Modeled camera layout method, system and device and storage medium

Abstract

The invention belongs to the technical field of monitoring security and protection, and particularly provides a modeling camera layout method, system and device and a storage medium, and the method comprises the steps: obtaining the three-dimensional space data of a target scene, and constructing a three-dimensional scene model; training a machine learning model based on preset layout optimization target parameters, the dynamic constraint condition set and the training data set; inputting the three-dimensional scene model and security and protection demand parameters obtained in real time into a machine learning model, and outputting an optimal camera layout scheme meeting layout optimization target parameters through the machine learning model; and according to the environment change parameters of the target scene acquired in real time, performing dynamic iterative optimization on the positions, angles and collaborative parameters of the cameras through a machine learning model, and outputting an updated camera layout scheme. Through collaborative optimization of three-dimensional scene modeling and a machine learning model, traditional experience-driven camera layout is converted into data-driven intelligent decision, and layout objectivity and adaptability are remarkably improved.

Description

Technical Field

[0001] The present invention belongs to the field of monitoring and security technology, and in particular relates to a modeling camera layout method, system, device and storage medium. Background Art

[0002] With growing awareness of security, surveillance systems are becoming increasingly common, serving as a crucial component of security. However, existing video surveillance layout design methods often rely on engineering designers' experience, simple measurements, and estimates to configure the layout. This manual approach is subject to significant subjective bias, making it difficult to assess the rationality of camera layouts. Without a unified, objective standard for evaluating camera layouts, camera layout quality varies widely, and blind spots are common.

[0003] To this end, the present invention provides a modeling camera layout method, system, device and storage medium to solve the above problems. Summary of the Invention

[0004] In order to overcome the deficiencies of the prior art, the present invention provides a modeling camera layout method, system, device and storage medium to solve the problems in the prior art.

[0005] One embodiment of the present invention provides a modeling camera layout method, comprising the following steps:

[0006] S10, acquiring three-dimensional spatial data of the target scene, and constructing a three-dimensional scene model including static object structure and dynamic environment parameters;

[0007] S20, training a machine learning model based on preset layout optimization target parameters, a dynamic constraint condition set, and a training data set to obtain a trained machine learning model for associating a mapping relationship between camera layout parameters and scene features;

[0008] S30, inputting the three-dimensional scene model and the security requirement parameters obtained in real time into a trained machine learning model, and outputting an optimal camera layout solution that meets the layout optimization target parameters through the machine learning model;

[0009] S40. Based on the environmental change parameters of the target scene obtained in real time, the position, angle and coordination parameters of the camera are dynamically iteratively optimized through the machine learning model, and an updated camera layout plan is output.

[0010] In one embodiment, after step S40, the following steps are further included:

[0011] S50, during the execution of the camera layout solution, when it is detected that a camera in the target scene triggers a preset monitoring failure determination rule, generating a monitoring failure signal and determining a location area of ​​the failed camera;

[0012] S60: activating a backup camera that meets a preset backup device activation rule according to the location area;

[0013] S70: Dynamically adjust the monitoring parameters of the backup camera to cover the failure area, and update the coordination parameter set in the camera layout solution.

[0014] In one embodiment, in step S60, the preset backup device activation rule includes at least one of the following:

[0015] The straight-line distance or path planning distance between the backup camera and the failure area is less than the preset distance threshold, and the closest available device is prioritized;

[0016] The current workload of the backup camera is lower than a preset threshold, where the workload includes at least one of CPU utilization, network bandwidth occupancy, and remaining storage space;

[0017] The field of view of the backup camera has unobstructed visual coverage with the failure area in the three-dimensional scene model.

[0018] In one embodiment, step S10 specifically includes the following steps:

[0019] S11. Acquire three-dimensional spatial data of a target scene through a multimodal acquisition module, wherein the three-dimensional spatial data includes geometric topology data, texture image data, and dynamic environment parameters;

[0020] S12. Extracting the spatial structure of buildings, fixed equipment, and functional areas based on the geometric topology data and texture image data, and labeling the passage priority and safety risk level of the static objects using a semantic analysis model;

[0021] S13. Acquire in real time the illumination distribution characteristics, surface reflection characteristics, and moving target trajectory of the dynamic environment parameters, perform behavioral semantic classification on the moving target, and generate a security response priority label dynamically associated with the three-dimensional spatial coordinates;

[0022] S14. Based on the illumination distribution characteristics and the surface reflection characteristics, predict the imaging attenuation area within the camera field of view using a light field reconstruction model, and mark it as a light field interference feature;

[0023] S15. Integrate the spatial structure, semantic annotation, security response priority label, and light field interference characteristics of the static object to construct a multi-dimensional three-dimensional scene model including geometric constraints, semantic rules, and light field interference characteristics.

[0024] In one embodiment, in step S20, the preset layout optimization target parameter includes at least one of the following:

[0025] Coverage optimization goal: maximizing the number of sub-areas within the monitoring area that are effectively covered, using the security risk level in the scene semantic attributes as a weight. Effective coverage requires that the light field interference characteristics in the 3D scene model are below a preset threshold.

[0026] Cost optimization goal: Minimize the overall cost of camera deployment using the number of devices, energy consumption, and deployment complexity as joint optimization variables. The deployment complexity is dynamically evaluated based on the obstacle distribution in the 3D scene model.

[0027] Redundancy optimization goal: Within an area where the security risk level is a preset threshold, maximize the number of sub-areas that are overlapped by multiple cameras.

[0028] In one embodiment, in step S20, the dynamic constraint condition set includes at least one of the following:

[0029] Field of view integrity constraint: The unobstructed ratio between the camera field of view coverage path and the obstacle area in the 3D scene model must reach a preset threshold. The obstacle area is dynamically verified based on real-time updated semantic attributes.

[0030] Timeliness constraints: Based on the scene activity density in dynamic environment parameters, the maximum generation delay threshold of the layout plan is adaptively adjusted to ensure that the response time of high-density scenes meets the preset safety timeliness;

[0031] Collaborative deployment constraints: The deployment distance between cameras must meet signal compatibility thresholds and physical safety thresholds.

[0032] In one embodiment, step S20 specifically includes the following steps:

[0033] S21. Generate a multi-scenario training dataset based on the preset layout optimization target parameters, dynamic constraint condition set, and training dataset, where each training sample includes:

[0034] Input features: geometric topology, dynamic environment parameters, and security requirement parameters extracted from historical 3D scene models;

[0035] Output label: an optimal camera layout parameter set that satisfies the layout optimization target parameters and complies with the dynamic constraint condition set;

[0036] S22. Construct a multi-objective optimization neural network model, the model comprising:

[0037] Coverage optimization module: Calculates the coverage efficiency of camera positions for the monitored area based on security risk level weights;

[0038] Cost Optimization Module: This module evaluates the complexity of equipment deployment based on obstacle distribution density and generates a layout plan under cost constraints.

[0039] Redundancy Optimization Module: Calculates the redundancy of overlapping coverage of multiple cameras’ fields of view in areas where the security risk level reaches a preset threshold;

[0040] S23. Input the multi-scenario training data set into the multi-objective optimization neural network model, use the coverage optimization objective, the cost optimization objective, and the redundancy optimization objective as optimization items, use the dynamic constraint condition set as the hard constraint item, and jointly train the model parameters through the constrained optimization algorithm;

[0041] S24. Verify whether the layout solution output by the trained model in the test scenario satisfies all dynamic constraints at the same time. If there is a constraint violation, adjust the weight coefficient of the layout optimization target parameter and retrain.

