problems: Many virtual modeling and simulation tools are based on static scene settings, which makes it difficult to simulate real-time changing environments; for example, in the design of smart city road lighting, natural light, traffic flow and environmental conditions change over time, and static simulations are difficult to capture these dynamic factors, resulting in the design scheme not being able to meet real-time control needs during actual operation. For scenes that need to be automatically adjusted according to factors such as personnel activities and ambient light (such as smart office areas or large exhibition centers), virtual models can usually only simulate fixed scenarios in advance, lack seamless integration with real-time control systems, and cannot provide instant feedback and optimize lighting layout. Summary of the invention

[0004] Based on this, it is necessary for the present invention to provide a modeled camera layout method and system to solve at least one of the above technical problems.

[0005] To achieve the above object, a modeled camera layout method includes the following steps:

[0006] Step S1: Acquire three-dimensional geometric scanning data and dynamic object data of the monitoring space; perform light field space modeling on the monitoring space according to the three-dimensional geometric scanning data to obtain spatial light field distribution data;

[0007] Step S2: performing ray tracing analysis on the spatial light field distribution data according to the dynamic object data to obtain light propagation characteristic data including light reflection, refraction and diffraction; using the light propagation characteristic data to perform effective coverage analysis on the monitoring area based on the light intensity threshold and the field of view angle range, thereby obtaining regional coverage characteristic data;

[0008] Step S3: performing adaptive optimization calculation on the initial layout of the camera through the regional coverage feature data and the pre-acquired environmental parameter data to obtain the camera layout parameter data, wherein the environmental parameter data includes optical environment parameters, physical environment parameters and camera performance parameters;

[0009] Step S4: performing coverage evaluation calculation on the monitoring area according to the camera layout parameter data to obtain coverage index data, wherein the coverage index data includes regional coverage data and blind spot distribution data;

[0010] Step S5: dynamically optimizing and adjusting the camera layout parameter data according to the coverage index data to obtain a camera layout solution, wherein the camera layout solution includes the final position coordinates, direction vector and field of view angle parameters of the camera.

[0011] The present invention can accurately present the light field distribution of the monitoring space by acquiring the three-dimensional geometric scanning data and dynamic object data of the monitoring space and performing light field space modeling, providing basic data for subsequent analysis, and ensuring a comprehensive and accurate grasp of the optical characteristics of the monitoring environment. Based on the dynamic object data, the spatial light field distribution data is subjected to ray tracing analysis to obtain the light propagation characteristic data, and then carry out effective coverage analysis, which helps to clarify the actual propagation of light in the monitoring area and whether each area is within the effective monitoring range, providing a key basis for the camera layout, and avoiding monitoring blind spots or insufficient coverage due to light problems. The initial layout of the camera is adaptively optimized and calculated in combination with the regional coverage characteristic data and the environmental parameter data, taking into full account various factors such as optics, physical environment and camera performance, so that the camera layout is more in line with the actual monitoring needs, and the monitoring effect and resource utilization efficiency are improved. The coverage rate evaluation calculation is performed according to the camera layout parameter data, and the coverage rate index data including the regional coverage rate and the blind spot distribution is obtained, which intuitively presents the monitoring coverage under the current layout, facilitates the discovery of potential problems, and provides a quantitative reference for subsequent optimization and adjustment. The camera layout parameter data is dynamically optimized and adjusted based on the coverage index data, and finally a scientific and reasonable camera layout plan is obtained to ensure that the camera's final position, direction, field of view and other parameters can achieve full coverage of the monitoring area to the greatest extent, reduce blind spots, improve the overall performance and reliability of the monitoring system, and meet the needs of efficient monitoring in complex monitoring environments.

[0012] The present invention evaluates the camera layout parameter data based on the coverage index data and determines the layout optimization target data. This step clarifies the direction of camera layout optimization, ensures that the optimization process is targeted, and accurately improves the monitoring coverage. According to the layout optimization target data, the importance weights of the monitoring areas are allocated to obtain regional priority data, so that the optimization process can focus on areas with high density of people and low coverage, and improve the utilization efficiency of monitoring resources. Based on the regional priority data, a camera layout optimization objective function containing three sub-goals of maximizing coverage, minimizing blind spots, and minimizing adjustment costs is constructed. This step provides comprehensive and scientific guidance for optimization calculations, ensuring that the optimization results achieve optimal balance in multiple key indicators. Iterative optimization calculations are performed using the optimization function model data until the termination conditions are met, and layout optimization iteration data is obtained. Through continuous iteration, the optimal solution is gradually approached to provide accurate parameters for the camera layout. The optimal solution is extracted from the layout optimization iteration data to obtain the optimal layout parameter data. This step locks the best camera layout solution and provides a scientific basis for subsequent installation. A constraint check is performed on the feasibility of camera installation. If the verification passes, the layout plan is output. If it fails, the optimization is returned to continue. This step ensures that the camera layout plan is not only optimal in theory, but also feasible in actual installation. The final output camera layout plan includes the final position coordinates, direction vector and field of view angle parameters, providing a strong guarantee for the efficient operation of the monitoring system.

[0013] The present invention also provides a modeled camera layout system for executing the modeled camera layout method as described above, wherein the modeled camera layout system comprises:

[0014] The light field modeling module is used to obtain the three-dimensional geometric scanning data and dynamic object data of the monitoring space; perform light field space modeling on the monitoring space according to the three-dimensional geometric scanning data to obtain spatial light field distribution data;

[0015] The light analysis module is used to perform ray tracing analysis on the spatial light field distribution data according to the dynamic object data to obtain light propagation characteristic data including light reflection, refraction and diffraction; the light propagation characteristic data is used to perform effective coverage analysis on the monitoring area based on the light intensity threshold and the field of view angle range, thereby obtaining regional coverage characteristic data;

[0016] A layout optimization module is used to perform adaptive optimization calculation on the initial layout of the camera through the regional coverage feature data and the pre-acquired environmental parameter data to obtain the camera layout parameter data, wherein the environmental parameter data includes optical environment parameters, physical environment parameters and camera performance parameters;

[0017] A coverage evaluation module is used to evaluate and calculate the coverage rate of the monitoring area according to the camera layout parameter data to obtain coverage rate index data, wherein the coverage rate index data includes regional coverage rate data and blind spot distribution data;

[0018] The scheme adjustment module is used to dynamically optimize and adjust the camera layout parameter data according to the coverage index data to obtain the camera layout scheme, wherein the camera layout scheme includes the final position coordinates, direction vector and field of view angle parameters of the camera.

[0019] The present invention obtains the three-dimensional geometric scanning data and dynamic object data of the monitoring space, and performs light field space modeling based on these data to generate spatial light field distribution data, which provides a basis for subsequent analysis. This process enables the system to accurately understand the light distribution in the monitoring space, thereby providing a scientific basis for the layout of the camera. The spatial light field distribution data is subjected to ray tracing analysis using dynamic object data to obtain propagation characteristic data such as light reflection, refraction and diffraction. These data are essential for understanding the propagation behavior of light in the monitoring area. The module further uses these light propagation characteristic data to perform effective coverage analysis on the monitoring area based on the light intensity threshold and the field of view angle range, and generates regional coverage characteristic data. This step ensures that the light conditions in the monitoring area can meet the monitoring requirements and provides key information for the layout of the camera. Combined with the regional coverage characteristic data and the pre-acquired environmental parameter data, the initial layout of the camera is adaptively optimized and calculated to obtain the camera layout parameter data. The environmental parameter data includes optical environment parameters, physical environment parameters and camera performance parameters. This process enables the camera layout to be adjusted according to the actual environmental conditions to ensure the rationality and effectiveness of the layout. According to the camera layout parameter data, the coverage rate of the monitoring area is evaluated and calculated to obtain coverage index data, including regional coverage data and blind spot distribution data. This evaluation process helps to understand the coverage of the monitoring area, identify blind spots, and provide a basis for subsequent optimization and adjustment. According to the coverage index data, the camera layout parameter data is dynamically optimized and adjusted to obtain the final camera layout plan. This plan includes the final position coordinates, direction vector and field of view angle parameters of the camera. Through dynamic optimization and adjustment, the system can continuously improve the camera layout to ensure full coverage of the monitoring area and improve the monitoring effect. In general, these steps together constitute a systematic camera layout optimization process, which ensures the efficiency and reliability of the monitoring system through precise light field modeling, light analysis, layout optimization, coverage evaluation and solution adjustment. This process not only improves the monitoring coverage rate, but also reduces blind spots and optimizes the layout of cameras, so that the monitoring system can better adapt to complex and changing monitoring environments. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] Other features, objects and advantages of the present invention will become more apparent from the detailed description of non-limiting embodiments thereof made with reference to the following drawings:

[0021] Figure 1 A schematic diagram of the steps of the camera layout method modeled in the present invention;

[0022] Figure 2 for Figure 1 Detailed step flow diagram of step S1;

[0023] Figure 3 for Figure 1 Detailed step flow chart of step S2 in FIG. DETAILED DESCRIPTION

[0024] The technical method of the present invention is described clearly and completely below in conjunction with the accompanying drawings. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by technicians in this field without creative work are within the scope of protection of the present invention.

[0025] In addition, the accompanying drawings are only schematic illustrations of the present invention and are not necessarily drawn to scale. The same reference numerals in the figures represent the same or similar parts, and their repeated description will be omitted. Some of the block diagrams shown in the accompanying 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 implemented in one or more hardware modules or integrated circuits, or implemented in different networks and / or processor methods and / or microcontroller methods.

[0026] It should be understood that, although the terms "first", "second", etc. may be used herein to describe various units, these units should not be limited by these terms. These terms are used only to distinguish one unit from another unit. 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.

