Regional security monitoring method and system based on Internet of Things

Abstract

The invention relates to the technical field of safety monitoring, and discloses a regional safety monitoring method and system based on the Internet of Things, and the method comprises the steps: obtaining a building planning drawing of a to-be-monitored region, so as to create a monitoring region model, obtaining monitoring deployment information, and marking each monitoring camera in the monitoring region model; monitoring parameter information of each monitoring camera is acquired in real time, and a monitoring coverage area of each monitoring camera is evaluated in the monitoring area model based on the monitoring azimuth information and the monitoring parameter information of each monitoring camera; based on the monitoring coverage condition of each area in the monitoring area model and a preset monitoring rating rule, evaluating the subarea monitoring level of each monitoring subarea in the to-be-monitored area; generating a corresponding early warning instruction based on the subarea monitoring level, and matching a corresponding inspection scheme; the method has the effect of improving the security risk detection rate.

Description

Technical Field

[0001] The present application relates to the technical field of security monitoring, and in particular to a regional security monitoring method and system based on the Internet of Things. Background Art

[0002] At present, for key areas with high security requirements, surveillance cameras are usually used to capture images of key areas in real time, and security guards ensure the safety of these areas by checking surveillance or patrolling. However, when security guards manually check surveillance images, there is a possibility of missing security risk events. On the other hand, the surveillance cameras themselves may be damaged or the lenses may be contaminated, resulting in a reduction in the monitoring range. Therefore, the above-mentioned related technologies have the problem of low security risk detection rate. Summary of the invention

[0003] In order to improve the detection rate of security risks, the present application provides a regional security monitoring method and system based on the Internet of Things.

[0004] The first invention objective of this application is achieved by adopting the following technical solution:

[0005] A regional security monitoring method based on the Internet of Things, comprising:

[0006] Obtain architectural planning drawings of the area to be monitored to create a monitoring area model, obtain monitoring deployment information, and mark each monitoring camera in the monitoring area model;

[0007] Acquire the monitoring parameter information of each monitoring camera in real time, and evaluate the monitoring coverage area of ​​each monitoring camera in the monitoring area model based on the monitoring position information and monitoring parameter information of each monitoring camera;

[0008] Based on the monitoring coverage of each area in the monitoring area model and the preset monitoring rating rules, the monitoring level of each monitoring area in the area to be monitored is evaluated;

[0009] Generate corresponding warning instructions based on the partition monitoring level and match the corresponding inspection plan;

[0010] The building planning drawings record the modeling parameter information of each building in the area to be monitored; the monitoring cameras are associated with corresponding monitoring position information.

[0011] By adopting the above technical solution, the building planning drawings of the area to be monitored are obtained, and a monitoring area model is created in a three-dimensional modeling program according to the modeling parameter information of each building in the area to be monitored, so as to facilitate the building information modeling processing of the area to be monitored, obtain the monitoring deployment information, mark each monitoring camera in the monitoring area model, and each monitoring camera is associated with the monitoring direction information, so as to facilitate the subsequent analysis of the monitoring range of each monitoring camera; the monitoring parameter information of each monitoring camera is obtained in real time, and combined with the monitoring direction information, the current monitoring coverage area of ​​each monitoring camera is evaluated in the monitoring area model, so as to know the coverage and overlap of the monitoring range of each monitoring camera; according to the monitoring coverage of each area in the monitoring area model and the monitoring rating rules, the partition monitoring level of each monitoring partition is evaluated, so as to know the monitoring degree of each partition relative to the monitoring camera; according to the partition monitoring level, an early warning instruction is generated and the corresponding inspection plan is matched, so as to inform the security guard to focus on the manual inspection of the area with low monitoring degree.

[0012] In a preferred example of the present application: the monitoring position information includes the installation position coordinates and the initial shooting direction of the monitoring camera; the monitoring parameter information includes the focal length, focal length, field of view, cropping factor, current shooting direction, shooting direction range, and resolution of the monitoring camera;

[0013] The real-time acquisition of monitoring parameter information of each monitoring camera, and based on the monitoring position information and monitoring parameter information of each monitoring camera, evaluating the monitoring coverage area of ​​each monitoring camera in the monitoring area model, includes:

[0014] Acquire monitoring parameter information and monitoring position information of each monitoring camera based on a preset update cycle;

[0015] Determine the target cameras one by one, determine the imaging cone space of the target cameras based on the installation position coordinates, current shooting direction and field of view angle of the target cameras, evaluate the clear imaging distance interval based on the focal length and resolution of the target cameras, and intercept the clear imaging space from the imaging cone space based on the clear imaging distance interval;

[0016] The monitoring coverage area is determined in the monitoring area model based on the superposition results of the clear imaging space of each target camera.

