A video surveillance point calibration method and system based on spatial intelligence algorithm

By applying a video surveillance point calibration method and system based on spatial intelligent algorithm in the video surveillance system, the problem of low intelligence in camera site selection and layout in the prior art is solved, and efficient and optimized video surveillance point calibration and Visual monitoring.

CN118798439BActive Publication Date: 2024-11-29PUBLIC SECURITY BUREAU OF CHANGZHOU CITY +1
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202411263161.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-09-10
Publication Date
2024-11-29
Estimated Expiration
2044-09-10

Smart Images

  • Figure CN118798439B_ABST
    Figure CN118798439B_ABST
Patent Text Reader

Abstract

The present application provides a method and system for calibrating video surveillance points based on a spatial intelligent algorithm, which relates to the field of image communication technology. The method includes: dividing to obtain multiple grid blocks; obtaining first multidimensional information based on target video surveillance requirements, wherein the first grid block has an identifier of a first coordinate position; generating an initial risk visual graph; generating a first site selection and layout decision; simulating and arranging the first site selection and layout decision in the initial risk visual graph to obtain first simulation information; obtaining a first decision fitness; and when the first decision fitness reaches a predetermined fitness limit, using the first site selection and layout decision as the target site selection decision for the target area. By calibrating the video surveillance points according to the surveillance point site selection decisions obtained based on actual needs and risk factor analysis, a visual and intuitive display of the video surveillance situation is achieved, thereby achieving the effects of improving surveillance efficiency, optimizing resource allocation, and enhancing surveillance quality.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of image communication technology, and in particular to a method and system for calibrating video surveillance points based on a spatial intelligence algorithm. Background Art

[0002] With the development of society and the improvement of security needs, video surveillance systems have become an important part of public security, urban management, traffic supervision and other fields. The effectiveness and practicality of video surveillance systems depend to a large extent on the location and deployment of cameras. However, traditional camera location selection and deployment methods often rely on manual experience, which has certain blindness and limitations and cannot fully consider the actual needs and risk factors of the target area.

[0003] To sum up, the existing technology has a low level of intelligence in camera site selection and deployment, and is unable to fully consider the actual needs and risk factors of the target area. At the same time, because the existing technology is often based on subjective judgment and lacks objective data support, it is further unable to ensure the optimality of the camera site selection and deployment plan, which ultimately leads to poor video surveillance efficiency and effectiveness. At the same time, there is a problem of being unable to perform visual monitoring of the actual deployment of video surveillance. Summary of the invention

[0004] The purpose of this application is to provide a video surveillance point calibration method and system based on a spatial intelligent algorithm to solve the technical problems that the camera site selection and deployment in the prior art has a low level of intelligence, cannot fully consider the actual needs and risk factors of the target area, and thus cannot provide a scientific and reasonable site selection and deployment plan, resulting in poor video surveillance efficiency and effect. In addition, the site selection situation cannot be intelligently calibrated, and visual deployment monitoring cannot be achieved.

[0005] In view of the above problems, the present application provides a video surveillance point calibration method and system based on spatial intelligence algorithm.

[0006] In the first aspect, the present application provides a video surveillance point calibration method based on a spatial intelligent algorithm, and the video surveillance point calibration method based on a spatial intelligent algorithm is implemented by a video surveillance point calibration system based on a spatial intelligent algorithm, wherein the video surveillance point calibration method based on a spatial intelligent algorithm includes: dividing the target area to obtain a target division result, and the target division result includes multiple grid blocks; reading the target video surveillance requirements, and based on the target video surveillance requirements, performing multi-dimensional feature collection on a first grid block to obtain first multi-dimensional information, wherein the first grid block refers to any one of the multiple grid blocks, and the first grid block has an identifier of a first coordinate position; combining and analyzing the first multi-dimensional information a first risk index obtained from the information and the first coordinate position, to generate an initial risk visual map of the target area; a first site selection and layout decision is generated, wherein the first site selection and layout decision refers to any site selection and layout decision for deploying a predetermined number of predetermined cameras in the target area; the first site selection and layout decision is simulated and laid out in the initial risk visual map to obtain first simulation information; a site selection and layout decision fitness evaluation function is introduced to evaluate and analyze the first simulation information to obtain a first decision fitness; when the first decision fitness reaches a predetermined fitness limit, the first site selection and layout decision is used as the target site selection decision for the target area; and the initial risk visual map is calibrated with video surveillance points according to the target site selection decision.

[0007] In the second aspect, the present application also provides a video surveillance point calibration system based on a spatial intelligent algorithm, which is used to execute a video surveillance point calibration method based on a spatial intelligent algorithm as described in the first aspect, wherein the video surveillance point calibration system based on a spatial intelligent algorithm includes: an area division module, the area division module is used to divide the target area to obtain a target division result, and the target division result includes multiple grid blocks; a feature collection module, the feature collection module is used to read the target video surveillance requirements, and based on the target video surveillance requirements, perform multi-dimensional feature collection on a first grid block to obtain first multi-dimensional information, the first grid block refers to any one of the multiple grid blocks, and the first grid block has an identifier of a first coordinate position; a risk visualization module, the risk visualization module is used to combine the first risk index obtained by analyzing the first multi-dimensional information with the first coordinate position Marking position, generating an initial risk visual map of the target area; a decision acquisition module, the decision acquisition module is used to generate a first site selection and layout decision, the first site selection and layout decision refers to any one of the site selection and layout decisions of deploying a predetermined number of predetermined cameras in the target area; a decision simulation module, the decision simulation module is used to simulate the layout of the first site selection and layout decision in the initial risk visual map to obtain first simulation information; a fitness evaluation module, the fitness evaluation module is used to introduce a site selection and layout decision fitness evaluation function to evaluate and analyze the first simulation information to obtain a first decision fitness; a site selection decision module, the site selection decision module is used to use the first site selection and layout decision as the target site selection decision for the target area when the first decision fitness reaches a predetermined fitness limit; the initial risk visual map is calibrated with video surveillance points according to the target site selection decision.