[0027] To achieve this, please refer to Figures 1 to 3 The present invention provides a modeled camera layout method, the method comprising the following steps:

[0028] Step S1: Acquire three-dimensional geometric scanning data and dynamic object data of the monitoring space; perform light field space modeling on the monitoring space according to the three-dimensional geometric scanning data to obtain spatial light field distribution data;

[0029] The embodiment of the present invention uses high-precision three-dimensional laser scanning equipment to perform a comprehensive scan of the monitored space, obtain point cloud data including walls, floors, ceilings and fixed objects in the space, and eliminate redundant data through point cloud stitching and denoising algorithms to build a complete three-dimensional geometric model. At the same time, millimeter wave radar, infrared depth sensor or video image analysis technology is used to obtain the position information, motion trajectory and morphological characteristics of dynamic objects in the monitored space in real time, and the dynamic object data is predicted in time series through Kalman filtering or particle filtering algorithms to reduce data noise and mutation effects. Subsequently, based on the three-dimensional geometric model and the light propagation model, a light field space model is constructed, and the propagation path of light at different angles is calculated through light projection to obtain the light field distribution data in the monitored space, providing basic data support for subsequent analysis.

[0030] Step S2: performing ray tracing analysis on the spatial light field distribution data according to the dynamic object data to obtain light propagation characteristic data including light reflection, refraction and diffraction; using the light propagation characteristic data to perform effective coverage analysis on the monitoring area based on the light intensity threshold and the field of view angle range, thereby obtaining regional coverage characteristic data;

[0031] The embodiment of the present invention adopts an optical simulation method based on ray tracing to analyze the light propagation characteristics of dynamic object data, specifically including calculating the reflection, refraction and diffraction path of the ambient light according to the surface material characteristics, shape and position of the dynamic object. First, the optical reflection law is used to calculate the direction of light reflection on the surface of the dynamic object, and the energy distribution of the reflected light is determined in combination with the diffuse reflection and mirror reflection coefficients of the material; secondly, the optical refraction law is used to calculate the refraction path of light of transparent or translucent objects, and the propagation deviation of light in different media is analyzed; finally, the diffraction phenomenon is calculated using the Huygens principle, and the diffraction angle and light field interference of light at the edge or pinhole of the dynamic object are analyzed. Based on the above light propagation characteristic data, combined with the light intensity threshold and the field of view angle range, the light field coverage of the monitoring area is analyzed, and the spatial distribution characteristics of the visible area and the shadow area in the monitoring area are calculated to obtain the regional coverage characteristic data.

[0032] Step S3: performing adaptive optimization calculation on the initial layout of the camera through the regional coverage feature data and the pre-acquired environmental parameter data to obtain the camera layout parameter data, wherein the environmental parameter data includes optical environment parameters, physical environment parameters and camera performance parameters;

[0033] The embodiment of the present invention analyzes the monitoring blind spots, insufficient light areas and high-reflection interference areas existing in the monitoring area according to the regional coverage feature data, and optimizes the initial layout of the camera in combination with the environmental parameter data. The environmental parameter data includes optical environment parameters (such as ambient light intensity, spectral distribution, reflectivity), physical environment parameters (such as space size, wall material, dynamic obstacle distribution) and camera performance parameters (such as lens focal length, sensor sensitivity, minimum illumination requirements). Through adaptive optimization calculation, comprehensive consideration of monitoring needs and camera performance, a method based on genetic algorithm or particle swarm optimization algorithm is used to calculate the optimal camera layout parameter data, including the initial position, orientation angle and focal length setting of the camera, so that it can cover the monitoring area to the greatest extent and reduce blind spots.

[0034] Step S4: performing coverage evaluation calculation on the monitoring area according to the camera layout parameter data to obtain coverage index data, wherein the coverage index data includes regional coverage data and blind spot distribution data;

[0035] The embodiment of the present invention evaluates and calculates the coverage of the monitoring area based on the camera layout parameter data using computer vision simulation technology, specifically including: first, based on the imaging model and light field characteristics of the camera, the field of view range of each camera is calculated to determine the coverage area of ​​each camera; secondly, for the overlapping areas of the camera fields of view at different viewing angles, the Monte Carlo method is used for statistical analysis to calculate the repeated coverage of different areas and evaluate possible visual redundancy or resource waste; finally, based on the three-dimensional structure and light propagation characteristics of the monitoring area, the blind spot distribution is determined, including the area that cannot be imaged due to obstacle obstruction or uneven lighting, and coverage index data is output, specifically including the overall area coverage value, the blind spot ratio and the specific distribution of the blind spots.

[0036] Step S5: dynamically optimizing and adjusting the camera layout parameter data according to the coverage index data to obtain a camera layout solution, wherein the camera layout solution includes the final position coordinates, direction vector and field of view angle parameters of the camera.

[0037] The embodiment of the present invention uses an iterative optimization strategy to dynamically adjust the camera layout parameter data based on the coverage index data to improve the coverage and reduce the monitoring blind spots. The specific adjustment method includes: for areas with larger blind spots, adjusting the installation height or field of view of the camera so that it can cover the original blind spots; for areas with too high repeated coverage, optimizing the orientation of the camera or reducing the number of redundant cameras to save resources; for areas with insufficient light, combining external fill light equipment or adjusting the exposure parameters of the camera to improve the imaging quality. Finally, based on the optimization calculation results, the final layout plan of the camera is determined, including the precise installation position coordinates, direction vectors, and field of view parameters of the camera, and a complete layout plan is output to provide a basis for the actual deployment of the monitoring system.

[0038] The present invention can accurately present the light field distribution of the monitoring space by acquiring the three-dimensional geometric scanning data and dynamic object data of the monitoring space and performing light field space modeling, providing basic data for subsequent analysis, and ensuring a comprehensive and accurate grasp of the optical characteristics of the monitoring environment. Based on the dynamic object data, the spatial light field distribution data is subjected to ray tracing analysis to obtain the light propagation characteristic data, and then carry out effective coverage analysis, which helps to clarify the actual propagation of light in the monitoring area and whether each area is within the effective monitoring range, providing a key basis for the camera layout, and avoiding monitoring blind spots or insufficient coverage due to light problems. The initial layout of the camera is adaptively optimized and calculated in combination with the regional coverage characteristic data and the environmental parameter data, taking into full account various factors such as optics, physical environment and camera performance, so that the camera layout is more in line with the actual monitoring needs, and the monitoring effect and resource utilization efficiency are improved. The coverage rate evaluation calculation is performed according to the camera layout parameter data, and the coverage rate index data including the regional coverage rate and the blind spot distribution is obtained, which intuitively presents the monitoring coverage under the current layout, facilitates the discovery of potential problems, and provides a quantitative reference for subsequent optimization and adjustment. The camera layout parameter data is dynamically optimized and adjusted based on the coverage index data, and finally a scientific and reasonable camera layout plan is obtained to ensure that the camera's final position, direction, field of view and other parameters can achieve full coverage of the monitoring area to the greatest extent, reduce blind spots, improve the overall performance and reliability of the monitoring system, and meet the needs of efficient monitoring in complex monitoring environments.

[0039] Preferably, step S1 comprises the following steps:

[0040] Step S11: Acquire three-dimensional geometric scanning data, surface structure data, and dynamic object data of the monitoring space;

[0041] The embodiment of the present invention uses a high-precision three-dimensional laser scanner (such as LiDAR) to perform an all-round scan of the monitored space, obtain point cloud data of the walls, ground, ceiling and fixed objects in the space, and use point cloud noise reduction and registration algorithms to remove redundant information to make the data more accurate and coherent. At the same time, a high-resolution camera combined with structured light or light field camera technology is used to perform texture sampling on the surface of objects in the space, extract microscopic surface undulation information, and thus obtain surface structure data. For dynamic object data, millimeter wave radar, infrared thermal imaging sensor or video image processing technology is used for detection to capture the position information, motion trajectory and behavior pattern of dynamic targets in the monitored space in real time, and Kalman filtering is used for data optimization to eliminate short-term noise interference and ensure data stability and accuracy.

[0042] Step S12: Reconstructing the spatial geometry according to the three-dimensional geometric scanning data, thereby obtaining spatial structure model data;

[0043] The embodiment of the present invention uses the Delaunay triangulation method or the octree segmentation method to perform topological reconstruction on the point cloud data based on the acquired three-dimensional geometric scanning data to form a gridded spatial geometric structure. First, the closed area of ​​the space is detected by the boundary point recognition algorithm, and the local missing area is supplemented by the Poisson reconstruction technology to ensure integrity. Then, the grid is simplified and optimized to reduce computational redundancy while maintaining geometric details to make the spatial structure model more expressive. Finally, the spatial structure model data is output, which contains the positional relationship, shape characteristics and topological connection information of each surface in the monitoring space, providing basic data for subsequent optical analysis and modeling.

[0044] Step S13: performing material optical characteristic analysis on the spatial structure model data according to the surface structure data, thereby obtaining surface optical characteristic data including reflectivity, scattering coefficient and transmittance;

[0045] The embodiment of the present invention adopts a method based on spectral reflectance measurement to analyze the optical properties of different material surfaces in the spatial structure model. The specific operation is: first, a hyperspectral camera or a spectrophotometer is used to measure the reflection characteristics of different surfaces in the visible light, infrared light and ultraviolet light bands, and the reflectance of each surface is calculated by the Lambertian reflection and specular reflection component decomposition algorithm. Secondly, a light field camera or polarization imaging technology is used to analyze the scattering behavior of the surface, and the scattering coefficient is calculated in combination with a scattering function model (such as Bidirectional Reflectance Distribution Function, BRDF). In addition, for transparent or translucent materials, the transmittance of light at different wavelengths is calculated through light transmission measurement experiments, and a corresponding transmission characteristic data table is established. Finally, the surface optical characteristic data is obtained, including the reflectance, scattering coefficient and transmittance of each surface material, to provide accurate optical parameters for light field modeling.

[0046] Step S14: Analyze the crowd density of the monitored space through dynamic object data to obtain regional dynamic characteristic data;

[0047] The embodiment of the present invention uses a density estimation algorithm to perform crowd density analysis based on the acquired dynamic object data. First, a target detection algorithm (such as YOLO or Mask R-CNN) is used to detect the crowd in the video data, and the individual's movement trajectory is identified in combination with optical flow analysis or target tracking algorithms (such as SORT or DeepSORT). Then, the Kernel Density Estimation (KDE) method is used to calculate the density of people per unit area in different areas of the monitoring space, and combined with a time series analysis model (such as LSTM or ARIMA), the dynamic change trend of the crowd flow is predicted. Finally, the regional dynamic characteristic data is obtained, which describes the density of people, movement direction and residence time distribution in different time periods in the monitoring space, and provides dynamic parameter support for subsequent light field modeling.