[0042] The present application also relates to a modeled camera layout system, comprising:

[0043] The data acquisition module is used to obtain the three-dimensional spatial data of the target scene and construct a three-dimensional scene model including static object structure and dynamic environment parameters;

[0044] A model training module is used to train a machine learning model based on preset layout optimization target parameters, a dynamic constraint condition set, and a training data set, thereby obtaining a trained machine learning model for associating a mapping relationship between camera layout parameters and scene features;

[0045] A solution output module is used to input the three-dimensional scene model and the security requirement parameters obtained in real time into a trained machine learning model, and output an optimal camera layout solution that meets the layout optimization target parameters through the machine learning model;

[0046] The iterative optimization module is used to dynamically iteratively optimize the position, angle and coordination parameters of the camera through the machine learning model based on the environmental change parameters of the target scene obtained in real time, and output an updated camera layout plan.

[0047] The present application also relates to a computer device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above-mentioned modeling camera layout method when executing the computer program.

[0048] The present application also relates to a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above-mentioned modeling camera layout method are implemented.

[0049] The above embodiments provide a modeling camera layout method, system, device, and storage medium with the following beneficial effects:

[0050] 1. Through the collaborative optimization of 3D scene modeling and machine learning models, traditional experience-driven camera layout is transformed into data-driven intelligent decision-making, significantly improving the objectivity and adaptability of the layout. Based on the 3D scene model, static structural and dynamic environmental parameters are precisely quantified. In conjunction with the machine learning model, a mapping relationship between scene characteristics and layout parameters is constructed, eliminating the subjective bias of human experience. Driven by both real-time security requirements and environmental change parameters, dynamic iterative optimization of camera position, angle, and coordination strategies is achieved, effectively reducing monitoring blind spots and improving the speed of response to sudden risks. At the same time, relying on training data sets and automated layout generation mechanisms, redundant equipment deployment and manual debugging costs are reduced, providing a high-precision, low-cost, standardized solution for security monitoring systems.

[0051] 2. In one implementation, failure detection and dynamic adjustment mechanisms address the monitoring blind spots caused by device anomalies in traditional deployments. Camera failures are identified in real time, the faulty area is located, and backup equipment is activated to compensate for the situation, ensuring monitoring continuity. Dynamic updates to collaborative parameter sets optimize multi-camera task allocation to avoid resource redundancy. Furthermore, automated response mechanisms reduce interruption time from minutes to seconds, significantly improving security reliability in high-density or high-risk scenarios.

[0052] 3. In one embodiment, multimodal data fusion and light field-enhanced modeling address the shortcomings of traditional 3D scene models in analyzing complex environments. Multimodal sensing simultaneously collects geometric and texture data, combined with semantic analysis to accurately annotate traffic priorities and safety risk areas, improving static modeling accuracy. Dynamic light field reconstruction quantifies the interference of light reflections and moving targets, predicts monitoring blind spots, and adaptively adjusts anti-interference parameters. A multidimensional model integrating geometric, semantic, and physical interference assessment provides a holographic decision-making basis for complex scenarios, enabling scientific deployment of security layouts in highly dynamic environments and significantly enhancing the system's environmental adaptability and anti-interference capabilities.

[0053] 4. In one embodiment, a joint training mechanism combining multi-objective collaborative optimization and dynamic constraints addresses the inadequate optimization capabilities of traditional layout models under multi-objective conflicts and complex physical rules. The multi-objective optimization neural network module hierarchically learns decision rules covering performance, cost control, and redundant safety, combining historical scenario data with real-time environmental parameters to generate adaptive layout strategies. A constrained optimization algorithm enforces visibility, timeliness, and device coordination rules for the layout plan to ensure strict compliance with dynamic constraints. Through incremental training and weight adjustment mechanisms, the model's generalization and response speed in highly dynamic scenarios are significantly improved, providing intelligent layout decision support that balances efficiency and reliability for complex security scenarios. BRIEF DESCRIPTION OF THE DRAWINGS

[0054] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the structures shown in these drawings without paying any creative work.

[0055] Figure 1 A flow chart of a camera layout modeling method provided by an embodiment of the present invention;

[0056] Figure 2 Another flow chart of a modeling camera layout method provided by an embodiment of the present invention;

[0057] Figure 3 A flowchart for implementing step S10 of a camera layout modeling method provided by an embodiment of the present invention;

[0058] Figure 4 A flowchart for implementing step S20 of a camera layout modeling method provided by an embodiment of the present invention;

[0059] Figure 5 A block diagram of a computer device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0060] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0061] It should be noted that if the embodiments of the present invention involve directional indications (such as up, down, left, right, front, back, etc.), the directional indications are only used to explain the relative position relationship, movement status, etc. between the components under a certain specific posture. If the specific posture changes, the directional indications will also change accordingly.

[0062] In addition, if there are descriptions involving "first", "second", etc. in the embodiments of the present invention, the descriptions of "first", "second", etc. are only for descriptive purposes and cannot be understood as indicating or suggesting their relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features limited to "first" and "second" may explicitly or implicitly include at least one of such features. In addition, if "and / or" or "and / or" appears in the full text, its meaning includes three parallel solutions. Taking "A and / or B" as an example, it includes solution A, solution B, or solutions that satisfy both A and B. In addition, the technical solutions between the various embodiments can be combined with each other, but it must be based on the ability of ordinary technicians in this field to implement. When the combination of technical solutions is mutually contradictory or cannot be implemented, it should be deemed that such a combination of technical solutions does not exist and is not within the scope of protection required by the present invention.

[0063] Reference Figure 1 One embodiment of the present invention provides a modeling camera layout method, comprising the following steps:

[0064] S10, acquiring three-dimensional spatial data of the target scene, and constructing a three-dimensional scene model including static object structure and dynamic environment parameters;

[0065] S20, training a machine learning model based on preset layout optimization target parameters, a dynamic constraint condition set, and a training data set to obtain a trained machine learning model for associating a mapping relationship between camera layout parameters and scene features;

[0066] S30, inputting the three-dimensional scene model and the security requirement parameters obtained in real time into a trained machine learning model, and outputting an optimal camera layout solution that meets the layout optimization target parameters through the machine learning model;

[0067] S40. Based on the environmental change parameters of the target scene obtained in real time, the position, angle and coordination parameters of the camera are dynamically iteratively optimized through the machine learning model, and an updated camera layout plan is output.

[0068] As described in step S10 above, the three-dimensional spatial data includes the geometric topological data of the target scene (such as building outlines, obstacle coordinates), texture image data (such as surface material, color information) and dynamic environmental parameters (such as light intensity, pedestrian trajectory, temperature and humidity), etc. Data is collected synchronously through multimodal sensing devices (such as lidar, RGB-D camera, etc.), and a three-dimensional scene model is constructed using point cloud registration and semantic segmentation algorithms. The model includes spatial representation of static object structures (such as walls, equipment positions), as well as real-time mapping of dynamic environmental parameters, providing a digital environment base for layout optimization.

[0069] As described in step S20 above, the preset layout optimization objective parameters are defined as maximizing coverage, minimizing equipment costs, and ensuring redundant monitoring in high-risk areas. The dynamic constraint set includes line-of-sight constraints, response latency constraints, and equipment anti-interference spacing. Based on a training dataset (historical scene samples and corresponding optimal layout solutions), a machine learning model is trained using a deep reinforcement learning framework to establish a mapping relationship between scene characteristics (such as safety level distribution and obstacle density) and layout parameters (camera coordinates, pitch angle, and focal length). A multi-objective optimization algorithm is then used to ensure that the layout solution meets both physical feasibility and security requirements.