[0017] By adopting the above technical solution, the current monitoring parameter information and monitoring orientation information of each monitoring camera are obtained based on the update cycle, so as to subsequently analyze the current shooting range of each monitoring camera; the target cameras are determined one by one, and the imaging cone space of the target camera is determined based on the installation position coordinates, current shooting direction and field of view of the target camera; based on the focal length and resolution of the target camera, the clear imaging distance interval is evaluated to intercept the clear imaging space from the imaging cone space to obtain the range that the target camera can clearly shoot; based on the clear imaging space of each target camera, they are superimposed to determine the monitoring coverage area in the monitoring area model.

[0018] In a preferred example of the present application, the monitoring coverage of each area in the monitoring area model and the preset monitoring rating rules are used to evaluate the monitoring level of each monitoring area in the monitored area, including:

[0019] Divide a number of spatial grids based on the common areas in the monitoring area model, and generate monitoring rating signals based on a preset evaluation cycle;

[0020] Receive the monitoring rating signal, determine the target squares one by one, count the percentage of the target squares in the frame during a previously preset analysis period, the number of times they are in the frame, and the monitoring rating rules, and calculate the square monitoring level of the target squares;

[0021] Based on the grid monitoring level and distribution of each target grid, evaluate the sub-district monitoring level of each monitoring sub-district in the area to be monitored;

[0022] When more than half of the space in the target square is within the clear imaging range, the target square is in the frame state; when the target square reaches a preset frame time in the frame state, an frame count is accumulated; the monitoring rating rule includes a calculation formula for the square monitoring level; the monitoring partition is an area including several space squares divided according to functions in the public area;

[0023] The calculation formula of the grid monitoring level is:

[0024]

[0025] i is the identification information of the spatial grid, L Ui is the grid monitoring level of spatial grid i, R i is the proportion of the frame duration corresponding to spatial grid i, F i is the number of shots corresponding to spatial grid i. When counting the shot duration and shot frequency, it is necessary to superimpose the shot duration and shot frequency detected by all surveillance cameras. i 、F i Both have upper limits, k R , k Fis the weight coefficient corresponding to the proportion of the duration of the scene and the number of scenes, and L0 is the base number for the level evaluation; So The floor rounding expression for the value to be rounded.

[0026] By adopting the above technical scheme, a number of spatial grids are divided based on the common area in the monitoring area model, and monitoring rating signals are regularly generated according to the evaluation cycle, so as to perform the monitoring level evaluation work on each spatial grid later; the monitoring rating signal is received to determine each spatial grid as a target grid one by one, and the proportion of the time and the number of times the target grid is in the frame in the previous analysis period are counted, so as to calculate the grid monitoring level of the target grid according to the monitoring rating rules, so as to determine the degree of monitoring of the target grid by the monitoring camera; based on the grid monitoring level and distribution of each target grid, the partition monitoring level of each partition in the monitored area is evaluated, so as to facilitate the subsequent adoption of different monitoring strategies for the different partition monitoring levels of each monitoring partition.

[0027] In a preferred example of the present application, before evaluating the partition monitoring level of each monitoring partition in the to-be-monitored area based on the grid monitoring level and distribution of each target grid, the method includes:

[0028] Based on the historical surveillance images of the area to be monitored, the number and location of personnel units in the historical surveillance images are identified through image recognition algorithms, so as to count the time period area flow of people entering each monitoring zone by time period unit;

[0029] Based on the flow of people in the time period area, calculate the flow impact coefficient corresponding to each monitoring zone;

[0030] When the cell monitoring level of the target cell is lower than the first threshold, obtaining the cell monitoring levels of several corresponding adjacent cells, and determining the adjacent influence parameter based on the lowest cell monitoring level;

[0031] Based on the adjacent influence parameters of the target square and the crowd influence coefficient of the monitoring zone, the corresponding square monitoring level is calculated;

[0032] The calculation formula of the flow influencing parameter is:

[0033] λ1=k1P

[0034] The calculation formula of the adjacency influence parameter is:

[0035] λ2=k2minadj{L Uxj}

[0036] The calculation formula for assigning the grid monitoring level is:

[0037] AL Uxj =λ1(L Uxj +λ2)

[0038] The calculation formula of the partition monitoring level is:

[0039]

[0040] j is the identification information of the monitoring partition, L Dj is the partition monitoring level of monitoring partition j, xj is the identification information of the spatial grid in monitoring partition j, xj∈i, L Uxj is the monitoring level of the spatial grid xj, λ1 is the flow influence coefficient, k1 is the flow influence assessment coefficient, P is the flow of people in the time period, λ2 is the adjacent influence parameter, k2 is the adjacent influence assessment coefficient, minadj{L Uxj} is the minimum cell monitoring level among the adjacent cells of the spatial cell xj, AL Uxj Assign a value to the monitoring level of the spatial grid xj, N xj To monitor the number of spatial grids in partition j.