[0008] One or more technical solutions provided in this application have at least the following technical effects or advantages:

[0009] The target area is divided to obtain a target division result, wherein the target division result includes a plurality of grid blocks; the target video surveillance requirement is read, and based on the target video surveillance requirement, multi-dimensional features of a first grid block are collected to obtain first multi-dimensional information, wherein the first grid block refers to any one of the plurality of grid blocks, and the first grid block has an identifier of a first coordinate position; an initial risk visual map of the target area is generated by combining and analyzing a first risk index and the first coordinate position obtained from the first multi-dimensional information; a first site selection and layout decision is generated, wherein the first site selection and layout decision refers to any one site selection and layout decision for deploying a predetermined number of predetermined cameras in the target area; the first site selection and layout decision is simulated and laid out in the initial risk visual map to obtain first simulation information; a site selection and layout decision fitness evaluation function is introduced to evaluate and analyze the first simulation information to obtain a first decision fitness; when the first decision fitness reaches a predetermined fitness limit, the first site selection and layout decision is used as a target site selection decision for the target area; and the initial risk visual map is calibrated for video surveillance points according to the target site selection decision. By calibrating the video surveillance points according to the monitoring point site selection decisions obtained based on actual needs and risk factor analysis, a visual and intuitive display of the video surveillance situation can be achieved, thereby improving monitoring efficiency, optimizing resource allocation, and enhancing monitoring quality.

[0010] The above description is only an overview of the technical solution of the present application. In order to more clearly understand the technical means of the present application, it can be implemented according to the contents of the specification, and in order to make the above and other purposes, features and advantages of the present application more obvious and easy to understand, the specific implementation methods of the present application are specifically cited below. It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended to limit the scope of the present application. Other features of the present application will become easy to understand through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings in the following description are only exemplary, and for ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0012] Figure 1 A schematic diagram of a flow chart of a method for calibrating video surveillance points based on a spatial intelligence algorithm for this application;

[0013] Figure 2 This is a structural diagram of a video surveillance point calibration system based on a spatial intelligent algorithm for this application.

[0014] Description of reference numerals:

[0015] Area division module 11, feature collection module 12, risk visualization module 13, decision acquisition module 14, decision simulation module 15, fitness evaluation module 16, site selection decision module 17, point calibration module 18. DETAILED DESCRIPTION

[0016] This application provides a method and system for calibrating video surveillance points based on a spatial intelligent algorithm, which solves the problem that the existing technology has a low level of intelligence in the selection and deployment of camera sites, and cannot fully consider the actual needs and risk factors of the target area. At the same time, since the existing technology is often based on subjective judgment and lacks objective data support, it is further unable to ensure the optimality of the camera site selection and deployment plan, which ultimately leads to poor video surveillance efficiency and effect. By calibrating the video surveillance points according to the monitoring point site selection decision obtained based on the analysis of actual needs and risk factors, a visual and intuitive display of the video surveillance situation is achieved, achieving the effect of improving monitoring efficiency, optimizing resource allocation, and enhancing monitoring quality.

[0017] Below, the technical solutions in the present application will be clearly and completely described with reference to the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all of the embodiments of the present application. It should be understood that the present application is not limited to the example embodiments described herein. Based on the embodiments of the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present application. It should also be noted that, for the convenience of description, only the parts related to the present application are shown in the accompanying drawings, rather than all of them.

[0018] For example, please refer to the attached Figure 1 The present application provides a method for calibrating video surveillance points based on a spatial intelligent algorithm, wherein the method for calibrating video surveillance points based on a spatial intelligent algorithm is applied to a video surveillance point calibration system based on a spatial intelligent algorithm, and the method for calibrating video surveillance points based on a spatial intelligent algorithm specifically includes the following steps:

[0019] Step 1: Divide the target area to obtain a target division result, wherein the target division result includes a plurality of grid blocks.

[0020] Specifically, first determine the target area to be divided, which can be set according to actual needs and application scenarios, such as urban planning, farmland management or environmental monitoring areas. Then use appropriate division methods, such as gridding technology based on geographic information systems, to subdivide the entire target area into multiple grid blocks. The size and shape of each grid block can be adjusted according to specific needs to adapt to different application scenarios. Next, each grid block is numbered or marked to facilitate subsequent data analysis and processing. In addition, relevant data such as population density, land use type or environmental quality indicators can be collected in each grid block to support more in-depth analysis. Finally, the information of all grid blocks is integrated to form a complete target division result, which can be used for various analyses and decision support. By subdividing the target area into multiple grid blocks, not only the accuracy and efficiency of regional analysis are improved, but also a structured basis is provided for subsequent data processing and decision-making.

[0021] Step 2: Read the target video surveillance requirements, and collect multi-dimensional features of the first grid block based on the target video surveillance requirements to obtain first multi-dimensional information, where the first grid block refers to any one of the multiple grid blocks, and the first grid block has an identifier of a first coordinate position.

[0022] Specifically, by carrying out customized data collection based on the specific needs of each grid block, accurate analysis and optimized management of the monitoring area can be achieved, thereby improving the efficiency and effectiveness of the video surveillance system. First, the target video surveillance needs are read and understood, which may include security monitoring, traffic flow monitoring, or crowd behavior analysis. Then, a grid block is selected from multiple grid blocks as the first grid block, which has a specific first coordinate position identifier for accurate positioning and analysis. Next, based on the target video surveillance needs, multi-dimensional features of the first grid block are collected. These features may include features of the geographic environment dimension, the crowd density dimension, and the historical monitoring dimension, depending on the monitoring needs. In addition, the collection process may also include analysis of environmental factors, such as lighting conditions, weather conditions, etc., to ensure the accuracy and completeness of the data. Finally, the collected multi-dimensional feature data is integrated into the first multi-dimensional information, which can be used for further monitoring analysis and decision support.

[0023] By reading the target video surveillance requirements and collecting multi-dimensional features of specific grid blocks, detailed and targeted surveillance data can be obtained, which helps to improve the efficiency and effectiveness of video surveillance, especially in application scenarios that require detailed monitoring of specific areas, such as urban security, traffic management, and large-scale event monitoring. In this way, accurate analysis and optimized management of the surveillance area can be achieved, thereby improving the overall surveillance quality and response speed.

[0024] Step three: Generate an initial risk visualization graph of the target area by combining the first risk index obtained by analyzing the first multi-dimensional information with the first coordinate position.

[0025] Further, it includes: the first multidimensional information includes multiple dimensional parameters of predetermined dimensions; the multiple dimensional parameters after normalization are weighted calculated using the coefficient of variation algorithm principle to obtain the first risk index; wherein the predetermined dimensions include at least geographical environment dimension, crowd density dimension and historical monitoring dimension.