[0048] Step S15: performing light field space modeling on the spatial structure model data using a four-dimensional light field function, thereby obtaining initial light field distribution data;

[0049] The embodiment of the present invention adopts a four-dimensional light field function (i.e., adding light direction parameters on the basis of three-dimensional space coordinates) to perform light field space modeling on the spatial structure model. The specific method includes: first, using the spatial geometry model and the light source position, based on the light propagation model (such as the ray casting method or the photon mapping method), the light direction distribution and energy intensity of each point in the space are calculated. Secondly, the light field rendering technology is used to calculate the illumination changes under different light source angles, and store them as a light field data structure (such as the radiance field). Finally, the light field data is optimized through interpolation methods (such as hierarchical voxel interpolation or neural network reconstruction) so that it changes continuously in space. Finally, the initial light field distribution data is obtained, which describes the propagation direction, intensity and interaction of light in space, providing a basis for subsequent optical analysis.

[0050] Step S16: converting the initial light field distribution data into a complex form according to the surface optical characteristic data, wherein the real part represents the light intensity attenuation data and the imaginary part represents the phase information data, thereby obtaining the complex light field distribution data;

[0051] The embodiment of the present invention converts the initial light field distribution data into a complex form based on the surface optical property data. The specific operation is as follows: first, the spatial variation of light intensity is calculated using the light attenuation model, and it is defined as the real component of the complex light field data, where the light intensity attenuation is affected by the surface reflectivity, scattering coefficient and transmittance, and is calculated using the light path integration method. Secondly, the light wave phase propagation model is used to analyze the phase offset according to the surface optical characteristics, and the phase information is used as the imaginary component of the complex light field data. Finally, the complex light field distribution data is obtained, which not only describes the intensity distribution of the light, but also contains the phase information of the light wave, so that the interference, diffraction and refraction effects of light can be described more accurately.

[0052] Step S17: Dynamically weight the complex light field distribution data according to the regional dynamic characteristic data, so as to obtain spatial light field distribution data, wherein the dynamic weight allocation is specifically an assignment in which the weight is linearly positively correlated with the crowd density.

[0053] The embodiment of the present invention dynamically assigns weights to the complex light field distribution data based on the regional dynamic characteristic data. The specific method is as follows: first, based on the crowd density data, a linear interpolation method is used to calculate the dynamic weight values ​​of different regions, wherein the higher the crowd density of the region, the greater the weight value, to reflect the importance of the light field in the region in the monitoring needs. Secondly, a weighted calculation is performed on the complex light field distribution data, that is, on the basis of the original light field data, the light intensity and phase value are adjusted to make the light field influence in the crowded area more prominent, while the light field influence in the low-density area is relatively reduced. Finally, the spatial light field distribution data is obtained, which introduces the dynamic influence of crowd flow while retaining the original light field characteristics, providing a basis for the optical optimization of the intelligent monitoring system.

[0054] The present invention comprehensively obtains the key data of the monitoring space, lays a solid foundation for the subsequent process, and ensures a comprehensive understanding of the monitoring environment. The spatial geometry is reconstructed based on the three-dimensional geometric scanning data to generate accurate spatial structure model data, so that the geometric form of the monitoring space can be clearly presented, providing an accurate framework for subsequent analysis. The spatial structure model data is combined with the surface structure data to carry out material optical property analysis, and key optical parameters such as reflectivity, scattering coefficient, and transmittance are obtained, so that the optical properties of different materials in the monitoring space are accurately grasped, providing an important basis for light propagation analysis. The dynamic object data is used to analyze the density of human flow, and the regional dynamic characteristic data is obtained, so that the monitoring system can make corresponding adjustments according to the changes in human flow density. The step uses a four-dimensional light field function to perform light field space modeling on the spatial structure model data, obtains initial light field distribution data, and preliminarily presents the light field situation of the monitoring space. The step converts the initial light field distribution data into a complex form according to the surface optical characteristic data, so that the light field data contains richer information, providing data support for subsequent refined analysis. The step is to dynamically weight the complex light field distribution data according to the regional dynamic characteristic data, so that the light field distribution data is more in line with the actual monitoring needs, so that the monitoring system can focus on crowded areas, improve the pertinence and effectiveness of monitoring, and make the camera layout method more scientific and practical as a whole, and better adapt to the complex and changeable monitoring environment.

[0055] Preferably, step S2 comprises the following steps:

[0056] Step S21: performing spatiotemporal alignment processing on the motion trajectory and position information in the dynamic object data and the spatial light field distribution data, thereby obtaining spatiotemporal matching data;

[0057] In order to achieve spatiotemporal alignment processing, the embodiment of the present invention first uses video analysis and target detection algorithms (such as YOLO or Mask R-CNN) to extract the motion trajectory and position information in the dynamic object data, and uses Kalman filtering or particle filtering algorithms to smooth the trajectory to reduce the deviation caused by detection noise. Then, based on the light propagation path in the spatial light field distribution data, three-dimensional coordinate mapping is performed on the dynamic object at each time step to ensure that the position of the object in the light field is consistent with the actual motion trajectory. An interpolation algorithm (such as B-spline interpolation or linear interpolation) is used to synchronize the discrete motion trajectory of the object in time to make its spatial position continuous under different light field states. Finally, spatiotemporal matching data is generated, which contains the precise position and motion trend of the dynamic object in the light field, providing basic data for subsequent light propagation simulation.

[0058] Step S22: performing ray tracing processing on the spatial light field distribution data according to the time-space matching data, and simulating the propagation of light in the monitoring area, thereby obtaining preliminary light propagation characteristic data including light reflection, refraction and diffraction;

[0059] The embodiment of the present invention performs ray tracing processing on the spatial light field distribution data based on the time-space matching data to simulate the propagation of light in the monitoring area. First, the reverse ray tracing algorithm is used to trace the light path along the light field propagation direction from the optical receiving end of the monitoring device to determine the key intersection points through which the light passes. Then, according to the optical geometric characteristics, the optical path calculation method (such as the Fresnel equation) is used to simulate the reflection and refraction behavior of light on the surfaces of different materials, and calculate the energy loss and angle change of light. At the same time, the wave optics modeling method is used to simulate the diffraction phenomenon of light on slits, edges or microstructure surfaces to ensure the physical consistency of light field propagation. Finally, the preliminary light propagation characteristic data is output, which includes the refractive index change, scattering distribution and interference diffraction characteristics of light in different spatial regions, providing input for light field optimization calculation.

[0060] Step S23: performing a refined correction process on the light propagation based on the preliminary light propagation characteristic data and a preset optical physics model, thereby obtaining the light propagation characteristic data;

[0061] In order to improve the accuracy of light propagation simulation, the embodiment of the present invention performs refined correction processing based on preliminary light propagation characteristic data and a preset optical physics model. First, the Monte Carlo path tracing method is used to randomly sample the light propagation path, and the multiple reflections, refractions, and scattering behaviors of light in a complex medium environment are calculated to improve the authenticity of the light propagation model. Secondly, a numerical model of light propagation is constructed based on high-precision optical simulation software (such as Zemax or OpticStudio), and compared and corrected with the measured ambient lighting data to ensure that the simulation results are consistent with the actual physical phenomena. In addition, for areas with obvious diffraction effects, the Fourier optical method is used to calculate the phase evolution of the light wavefront, and the amplitude distribution of the light field is corrected, so that the final light propagation characteristic data has higher calculation accuracy.

[0062] Step S24: Use the light propagation characteristic data to perform effective coverage analysis on the monitoring area based on the light intensity threshold and the field of view angle range, so as to obtain regional coverage characteristic data.

[0063] The embodiment of the present invention performs optical coverage analysis on the monitoring area based on the light propagation characteristic data to evaluate the light visibility of different areas. First, a light intensity threshold is set, and the area in the light field that can form an effective image is screened according to the human eye visual model or the minimum detectable light intensity of the imaging device, and the area with light intensity lower than the threshold is eliminated. Secondly, combined with the field of view angle range of the monitoring device, the light projection method is used to calculate the coverage of the target area by different monitoring points to ensure that all key areas are within the monitoring field of view. In addition, the occlusion of each area is calculated through the visibility analysis algorithm (such as Z-buffer or ray depth detection), and the layout strategy of the monitoring equipment is optimized to maximize the effective monitoring range. Finally, the regional coverage characteristic data is generated, which describes the uniformity, visibility and occlusion effects of the light field in the monitoring area, and provides a decision-making basis for the optical optimization of the monitoring system.

[0064] The present invention performs spatiotemporal alignment processing on the motion trajectory and position information in the dynamic object data and the spatial light field distribution data to obtain spatiotemporal matching data. This step ensures that the position and motion of the dynamic object in the monitoring area accurately correspond to the light field distribution data, providing an accurate basis for subsequent analysis. Based on the spatiotemporal matching data, the spatial light field distribution data is subjected to ray tracing processing to simulate the propagation of light in the monitoring area, and preliminary light propagation characteristic data, including light reflection, refraction and diffraction, are obtained, which helps to understand the actual propagation of light in the monitoring area and provides data support for subsequent refined analysis. Based on the preliminary light propagation characteristic data and the preset optical physics model, the light propagation is subjected to refined correction processing to obtain more accurate light propagation characteristic data. This step improves the accuracy of the light propagation data and makes the subsequent analysis more reliable. The light propagation characteristic data is used to perform effective coverage analysis on the monitoring area based on the light intensity threshold and the field of view angle range to obtain regional coverage characteristic data, which helps to determine the effective coverage range in the monitoring area, provides a key basis for the camera layout, ensures that the light conditions in the monitoring area meet the monitoring requirements, and improves the monitoring effect.