[0070] As described in step S30 above, the 3D scene model (including static structure and dynamic parameter annotations) and security requirement parameters (such as key monitoring areas in the target scene, risk level weights, and budget costs) are input into the trained model. The model iteratively calculates and outputs an optimal camera layout plan, including device type, quantity, spatial coordinates, and coordination strategy (such as master-slave tracking logic), ensuring that the plan meets the preset optimization goals and dynamic constraints.

[0071] As described in step S40 above, environmental change parameters include the coordinates of newly added obstacles, sudden changes in crowd density, and shifts in lighting conditions. Real-time data drives the machine learning model for dynamic iterative optimization: adjusting camera positions to avoid obstructions, switching angles to expand coverage, updating collaborative parameter sets (such as enabling backup device linkage), and outputting the updated layout parameter set to achieve continuous adaptation.

[0072] In this embodiment, through the collaborative optimization of three-dimensional scene modeling and machine learning models, the traditional experience-driven camera layout is transformed into data-driven intelligent decision-making, significantly improving the objectivity and adaptability of the layout: based on the three-dimensional scene model, the static structure and dynamic environmental parameters are accurately quantified, and the mapping relationship between scene characteristics and layout parameters is constructed in combination with the machine learning model to eliminate the subjective bias of human experience; through the dual drive of real-time security demand parameters and environmental change parameters, dynamic iterative optimization of camera position, angle and collaborative strategy is achieved, effectively reducing monitoring blind spots and improving the response speed of sudden risks; at the same time, relying on training data sets and automated layout generation mechanisms, the deployment of redundant equipment and manual debugging costs are reduced, providing a high-precision, low-cost standardized solution for security monitoring systems.

[0073] In one possible embodiment, it is assumed that:

[0074] A shopping mall needs to deploy a surveillance system covering the jewelry area (high-risk), fire escape routes (critical traffic nodes) and atriums (high-traffic areas).

[0075] Step S10:

[0076] The building structure is scanned by LiDAR, and the shelf texture is captured by RGB-D camera to construct a centimeter-level accurate 3D model.

[0077] Mark static structures: such as jewelry counters (safety level 9) and fire doors (access priority A);

[0078] Integrated dynamic parameters: peak reflective intensity of the glass curtain wall at noon (1200 lux) and pedestrian flow trajectory during off-peak hours (2 people / 10 m2).

[0079] Step S20:

[0080] Preset goals: 100% coverage of the jewelry area, total cost ≤ ￥500,000, redundant monitoring rate ≥ 90%;

[0081] Constraints: visibility ≥ 98%, response delay ≤ 1.5 seconds;

[0082] Model training: Input several relevant shopping mall historical layout samples and output the scene feature-layout parameter mapping relationship (such as "high reflective area → wide-angle anti-glare camera").

[0083] Step S30:

[0084] Input real-time demand: During the event, the risk weight of the jewelry area is increased to the highest level;

[0085] Model output scheme:

[0086] Jewelry area: 3 4K cameras (redundant coverage + face tracking), with a pitch angle of 25° to avoid reflections;

[0087] Fire passage: Two-way camera shooting to ensure no blind spots;

[0088] Atrium: Deploy one PTZ camera for every 100 square meters, reducing the total number of devices by 22%.

[0089] Step S40:

[0090] Scene change 1: A temporary promotion booth blocks the fire escape camera;

[0091] Real-time point cloud detection and occlusion detection: the model shuts down the blocked camera within 0.5 seconds, activates the backup device, and adjusts the angle of the adjacent camera to fill the blind spot.

[0092] Scene change 2: Heavy rain causes the natural light to disappear;

[0093] The light sensor triggers the model to switch all cameras to infrared mode and simultaneously increase the gain parameters to ensure imaging clarity.

[0094] Reference Figure 2 In one embodiment, after step S40, the following steps are further included:

[0095] S50, during the execution of the camera layout solution, when it is detected that a camera in the target scene triggers a preset monitoring failure determination rule, generating a monitoring failure signal and determining a location area of ​​the failed camera;

[0096] S60: activating a backup camera that meets a preset backup device activation rule according to the location area;

[0097] S70: Dynamically adjust the monitoring parameters of the backup camera to cover the failure area, and update the coordination parameter set in the camera layout solution.

[0098] As described in step S50 above, the monitoring failure determination rule is defined as being triggered by any of the following conditions:

[0099] The camera is offline for ≥10 seconds;

[0100] The effective frame rate of the video stream is ≤5fps (normally ≥15fps);

[0101] The coverage loss rate in key areas is ≥30% (such as a sudden increase in blind areas).

[0102] Through real-time heartbeat detection and video quality analysis engine, a monitoring failure signal is generated when failure is determined, and the location area of ​​the failed camera (such as coordinate range and associated coverage responsibility area) is determined based on the three-dimensional scene model coordinate mapping.

[0103] As described in step S60 above, the standby device activation rule contains three constraints:

[0104] Vision coverage constraint: There is no physical obstruction between the backup camera and the failure area (visibility rate ≥ 95%);

[0105] Load balancing constraint: The current load of the standby device is ≤ 70% (to avoid overload);

[0106] Path reachability constraint: For mobile devices, the path distance to the failure area must be ≤ 50 meters and there must be no dynamic obstacles.

[0107] The optimal backup camera is selected based on the rules, and the activation command is issued in real time through the device control bus.

[0108] As described in step S70 above:

[0109] (1) Dynamically adjust monitoring parameters including:

[0110] Adjust the backup camera's focus and pitch angle to cover the failure area;

[0111] Switch to wide-angle mode to expand the area of ​​responsibility;

[0112] Enable digital zoom to capture enhanced details.

[0113] (2) Updating the coordination parameter set means:

[0114] Reassign the master-slave tracking relationship (e.g., transfer the tracking target of a failed camera to a backup device);

[0115] Modify alarm linkage rules (such as backup equipment taking over access control authority);

[0116] Generate a new device topology diagram and synchronize it to the security platform.

[0117] In this embodiment, the problem of monitoring blind spots caused by equipment anomalies in traditional layouts is solved through failure detection and dynamic adjustment mechanisms: camera failure events are identified in real time and the fault area is located, and backup equipment compensation coverage is activated to ensure monitoring continuity; multi-camera task allocation is optimized by dynamically updating the collaborative parameter set to avoid resource redundancy; and at the same time, relying on the automated response mechanism, the abnormal interruption time is shortened from minutes to seconds, significantly improving the security reliability of high-density or high-risk scenarios.

[0118] In one possible embodiment, it is assumed that:

[0119] A fixed camera in the jewelry area of ​​a shopping mall failed due to a circuit fault. The failure area was the high-risk area of ​​the checkout counter (coordinates X1-Y1).

[0120] Step S50 is performed (failure detection and location):

[0121] The system detects that the camera is offline for 12 seconds, the video stream is interrupted, and a monitoring failure signal is triggered;

[0122] 3D model positioning failure area: 5-meter radius around the cash register (security level 9).

[0123] Step S60 is executed (standby device activation), screening candidate standby devices:

[0124] Fixed backup camera A: visibility is 99%, but the load has reached 85% (exceeding the threshold);

[0125] Patrol robot B: load 40%, visibility 100%, 20 meters from the failure zone;

[0126] Ceiling PTZ camera C: load 60%, visibility 90%, 8 meters from failure zone.