[0026] Specifically, the first risk index and the first coordinate position obtained from the first multi-dimensional information are used to generate an initial risk visualization diagram of the target area. By converting complex risk data into an intuitive visual representation, users can quickly understand and identify the risk distribution in the target area. By combining the risk index and geographic location information, more accurate and practical risk analysis results can be provided, thereby assisting effective risk management.

[0027] Specifically, first, the first multidimensional information is analyzed to determine the risk level of the first grid block. This may involve in-depth analysis of monitoring data, such as identification of abnormal behavior, detection of security incidents, etc. First, multiple dimensional parameters related to the predetermined dimensions are identified and collected. These dimensions include at least the geographical environment dimension, the human flow density dimension, and the historical monitoring dimension, and each dimension contains a series of parameters reflecting the characteristics of the dimension. For example, the geographical environment dimension may include factors such as terrain and climate, the human flow density dimension may include population size, flow pattern, etc., and the historical monitoring dimension may include the frequency and severity of past events. Then, these dimensional parameters are normalized to eliminate the influence of dimension and scale and ensure comparison on the same scale. Next, these normalized parameters are weighted calculated using the coefficient of variation algorithm principle. The coefficient of variation algorithm can consider the relative changes and importance of each parameter, so as to more accurately assess the risk. In addition, during the calculation process, the weights of each parameter can be adjusted according to the actual situation to reflect the degree of influence of different dimensions on the risk. Finally, the first risk index is obtained through weighted calculation, which integrates information from multiple dimensions and can more comprehensively reflect the risk level. Then, the first risk index obtained from the analysis is combined with the first coordinate position to ensure that each risk point can be accurately located in the target area. Next, use this information to generate an initial risk visualization. This visualization may use heat maps, color-coded maps, or other visualization techniques to intuitively display the risk levels of different areas. In addition, other auxiliary information such as population density, traffic flow, etc. can be added to the visualization to provide a more comprehensive risk assessment. Finally, the generated initial risk visualization is reviewed and adjusted to ensure its accuracy and practicality.

[0028] By weighting multiple dimensional parameters through the coefficient of variation algorithm principle, a first risk index that comprehensively considers multiple factors such as geographical environment, crowd density, and historical monitoring can be obtained. By combining the risk index and coordinate location information to generate an initial risk visualization graph, complex risk data can be effectively converted into an easy-to-understand visual format. Providing an intuitive risk distribution view helps to quickly identify high-risk areas so that appropriate preventive measures and response strategies can be taken.

[0029] Step 4: Generate a first site selection and deployment decision, where the first site selection and deployment decision refers to any site selection and deployment decision for deploying a predetermined number of predetermined cameras in the target area.

[0030] Step 5: Simulate the first site selection and layout decision in the initial risk visualization diagram to obtain first simulation information.

[0031] Step 6: Introduce a site selection and layout decision fitness evaluation function to evaluate and analyze the first simulation information to obtain a first decision fitness.

[0032] Further, it includes: introducing the site selection and layout decision fitness evaluation function to evaluate and analyze the first simulation information to obtain the first decision fitness; wherein the first simulation information includes multiple simulated monitoring ranges of the predetermined number of the predetermined cameras, and the expression of the site selection and layout decision fitness evaluation function is as follows: ;in, Refers to the first site selection decision The first decision fitness, Refers to the first site selection decision The first total simulation coverage, Refers to the first site selection decision The first total simulation monitoring range, refers to the first of the multiple simulated monitoring ranges of the predetermined camera Camera No. A simulation monitoring range, means the predetermined quantity, refers to the target size range, Refers to the first site selection decision The first total simulation overlap ratio, The first site selection decision The overlapping monitoring ranges, and It refers to Simulated monitoring range of cameras With Simulated monitoring range of cameras The overlapping range of The camera and the The camera is the first location for the decision For any two cameras with overlapping surveillance, Refers to the first site selection decision The number of simulation monitoring overlap ranges in , and refer to the first coefficient and the second coefficient respectively, and .

[0033] Specifically, a camera location and deployment decision for the target area is first generated, and this decision is optimized through simulation and evaluation analysis. The best surveillance coverage of the area can be achieved by effectively deploying cameras in the target area. By introducing the fitness evaluation function of the location and deployment decision, the effects of different deployment schemes can be quantitatively evaluated, thereby assisting in selecting the optimal deployment strategy.

[0034] Specifically, first, a first site selection and deployment decision is generated, that is, any site selection and deployment decision to deploy a predetermined number of predetermined cameras in the target area. This decision needs to consider multiple factors, such as monitoring requirements, budget constraints, and regional characteristics. Then, the first site selection and deployment decision is simulated in the initial risk visibility graph to simulate the deployment effect of the camera in the actual environment. Next, a site selection and deployment decision fitness evaluation function is introduced. This function can comprehensively consider multiple factors such as monitoring range and risk coverage to evaluate and analyze the first simulation information. In addition, the evaluation process can also include performance testing of the simulated deployed cameras, such as field of view, image clarity, etc., to ensure the quality of monitoring. Finally, the first decision fitness is obtained through evaluation and analysis. This fitness value reflects the effectiveness and feasibility of the current deployment plan. Among them, the first simulation information includes multiple simulated monitoring ranges of the predetermined number of the predetermined cameras, and the expression of the site selection and deployment decision fitness evaluation function is as follows: ;in, Refers to the first site selection decision The first decision fitness, Refers to the first site selection decision The first total simulation coverage, Refers to the first site selection decision The first total simulation monitoring range, refers to the first of the multiple simulated monitoring ranges of the predetermined camera Camera No. A simulation monitoring range, means the predetermined quantity, refers to the target size range, Refers to the first site selection decision The first total simulation overlap ratio, The first site selection decision The overlapping monitoring ranges, and It refers to Simulated monitoring range of cameras With Simulated monitoring range of cameras The overlapping range of The camera and the The camera is the first location for the decision For any two cameras with overlapping surveillance, Refers to the first site selection decision The number of simulation monitoring overlap ranges in , and refer to the first coefficient and the second coefficient respectively, and .

[0035] By generating site selection and deployment decisions, simulating deployment and evaluating analysis, the camera deployment in the target area can be effectively optimized. By quantitatively evaluating the effects of different deployment plans, the pros and cons of different plans can be better understood, and the deployment strategy with the highest adaptability can be selected to achieve the best monitoring effect and resource utilization.

[0036] Step 7: When the fitness of the first decision reaches a predetermined fitness limit, the first site selection and layout decision is used as the target site selection decision of the target area;

[0037] Step 8: Calibrate the video surveillance points of the initial risk visual map according to the target site selection decision.