[0065] Preferably, step S24 comprises the following steps:

[0066] Step S241: extracting and processing the light intensity of each sampling point in the monitoring area based on the light propagation characteristic data, thereby obtaining local light intensity data of each sampling point; screening and processing each sampling point using a preset light intensity threshold according to the local light intensity data, thereby obtaining area division data that meets the light intensity coverage requirements;

[0067] The embodiment of the present invention discretizes the monitoring area into multiple sampling points according to the grid division method based on the light propagation characteristic data, and uses the ray tracing algorithm to calculate the light intensity at each sampling point. During the calculation process, the radiometric method is used to analyze the energy distribution of the light at the sampling point, and the incident angle, reflection loss and scattering effect of the light are considered to obtain the real local light intensity data. Then, a preset light intensity threshold is set, which can be determined according to the minimum photosensitivity of the monitoring equipment or the standard lighting conditions. For example, the minimum illumination requirement is set to 0.1lux in a night environment. Subsequently, the local light intensity data of all sampling points are traversed in turn, and the areas where the light intensity meets the preset threshold are screened out, and the areas with insufficient light are eliminated, and finally the regional division data that meets the light intensity coverage requirements is obtained. This data can be used to guide the fill light configuration of the monitoring equipment to ensure the uniformity of light in the monitoring area.

[0068] Step S242: extracting and processing the field of view angle of each sampling point in the monitoring area based on the light propagation characteristic data, thereby obtaining local field of view angle data of each sampling point; comparing and processing each sampling point according to the local field of view angle data and the preset camera field of view angle range, thereby obtaining regional distribution data that meets the field of view angle coverage requirements;

[0069] The embodiment of the present invention uses light propagation characteristic data to extract and process the field of view of each sampling point in the monitoring area. In the calculation process, an optical projection model is used to calculate the projection range of each sampling point in the light field according to the installation height, lens focal length and monitoring angle of the monitoring camera. Then, the local field of view data of each sampling point is normalized to match the preset camera field of view range. The preset camera field of view range can be determined according to the model of the monitoring equipment. For example, the horizontal field of view of a wide-angle camera is 120° and the vertical field of view is 90°. Subsequently, based on the field of view comparison processing, the sampling points that are not within the effective field of view of the camera are eliminated, and the regional distribution data that meets the field of view coverage requirements are extracted. This data can be used to analyze monitoring blind spots and optimize the layout of cameras to improve monitoring coverage.

[0070] Step S243: Perform fusion analysis and processing based on the area division data and the area distribution data to obtain effective coverage feature data of the monitoring area.

[0071] The embodiment of the present invention performs spatial alignment processing on the regional division data and the regional distribution data to ensure that the data coordinate systems of the two are consistent. Then, a fusion analysis method is used to perform superposition operations on the two types of data, and the effective coverage characteristics of each region are calculated. Specifically, the two data sets are firstly subjected to regional binarization processing, that is, the area that meets the light intensity coverage requirements is marked as 1, and the other areas are marked as 0; similarly, the area that meets the field of view angle coverage requirements is marked as 1, and the other areas are marked as 0. Subsequently, through matrix operations, the two binary areas are multiplied point by point to screen out areas that meet both the light intensity requirements and the field of view angle coverage requirements, and finally generate effective coverage feature data for the monitoring area. This data can be used to evaluate the monitoring effect of the monitoring area, identify lighting blind spots or field of view blind spots, and provide a basis for subsequent optimization of the monitoring system.

[0072] The present invention extracts the light intensity of each sampling point in the monitoring area based on the light propagation characteristic data to obtain local light intensity data, and then uses the preset light intensity threshold to screen the sampling points to obtain regional division data that meets the light intensity coverage requirements. This step ensures that the light intensity in the monitoring area meets the monitoring requirements and provides a basis for subsequent analysis. Based on the light propagation characteristic data, the field of view angle of each sampling point in the monitoring area is extracted to obtain local field of view angle data, and then the sampling points are compared according to the preset camera field of view angle range to obtain regional distribution data that meets the field of view angle coverage requirements. This step ensures that the camera's field of view can cover the monitoring area and avoid the occurrence of monitoring blind spots. The regional division data and the regional distribution data are fused and analyzed to obtain effective coverage characteristic data of the monitoring area. This step integrates information from two dimensions, light intensity and field of view angle, and comprehensively evaluates the coverage of the monitoring area, providing a key basis for camera layout, ensuring that the light conditions and camera field of view angles in the monitoring area can meet the monitoring requirements and improve the monitoring effect.

[0073] Preferably, step S3 comprises the following steps:

[0074] Step S31: Acquire environmental parameter data, including optical environmental parameters, physical environmental parameters and camera performance parameters;

[0075] The embodiment of the present invention obtains environmental parameter data through a sensor network, wherein optical environmental parameters include ambient illumination, light source distribution, light reflectivity, etc., physical environmental parameters include temperature, humidity, wind speed, etc., and camera performance parameters include the camera's photosensitivity, dynamic range, lens focal length, etc. The ambient illumination data can be collected by a high-precision illuminance meter. For example, in an outdoor monitoring scene, the illumination level of each monitoring area may fluctuate between 100 lux and 1000 lux. The light source distribution can be obtained by an ambient light sensor combined with a light source layout diagram to analyze the uniformity of illumination in the monitoring area. The physical environmental parameters are obtained through an integrated meteorological station or environmental sensor to ensure that the monitoring equipment can adapt to different environmental conditions. The camera performance parameters are provided by the equipment manufacturer and calibrated in combination with actual test data. For example, the minimum illumination of a certain camera is 0.01 lux, which is suitable for low-light environments. Finally, all environmental parameter data are standardized and stored in an environmental parameter database for subsequent calculations.

[0076] Step S32: compensating and correcting the regional coverage feature data using the optical environment parameters and the physical environment parameters, thereby obtaining the environment adaptive coverage feature data; performing grid processing on the monitoring area based on the environment adaptive coverage feature data and the camera performance parameters and generating candidate layout positions, thereby obtaining the initial layout point set data;

[0077] The embodiment of the present invention compensates and corrects the regional coverage feature data according to the optical environment parameters. For example, the illumination distribution data is used to correct the monitoring blind area, the light field model is adjusted in the low-light area, the weight of the insufficiently illuminated area is increased, and the stability of the calculation results is ensured. Then, compensation is performed according to the physical environment parameters. For example, in a strong wind area, the installation angle range of the camera is adjusted to reduce the impact of wind vibration. After compensation and correction, the environmental adaptive coverage feature data is obtained. Next, based on the environmental adaptive coverage feature data and the camera performance parameters, the monitoring area is grid-divided. For example, the monitoring area is divided into 1m×1m grid units, and the optical characteristics, physical characteristics, and field of view characteristics of each grid unit are calculated once, and the grid points that meet the camera installation conditions are screened to form candidate layout positions. Finally, combined with the effective coverage rate of each grid point, the point set that meets the basic coverage requirements is screened out to generate the initial layout point set data.

[0078] Step S33: performing scoring calculation on the initial layout point set data based on coverage area, imaging quality and monitoring continuity, thereby obtaining layout point set scoring data;

[0079] The embodiment of the present invention performs a multi-dimensional characteristic analysis on the initial layout point set data, and calculates the coverage area, imaging quality and monitoring continuity score for each candidate layout point. The coverage area calculation is based on the field of view angle model, which evaluates the spatial range that can be monitored after the camera is installed at this position. For example, when a camera is installed at point A, its maximum coverage radius is 30m, then the coverage area score of point A is higher. The imaging quality score takes into account the lighting conditions, physical environmental factors and camera performance parameters. For example, in low-light areas, the imaging quality score is reduced, while in good lighting conditions, the score is higher. The monitoring continuity score is calculated based on the coverage overlap between adjacent cameras. For example, if the overlap between a layout point and the monitoring area of ​​an adjacent camera is too low, the continuity score is low. Finally, a comprehensive score is calculated using multi-indicator weighting, and layout point set scoring data is generated to ensure that the optimal location can be selected during subsequent layout optimization.

[0080] Step S34: performing priority sorting processing on the initial layout point set data according to the layout point set scoring data, thereby obtaining optimized layout sequence data;

[0081] The embodiment of the present invention prioritizes the initial layout point set data according to the layout point set scoring data. During the sorting process, the points with the highest comprehensive scores are given priority, while taking into account the uniform coverage of the monitoring area. The specific operations include: first, arranging all layout points in descending order according to the comprehensive scores; second, using the non-maximum suppression method to eliminate overly dense layout points to avoid redundant deployment of cameras; finally, based on the regional balancing strategy, ensuring that the cameras in the monitoring area are evenly distributed. For example, in an open area of ​​100m×100m, if the layout point density of a certain area is too high, the number of points in the area is appropriately reduced, while the number of points in the low-density area is increased. Finally, the optimized layout sequence data is generated, which is used to guide the final camera layout calculation.

[0082] Step S35: Perform final layout optimization calculation according to the optimized layout sequence data and the camera performance parameters, so as to obtain camera layout parameter data, wherein the camera layout parameter data includes the spatial coordinate data, orientation angle data and field of view angle data of the camera.

[0083] The embodiment of the present invention performs the final layout optimization calculation based on the optimized layout sequence data and the camera performance parameters. In the calculation process, the installation height, orientation angle and field of view of the camera are first determined for each layout point. For example, for a certain camera, the optimal installation height is between 3m and 5m, and the installation point within this range is preferably selected. The orientation angle is calculated by an optimization algorithm to ensure that the monitoring direction of each camera is aligned with the key monitoring point of the target area. For example, in a crowded area, the camera should be tilted downward to obtain the best facial recognition effect. The field of view angle data is dynamically adjusted in combination with environmental parameters. For example, in a uniformly illuminated area, a larger field of view angle (such as 120°) is used, and in a low-light area, a smaller field of view angle (such as 90°) is used to improve the imaging quality. Finally, the camera layout parameter data is generated, including the spatial coordinates (X, Y, Z), orientation angle (horizontal rotation angle, pitch angle) and field of view angle information of each camera, which can be used to guide the installation and deployment of the actual camera.

[0084] The present invention comprehensively collects environmental parameter data, covering optical, physical and camera performance aspects, providing a key basis for subsequent precise optimization and ensuring that the camera layout fits the actual environment requirements. The regional coverage feature data is compensated and corrected using optical and physical environmental parameters to obtain environmental adaptive coverage feature data, so that the coverage data is more in line with the real environment; grid processing is performed based on this data and camera performance parameters to generate candidate layout positions, obtain initial layout point set data, and provide a preliminary solution for camera layout. The initial layout point set data is scored from multiple dimensions such as coverage area, imaging quality, and monitoring continuity to obtain layout point set scoring data, and the advantages and disadvantages of each layout point are comprehensively evaluated. The initial layout point set is prioritized according to the scoring data to obtain optimized layout sequence data and clarify the order of layout optimization. The final layout optimization calculation is combined with the optimized layout sequence data and camera performance parameters to obtain camera layout parameter data containing detailed parameters such as camera spatial coordinates, orientation angle, and field of view angle, providing scientific guidance for the precise installation of the camera, ensuring that the camera layout achieves the best monitoring effect in the actual environment, meeting the diverse needs under complex monitoring scenarios, and improving the overall performance and reliability of the monitoring system.