[0127] Activation decision: Select patrol robot B (which satisfies the triple rule and has a reachable path).

[0128] Step S70 execution (dynamic adjustment and coordinated update):

[0129] (1) Parameter adjustment:

[0130] Patrol Robot B switches to 10x zoom mode and lowers its pitch angle by 15° to cover the cashier counter.

[0131] Enable thermal imaging to enhance low-light detail (reflections from jewelry cabinet glass can interfere).

[0132] (2) Collaborative Update:

[0133] Transfer the face tracking task of the original failed camera to robot B;

[0134] Modify the alarm rules: abnormal transactions at the cash register trigger Robot B to automatically approach and record the video;

[0135] Update the layout plan: mark the failed equipment as pending repair and include Robot B in the fixed monitoring network.

[0136] In one embodiment, in step S60, the preset backup device activation rule includes at least one of the following:

[0137] 1) The straight-line distance or path planning distance between the backup camera and the failure area is less than the preset distance threshold, and the closest available device is prioritized;

[0138] 2) The current workload of the backup camera is lower than a preset threshold, where the workload includes at least one of CPU utilization, network bandwidth occupancy, and remaining storage space;

[0139] 3) The field of view of the backup camera has unobstructed visual coverage with the failure area in the three-dimensional scene model.

[0140] In this embodiment:

[0141] (1) Path planning distance refers to the shortest feasible path length (including detours around obstacles) from the backup camera to the failure area in the 3D scene model. The preset distance threshold is set to 50 meters (configurable). The distance priority strategy calculates the path distance of each backup device using the Dijkstra algorithm and selects the device with the minimum value to activate. If the straight-line distance is ≤ 10 meters and there is no obstruction, the straight-line distance is directly used for judgment.

[0142] (2) Workload quantitative indicators include:

[0143] CPU utilization (threshold ≤ 80%);

[0144] Network bandwidth utilization (threshold ≤ 70%);

[0145] The remaining storage space (threshold ≥ 20%).

[0146] The preset load threshold supports dynamic adjustment (such as relaxing it to 90% during peak hours). The load assessment engine collects device status data in real time and only selects backup devices whose all indicators are below the threshold.

[0147] (3) Unobstructed visibility coverage must meet the following requirements:

[0148] There are no physical obstacles (walls, large equipment) between the center line of the backup camera's field of view and the failure area;

[0149] The visibility rate is ≥95% (verified by 3D model ray collision detection).

[0150] If there is a semi-transparent medium such as glass, it is necessary to additionally verify that the transmittance is ≥ 85% (to avoid blurred imaging).

[0151] In one possible embodiment, it is assumed that:

[0152] A fixed camera in the jewelry section of a shopping mall fails due to a circuit fault. The failure area is the high-risk area of ​​the cash register (coordinates X1-Y1). Assume that the candidate backup devices are as follows:

[0153] equipment Path distance CPU utilization Visibility Ceiling Camera A 6 meters 75％ 100％ Patrol Robot B 8 meters 40％ 98％ Column camera C 4 meters 90％ 100％

[0154] The rule execution logic is:

[0155] Distance priority (Rule 1):

[0156] Path C of the pillar camera is the closest (4 meters), but its CPU utilization exceeds the threshold (preset 80%) by 90%, so it is excluded.

[0157] Ceiling camera A (6 meters) and robot B (8 meters) enter the next round of screening.

[0158] Load verification (rule 2):

[0159] Ceiling camera A load 75% ≤ 80%, in compliance;

[0160] Robot B load 40% compliance, both passed.

[0161] Verification of line of sight coverage (Rule 3):

[0162] Ceiling camera A: X-ray detection shows a 100% visibility rate (unobstructed);

[0163] Robot B: Visibility rate 98% (because 2% of the area is blocked by a temporary promotion booth), excluded.

[0164] Finally, ceiling camera A is activated.

[0165] In this embodiment, multi-dimensional backup equipment activation rules are used to solve the problems of misselection and inefficiency under a single decision-making dimension: the line-of-sight coverage rule avoids secondary blind spots caused by wall obstruction, the load balancing rule prevents cascading failures caused by hardware overload, and the path planning distance rule adapts to complex building structures to reduce the cost of ineffective deployment; at the same time, priority is given to low-load, short-distance and line-of-sight backup equipment to extend the hardware service life and reduce operation and maintenance costs, forming an intelligent fault-tolerant mechanism that takes into account both efficiency and economy.

[0166] Reference Figure 3 In one embodiment, step S10 specifically includes the following steps:

[0167] S11. Acquire three-dimensional spatial data of a target scene through a multimodal acquisition module, wherein the three-dimensional spatial data includes geometric topology data, texture image data, and dynamic environment parameters;

[0168] S12. Extracting the spatial structure of buildings, fixed equipment, and functional areas based on the geometric topology data and texture image data, and labeling the passage priority and safety risk level of the static objects using a semantic analysis model;

[0169] S13. Acquire in real time the illumination distribution characteristics, surface reflection characteristics, and moving target trajectory of the dynamic environment parameters, perform behavioral semantic classification on the moving target, and generate a security response priority label dynamically associated with the three-dimensional spatial coordinates;

[0170] S14. Based on the illumination distribution characteristics and the surface reflection characteristics, predict the imaging attenuation area within the camera field of view using a light field reconstruction model, and mark it as a light field interference feature;

[0171] S15. Integrate the spatial structure, semantic annotation, security response priority label, and light field interference characteristics of the static object to construct a multi-dimensional three-dimensional scene model including geometric constraints, semantic rules, and light field interference characteristics.

[0172] As described in step S11 above, the multimodal acquisition module includes a lidar (to obtain geometric topological point cloud), an RGB-D camera (to capture texture images), and an environmental sensor (to monitor temperature, humidity, and light intensity).

[0173] Three-dimensional spatial data includes:

[0174] Geometric topological data: building outlines, obstacle coordinates, and spatial connectivity (such as door / window opening and closing status);

[0175] Texture image data: surface material properties (such as glass reflectivity, wall roughness);

[0176] Dynamic environmental parameters: real-time crowd density, lighting distribution map and moving target (personnel / vehicle) trajectory.

[0177] As described in step S12 above, spatial structures (such as wall boundaries and shelf locations) and functional areas (checkout counters and fire escapes) are extracted from the geometric and texture data through point cloud segmentation and image semantic segmentation algorithms.

[0178] The semantic analysis model (based on a hybrid network of ResNet-50+CRF) annotates static objects:

[0179] Access priority: Fire lanes are Class A (highest), shelf clearances are Class C (restricted access);

[0180] Security risk level: Jewelry counters are level 9 (highest risk), and ordinary shops are level 3.

[0181] As described in step S13 above:

[0182] (1) Dynamic environment parameter processing:

[0183] Light distribution characteristics: A 0.5m×0.5m gridded light map is generated through a light intensity sensor array;

[0184] Surface reflection characteristics: Match reflectivity parameters based on the material library (e.g. 85% reflectivity of glass curtain wall);

[0185] Moving target trajectory: Track the trajectory of people / vehicles through the YOLOv7+DeepSORT algorithm (target tracking algorithm).

[0186] (2) Behavioral semantic classification:

[0187] Normal behavior (walking in a straight line, staying for <30 seconds) was marked as low priority;

[0188] Abnormal behaviors (wandering, walking against the flow) are marked as high priority, and a security response priority label (such as "abnormal aggregation - high risk") is generated and dynamically bound to the three-dimensional coordinates.