[0041] By adopting the above technical solution, before evaluating the partition monitoring level of the monitoring partition, the image recognition algorithm is used to process the historical monitoring images of the monitoring area to be monitored, and the number and position of the personnel units in the historical monitoring images are identified, and then the time period flow of people entering each monitoring partition is counted according to the time period unit, so as to facilitate the analysis of the flow of people in each monitoring partition in the monitored area at different time periods; based on the time period area flow of people, the corresponding flow of people influence coefficient corresponding to each monitoring partition is calculated, so as to facilitate the subsequent evaluation of the influence of the flow of people on the safety of the monitoring partition; because there may be some spatial grids within the monitoring range at the edge of the monitoring range of the monitoring camera, and the flow of people in these spatial grids can be analyzed according to the flow of people within the monitoring range, therefore, when the grid monitoring level of the target grid is lower than the first threshold, the adjacency influence coefficient of the target grid is determined according to the lowest grid monitoring level among several adjacent grids, so as to facilitate the subsequent more scientific evaluation of the monitoring degree of the spatial grid at the edge of the monitoring range; based on the adjacency influence parameter and the flow of people influence coefficient of the target grid, the grid monitoring level assignment of the target grid is calculated, so as to facilitate the more scientific evaluation of the monitoring degree of the target grid.

[0042] In a preferred example of the present application, the generating of corresponding warning instructions based on the partition monitoring level and matching of corresponding inspection plans include:

[0043] Compare the monitoring level of each partition with the preset inspection threshold, define the monitoring partition whose monitoring level is less than the inspection threshold as the partition to be inspected and send it to the inspection terminal;

[0044] When a sudden change in the partition monitoring level is detected, a corresponding monitoring image detection instruction is generated to evaluate the image anomaly type of each monitoring camera through an image recognition algorithm;

[0045] If the image anomaly type is equipment damage, the monitoring camera based on the equipment damage generates equipment inspection information and sends it to the inspection terminal.

[0046] By adopting the above technical solution, the monitoring partition whose partition monitoring level is less than the inspection threshold is defined as the partition to be inspected and sent to the inspection terminal, so as to prompt the inspection personnel to carry out targeted inspection work on the monitoring partition with a small degree of monitoring; when a sudden change in the partition monitoring level is detected, it is considered that the camera is damaged, and a monitoring image detection instruction is generated to identify whether there is an abnormality in the monitoring image through an image recognition algorithm and determine the type of image abnormality; when the image abnormality type is equipment damage, equipment inspection information is generated based on the damaged monitoring camera and sent to the inspection terminal, so as to inform the inspection personnel to check the cause of the damage to the monitoring camera during the inspection.

[0047] In a preferred example of the present application, the process of comparing the monitoring level of each partition with a preset inspection threshold and defining the monitoring partition whose monitoring level is less than the inspection threshold as the partition to be inspected includes:

[0048] Mark the areas to be inspected and the HD cameras in the monitoring area model;

[0049] Determine the target inspection zones one by one, and based on the target inspection zones and the installation position coordinates and shooting direction range of each HD camera, analyze the HD cameras whose optical axes can point to the target inspection zones after one refraction and mark them as corresponding candidate cameras, and mark the corresponding refraction positions of the candidate cameras in the monitoring area model;

[0050] In the monitoring area model, it is simulated to set up reflectors at various refraction positions, set the optimization goal of maximizing the monitoring of the partition to be inspected, evaluate the installation angles of each candidate camera and the corresponding reflector through the automatic optimization algorithm, determine the optimal reflection combination of the candidate camera and the reflector, and generate monitoring optimization information based on the reflection combination of the partition to be inspected that maximizes the monitoring and sends it to the inspection terminal;

[0051] The high-definition camera refers to a monitoring camera whose monitoring parameter information meets the preset high-definition standard; when performing optical axis refraction analysis, the refraction angle ranges from 15 to 75°, and the refraction position is located on the building wall.

[0052] By adopting the above technical solution, high-definition cameras are screened from various surveillance cameras according to preset high-definition standards, and the locations of the partitions to be inspected and the high-definition cameras are marked in the monitoring area model, so as to facilitate subsequent analysis and optimization of the monitoring expansion plan; the target partitions to be inspected are determined one by one, and based on the locations of the partitions to be inspected and the installation position coordinates and shooting direction range of each high-definition camera, an optical analysis plug-in is used to analyze the high-definition cameras that can point to the target partitions to be inspected after one refraction of the optical axis, and these high-definition cameras are marked as candidate cameras corresponding to the target partitions to be inspected, and the candidate cameras and the corresponding refractions are marked in the monitoring area model. reflective position; in the monitoring area model, it is simulated to set up reflectors at various refraction positions, and the optimization goal of maximizing the monitoring of the partition to be inspected is set. The installation angles of the candidate cameras and the corresponding reflectors are discarded through the automatic optimization algorithm, so as to select the best reflection combination from the reflection combinations composed of several candidate cameras and reflectors. According to the best reflection combination, monitoring optimization information is generated and sent to the inspection terminal, so that the inspection personnel can increase the monitoring range of the monitoring camera by setting up reflectors in the area to be monitored and adjusting the camera angle, thereby reducing the area that needs regular manual inspection and improving the detection rate of safety risks.