[0085] Preferably, step S32 includes the following steps:

[0086] Step S321: performing illumination compensation processing on the regional coverage characteristic data according to the optical environment parameters, thereby obtaining illumination compensation coverage characteristic data;

[0087] The embodiment of the present invention obtains optical environment parameters, including data such as ambient illumination, light source distribution, and light reflectivity, wherein the ambient illumination can be measured by a high-precision illuminance meter at different locations in the monitoring area. For example, it may exceed 5000 lux in the direct sunlight area during the day, while it may be less than 100 lux in the indoor low-light environment. Next, based on the regional coverage feature data, the illumination distribution of each monitoring point is analyzed, and the coverage feature is optimized using an illumination compensation method. For example, in areas with insufficient light, the image quality can be enhanced by increasing the exposure time of the camera or adjusting the gain parameters, while in areas with excessive light, the exposure is appropriately reduced to reduce overexposure. In addition, the reflective interference of the monitoring scene can also be analyzed by light reflectivity. For example, for glass curtain wall areas, it should be considered to add a polarization filter to reduce the reflection effect. Finally, the illumination compensation coverage feature data is combined with the coverage feature data after illumination compensation to form optimized optical information for subsequent environmental adaptability adjustments.

[0088] Step S322: performing environmental impact correction processing on the illumination compensation coverage characteristic data according to the physical environment parameters, thereby obtaining environmental adaptive coverage characteristic data;

[0089] After obtaining the illumination compensation coverage feature data, the embodiment of the present invention further considers the influence of physical environmental parameters on the monitoring area, such as temperature, humidity, wind speed and other factors, wherein the temperature and humidity can be monitored in real time by environmental sensors. For example, in a high temperature environment (over 40°C), the electronic components of the camera may be affected by overheating, thereby reducing the image quality. Therefore, a high temperature resistant camera or a heat sink should be used in this area. The wind speed parameter is particularly important for outdoor monitoring. For example, in an environment where the wind speed exceeds 10m / s, the fixed bracket of the camera needs to be adjusted to increase the wind resistance stability. For special physical environments, such as high salt fog environments in coastal areas, cameras with anti-corrosion coatings need to be selected. Based on these physical environmental parameters, an environmental impact correction model is used to adjust the illumination compensation coverage feature data, such as appropriately reducing the field of view of the camera in areas with higher wind speeds to reduce the blurring effect caused by picture jitter. Finally, environmental adaptive coverage feature data is obtained, so that the coverage characteristics of the monitoring area can adapt to different environmental changes and improve the overall monitoring effect.

[0090] Step S323: performing grid division processing on the monitoring area based on the environment adaptive coverage feature data, thereby obtaining monitoring area grid data, wherein the grid size in the monitoring area grid data is inversely proportional to the regional coverage feature density;

[0091] The embodiment of the present invention performs grid division on the monitoring area based on the environmental adaptive coverage feature data. First, the overall scope of the monitoring area is determined. For example, in a 500m×500m square, there may be areas with uniform lighting and areas with complex light changes. In order to improve the calculation efficiency, the grid size is inversely proportional to the regional coverage feature density during grid division, that is, smaller grid units are used in areas with large changes in coverage features, and larger grid units are used in areas with relatively uniform coverage features. For example, in areas with uniform lighting, a 10m×10m grid can be used, and in areas with strong changes in lighting, such as areas where shade and sunlight alternate, a small 2m×2m grid can be used. In the process of grid division, the fine-grained requirements of the monitoring target must also be considered. For example, in the entrance and exit areas with dense traffic, smaller grid units are required to ensure monitoring accuracy. Finally, the monitoring area grid data is generated, which records the lighting, physical environment parameters and coverage feature information of each grid unit, providing a basic basis for the reasonable layout of the camera.

[0092] Step S324: Generate candidate layout positions of the camera according to the monitoring area grid data and camera performance parameters, thereby obtaining initial layout point set data.

[0093] After obtaining the grid data of the monitoring area, the embodiment of the present invention calculates and generates the candidate layout positions of the camera in combination with the camera performance parameters. First, based on the environmental adaptive coverage feature data of each grid unit, it is evaluated whether it meets the installation conditions of the camera, such as whether it has sufficient supporting structures, whether there are obstructions, etc. Then, in combination with the performance parameters of the camera such as the field of view, resolution, focal length, etc., a suitable installation point is determined. For example, for a camera with a field of view of 120°, the optimal installation height is 3m to 5m, and grid units that meet this height range are preferentially selected. In addition, in the selection process of candidate layout points, the priority of the monitoring target must also be considered. For example, the camera coverage density should be increased in crowded areas, while the number of camera deployments can be reduced in open areas to optimize resource allocation. Finally, based on these calculation results, the initial layout point set data is generated, which contains all possible camera layout positions and provides alternative solutions for subsequent optimized layout.

[0094] The present invention performs illumination compensation processing on the regional coverage feature data according to the optical environment parameters to obtain illumination compensation coverage feature data. This step can effectively compensate for the coverage feature deviation caused by the change of illumination conditions, so that the coverage data can more accurately reflect the monitoring area situation under the actual illumination environment. According to the physical environment parameters, the illumination compensation coverage feature data is subjected to environmental impact correction processing to obtain environmental adaptive coverage feature data. This step further considers the influence of physical environment factors on the monitoring area, so that the coverage feature data is more in line with the actual monitoring environment, and provides a more reliable basis for subsequent layout. Based on the environmental adaptive coverage feature data, the monitoring area is grid-divided to obtain the monitoring area grid data, wherein the grid size is inversely proportional to the regional coverage feature density. This step can analyze the coverage of the monitoring area more carefully through reasonable grid division, and provide a more accurate spatial division basis for the camera layout. According to the monitoring area grid data and the camera performance parameters, the candidate layout position of the camera is generated to obtain the initial layout point set data. This step comprehensively considers the grid division and the camera performance, and provides a scientific and reasonable candidate position for the initial layout of the camera, laying a foundation for the subsequent optimization calculation.

[0095] Preferably, step S4 comprises the following steps:

[0096] Step S41: performing grid subdivision processing on the monitoring area according to the camera layout parameter data, thereby obtaining high-precision grid data of the monitoring area;

[0097] The embodiment of the present invention obtains the camera layout parameter data of step S3, including the spatial coordinates, orientation angle, field of view angle, and installation height of the camera. For example, in a 100m×100m square monitoring area, a camera is installed at (30m, 40m), with an orientation of 120°, a field of view angle of 90°, and an installation height of 4m. Based on the parameters, the monitoring area is grid-subdivided. The subdivision granularity depends on the camera resolution and monitoring accuracy requirements. For example, a 0.5m×0.5m grid unit can provide more sophisticated monitoring analysis. During the grid subdivision process, it is necessary to ensure that the grid division can cover the field of view of all cameras, and at the same time, the areas that may have overlapping coverage are merged to optimize the computing efficiency. Finally, high-precision grid data is generated, which records the spatial coordinate division of the monitoring area in detail, providing a basis for subsequent sampling point generation and coverage analysis.

[0098] Step S42: generating sampling points for the monitoring area based on the high-precision grid data, thereby obtaining sampling point data for the monitoring area;

[0099] The embodiment of the present invention generates sampling points for the monitoring area based on high-precision grid data. First, an initial sampling point is set at the center position of each grid unit. For example, in the case of 0.5m×0.5m grid division, each grid center point can be regarded as a potential monitoring target point. In addition, in order to improve the evaluation accuracy, additional sampling points are added in key areas (such as entrances and exits, corners, and near obstructions). For example, in the corner area of ​​a building, each 0.5m grid can be further subdivided into 4 sampling points to improve the visibility analysis accuracy of the boundary area. At the same time, the sampling point density can be appropriately reduced in wide unmanned areas to optimize computing resources. Finally, the monitoring area sampling point data is generated, which contains the coordinates of the sampling points in all grids and marks their relative positions and importance in the monitoring area.

[0100] Step S43: performing line of sight accessibility analysis based on the monitoring area sampling point data and the camera layout parameter data, thereby obtaining the sampling point visibility data; performing statistical analysis on the sampling point visibility data, thereby obtaining preliminary area coverage rate data;

[0101] The embodiment of the present invention performs a line of sight reachability analysis based on the sampling point data of the monitoring area and the camera layout parameter data. First, the visible range of each camera is calculated, and based on the ray tracing technology, it is determined whether each sampling point is within the linear field of view of the camera. For example, three-dimensional geometric analysis is used to determine whether the light of a camera can directly reach a certain sampling point, while considering occlusion factors such as buildings and trees. If there is an occlusion between the sampling point and the camera, the point is deemed unreachable. After completing the reachability analysis, the visibility of all sampling points is counted, and the preliminary coverage data of each area is calculated. For example, in a 100m×100m area, if the visible sampling points account for 85% of the total sampling points, the preliminary area coverage is 85%.

[0102] Step S44: performing imaging quality evaluation on the preliminary area coverage data based on light field propagation theory, thereby obtaining imaging quality data including a clarity index, a contrast index, and a signal-to-noise ratio index;

[0103] The embodiment of the present invention performs imaging quality evaluation on the preliminary regional coverage data based on the light field propagation theory. First, the imaging clarity of sampling points in different regions is calculated based on the camera's resolution, focal length, aperture size, and ambient lighting conditions. For example, for a 1080P high-definition camera, its unit pixel resolution can reach 0.1m, and the low-light environment may cause the signal-to-noise ratio to decrease. Secondly, the contrast situation is analyzed to calculate the contrast changes in different regions. For example, in areas with strong light interference, overexposure or reflection may occur, resulting in a decrease in contrast. Finally, the signal-to-noise ratio is calculated, taking into account factors such as environmental noise and camera sensor noise. For example, in a low-light environment at night, if the signal-to-noise ratio is lower than 30dB, the image quality decreases. Finally, imaging quality data is generated, which contains the clarity, contrast, and signal-to-noise ratio indicators of each sampling point for subsequent regional coverage correction.