[0038] Specifically, by evaluating the fitness of the first decision, it is determined whether to use it as the target location decision of the target area. When the fitness of the first decision reaches a predetermined fitness limit, it means that the deployment decision can meet the monitoring requirements and achieve the expected effect.

[0039] Specifically, first, a predetermined fitness limit is set, which is determined based on factors such as monitoring requirements, budget constraints and regional characteristics, and is used to evaluate the pros and cons of site selection and layout decisions. Then, the decision fitness of the first site selection and layout decision is calculated. If this fitness reaches or exceeds the predetermined fitness limit, it means that the layout decision is effective and can meet the monitoring requirements. Next, this first site selection and layout decision is used as the target site selection decision for the target area. This means that the decision will be adopted and used for actual monitoring point calibration. Finally, the actual site selection of the video monitoring point is carried out according to the target site selection decision. For example, the specific location, installation angle and configuration parameters of the camera are determined. By evaluating the fitness of the first decision and determining whether the predetermined fitness limit is reached, the site selection of the video monitoring point in the target area can be effectively selected and implemented, and then the video monitoring point calibration of the initial risk visual map can be carried out according to the target site selection decision. By ensuring the scientificity and efficiency of the site selection decision, the optimized monitoring of the target area can be achieved, and the performance and efficiency of the monitoring system can be improved.

[0040] Further, it includes: analyzing the camera control parameters of the predetermined camera to obtain a predetermined monitoring frame; and determining the predetermined number according to the predetermined monitoring frame and the target size range of the target area.

[0041] Specifically, the predetermined monitoring frame is determined by analyzing the camera control parameters of the predetermined camera, and then the predetermined number of required cameras is determined according to the target size range of the target area. The main advantage of this method is that it can ensure that the monitoring frame matches the size of the target area, thereby achieving full coverage of the area. By accurately calculating the number of required cameras, resource waste can be avoided while ensuring the effectiveness and efficiency of the monitoring system.

[0042] Specifically, the camera control parameters of the predetermined cameras are first analyzed. These parameters may include the camera's field of view, resolution, zoom capability, etc. Through these parameters, the size of the surveillance frame that each camera can cover can be determined. Then, the required surveillance frame is determined based on the target size range of the target area, that is, the size of the area to be monitored. Next, the predetermined surveillance frame is compared with the target size range to determine the number of cameras that need to be deployed in order to fully cover the target area. In addition, in the process of determining the predetermined number, other factors such as budget constraints and installation conditions need to be considered to ensure the feasibility and economy of the solution. Finally, the predetermined number, that is, the number of required cameras, is determined through these analyses. By analyzing the camera control parameters of the camera and the size range of the target area, the number of required cameras can be accurately determined. By ensuring that the surveillance frame matches the size of the target area, blind spots can be effectively avoided and the coverage and performance of the surveillance system can be improved. At the same time, this method also helps to optimize resource allocation and avoid unnecessary cost expenditures.

[0043] Further, it includes: determining whether the first risk index is within a first predetermined risk threshold; if so, marking the first grid block with a first risk level, and if not, determining whether the first risk index is within a second predetermined risk threshold; if so, marking the first grid block with a second risk level, and if not, marking the first grid block with a third risk level; analyzing the first simulation information to obtain a first grid block simulation monitoring range of the first grid block; recording a first ratio of the first grid block simulation monitoring range to a first size range of the first grid block as a first monitoring index of the first site selection and layout decision for the first grid block; weighting the first monitoring index based on the identification of the first risk level or the second risk level or the third risk level to obtain a first target monitoring index; taking the average of the first target monitoring indices as a target comprehensive monitoring index, and adjusting the first decision fitness with the target comprehensive monitoring index.

[0044] Specifically, the risk level of the first grid block is marked according to the relationship between the first risk index and the predetermined risk threshold, and based on this, the simulated monitoring range of the first grid block is analyzed to calculate the first monitoring index. Then, the target comprehensive monitoring index is obtained by weighted calculation of the first monitoring index, and the first decision fitness is adjusted accordingly, so that the deployment effect of the monitoring system can be more accurately evaluated and optimized to ensure that high-risk areas are properly covered by monitoring.

[0045] Specifically, first, determine whether the first risk index is within the first predetermined risk threshold. If so, mark the first grid block with the first risk level; if not, further determine whether the first risk index is within the second predetermined risk threshold. If so, mark the first grid block with the second risk level; if not, mark the first grid block with the third risk level. Next, analyze the first simulation information to obtain the first grid block simulation monitoring range of the first grid block. Then, calculate the first ratio of the first grid block simulation monitoring range to the first size range of the first grid block. This ratio is the first monitoring index, which reflects the efficiency of monitoring coverage. In addition, based on the risk level of the first grid block, the first monitoring index is weighted to reflect the impact of the risk level on the monitoring requirements. Finally, calculate the mean of the first target monitoring index of all grid blocks to obtain the target comprehensive monitoring index, and adjust the first decision fitness accordingly.

[0046] By determining the risk level, calculating the monitoring index and adjusting the decision-making fitness, the deployment effect of the monitoring system can be effectively evaluated and optimized. By providing a comprehensive and quantitative monitoring evaluation, it helps to better understand the monitoring effect and adopt an effective monitoring deployment strategy.

[0047] Further, it includes: when the first decision fitness does not reach the predetermined fitness limit, obtaining a taboo optimization instruction; based on the taboo optimization instruction, calling a predetermined taboo optimization mechanism, and performing global optimization according to the predetermined taboo optimization mechanism to obtain the target site selection decision.

[0048] Further, it includes: constructing a deployment decision space according to a predetermined indicator threshold of a predetermined deployment control indicator; taking the predetermined number as a deployment constraint, taking the site selection deployment decision fitness evaluation function as a deployment evaluation strategy, and optimizing the deployment decision of the predetermined camera in the deployment decision space, recorded as the predetermined taboo optimization mechanism; wherein the predetermined deployment control indicator includes a deployment position and a deployment direction.

[0049] Specifically, when the fitness of the first decision does not reach the predetermined fitness limit, the taboo search algorithm is used to perform global optimization to obtain a better monitoring deployment plan. Among them, the taboo search algorithm can effectively avoid local optimal solutions and explore a wider solution space, thereby improving the efficiency and effect of monitoring deployment. By constructing a deployment decision space and based on predetermined deployment control indicators such as deployment location and deployment orientation, it can ensure that the optimization process is both scientific and efficient.