[0189] As described in step S14 above, the light field reconstruction model (based on the NeRF neural radiation field) simulates the transmission path of light in the scene and combines the surface reflection characteristics to predict the imaging attenuation area within the camera's field of view:

[0190] Strong reflective area: the area where the glass curtain wall causes overexposure;

[0191] Low light attenuation area: The imaging blurry area caused by shadow occlusion.

[0192] The attenuation area is marked as a light field interference feature (such as coordinate range + interference intensity value) to avoid or enable anti-interference mode during layout optimization.

[0193] As described in step S15 above, multi-dimensional model fusion:

[0194] Geometric constraints: building structures restrict camera installation locations;

[0195] Semantic rules: mandatory redundant coverage in high-risk areas;

[0196] Light field interference characteristics: Mark the imaging attenuation areas that need to be avoided or compensated.

[0197] Through spatiotemporal alignment and feature weighting (such as the safety level weight accounts for 60%), a unified three-dimensional scene representation is generated to drive subsequent layout decisions.

[0198] In this embodiment, multimodal data fusion and light field enhanced modeling are used to address the shortcomings of traditional three-dimensional scene models in insufficient analysis of complex environments: multimodal sensing simultaneously collects geometric and texture data, and combines semantic analysis to accurately mark traffic priorities and safety risk areas, thereby improving the accuracy of static modeling; dynamic light field reconstruction quantifies the interference of light reflection and moving targets, predicts monitoring blind spots, and adaptively adjusts anti-interference parameters; a multi-dimensional model that integrates geometric, semantic, and physical interference assessments provides a holographic decision-making basis for complex scenarios, enables scientific deployment of security layouts in highly dynamic environments, and significantly enhances the system's environmental adaptability and anti-interference capabilities.

[0199] In a feasible embodiment, assume that a shopping mall needs to build a three-dimensional security monitoring scene model covering the jewelry area, atrium, and fire escape.

[0200] Step S11 execution (data collection):

[0201] LiDAR scanning: obtain centimeter-level accuracy of shelf and column coordinates;

[0202] RGB-D camera capture: marking glass curtain wall (reflectivity 85%) and marble floor (reflectivity 10%);

[0203] Environmental sensor: monitors the peak natural light intensity at noon (1500 lux).

[0204] Step S12 execution (static structure annotation):

[0205] Semantic model output:

[0206] Jewelry counter (security level 9, access priority B);

[0207] Fire escape (safety level 7, access priority A);

[0208] Atrium glass guardrail (reflectivity 85%, marked as a source of reflective interference).

[0209] Step S13 execution (dynamic parameter processing):

[0210] Light distribution: The atrium lighting map shows that the reflection intensity of the west glass curtain wall reaches 1300 lux;

[0211] Mobile Target: 3 people were detected wandering in the jewelry area for more than 2 minutes, marked as "Abnormal Gathering - High Risk", and their coordinates were bound to the jewelry cabinet (X3-Y3);

[0212] Security tag generation: The jewelry cabinet is associated with the "High Risk + Abnormal Aggregation" tag, and the weight value is increased to 0.9.

[0213] Step S14 performs (light field interference prediction):

[0214] The NeRF model predicts that a strong reflective band with a width of 2m will form on the west curtain wall between 14:00 and 15:00 (interference intensity 0.8);

[0215] This is marked as a light field interference feature. It is recommended to avoid or enable polarization filters during layout.

[0216] Step S15 execution (model fusion):

[0217] Fusion results:

[0218] Geometric constraints: Fire passages are prohibited from installing suspended equipment;

[0219] Semantic rule: Two cameras are required in the jewelry cabinet (redundant coverage);

[0220] Light field interference: The camera pitch angle in the west curtain wall area must be ≥30°.

[0221] In one embodiment, in step S20, the preset layout optimization target parameter includes at least one of the following:

[0222] Coverage optimization goal: maximizing the number of sub-areas within the monitoring area that are effectively covered, using the security risk level in the scene semantic attributes as a weight. Effective coverage requires that the light field interference characteristics in the 3D scene model are below a preset threshold.

[0223] Cost optimization goal: Minimize the overall cost of camera deployment using the number of devices, energy consumption, and deployment complexity as joint optimization variables. The deployment complexity is dynamically evaluated based on the obstacle distribution in the 3D scene model.

[0224] Redundancy optimization goal: Within an area where the security risk level is a preset threshold, maximize the number of sub-areas that are overlapped by multiple cameras.

[0225] In this embodiment:

[0226] (1) Coverage optimization objectives:

[0227] Safety risk level weight: The weight of high-risk areas (such as jewelry areas) is set at 1.0, medium-risk areas (cashier counters) at 0.6, and low-risk areas (rest areas) at 0.3;

[0228] To determine effective coverage, the following conditions must be met simultaneously:

[0229] The monitoring field of view completely covers the sub-area;

[0230] Light field interference characteristic value ≤ 0.3 (preset threshold, corresponding to imaging clarity ≥ 90%);

[0231] Optimization logic: The goal is to maximize the number of weighted sub-area coverage, giving priority to ensuring interference-free coverage in high-risk areas.

[0232] (2) Cost optimization goals:

[0233] Joint optimization variables:

[0234] Number of devices (cost factor per device is 1.0);

[0235] Energy consumption (cost factor 0.2 per watt-hour);

[0236] Deployment complexity (dynamic calculation based on obstacle density):

[0237] Complexity = number of obstacles / 10 m2 × installation height factor (ceiling = 1.0, column = 1.5);

[0238] Optimization objective, minimize the total cost function:

[0239] Total cost = number of devices × 1.0 + total energy consumption × 0.2 + total complexity × 0.5.

[0240] (3) Redundancy optimization goal:

[0241] Preset risk threshold: security level ≥ 8 (such as jewelry area, vault);

[0242] Overlap coverage requirement: at least 2 cameras have a field of view overlap rate of ≥30%;

[0243] Optimization logic: Maximize the proportion of sub-regions within high-risk areas that meet overlap requirements.

[0244] In a feasible embodiment, it is assumed that the shopping mall needs to optimize the monitoring layout, focusing on covering the jewelry area (risk level 9), fire escape (risk level 7) and general shelf area (risk level 3).

[0245] (1) Coverage optimization target execution:

[0246] Input data:

[0247] The light field interference value in the jewelry area is 0.4 (caused by glass reflection) and needs to be reduced to ≤0.3;

[0248] The fire channel interference value is 0.1 (meets the requirements).

[0249] Optimization measures:

[0250] Jewelry area: Deploy wide-angle anti-glare cameras, installed at a 25° angle to avoid reflections, reducing the interference value to 0.2;

[0251] Ordinary shelf area: Due to the low risk weight, the number of cameras will be reduced by 20%, and resources will be allocated to high-risk areas.

[0252] result:

[0253] The number of effectively covered sub-areas increased to 98% (85% in the original plan);

[0254] The coverage rate of high-risk areas is 100%.

[0255] (2) Cost optimization target execution:

[0256] Variable calculation:

[0257]

[0258]

[0259] Optimization strategy:

[0260] Number of devices: One 360° panoramic camera replaces three standard cameras in the shelf area;

[0261] Energy consumption: Low illumination mode is enabled in high-risk areas (power consumption is reduced by 40%);

[0262] Complexity: Fire escape routes are now wall-mounted (complexity increased from 0.3 to 0.1).