[0104] Step S45: correcting the preliminary area coverage data according to the imaging quality data, thereby obtaining area coverage data;

[0105] The embodiment of the present invention corrects the preliminary regional coverage data based on the imaging quality data. First, for low-definition areas, the visible range is calculated based on the camera resolution and focal length adjustment. For example, in areas with blurred edges, the coverage data is corrected by reducing the effective coverage range. Secondly, for low-contrast areas (such as backlight areas), it is necessary to reduce the coverage contribution of the area to avoid overestimating the coverage capability. Finally, for areas with low signal-to-noise ratio (such as night monitoring scenes), the effective monitoring weight of the area is appropriately reduced to ensure that the coverage assessment is more in line with the actual situation. After correction, the final regional coverage data is more in line with the actual imaging capability, ensuring the accuracy of the monitoring quality assessment.

[0106] Step S46: performing blind spot detection on the monitoring area according to the camera layout parameter data and the area coverage rate data, thereby obtaining blind spot location data; performing connectivity analysis on the blind spot location data, thereby obtaining blind spot distribution data;

[0107] The embodiment of the present invention performs blind spot detection on the monitoring area based on the camera layout parameter data and the area coverage data. First, traverse all sampling points to find out the areas where the coverage is lower than the set threshold (such as 30%), and mark these areas as blind spots. For example, in a 200m×200m industrial park, if the coverage of some corner areas is only 20%, these areas are marked as blind spots. Then, the blind spot location data is subjected to connectivity analysis to determine whether these blind spots are interconnected or form isolated blind spots. For example, if the area of ​​adjacent blind spots is less than 1m 2 , then the blind area can be considered negligible, and if the continuous blind area of ​​a certain area exceeds 10m 2 , special attention should be paid. Finally, the blind area distribution data is generated to indicate the blind area range of the monitoring system, providing a basis for optimizing the layout.

[0108] Step S47: Perform coverage index evaluation based on coverage level, blind spot size, and blind spot distribution uniformity according to the regional coverage data and the blind spot distribution data, thereby obtaining coverage index data.

[0109] The embodiment of the present invention evaluates the coverage index based on the regional coverage data and blind spot distribution data. First, the overall coverage level is calculated. For example, in a 500m×500m square, the proportion of all visible sampling points is calculated. If the total coverage is 92%, it means that the monitoring system has a relatively complete coverage. Secondly, the size of the blind spot is evaluated and the blind spot area of ​​different areas is analyzed. For example, if a 100m 2 If the blind spots are larger than the above ones, additional cameras may be needed. Finally, evaluate the uniformity of blind spot distribution, that is, calculate the spatial distribution characteristics of blind spots. For example, if the blind spots are mainly concentrated in a specific area, it is necessary to adjust the camera angle or add additional monitoring equipment. Finally, generate coverage index data, which provides quantitative evaluation results of the overall monitoring coverage level and provides guidance for monitoring system optimization and adjustment.

[0110] The present invention performs grid subdivision on the monitoring area according to the camera layout parameter data, obtains high-precision grid data, lays the foundation for subsequent detailed evaluation, makes the division of the monitoring area more refined, and helps to accurately analyze the monitoring situation of each area. Based on the high-precision grid data, the monitoring area sampling point data is generated. These sampling points can represent different positions in the monitoring area, provide specific objects for the subsequent line of sight accessibility analysis, and ensure the comprehensiveness of the evaluation. The line of sight accessibility analysis is performed by combining the sampling point data with the camera layout parameter data to obtain the sampling point visibility data. The preliminary area coverage data is obtained through statistical analysis, and the coverage degree of the camera to the monitoring area is intuitively presented, providing a quantitative basis for subsequent optimization. The initial area coverage data is evaluated for imaging quality using the light field propagation theory to obtain imaging quality data such as clarity, contrast, and signal-to-noise ratio. The monitoring effect is evaluated from the perspective of image quality to ensure the availability and effectiveness of the monitoring screen. The preliminary area coverage data is corrected according to the imaging quality data to obtain more accurate area coverage data, so that the evaluation results are more in line with the actual monitoring needs and the reliability of the evaluation is improved. Based on the camera layout parameter data and regional coverage data, blind spot detection is performed to obtain blind spot location data, and blind spot distribution data is obtained through connectivity analysis to clarify the blind spot situation in the monitoring area, provide key information for subsequent optimization and adjustment, and help eliminate blind spots. Comprehensive regional coverage data and blind spot distribution data are evaluated from multiple dimensions such as coverage level, blind spot size, and blind spot distribution uniformity to obtain comprehensive coverage index data, which provides strong support for the overall performance evaluation of the monitoring system, ensures the scientificity and rationality of the monitoring layout, and meets the requirements of efficient monitoring.

[0111] Preferably, step S46 includes the following steps:

[0112] Step S461: segmenting the visibility data of the sampling points based on a preset threshold according to the area coverage data, thereby obtaining non-coverage area data;

[0113] The embodiment of the present invention collects regional coverage data, which includes the visibility of each sampling point, usually expressed as a coverage value. For example, the coverage of a sampling point in a monitoring area is 85%, while the coverage of another sampling point is only 20%. Then, the visibility data of the sampling points is segmented based on a preset threshold. For example, if the coverage threshold is set to 30%, all sampling points with a coverage rate lower than 30% are marked as non-covered areas. For each sampling point, its visibility under multiple camera perspectives is checked. If the proportion of time that the point is visible to the camera is lower than the threshold, or it is affected by strong occlusion and cannot be directly reached, it is classified as a non-covered area. Finally, the non-covered area data is obtained, which indicates the spatial distribution of all monitoring blind spots and provides a basis for subsequent blind spot contour analysis.

[0114] Step S462: performing spatial clustering processing on the non-covered area data and extracting contour features of the non-covered area to obtain blind spot location data;

[0115] The embodiment of the present invention performs spatial clustering processing on the data of the uncovered area to extract the contour features of the blind spot. First, a density-based clustering algorithm (such as DBSCAN) is used to cluster the sampling points in the uncovered area, and the adjacent low coverage points are merged into an overall area. For example, in a parking lot monitoring system, if a group of adjacent sampling points are not covered by the camera, these points will be clustered into a blind spot. Then, the contour features of each blind spot are extracted using a boundary tracking algorithm. For example, by calculating the curvature change of the blind spot boundary, a more regular rectangular blind spot and a complex irregular blind spot are identified. If the curvature change of a blind spot boundary is small, it indicates that it is close to a rectangle and can be approximately described by the minimum circumscribed rectangle. If the boundary is jagged or variable curve, the contour feature extraction needs to be further refined. Finally, the blind spot position data is generated, which contains the specific spatial coordinates, shape features and boundary information of the blind spot, providing input data for connectivity analysis.

[0116] Step S463: Calculate the spatial relationship and topological structure between blind spots based on the blind spot location data, and perform connectivity analysis to obtain blind spot distribution data, wherein the blind spot distribution data includes the area, shape, location and mutual connectivity characteristics of the blind spots.

[0117] The embodiment of the present invention calculates the spatial relationship and topological structure between blind spots based on the blind spot location data to complete the connectivity analysis. First, the spatial distance between each blind spot is calculated. For example, in an industrial plant, if the minimum spacing between two blind spots is less than 1m, they may belong to the same connected area, and if the spacing exceeds 10m, they may be independent blind spots. Secondly, a topological modeling method is used to convert the spatial relationship between blind spots into a graph structure, in which the blind spots are used as nodes and the connected paths between adjacent blind spots are used as edges. For example, if there are no obstacles between two blind spots and the distance between them is less than a set threshold, they are considered to be connected. Next, the connected component analysis method is used to determine whether there is a large area of ​​connected blind spots in the monitoring area. If the area of ​​a connected blind spot exceeds 50m 2 , then it needs to be paid special attention. Finally, the blind spot distribution data is generated, which describes the area, shape, location and interconnectivity of the blind spots in detail, providing guidance for monitoring optimization.

[0118] The present invention performs segmentation processing on the visibility data of the sampling points based on the preset threshold according to the regional coverage data to obtain the non-covered area data. This step can accurately screen out the areas that are not effectively covered from a large amount of sampling point data, and provide a clear data basis for the subsequent blind spot analysis. The non-covered area data is spatially clustered, and the contour features of the non-covered area are extracted to obtain the blind spot position data. Through clustering and contour extraction, the scattered non-covered area data are integrated into blind spot information with clear shape and position, making the distribution of the blind spots more intuitive and clear. Based on the blind spot position data, the spatial relationship and topological structure between the blind spots are calculated, and the connectivity analysis is performed to obtain the blind spot distribution data including the blind spot area, shape, position and mutual connectivity characteristics. This step further deepens the understanding of the blind spots, not only clarifies the characteristics of each blind spot itself, but also reveals the spatial relationship between the blind spots, and provides comprehensive and detailed blind spot information for subsequent optimization and adjustment, which helps to eliminate or reduce the blind spots in a targeted manner and improve the overall coverage and monitoring effect of the monitoring system.

[0119] Preferably, step S5 comprises the following steps:

[0120] Step S51: Based on the coverage index data, the camera layout parameter data is evaluated for layout optimization targets based on camera position, direction and field of view, so as to obtain layout optimization target data;

[0121] The embodiment of the present invention evaluates the camera layout parameter data based on the coverage index data to optimize the camera position, direction and field of view. First, the coverage index data is used, which reflects the monitoring effect of each area under the current layout, for example, the coverage of some areas is 85%, while other areas are only 50%. Then, the optimization target is set in combination with the current position, orientation and field of view data of the camera. For example, if the monitoring effect within the camera coverage area at a certain position is poor, the layout parameters of this position need to be optimized. During the evaluation process, it will be considered how to improve the overall monitoring coverage by adjusting the field of view or position of the camera. The calculation process determines the effect of each adjustment method on the coverage improvement based on the existing monitoring area and camera parameter data. By evaluating each possible layout scheme, a set of layout optimization target data is obtained to provide a reference for subsequent optimization calculations.