[0050] Specifically, first, when the fitness of the first decision does not reach the predetermined fitness limit, a taboo optimization instruction is obtained, which indicates that the current deployment decision is not optimal and needs to be further optimized. Then, the predetermined taboo optimization mechanism is called based on the taboo optimization instruction. This mechanism includes constructing a deployment decision space, where the space is determined by a predetermined indicator threshold of a predetermined deployment control indicator, such as a deployment position and a deployment orientation. Next, the taboo search algorithm is used to optimize the deployment decision in the deployment decision space with a predetermined number as the deployment constraint, that is, the number of cameras. The taboo search algorithm avoids repeated searches for known suboptimal solutions by memorizing past historical information, thereby guiding the search process towards a more optimal solution. In addition, the algorithm can also dynamically adjust the taboo table to balance the relationship between exploration and utilization and ensure the global optimization. Finally, the target location decision is obtained through the taboo search algorithm, which can better meet the monitoring needs and expected results.

[0051] By obtaining the taboo optimization instruction and calling the predetermined taboo optimization mechanism, the taboo search algorithm can be used to perform global optimization when the first decision fitness is not up to standard to obtain a better monitoring deployment plan. This method is particularly useful in situations where fine optimization of monitoring deployment is required, such as urban security, traffic management, and large-scale event monitoring. The taboo search algorithm can ensure that the deployment of the monitoring system is both scientific and efficient, thereby improving the monitoring coverage and performance.

[0052] Further, it includes: obtaining on-site verification information, the on-site verification information refers to the on-site information for calibrating video surveillance points according to the target site selection decision; extracting the first monitoring image of the first camera in the on-site verification information, and collecting verification information of the first camera and the first monitoring image to obtain first verification information; reading a predetermined verification strategy, and analyzing the first verification information based on the predetermined verification strategy to obtain a first actual orientation; comparing the first actual orientation with the first deployment orientation of the first camera in the target site selection decision to obtain a first orientation comparison result; and verifying the on-site execution of the target site selection decision according to the first orientation comparison result.

[0053] Specifically, the target location decision is verified by obtaining field verification information. This involves extracting surveillance images, collecting verification information, and analyzing it based on a predetermined verification strategy to determine the actual orientation of the camera. The actual orientation is then compared with the expected orientation in the deployment decision to verify the field execution of the target location decision.

[0054] Specifically, first, obtain the on-site verification information, which is the on-site information for calibrating the video surveillance point according to the target site selection decision. Then, extract the first surveillance image of the first camera from the on-site verification information. Next, collect the verification information of the first camera and the first surveillance image to obtain the first verification information. This part of information may include the position, angle, coverage, etc. of the camera. Then, read the predetermined verification strategy, which defines how to analyze the verification information to determine the actual orientation of the camera. Analyze the first verification information based on the predetermined verification strategy to obtain the first actual orientation. Next, compare the first actual orientation with the first layout orientation of the first camera in the target site selection decision to obtain the first orientation comparison result. Finally, verify the on-site execution of the target site selection decision based on the first orientation comparison result. If the actual orientation is consistent with the expected orientation, it means that the layout decision is properly executed; if there is a difference, it may be necessary to adjust the layout strategy or re-evaluate the decision. By obtaining the on-site verification information, extracting the surveillance image, collecting the verification information, and analyzing it based on the predetermined verification strategy, the on-site execution of the target site selection decision can be effectively verified. By verifying the execution of the layout decision, deviations can be discovered and corrected in a timely manner to ensure the performance and efficiency of the monitoring system.

[0055] Further, it includes: extracting the first image frame in the first monitoring image; determining whether the first image frame meets the predetermined frame conditions; if so, collecting multi-dimensional features of the first image frame based on the predetermined verification strategy to obtain first frame feature parameters; introducing a direction calculation function to calculate and analyze the first frame feature parameters to obtain the first actual direction.

[0056] Specifically, first, a monitoring image is randomly obtained from the first monitoring image monitored by the first camera. If the randomly obtained monitoring image meets the predetermined requirements, it is marked and recorded as the first image frame. For example, the monitoring clip is extracted from the real-time or historical video streaming media of the camera through the camera image extraction unit to form a continuous dynamic picture, and whether there are objects such as electric poles, street light poles, and tree trunks in the dynamic picture. If there are, the last frame in the above video monitoring clip is extracted and saved in a picture format, that is, as the first image frame. If not, re-extract and detect whether there is a moving object in the dynamic picture. Further, the moving object in the dynamic picture is extracted, and the height pixel value and aspect ratio of the object are measured. When the height pixel value is greater than 25% of the vertical height pixel of the monitoring picture and the height: width>2.5:1, the last frame in the above video monitoring clip is extracted and saved in a picture format, and the image source camera code and the last frame image timestamp information attached to the camera monitoring video clip are recorded. The coordinates of the static or moving objects that meet the conditions in the image are recorded and associated with the picture file.

[0057] Further, it is determined whether the first image frame meets the predetermined frame condition. If the first image frame meets the predetermined frame condition, multi-dimensional feature collection is performed on the first image frame based on the predetermined verification strategy to obtain first frame feature parameters. Then, a direction calculation function is introduced to calculate and analyze the first frame feature parameters to obtain the first actual direction.