[0263] result:

[0264] Total costs are reduced by 35% (number of devices - 22%, energy consumption - 30%, complexity - 40%).

[0265] (3) Redundant optimization target execution:

[0266] High-risk areas: jewelry area (risk level 9 > threshold 8);

[0267] Overlap coverage requirements:

[0268] Deploy three cameras (A / B / C) with a field of view overlap of ≥40%;

[0269] Real-time verification: A and B overlap by 45%, and B and C overlap by 50%, both meeting the standards.

[0270] Dynamic Adjustment:

[0271] The addition of new booths resulted in the overlap of camera B’s field of view decreasing to 25%;

[0272] The system automatically adjusted the C camera angle to restore the overlap rate to 38%.

[0273] result:

[0274] The overlapping coverage rate of high-risk areas is 100% (traditional solutions are only 70%).

[0275] In this embodiment, the collaborative design of multi-dimensional layout optimization target parameters is used to solve the problems of uneven coverage and resource waste caused by single-target optimization in traditional camera layout: the coverage optimization target with security level as the weight prioritizes the monitoring efficiency of high-risk areas, and combines the light field interference threshold to avoid areas with image quality attenuation, eliminating the risk of missed detection in key areas caused by manual experience; through the joint cost optimization of equipment quantity, energy consumption and deployment complexity, the security effectiveness and economic benefits are balanced, and the deployment of redundant equipment is reduced; at the same time, redundant coverage is enforced in core areas where the security level reaches the threshold, forming multiple monitoring lines of defense, significantly improving the security reliability of high-risk scenarios such as bank vaults and hazardous chemical warehouses.

[0276] In one embodiment, in step S20, the dynamic constraint condition set includes at least one of the following:

[0277] Field of view integrity constraint: The unobstructed ratio between the camera field of view coverage path and the obstacle area in the 3D scene model must reach a preset threshold. The obstacle area is dynamically verified based on real-time updated semantic attributes.

[0278] Timeliness constraints: Based on the scene activity density in dynamic environment parameters, the maximum generation delay threshold of the layout plan is adaptively adjusted to ensure that the response time of high-density scenes meets the preset safety timeliness;

[0279] Collaborative deployment constraints: The deployment distance between cameras must meet signal compatibility thresholds and physical safety thresholds.

[0280] In this embodiment:

[0281] (1) Visual field integrity constraints:

[0282] The preset threshold of the unobstructed rate is ≥95% (i.e. the proportion of the effective coverage area within the camera's field of view);

[0283] Dynamic obstacle area verification: Based on the semantic attributes in the real-time 3D scene model (such as adding a temporary booth marked as a "movable obstacle"), a ray collision detection algorithm is used to calculate the intersection ratio between the field of view path and the obstacle. If the occlusion rate is greater than 5%, the constraint is determined to be unsatisfied.

[0284] Verification mechanism: Scan scene changes every 5 seconds to trigger real-time view rate recalculation.

[0285] (2) Time constraints:

[0286] Scene activity density classification:

[0287] Low density (≤3 people / 10㎡): Layout generation delay threshold ≤5 seconds;

[0288] Medium density (4-6 people / 10㎡): delay threshold ≤ 3 seconds;

[0289] High density (≥7 people / 10㎡): Delay threshold ≤ 1 second (preset safety time limit);

[0290] Adaptive adjustment logic: Use crowd heat maps to divide density areas in real time and assign differentiated delay thresholds to different areas.

[0291] (3) Collaborative deployment constraints:

[0292] Signal compatibility threshold:

[0293] The distance between cameras in the same frequency band should be ≥3 meters (to prevent Wi-Fi / Bluetooth interference);

[0294] The distance between devices in different frequency bands is ≥ 1 meter;

[0295] Physical security thresholds:

[0296] The distance between fixed cameras should be ≥ device width × 1.5 (to prevent mechanical collision);

[0297] The vertical distance between mobile equipment and fixed equipment is ≥0.5 meters (to prevent suspension collision).

[0298] In a feasible embodiment, assuming that the mall is in the process of an event, the crowd density in the atrium reaches "8 people / 10 m2" (high risk), and the layout needs to be adjusted in real time.

[0299] (1) Horizon integrity constraint enforcement:

[0300] Scene change: A temporary promotion booth (coordinates X4-Y4) is built to block the field of view of the original camera C;

[0301] Dynamic verification:

[0302] Ray collision detection showed that the occlusion rate rose to 12% (>5% threshold);

[0303] The semantic attribute marks the booth as a “temporary obstacle”;

[0304] Response measures:

[0305] Automatically lower the pitch angle of camera C by 20°, reducing the occlusion rate to 4%;

[0306] Update the 3D model obstacle coordinate library.

[0307] (2) Time constraint execution:

[0308] Density monitoring:

[0309] Atrium (8 people / 10 m2) → Delay threshold ≤ 1 second;

[0310] Clothing area (5 people / 10㎡) → Delay threshold ≤ 3 seconds;

[0311] Layout generation:

[0312] In the case of a sudden gathering in the atrium, the model outputs a solution within 0.8 seconds:

[0313] Activate 2 patrol robots for reinforcement;

[0314] Adjust 4 wide-angle cameras to track the flow of people.

[0315] (3) Collaborative deployment and constraint execution:

[0316] New device conflicts:

[0317] equipment coordinate frequency band Physical dimensions Fixed camera D (X5,Y5) 2.4GHz 0.2m×0.2m Patrol Robot E (X5.2,Y5.3) 5GHz 0.8m×0.6m

[0318] Constraint checking:

[0319] Signal compatibility: horizontal distance 0.3 meters (<1 meter threshold) → conflict

[0320] Physical security: vertical separation of 0.4 meters (<0.5 meter threshold) → conflict

[0321] Dynamic Adjustment:

[0322] Move the robot's E path 1.2 meters west to meet the spacing requirements (1.5 meters horizontally and 0.6 meters vertically).

[0323] Switch Robot E to the 5GHz high frequency channel to eliminate signal interference.

[0324] In this embodiment, the real-time adaptation mechanism of the dynamic constraint condition set is used to overcome the problem of insufficient scene compatibility caused by the rigidity of traditional layout rules: the field of view integrity constraint is dynamically updated based on semantically annotated obstacles to ensure that the unobstructed rate of the camera field of view path is ≥ the preset threshold, eliminating the monitoring blind spots caused by temporary obstacles (such as construction fences); the timeliness constraint adaptively adjusts the response delay according to the scene activity density, increasing the layout generation speed during peak hours by more than 50%, meeting the emergency response needs of sudden incidents; the collaborative deployment constraint solves the signal interference and mechanical collision risks in multi-device deployment through dual verification of signal compatibility and physical safety thresholds, reducing equipment failure rate and extending hardware service life.

[0325] Reference Figure 4 In one embodiment, step S20 specifically includes the following steps:

[0326] S21. Generate a multi-scenario training dataset based on the preset layout optimization target parameters, dynamic constraint condition set, and training dataset, where each training sample includes:

[0327] Input features: geometric topology, dynamic environment parameters, and security requirement parameters extracted from historical 3D scene models;

[0328] Output label: an optimal camera layout parameter set that satisfies the layout optimization target parameters and complies with the dynamic constraint condition set;

[0329] S22. Construct a multi-objective optimization neural network model, the model comprising:

[0330] Coverage optimization module: Calculates the coverage efficiency of camera positions for the monitored area based on security risk level weights;

[0331] Cost Optimization Module: This module evaluates the complexity of equipment deployment based on obstacle distribution density and generates a layout plan under cost constraints.