[0122] Step S52: assigning importance weights to the monitoring areas according to the layout optimization target data, thereby obtaining regional priority data, wherein the regional priority of the regional priority data is inversely proportional to the coverage level in the area and directly proportional to the crowd density;

[0123] The embodiment of the present invention assigns importance weights to the monitoring areas according to the layout optimization target data to obtain regional priority data. The assignment of regional priorities is based on two factors: coverage level and crowd density. First, by analyzing the coverage index data, higher priorities are given to areas with lower coverage because these areas are in urgent need of optimization; while lower priorities are given to areas with higher coverage. Secondly, according to crowd density data, for example, areas such as shopping malls and conference rooms have higher crowd density, and these areas will be given higher priorities. For areas with less crowds, lower priorities are assigned. In this way, the final regional priority data can help better balance the needs of different areas during the optimization process, so that areas with high crowds and high demands receive more attention.

[0124] Step S53: constructing an objective function for camera layout optimization based on the regional priority data, thereby obtaining optimization function model data, wherein the objective function includes three sub-objectives: maximizing coverage, minimizing blind spots, and minimizing adjustment costs;

[0125] The embodiment of the present invention constructs an objective function for camera layout optimization based on regional priority data. The objective function consists of three sub-objectives: maximizing coverage, minimizing blind spots, and minimizing adjustment costs. First, the coverage maximization sub-objective improves the overall monitoring effect by increasing the camera coverage in high-priority areas; the blind spot minimization sub-objective focuses on reducing the number of blind spots in the monitoring area, especially in high-priority areas, and strives to reduce the blind spots to a minimum; the adjustment cost minimization sub-objective focuses on how to minimize the physical adjustment of the camera when optimizing the layout, such as reducing position movement or angle changes, to reduce implementation costs. The objective function combines these three sub-objectives by weighted summation, among which maximizing coverage and minimizing blind spots are usually given higher weights, while minimizing adjustment costs is adjusted according to actual needs. Finally, the optimization function model data is obtained, which provides a basis for further iterative optimization.

[0126] Step S54: performing iterative optimization calculation on the camera layout parameters using the optimization function model data, wherein the iteration termination condition is that the coverage index is less than a preset threshold or reaches a maximum number of iterations, thereby obtaining layout optimization iteration data;

[0127] The embodiment of the present invention uses the optimization function model data to perform iterative optimization calculations on the camera layout parameters. During the optimization process, the camera layout parameters, such as position, orientation angle, and field of view angle, are first initialized, and the optimization effect of the current layout is calculated according to the objective function. Then, through iterative calculations, the layout parameters are continuously adjusted to optimize the camera layout plan. In each iteration, the layout parameters are updated according to the evaluation results of the objective function until the optimization results meet the preset termination conditions. The termination conditions include the coverage index reaching a predetermined threshold, such as the coverage exceeding 95%, or reaching the maximum number of iterations to ensure that the optimization process does not continue indefinitely. Finally, the layout optimization iteration data is obtained to prepare for obtaining the optimal solution.

[0128] Step S55: extracting the optimal solution according to the layout optimization iteration data, thereby obtaining the optimal layout parameter data;

[0129] The embodiment of the present invention extracts the optimal solution based on the layout optimization iteration data to obtain the optimal layout parameter data. First, according to the output data in the iterative optimization process, the layout parameters that meet the optimal solution of the objective function are selected. These parameters will ensure that the coverage is maximized, the blind spots are minimized, and the adjustment cost is minimized. For example, through iteration, a layout scheme is finally selected, in which the configuration of the camera can cover all key points of the monitoring area, while minimizing the adjustment cost and avoiding unnecessary large-scale position changes. Finally, the optimal solution is extracted, including the optimal position coordinates, orientation angle and field of view angle of the camera, as the final layout scheme.

[0130] Step S56: Perform constraint check on the installation feasibility of the camera based on the optimal layout parameter data. If the verification passes, directly output the camera layout plan. If the verification fails, return to step S54 to continue iterative optimization, where the camera layout plan includes the camera's final position coordinates, direction vector and field of view angle parameters.

[0131] The embodiment of the present invention performs a constraint check on the installation feasibility of the camera based on the optimal layout parameter data. First, check whether the optimal layout parameters meet the installation space and equipment requirements. For example, some cameras may need to be installed at a specific height or a specific angle, and it must be ensured that the selected layout plan can be actually implemented. Secondly, if the constraint check passes and verifies that the position, angle, and field of view of the camera are feasible in the physical space and are not blocked by other facilities or obstacles, the final camera layout plan is output. If the verification fails, that is, the layout plan is not implementable, return to step S54 and continue iterative optimization until a plan is found that meets the layout requirements and can be actually installed. The camera layout plan finally output will include data such as the precise position coordinates, direction vector, and field of view of each camera to ensure comprehensive coverage of the monitoring area.

[0132] The present invention evaluates the camera layout parameter data based on the coverage index data and determines the layout optimization target data. This step clarifies the direction of camera layout optimization, ensures that the optimization process is targeted, and accurately improves the monitoring coverage. According to the layout optimization target data, the importance weights of the monitoring areas are allocated to obtain regional priority data, so that the optimization process can focus on areas with high density of people and low coverage, and improve the utilization efficiency of monitoring resources. Based on the regional priority data, a camera layout optimization objective function containing three sub-goals of maximizing coverage, minimizing blind spots, and minimizing adjustment costs is constructed. This step provides comprehensive and scientific guidance for optimization calculations, ensuring that the optimization results achieve optimal balance in multiple key indicators. Iterative optimization calculations are performed using the optimization function model data until the termination conditions are met, and layout optimization iteration data is obtained. Through continuous iteration, the optimal solution is gradually approached to provide accurate parameters for the camera layout. The optimal solution is extracted from the layout optimization iteration data to obtain the optimal layout parameter data. This step locks the best camera layout solution and provides a scientific basis for subsequent installation. A constraint check is performed on the feasibility of camera installation. If the verification passes, the layout plan is output. If it fails, the optimization is returned to continue. This step ensures that the camera layout plan is not only optimal in theory, but also feasible in actual installation. The final output camera layout plan includes the final position coordinates, direction vector and field of view angle parameters, providing a strong guarantee for the efficient operation of the monitoring system.

[0133] The present invention also provides a modeled camera layout system for executing the modeled camera layout method as described above, wherein the modeled camera layout system comprises:

[0134] The light field modeling module is used to obtain the three-dimensional geometric scanning data and dynamic object data of the monitoring space; perform light field space modeling on the monitoring space according to the three-dimensional geometric scanning data to obtain spatial light field distribution data;

[0135] The light analysis module is used to perform ray tracing analysis on the spatial light field distribution data according to the dynamic object data to obtain light propagation characteristic data including light reflection, refraction and diffraction; the light propagation characteristic data is used to perform effective coverage analysis on the monitoring area based on the light intensity threshold and the field of view angle range, thereby obtaining regional coverage characteristic data;

[0136] A layout optimization module is used to perform adaptive optimization calculation on the initial layout of the camera through the regional coverage feature data and the pre-acquired environmental parameter data to obtain the camera layout parameter data, wherein the environmental parameter data includes optical environment parameters, physical environment parameters and camera performance parameters;

[0137] A coverage evaluation module is used to evaluate and calculate the coverage rate of the monitoring area according to the camera layout parameter data to obtain coverage rate index data, wherein the coverage rate index data includes regional coverage rate data and blind spot distribution data;

[0138] The scheme adjustment module is used to dynamically optimize and adjust the camera layout parameter data according to the coverage index data to obtain the camera layout scheme, wherein the camera layout scheme includes the final position coordinates, direction vector and field of view angle parameters of the camera.

[0139] The present invention obtains the three-dimensional geometric scanning data and dynamic object data of the monitoring space, and performs light field space modeling based on these data to generate spatial light field distribution data, which provides a basis for subsequent analysis. This process enables the system to accurately understand the light distribution in the monitoring space, thereby providing a scientific basis for the layout of the camera. The spatial light field distribution data is subjected to ray tracing analysis using dynamic object data to obtain propagation characteristic data such as light reflection, refraction and diffraction. These data are essential for understanding the propagation behavior of light in the monitoring area. The module further uses these light propagation characteristic data to perform effective coverage analysis on the monitoring area based on the light intensity threshold and the field of view angle range, and generates regional coverage characteristic data. This step ensures that the light conditions in the monitoring area can meet the monitoring requirements and provides key information for the layout of the camera. Combined with the regional coverage characteristic data and the pre-acquired environmental parameter data, the initial layout of the camera is adaptively optimized and calculated to obtain the camera layout parameter data. The environmental parameter data includes optical environment parameters, physical environment parameters and camera performance parameters. This process enables the camera layout to be adjusted according to the actual environmental conditions to ensure the rationality and effectiveness of the layout. According to the camera layout parameter data, the coverage rate of the monitoring area is evaluated and calculated to obtain coverage index data, including regional coverage data and blind spot distribution data. This evaluation process helps to understand the coverage of the monitoring area, identify blind spots, and provide a basis for subsequent optimization and adjustment. According to the coverage index data, the camera layout parameter data is dynamically optimized and adjusted to obtain the final camera layout plan. This plan includes the final position coordinates, direction vector and field of view angle parameters of the camera. Through dynamic optimization and adjustment, the system can continuously improve the camera layout to ensure full coverage of the monitoring area and improve the monitoring effect. In general, these steps together constitute a systematic camera layout optimization process, which ensures the efficiency and reliability of the monitoring system through precise light field modeling, light analysis, layout optimization, coverage evaluation and solution adjustment. This process not only improves the monitoring coverage rate, but also reduces blind spots and optimizes the layout of cameras, so that the monitoring system can better adapt to complex and changing monitoring environments.

[0140] Therefore, the embodiments should be regarded as illustrative and non-restrictive from all points, and the scope of the present invention is limited by the appended claims rather than the above description, and it is therefore intended that all changes falling within the meaning and range of equivalent elements of the application documents are included in the present invention.