[0058] Specifically, the predetermined frame conditions include predetermined frame acquisition conditions and predetermined frame content conditions. Among them, the predetermined frame acquisition conditions refer to the time and weather conditions when the corresponding image, that is, the first image frame here, is acquired, and the predetermined frame content conditions refer to the corresponding object and its object shadow condition in the acquired corresponding image, that is, the first image frame here. That is to say, after extracting the first image frame, the acquisition time of the first image frame, the weather conditions when the image frame is acquired, the object in the image frame and the object shadow condition information are obtained, and it is determined whether the acquisition time of the first image frame, the weather conditions when the image frame is acquired, and the object in the image frame and the shadow condition information meet the predetermined frame conditions. For example, the standard time of the external time calibration system is obtained through the time calculation unit at a frequency of not less than once every 20 minutes, and the source device of the camera image extraction unit extracts the picture, extracts the real-time time of the camera, and compares it with the current time of the time correction unit. If the difference does not exceed 90 seconds, it is qualified and can enter the next stage of analysis according to the process. If it exceeds 90 seconds, it is unqualified and needs to be recorded in the camera image extraction unit, and then the date is converted to Julian day and the time is converted to world time; at the same time, according to the Chinese standard calendar of the year, the parameters such as apparent solar time and mean solar time are calculated. The external real-time meteorological data, including sunrise and sunset time, hourly cloudy and sunny state, temperature, wind force and wind direction, visibility, cloud cover, air quality, and rainfall probability, are obtained through the weather state and image illumination analysis unit. Then, the monitoring video is analyzed by the image recognition method to see whether there are special weather such as rain, snow, fog, etc., and the illumination conditions in the monitoring video are identified. Finally, the meteorological information, real-time weather state, illumination state, sunrise and sunset time, current time and other factors are comprehensively judged whether it is suitable for subsequent analysis. If it is not suitable, it does not meet the predetermined frame acquisition conditions, and the corresponding first image frame cannot be used to verify the camera layout. Next, the first image frame is judged whether the predetermined frame content conditions are met. For example, the target element picking unit in the image locates the calculated object according to the coordinates of the static or moving object that meets the conditions provided by the "camera image extraction unit" in the image, and detects whether there is interference from adjacent similar objects in the image. If so, the calculated image is defined as invalid. For another example, the target object and shadow segmentation unit automatically searches for the shadow features of the qualified object recorded by the "camera image extraction unit", verifies the association logic between the shadow and the object body, and performs rectangular frame extraction and shape mask extraction on the object and shadow respectively, saves the paired object instance and shadow instance, and then calculates the rectangular height and width pixel values ​​of the segmented object instance, and calculates the length and width pixel values ​​between the farthest fixed points of the shadow instance mask.Next, the ratio of the object height and the shadow length is calculated. When the object height: shadow length is greater than 2, it is considered that the shadow may exceed the image boundary and the calculated image is invalid. The ratio of the object width and the shadow width is calculated. When the shadow width: object width is greater than 1.5, it is considered that the shadow may not match the object properly and the calculated image is invalid.

[0059] When the first image frame satisfies both the predetermined frame acquisition condition and the predetermined frame content condition, the solar azimuth and altitude angle calculation unit calculates the solar obliquity, solar ecliptic longitude, solar declination, zenith angle, etc. according to the almanac, calculates the true solar time correction parameters and longitude correction parameters, and accurately calculates the solar azimuth at the specified time and the specified location according to the optimized solar azimuth calculation method. Finally, the solar altitude at the specified time and the specified location is accurately calculated according to the optimized solar azimuth calculation method. Further, the angle between the object instance and the shadow instance in the calculated image is calculated by the monitoring camera orientation angle calibration unit, where the object instance is abstracted as the height center line of the object rectangular frame, and the shadow instance is abstracted as the line connecting the vertices of the shadow shape mask length. Then, according to the solar azimuth and the image angle, the orientation angle of the monitoring camera is calculated according to the formula. That is, the first actual orientation.

[0060] In summary, the video surveillance point calibration method based on spatial intelligence algorithm provided by this application has the following technical effects:

[0061] The target area is divided to obtain a target division result, wherein the target division result includes a plurality of grid blocks; the target video surveillance requirement is read, and based on the target video surveillance requirement, multi-dimensional features of a first grid block are collected to obtain first multi-dimensional information, wherein the first grid block refers to any one of the plurality of grid blocks, and the first grid block has an identifier of a first coordinate position; an initial risk visual map of the target area is generated by combining and analyzing a first risk index and the first coordinate position obtained from the first multi-dimensional information; a first site selection and layout decision is generated, wherein the first site selection and layout decision refers to any one site selection and layout decision for deploying a predetermined number of predetermined cameras in the target area; the first site selection and layout decision is simulated and laid out in the initial risk visual map to obtain first simulation information; a site selection and layout decision fitness evaluation function is introduced to evaluate and analyze the first simulation information to obtain a first decision fitness; when the first decision fitness reaches a predetermined fitness limit, the first site selection and layout decision is used as a target site selection decision for the target area; and the initial risk visual map is calibrated for video surveillance points according to the target site selection decision. By comprehensively analyzing the actual needs and risk factors of the target area, scientific and reasonable monitoring point calibration decisions are made, achieving the technical goals of improving monitoring efficiency, optimizing resource allocation, and enhancing monitoring effects.

[0062] Embodiment 2, based on the same inventive concept as the video surveillance point calibration method based on spatial intelligent algorithm in the above embodiment, the present application also provides a video surveillance point calibration system based on spatial intelligent algorithm, please refer to the attached Figure 2 , the video surveillance point calibration system based on spatial intelligence algorithm includes:

[0063] A region division module 11, the region division module 11 is used to divide the target region to obtain a target division result, and the target division result includes a plurality of grid blocks; a feature collection module 12, the feature collection module 12 is used to read the target video surveillance requirements, and based on the target video surveillance requirements, perform multi-dimensional feature collection on a first grid block to obtain first multi-dimensional information, wherein the first grid block refers to any one of the plurality of grid blocks, and the first grid block has an identifier of a first coordinate position; a risk visualization module 13, the risk visualization module 13 is used to combine a first risk index obtained by analyzing the first multi-dimensional information with the first coordinate position to generate an initial risk visualization diagram of the target region; a decision acquisition module 14, the decision acquisition module 14 is used to generate a first site selection and layout decision, the first site selection and layout Decision refers to any one of the site selection and layout decisions for deploying a predetermined number of predetermined cameras in the target area; decision simulation module 15, the decision simulation module 15 is used to simulate the layout of the first site selection and layout decision in the initial risk visual map to obtain first simulation information; fitness evaluation module 16, the fitness evaluation module 16 is used to introduce the site selection and layout decision fitness evaluation function to evaluate and analyze the first simulation information to obtain the first decision fitness; site selection decision module 17, the site selection decision module 17 is used to use the first site selection and layout decision as the target site selection decision for the target area when the first decision fitness reaches a predetermined fitness limit; point calibration module 18, the point calibration module 18 is used to calibrate the video surveillance points of the initial risk visual map according to the target site selection decision.

[0064] Furthermore, the risk visualization module 13 in the video surveillance point calibration system based on spatial intelligent algorithm is also used for: the first multidimensional information includes multiple dimensional parameters of predetermined dimensions; the multiple dimensional parameters after normalization are weighted calculated using the principle of coefficient of variation algorithm to obtain the first risk index; wherein the predetermined dimensions include at least geographical environment dimension, crowd density dimension and historical monitoring dimension.