[0332] Redundancy Optimization Module: Calculates the redundancy of overlapping coverage of multiple cameras’ fields of view in areas where the security risk level reaches a preset threshold;

[0333] S23. Input the multi-scenario training data set into the multi-objective optimization neural network model, use the coverage optimization objective, the cost optimization objective, and the redundancy optimization objective as optimization items, use the dynamic constraint condition set as the hard constraint item, and jointly train the model parameters through the constrained optimization algorithm;

[0334] S24. Verify whether the layout solution output by the trained model in the test scenario satisfies all dynamic constraints at the same time. If there is a constraint violation, adjust the weight coefficient of the layout optimization target parameter and retrain.

[0335] As described in step S21 above, the logic for constructing the multi-scenario training dataset is as follows:

[0336] Input features:

[0337] Geometric topological structure: building outline point cloud, obstacle spatial coordinates;

[0338] Dynamic environmental parameters: lighting distribution matrix, crowd flow heat map;

[0339] Security requirement parameters: risk level distribution map (e.g., jewelry area = level 9).

[0340] Output tags:

[0341] Optimal layout parameter set: camera coordinates (x, y, z), pitch angle (α), focal length (f);

[0342] Verification criteria: coverage ≥ 95%, cost ≤ budget ceiling, and high-risk area redundancy ≥ 2.

[0343] As described in step S22 above, the multi-objective optimization neural network model architecture:

[0344] (1) Coverage Optimization Module (Graph Convolutional Network):

[0345] Input: Risk level weight matrix (e.g., jewelry area weight 1.0);

[0346] Output: Coverage effectiveness score (calculation formula: ∑(sub-region risk weight × coverage status)).

[0347] (2) Cost optimization module (fully connected network):

[0348] Input: obstacle density map + installation location code;

[0349] Output: Deployment complexity score (formula: 0.5 × number of devices + 0.3 × complexity).

[0350] (3) Redundancy Optimization Module (Attention Mechanism Network):

[0351] Input: coordinate range of high-risk area;

[0352] Output: Redundancy score (calculation formula: overlapping area / total area of ​​high-risk areas).

[0353] As described in step S23 above, the joint training mechanism:

[0354] Optimization goal: maximize the total utility function:

[0355] U = 0.6 × coverage effectiveness + 0.3 × (1 / cost points) + 0.1 × redundancy.

[0356] Hard constraints (injected through penalty function):

[0357] Visibility < 95% → Penalty +1000;

[0358] Equipment distance < safety threshold → penalty + 500;

[0359] Training algorithm: The constrained NSGA-II multi-objective evolutionary algorithm is used, with 1000 iterations.

[0360] As described in step S24 above, the constraint violation processing flow is as follows:

[0361] Test scenario: Simulates the addition of new obstacles, causing the visibility rate to drop to 90%;

[0362] Constraint detection: The visibility rate of the model output solution does not meet the standard (<95%);

[0363] Weight adjustment:

[0364] The original coverage efficiency weight was increased from 0.6 to 0.7;

[0365] Retrain until the test set constraint compliance rate is ≥ 99%.

[0366] In this embodiment, a joint training mechanism of multi-objective collaborative optimization and dynamic constraints is used to solve the problem of insufficient optimization ability of traditional layout models under multi-objective conflicts and complex physical rules: the multi-objective optimization neural network module hierarchically learns decision rules covering efficiency, cost control and redundant safety, and generates an adaptive layout strategy by combining historical scene data and real-time environmental parameters; the constraint optimization algorithm forcibly verifies the visibility, timeliness and equipment coordination rules of the layout plan to ensure that the plan strictly complies with the dynamic constraints; through incremental training and weight adjustment mechanisms, the generalization and response speed of the model in highly dynamic scenarios are significantly improved, providing intelligent layout decision support that takes into account both efficiency and reliability for complex security scenarios.

[0367] In a feasible embodiment, it is assumed that the mall is in the process of an event and the crowd density in the mall atrium increases sharply (12 people / 10 m2), and the layout needs to be optimized urgently.

[0368] Step S21 is executed (training data generation):

[0369] Input feature extraction:

[0370] Geometric topology: atrium column coordinates, temporary stage boundaries;

[0371] Dynamic parameters: peak thermal area of ​​human flow (coordinates X6-Y6);

[0372] Security requirements: The risk level of the stage area is raised to level 8.

[0373] Output label generation:

[0374] The best solution in history: deploy 8 cameras (with a pitch angle of 15°-30°), with a coverage efficiency of 92%.

[0375] Step S22 execution (model building):

[0376] Optimization module Input Data Output decision example Coverage optimization Stage area risk weight 0.9 Add 2 wide-angle cameras Cost Optimization Column density: 2.5 / 10㎡ Use a wall mount instead (reduces complexity by 30%) Redundancy optimization Stage area coordinate range Increased field of view overlap to 45%

[0377] Step S23 performs (joint training):

[0378] Initial solution flaws:

[0379] Device distance 1.2 meters (<1.5 meters safety threshold) → penalty +500;

[0380] The stage area coverage efficiency was only 85% (<95% target).

[0381] Optimized solution:

[0382] Adjust the camera position and increase the distance to 1.6 meters;

[0383] One anti-occlusion camera was added to the stage area, with a coverage efficiency of 96%.

[0384] Step S24 execution (constraint verification and tuning):

[0385] Test scenario: Temporarily install a lighting stand (additional obstruction);

[0386] Constraint violation: Visibility rate dropped to 88%;

[0387] Weight adjustment:

[0388] Coverage effectiveness weight 0.6→0.75;

[0389] After retraining, the visual access rate recovered to 96%.

[0390] It should be understood that the size of the serial numbers of the steps in the above embodiments does not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of this application.

[0391] In one embodiment, a modeling camera layout system is provided, which corresponds to the modeling camera layout method in the above embodiment. The modeling camera layout system includes:

[0392] The data acquisition module is used to obtain the three-dimensional spatial data of the target scene and construct a three-dimensional scene model including static object structure and dynamic environment parameters;

[0393] A model training module is used to train a machine learning model based on preset layout optimization target parameters, a dynamic constraint condition set, and a training data set, thereby obtaining a trained machine learning model for associating a mapping relationship between camera layout parameters and scene features;

[0394] A solution output module is used to input the three-dimensional scene model and the security requirement parameters obtained in real time into a trained machine learning model, and output an optimal camera layout solution that meets the layout optimization target parameters through the machine learning model;

[0395] The iterative optimization module is used to dynamically iteratively optimize the position, angle and coordination parameters of the camera through the machine learning model based on the environmental change parameters of the target scene obtained in real time, and output an updated camera layout plan.

[0396] The specific definition of a modeled camera layout system can be found in the definition of a modeled camera layout method described above and will not be repeated here. Each module in the aforementioned modeled camera layout system can be implemented in whole or in part through software, hardware, or a combination thereof. Each of the aforementioned modules can be embedded in or independent of a processor in a computer device in hardware form, or can be stored in a computer device memory in software form, so that the processor can call and execute the corresponding operations of each of the aforementioned modules.