[0141] The above description is only a specific embodiment of the present invention, so that those skilled in the art can understand or implement the present invention. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein may 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 the embodiments shown herein, but should conform to the widest 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: Acquire three-dimensional geometric scanning data and dynamic object data of the monitoring space; perform light field space modeling on the monitoring space according to the three-dimensional geometric scanning data to obtain spatial light field distribution data; Step S2: performing ray tracing analysis on the spatial light field distribution data according to the dynamic object data to obtain light propagation characteristic data including light reflection, refraction and diffraction; using the light propagation characteristic data to perform effective coverage analysis on the monitoring area based on the light intensity threshold and the field of view angle range, thereby obtaining regional coverage characteristic data; Step S3: performing adaptive optimization calculation on the initial layout of the camera through the regional coverage feature data and the pre-acquired environmental parameter data to obtain the camera layout parameter data, wherein the environmental parameter data includes optical environment parameters, physical environment parameters and camera performance parameters; Step S4: performing coverage evaluation calculation on the monitoring area according to the camera layout parameter data to obtain coverage index data, wherein the coverage index data includes regional coverage data and blind spot distribution data; Step S5: dynamically optimizing and adjusting the camera layout parameter data according to the coverage index data to obtain a camera layout solution, wherein the camera layout solution includes the final position coordinates, direction vector and field of view angle parameters of the camera.

2. The modeled camera layout method according to claim 1, characterized in that: Step S1 includes the following steps: Step S11: Acquire three-dimensional geometric scanning data, surface structure data, and dynamic object data of the monitoring space; Step S12: reconstructing the spatial geometry according to the three-dimensional geometric scanning data, thereby obtaining spatial structure model data; Step S13: performing material optical characteristic analysis on the spatial structure model data according to the surface structure data, thereby obtaining surface optical characteristic data including reflectivity, scattering coefficient and transmittance; Step S14: Analyze the crowd density of the monitored space through dynamic object data to obtain regional dynamic characteristic data; Step S15: performing light field space modeling on the spatial structure model data using a four-dimensional light field function, thereby obtaining initial light field distribution data; Step S16: converting the initial light field distribution data into a complex form according to the surface optical characteristic data, wherein the real part represents the light intensity attenuation data and the imaginary part represents the phase information data, thereby obtaining the complex light field distribution data; Step S17: Dynamically weight the complex light field distribution data according to the regional dynamic characteristic data, so as to obtain spatial light field distribution data, wherein the dynamic weight allocation is specifically an assignment in which the weight is linearly positively correlated with the crowd density.

3. The modeled camera layout method according to claim 2, characterized in that: Step S2 includes the following steps: Step S21: performing spatiotemporal alignment processing on the motion trajectory and position information in the dynamic object data and the spatial light field distribution data, thereby obtaining spatiotemporal matching data; Step S22: performing ray tracing processing on the spatial light field distribution data according to the time-space matching data, and simulating the propagation of light in the monitoring area, thereby obtaining preliminary light propagation characteristic data including light reflection, refraction and diffraction; Step S23: performing a refined correction process on the light propagation based on the preliminary light propagation characteristic data and a preset optical physics model, thereby obtaining the light propagation characteristic data; Step S24: Use the light propagation characteristic data to perform effective coverage analysis on the monitoring area based on the light intensity threshold and the field of view angle range, so as to obtain regional coverage characteristic data.

4. The modeled camera layout method according to claim 3, characterized in that: Step S24 includes the following steps: Step S241: extracting and processing the light intensity of each sampling point in the monitoring area based on the light propagation characteristic data, thereby obtaining local light intensity data of each sampling point; screening and processing each sampling point using a preset light intensity threshold according to the local light intensity data, thereby obtaining area division data that meets the light intensity coverage requirements; Step S242: extracting and processing the field of view angle of each sampling point in the monitoring area based on the light propagation characteristic data, thereby obtaining local field of view angle data of each sampling point; comparing and processing each sampling point according to the local field of view angle data and the preset camera field of view angle range, thereby obtaining regional distribution data that meets the field of view angle coverage requirements; Step S243: Perform fusion analysis and processing based on the area division data and the area distribution data to obtain effective coverage feature data of the monitoring area.

5. The modeled camera layout method according to claim 4, characterized in that: Step S3 includes the following steps: Step S31: Acquire environmental parameter data, including optical environmental parameters, physical environmental parameters and camera performance parameters; Step S32: compensating and correcting the regional coverage feature data using the optical environment parameters and the physical environment parameters, thereby obtaining the environment adaptive coverage feature data; performing grid processing on the monitoring area based on the environment adaptive coverage feature data and the camera performance parameters and generating candidate layout positions, thereby obtaining the initial layout point set data; Step S33: performing scoring calculation on the initial layout point set data based on coverage area, imaging quality and monitoring continuity, thereby obtaining layout point set scoring data; Step S34: performing priority sorting processing on the initial layout point set data according to the layout point set scoring data, thereby obtaining optimized layout sequence data; Step S35: Perform final layout optimization calculation according to the optimized layout sequence data and the camera performance parameters, so as to obtain camera layout parameter data, wherein the camera layout parameter data includes the spatial coordinate data, orientation angle data and field of view angle data of the camera.

6. The modeled camera layout method according to claim 5, characterized in that: Step S32 includes the following steps: Step S321: performing illumination compensation processing on the regional coverage characteristic data according to the optical environment parameters, thereby obtaining illumination compensation coverage characteristic data; Step S322: performing environmental impact correction processing on the illumination compensation coverage characteristic data according to the physical environment parameters, thereby obtaining environmental adaptive coverage characteristic data; Step S323: performing grid division processing on the monitoring area based on the environment adaptive coverage feature data, thereby obtaining monitoring area grid data, wherein the grid size in the monitoring area grid data is inversely proportional to the regional coverage feature density; Step S324: Generate candidate layout positions of the camera according to the monitoring area grid data and camera performance parameters, thereby obtaining initial layout point set data.

7. The modeled camera layout method according to claim 6, characterized in that: Step S4 includes the following steps: Step S41: performing grid subdivision processing on the monitoring area according to the camera layout parameter data, thereby obtaining high-precision grid data of the monitoring area; Step S42: generating sampling points for the monitoring area based on the high-precision grid data, thereby obtaining sampling point data for the monitoring area; Step S43: performing line of sight accessibility analysis based on the monitoring area sampling point data and the camera layout parameter data, thereby obtaining the sampling point visibility data; performing statistical analysis on the sampling point visibility data, thereby obtaining preliminary area coverage rate data; Step S44: performing imaging quality evaluation on the preliminary area coverage data based on light field propagation theory, thereby obtaining imaging quality data including a clarity index, a contrast index, and a signal-to-noise ratio index; Step S45: correcting the preliminary area coverage data according to the imaging quality data, thereby obtaining the area coverage data; Step S46: performing blind spot detection on the monitoring area according to the camera layout parameter data and the area coverage rate data, thereby obtaining blind spot location data; performing connectivity analysis on the blind spot location data, thereby obtaining blind spot distribution data; Step S47: Perform coverage index evaluation based on coverage level, blind spot size, and blind spot distribution uniformity according to the regional coverage data and the blind spot distribution data, thereby obtaining coverage index data.

8. The modeled camera layout method according to claim 7, characterized in that: Step S46 includes the following steps: Step S461: segmenting the visibility data of the sampling points based on a preset threshold according to the area coverage data, thereby obtaining non-coverage area data; Step S462: performing spatial clustering processing on the non-covered area data and extracting contour features of the non-covered area to obtain blind spot location data; Step S463: Calculate the spatial relationship and topological structure between blind spots based on the blind spot location data, and perform connectivity analysis to obtain blind spot distribution data, wherein the blind spot distribution data includes the area, shape, location and mutual connectivity characteristics of the blind spots.

9. The modeled camera layout method according to claim 8, characterized in that: Step S5 includes the following steps: Step S51: Based on the coverage index data, the camera layout parameter data is evaluated for layout optimization targets based on camera position, direction and field of view, so as to obtain layout optimization target data; Step S52: assigning importance weights to the monitoring areas according to the layout optimization target data, thereby obtaining regional priority data, wherein the regional priority of the regional priority data is inversely proportional to the coverage level in the area and directly proportional to the crowd density; Step S53: constructing an objective function for camera layout optimization based on the regional priority data, thereby obtaining optimization function model data, wherein the objective function includes three sub-objectives: maximizing coverage, minimizing blind spots, and minimizing adjustment costs; Step S54: performing iterative optimization calculation on the camera layout parameters using the optimization function model data, wherein the iteration termination condition is that the coverage index is less than a preset threshold or reaches a maximum number of iterations, thereby obtaining layout optimization iteration data; Step S55: extracting the optimal solution according to the layout optimization iteration data, thereby obtaining the optimal layout parameter data; Step S56: Perform constraint check on the installation feasibility of the camera based on the optimal layout parameter data. If the verification passes, directly output the camera layout plan. If the verification fails, return to step S54 to continue iterative optimization, where the camera layout plan includes the camera's final position coordinates, direction vector and field of view angle parameters.

10. A modeled camera layout system, characterized in that: For executing the modeled camera layout method according to claim 1, the modeled camera layout system comprises: The light field modeling module is used to obtain the three-dimensional geometric scanning data and dynamic object data of the monitoring space; perform light field space modeling on the monitoring space according to the three-dimensional geometric scanning data to obtain spatial light field distribution data; The light analysis module is used to perform ray tracing analysis on the spatial light field distribution data according to the dynamic object data to obtain light propagation characteristic data including light reflection, refraction and diffraction; the light propagation characteristic data is used to perform effective coverage analysis on the monitoring area based on the light intensity threshold and the field of view angle range, thereby obtaining regional coverage characteristic data; A layout optimization module is used to perform adaptive optimization calculation on the initial layout of the camera through the regional coverage feature data and the pre-acquired environmental parameter data to obtain the camera layout parameter data, wherein the environmental parameter data includes optical environment parameters, physical environment parameters and camera performance parameters; A coverage evaluation module is used to evaluate and calculate the coverage rate of the monitoring area according to the camera layout parameter data to obtain coverage rate index data, wherein the coverage rate index data includes regional coverage rate data and blind spot distribution data; The scheme adjustment module is used to dynamically optimize and adjust the camera layout parameter data according to the coverage index data to obtain the camera layout scheme, wherein the camera layout scheme includes the final position coordinates, direction vector and field of view angle parameters of the camera.

Images