[0065] Furthermore, the decision acquisition module 14 in the video surveillance point calibration system based on spatial intelligent algorithm is also used to: analyze the camera control parameters of the predetermined camera to obtain a predetermined monitoring frame; and determine the predetermined number based on the predetermined monitoring frame and the target size range of the target area.

[0066] Furthermore, the fitness evaluation module 16 in the video surveillance point calibration system based on the spatial intelligent algorithm is also used to: introduce the site selection and layout decision fitness evaluation function to evaluate and analyze the first simulation information to obtain the first decision fitness; wherein the first simulation information includes multiple simulated monitoring ranges of the predetermined number of the predetermined cameras, and the expression of the site selection and layout decision fitness evaluation function is as follows: ;in, Refers to the first site selection decision The first decision fitness, Refers to the first site selection decision The first total simulation coverage, Refers to the first site selection decision The first total simulation monitoring range, refers to the first of the multiple simulated monitoring ranges of the predetermined camera Camera No. A simulation monitoring range, means the predetermined quantity, refers to the target size range, Refers to the first site selection decision The first total simulation overlap ratio, The first site selection decision The overlapping monitoring ranges, and It refers to Simulated monitoring range of cameras With Simulated monitoring range of cameras The overlapping range of The camera and the The camera is the first location for the decision For any two cameras with overlapping surveillance, Refers to the first site selection decision The number of simulation monitoring overlap ranges in , and refer to the first coefficient and the second coefficient respectively, and .

[0067] Furthermore, the video surveillance point calibration system based on spatial intelligent algorithm also includes a fitness adjustment module, which is used to: determine whether the first risk index is within a first predetermined risk threshold; if so, mark the first grid block with a first risk level, and if not, determine whether the first risk index is within a second predetermined risk threshold; if so, mark the first grid block with a second risk level, and if not, mark the first grid block with a third risk level; analyze the first simulation information to obtain a first grid block simulation monitoring range of the first grid block; record a first ratio of the first grid block simulation monitoring range to the first size range of the first grid block as the first monitoring index of the first site selection and layout decision for the first grid block; weight the first monitoring index based on the identification of the first risk level or the second risk level or the third risk level to obtain a first target monitoring index; take the average of the first target monitoring index as the target comprehensive monitoring index, and adjust the first decision fitness based on the target comprehensive monitoring index.

[0068] Furthermore, the video surveillance point calibration system based on spatial intelligent algorithm also includes a taboo optimization module, which is used to: when the first decision fitness does not reach the predetermined fitness limit, obtain a taboo optimization instruction; based on the taboo optimization instruction, call a predetermined taboo optimization mechanism, and perform global optimization according to the predetermined taboo optimization mechanism to obtain the target site selection decision.

[0069] Furthermore, the taboo optimization module in the video surveillance point calibration system based on the spatial intelligent algorithm is also used to: construct a deployment decision space according to a predetermined indicator threshold of a predetermined deployment control indicator; use the predetermined number as the deployment constraint, and the site selection deployment decision fitness evaluation function as the deployment evaluation strategy, and optimize the deployment decision of the predetermined camera in the deployment decision space, which is recorded as the predetermined taboo optimization mechanism; wherein the predetermined deployment control indicator includes a deployment position and a deployment direction.

[0070] Furthermore, the video surveillance point calibration system based on spatial intelligent algorithm also includes a field verification module, which is used to: obtain field verification information, the field verification information refers to the field information for video surveillance point calibration based on the target site selection decision; extract the first surveillance image of the first camera in the field verification information, and collect verification information of the first camera and the first surveillance image to obtain first verification information; read a predetermined verification strategy, and analyze the first verification information based on the predetermined verification strategy to obtain a first actual direction; compare the first actual direction with the first layout direction of the first camera in the target site selection decision to obtain a first direction comparison result; and verify the on-site execution of the target site selection decision based on the first direction comparison result.

[0071] Furthermore, the video surveillance point calibration system based on spatial intelligent algorithm also includes a point calibration module, which is used to extract the first image frame in the first surveillance image; determine whether the first image frame meets the predetermined frame conditions; if so, collect multi-dimensional features of the first image frame based on the predetermined verification strategy to obtain first frame feature parameters; introduce a direction calculation function to calculate and analyze the first frame feature parameters to obtain the first actual direction.

[0072] The various embodiments in this specification are described in a progressive manner, and each embodiment focuses on the differences from other embodiments. Figure 1 The video surveillance point calibration method based on spatial intelligent algorithm and the specific examples in Example 1 are also applicable to the video surveillance point calibration system based on spatial intelligent algorithm in this embodiment. Through the above detailed description of the video surveillance point calibration method based on spatial intelligent algorithm, those skilled in the art can clearly know the video surveillance point calibration system based on spatial intelligent algorithm in this embodiment, so for the sake of brevity of the specification, it will not be described in detail here. For the system disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part description.

[0073] The above description of the disclosed embodiments enables those skilled in the art to implement or use the present application. 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 application. Therefore, the present application will not be limited to the embodiments shown herein, but will conform to the widest scope consistent with the principles and novel features disclosed herein.

[0074] Obviously, those skilled in the art can make various changes and modifications to the present application without departing from the spirit and scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalent technology, the present application is also intended to include these modifications and variations.