[0397] In one embodiment, a computer device is provided. The computer device may be a server, and its internal structure diagram may be as follows: Figure 5 The computer device includes a processor, a memory, a network interface, and a database connected via a system bus. The processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The internal memory provides an environment for the operation of the operating system and computer program in the non-volatile storage medium. The database of the computer device is used for data storage, data processing, data analysis, etc. The network interface of the computer device is used to communicate with an external terminal via a network connection. When the computer program is executed by the processor, a modeled camera layout method is implemented.

[0398] In one embodiment, a computer device is provided, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, a modeling camera layout method is implemented.

[0399] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, a modeling camera layout method is implemented.

[0400] Those skilled in the art will appreciate that all or part of the processes in the above-mentioned embodiments can be implemented by instructing the relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in this application can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in various forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0401] Those skilled in the art will clearly understand that for the sake of convenience and brevity of description, only the division of the above-mentioned functional units and modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional units and modules as needed, that is, the internal structure of the device can be divided into different functional units or modules to complete all or part of the functions described above.

[0402] The above-described embodiments are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present application, and should all be included in the scope of protection of the present application.

Claims

1. A camera layout modeling method, characterized in that: The steps include: S10, acquiring three-dimensional spatial data of the target scene, and constructing a three-dimensional scene model including static object structure and dynamic environment parameters; S20, training a machine learning model based on preset layout optimization target parameters, a dynamic constraint condition set, and a training data set to obtain a trained machine learning model for associating a mapping relationship between camera layout parameters and scene features; S30, inputting the three-dimensional scene model and the security requirement parameters obtained in real time into a trained machine learning model, and outputting an optimal camera layout solution that meets the layout optimization target parameters through the machine learning model; S40. Based on the environmental change parameters of the target scene obtained in real time, the position, angle and coordination parameters of the camera are dynamically iteratively optimized through the machine learning model, and an updated camera layout plan is output.

2. The modeling camera layout method according to claim 1, wherein: After step S40, the following steps are also included: S50, during the execution of the camera layout solution, when it is detected that a camera in the target scene triggers a preset monitoring failure determination rule, generating a monitoring failure signal and determining a location area of ​​the failed camera; S60: activating a backup camera that meets a preset backup device activation rule according to the location area; S70: Dynamically adjust the monitoring parameters of the backup camera to cover the failure area, and update the collaborative parameter set in the camera layout solution.

3. The modeling camera layout method according to claim 2, wherein: In step S60, the preset standby device activation rule includes at least one of the following: The straight-line distance or path planning distance between the backup camera and the failure area is less than the preset distance threshold, and the closest available device is prioritized; The current workload of the backup camera is lower than a preset threshold, where the workload includes at least one of CPU utilization, network bandwidth occupancy, and remaining storage space; The field of view of the backup camera has unobstructed visual coverage with the failure area in the three-dimensional scene model.

4. The modeling camera layout method according to claim 1, wherein: The step S10 specifically includes the following steps: S11. Acquire three-dimensional spatial data of a target scene through a multimodal acquisition module, wherein the three-dimensional spatial data includes geometric topology data, texture image data, and dynamic environment parameters; S12. Extracting the spatial structure of buildings, fixed equipment, and functional areas based on the geometric topology data and texture image data, and labeling the passage priority and safety risk level of the static objects using a semantic analysis model; S13. Acquire in real time the illumination distribution characteristics, surface reflection characteristics, and moving target trajectory of the dynamic environment parameters, perform behavioral semantic classification on the moving target, and generate a security response priority label dynamically associated with the three-dimensional spatial coordinates; S14. Based on the illumination distribution characteristics and the surface reflection characteristics, predict the imaging attenuation area within the camera field of view using a light field reconstruction model, and mark it as a light field interference feature; S15. Integrate the spatial structure, semantic annotation, security response priority label, and light field interference characteristics of the static object to construct a multi-dimensional three-dimensional scene model including geometric constraints, semantic rules, and light field interference characteristics.

5. The modeling camera layout method according to claim 4, wherein: In step S20, the preset layout optimization target parameter includes at least one of the following: Coverage optimization goal: maximizing the number of sub-areas within the monitoring area that are effectively covered, using the security risk level in the scene semantic attributes as a weight. Effective coverage requires that the light field interference characteristics in the 3D scene model are below a preset threshold. Cost optimization goal: Minimize the overall cost of camera deployment using the number of devices, energy consumption, and deployment complexity as joint optimization variables. The deployment complexity is dynamically evaluated based on the obstacle distribution in the 3D scene model. Redundancy optimization goal: Within an area where the security risk level is a preset threshold, maximize the number of sub-areas that are overlapped by multiple cameras.

6. The modeling camera layout method according to claim 5, wherein: In step S20, the dynamic constraint condition set includes at least one of the following: Field of view integrity constraint: The unobstructed ratio between the camera field of view coverage path and the obstacle area in the 3D scene model must reach a preset threshold. The obstacle area is dynamically verified based on real-time updated semantic attributes. Timeliness constraints: Based on the scene activity density in dynamic environment parameters, the maximum generation delay threshold of the layout plan is adaptively adjusted to ensure that the response time of high-density scenes meets the preset safety timeliness; Collaborative deployment constraints: The deployment distance between cameras must meet signal compatibility thresholds and physical safety thresholds.

7. The modeling camera layout method according to claim 6, wherein: The step S20 specifically includes the following steps: S21. Generate a multi-scenario training dataset based on the preset layout optimization target parameters, dynamic constraint condition set, and training dataset, where each training sample includes: Input features: geometric topology, dynamic environment parameters, and security requirement parameters extracted from historical 3D scene models; Output label: an optimal camera layout parameter set that satisfies the layout optimization target parameters and complies with the dynamic constraint condition set; S22. Construct a multi-objective optimization neural network model, the model comprising: Coverage optimization module: Calculates the coverage efficiency of camera positions for the monitored area based on security risk level weights; Cost Optimization Module: This module evaluates the complexity of equipment deployment based on obstacle distribution density and generates a layout plan under cost constraints. Redundancy Optimization Module: Calculates the redundancy of overlapping coverage of multiple cameras’ fields of view in areas where the security risk level reaches a preset threshold; S23. Input the multi-scenario training data set into the multi-objective optimization neural network model, use the coverage optimization objective, the cost optimization objective, and the redundancy optimization objective as optimization items, use the dynamic constraint condition set as the hard constraint item, and jointly train the model parameters through the constrained optimization algorithm; S24. Verify whether the layout solution output by the trained model in the test scenario satisfies all dynamic constraints at the same time. If there is a constraint violation, adjust the weight coefficient of the layout optimization target parameter and retrain.

8. A modeling camera layout system, used to implement the steps of a modeling camera layout method according to any one of claims 1 to 7, characterized in that: include: The data acquisition module is used to obtain the three-dimensional spatial data of the target scene and construct a three-dimensional scene model including static object structure and dynamic environment parameters; A model training module is used to train a machine learning model based on preset layout optimization target parameters, a dynamic constraint condition set, and a training data set, thereby obtaining a trained machine learning model for associating a mapping relationship between camera layout parameters and scene features; A solution output module is used to input the three-dimensional scene model and the security requirement parameters obtained in real time into a trained machine learning model, and output an optimal camera layout solution that meets the layout optimization target parameters through the machine learning model; The iterative optimization module is used to dynamically iteratively optimize the position, angle and coordination parameters of the camera through the machine learning model based on the environmental change parameters of the target scene obtained in real time, and output an updated camera layout plan.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the steps of the modeling camera layout method as described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the modeling camera layout method as described in any one of claims 1 to 7 are implemented.

Images