Claims

1. A video surveillance point calibration method based on spatial intelligence algorithm, characterized in that: include: Dividing the target area to obtain a target division result, wherein the target division result includes a plurality of grid blocks; Reading a target video surveillance requirement, and collecting multi-dimensional features of a first grid block based on the target video surveillance requirement to obtain first multi-dimensional information, wherein the first grid block refers to any one of the plurality of grid blocks, and the first grid block has an identifier of a first coordinate position; Generate an initial risk visualization graph of the target area by combining a first risk index obtained by analyzing the first multi-dimensional information with the first coordinate position; Generate a first site selection and deployment decision, wherein the first site selection and deployment decision is any site selection and deployment decision for deploying a predetermined number of predetermined cameras in the target area; Performing simulation layout of the first site selection and layout decision in the initial risk visualization graph to obtain first simulation information; Introducing a site selection and layout decision fitness evaluation function to evaluate and analyze the first simulation information to obtain a first decision fitness; When the fitness of the first decision reaches a predetermined fitness limit, the first site selection and layout decision is used as the target site selection decision of the target area; Calibrate video monitoring points on the initial risk visual map according to the target site selection decision; Among them, include: The first multi-dimensional information includes a plurality of dimensional parameters of predetermined dimensions; Performing weighted calculation on the normalized multiple dimensional parameters using the coefficient of variation algorithm principle to obtain the first risk index; The predetermined dimensions include at least a geographical environment dimension, a crowd density dimension, and a historical monitoring dimension; Among them, include: Analyzing the camera control parameters of the predetermined camera to obtain a predetermined monitoring frame; Determining the predetermined number according to the predetermined monitoring frame and the target size range of the target area; Among them, include: Introducing the site selection and layout decision fitness evaluation function to evaluate and analyze the first simulation information to obtain the first decision fitness; The first simulation information includes multiple simulated monitoring ranges of the predetermined number of the predetermined cameras, and the expression of the site selection and layout decision fitness evaluation function is as follows: ; in, Refers to the first site selection decision The first decision fitness, Refers to the first site selection decision The first total simulation coverage, Refers to the first site selection decision The first total simulation monitoring range, refers to the first of the multiple simulated monitoring ranges of the predetermined camera Camera No. A simulation monitoring range, means the predetermined quantity, refers to the target size range, Refers to the first site selection decision The first total simulation overlap ratio, The first site selection decision The overlapping monitoring ranges, and It refers to Simulated monitoring range of cameras With Simulated monitoring range of cameras The overlapping range of The camera and the The camera is the first location for the decision For any two cameras with overlapping surveillance, Refers to the first site selection decision The number of simulation monitoring overlap ranges in , and refer to the first coefficient and the second coefficient respectively, and .

2. According to claim 1, a method for calibrating video surveillance points based on spatial intelligence algorithm is characterized in that: Also includes: Determining whether the first risk index is within a first predetermined risk threshold; If so, marking the first grid block with a first risk level, and if not, determining whether the first risk index is within a second predetermined risk threshold; Alternatively, if it is, marking the first grid block with a second risk level, and if it is not, marking the first grid block with a third risk level; Analyzing the first simulation information to obtain a first grid block simulation monitoring range of the first grid block; Recording a first ratio of the simulation monitoring range of the first grid block to the first size range of the first grid block as a first monitoring index of the first site selection and layout decision for the first grid block; Weighting the first monitoring index based on the identifier of the first risk level, the second risk level, or the third risk level to obtain a first target monitoring index; The average of the first target monitoring index is taken as the target comprehensive monitoring index, and the first decision fitness is adjusted according to the target comprehensive monitoring index.

3. According to claim 1, a method for calibrating video surveillance points based on spatial intelligence algorithm is characterized in that: Also includes: When the first decision fitness does not reach the predetermined fitness limit, obtaining a taboo optimization instruction; Based on the taboo optimization instruction, a predetermined taboo optimization mechanism is called, and global optimization is performed according to the predetermined taboo optimization mechanism to obtain the target site selection decision.

4. According to claim 3, a method for calibrating video surveillance points based on spatial intelligence algorithm is characterized in that: Also includes: Constructing a deployment decision space according to predetermined indicator thresholds of predetermined deployment control indicators; Taking the predetermined number as the deployment constraint and the location deployment decision fitness evaluation function as the deployment evaluation strategy, the deployment decision optimization of the predetermined cameras is performed in the deployment decision space, which is recorded as the predetermined taboo optimization mechanism; Wherein, the predetermined deployment control index includes deployment position and deployment direction.

5. According to claim 1, a method for calibrating video surveillance points based on spatial intelligence algorithm is characterized in that: Also includes: Acquiring on-site verification information, wherein the on-site verification information refers to on-site information for selecting a video surveillance point location according to the target location selection decision; Extracting a first monitoring image of a first camera from the on-site verification information, and collecting verification information of the first camera and the first monitoring image to obtain first verification information; Reading a predetermined verification strategy, and analyzing the first verification information based on the predetermined verification strategy to obtain a first actual orientation; Comparing the first actual orientation with the first layout orientation of the first camera in the target site selection decision to obtain a first orientation comparison result; The on-site implementation status of the target site selection decision is verified based on the first orientation comparison result.

6. According to claim 5, a method for calibrating video surveillance points based on spatial intelligence algorithm is characterized in that: include: Extracting a first image frame from the first surveillance image; Determining whether the first image frame meets a predetermined frame condition; If it is in compliance, performing multi-dimensional feature collection on the first image frame based on the predetermined verification strategy to obtain first frame feature parameters; A direction calculation function is introduced to calculate and analyze the first frame feature parameters to obtain the first actual direction.

7. A video surveillance point calibration system based on spatial intelligence algorithm, characterized in that: The steps for implementing the method for calibrating video surveillance points based on a spatial intelligence algorithm as described in any one of claims 1 to 6, wherein the video surveillance point calibration system based on a spatial intelligence algorithm comprises: A region division module, wherein the region division module is used to divide the target region to obtain a target division result, wherein the target division result includes a plurality of grid blocks; A feature collection module, the feature collection module is used to read the target video surveillance requirements, and based on the target video surveillance requirements, perform multi-dimensional feature collection on a first grid block to obtain first multi-dimensional information, wherein the first grid block refers to any one of the multiple grid blocks, and the first grid block has an identifier of a first coordinate position; A risk visualization module, the risk visualization module is used to generate an initial risk visualization diagram of the target area by combining a first risk index obtained by analyzing the first multi-dimensional information with the first coordinate position; A decision acquisition module, the decision acquisition module is used to generate a first location selection and deployment decision, the first location selection and deployment decision is any location selection and deployment decision of deploying a predetermined number of predetermined cameras in the target area; A decision simulation module, the decision simulation module is used to simulate the first site selection and layout decision in the initial risk visualization diagram to obtain first simulation information; A fitness evaluation module, wherein the fitness evaluation module is used to introduce a site selection and layout decision fitness evaluation function to evaluate and analyze the first simulation information to obtain a first decision fitness; A site selection decision module, wherein the site selection decision module is used to use the first site selection decision as a target site selection decision for the target area when the fitness of the first decision reaches a predetermined fitness limit; A point calibration module is used to calibrate the video monitoring points of the initial risk visual map according to the target site selection decision.

Citation Information

Patent Citations

  • Transformer substation site selection area intelligent division method based on GIS space analysis technology

    CN116777230A

  • Public safety video monitoring point location layout method and system based on spatial big data

    CN118333245A