[0053] The second invention objective of this application is achieved by the following technical solution:

[0054] An Internet of Things-based regional security monitoring system, applied to any of the Internet of Things-based regional security monitoring methods described above, comprising:

[0055] A monitoring area model creation module is used to obtain the architectural planning drawings of the area to be monitored to create a monitoring area model, obtain monitoring deployment information, and mark each monitoring camera in the monitoring area model;

[0056] A monitoring coverage area evaluation module is used to obtain monitoring parameter information of each monitoring camera in real time, and evaluate the monitoring coverage area of ​​each monitoring camera in the monitoring area model based on the monitoring position information and monitoring parameter information of each monitoring camera;

[0057] A zone monitoring level assessment module is used to assess the zone monitoring level of each monitoring zone in the monitored area based on the monitoring coverage of each zone in the monitoring area model and preset monitoring rating rules;

[0058] Inspection plan matching module, used to generate corresponding warning instructions based on the partition monitoring level and match the corresponding inspection plan;

[0059] The building planning drawings record the modeling parameter information of each building in the area to be monitored; the monitoring cameras are associated with corresponding monitoring position information.

[0060] In a preferred example of the present application: the monitoring coverage area assessment module includes:

[0061] The camera information analysis submodule is used to obtain the monitoring parameter information and monitoring position information of each monitoring camera based on a preset update cycle;

[0062] A clear imaging space determination submodule is used to determine the target cameras one by one, determine the imaging cone space of the target camera based on the installation position coordinates, current shooting direction and field angle of the target camera, evaluate the clear imaging distance interval based on the focal length and resolution of the target camera, and intercept the clear imaging space from the imaging cone space based on the clear imaging distance interval;

[0063] A clear imaging space superposition submodule, used to determine the monitoring coverage area in the monitoring area model based on the superposition results of the clear imaging spaces of each target camera;

[0064] The monitoring position information includes the installation position coordinates and initial shooting direction of the monitoring camera; the monitoring parameter information includes the focal length, focal length, field of view, cropping factor, current shooting direction, shooting direction range, and resolution of the monitoring camera.

[0065] The third invention objective of this application is achieved by the following technical solution:

[0066] A computer device comprises 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 regional security monitoring method based on the Internet of Things when executing the computer program.

[0067] The fourth invention objective of this application is achieved by the following technical solution:

[0068] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned regional security monitoring method based on the Internet of Things.

[0069] In summary, the present application includes at least one of the following beneficial technical effects:

[0070] 1. Obtain the architectural planning drawings of the area to be monitored, create a monitoring area model in a three-dimensional modeling program according to the modeling parameter information of each building in the area to be monitored, so as to facilitate the building information modeling processing of the area to be monitored, obtain the monitoring deployment information, mark each monitoring camera in the monitoring area model, and each monitoring camera is associated with the monitoring position information, so as to facilitate the subsequent analysis of the monitoring range of each monitoring camera; obtain the monitoring parameter information of each monitoring camera in real time, and combine it with the monitoring position information to evaluate the current monitoring coverage area of ​​each monitoring camera in the monitoring area model, so as to know the coverage and overlap of the monitoring range of each monitoring camera; evaluate the partition monitoring level of each monitoring partition according to the monitoring coverage of each area in the monitoring area model and the monitoring rating rules, so as to know the degree of monitoring of each partition relative to the monitoring camera; generate early warning instructions according to the partition monitoring level and match the corresponding inspection plan, so as to inform the security guards to focus on manual inspections of areas with low monitoring levels.

[0071] 2. Based on the update cycle, the current monitoring parameter information and monitoring orientation information of each monitoring camera are obtained to facilitate subsequent analysis of the current shooting range of each monitoring camera; the target cameras are determined one by one, and the imaging cone space of the target camera is determined based on the installation position coordinates, current shooting direction and field of view of the target camera; based on the focal length and resolution of the target camera, the clear imaging distance interval is evaluated to intercept the clear imaging space from the imaging cone space to obtain the range within which the target camera can clearly shoot; the clear imaging space of each target camera is superimposed to determine the monitoring coverage area in the monitoring area model.

[0072] 3. Based on the common area in the monitoring area model, a number of spatial grids are divided, and monitoring rating signals are regularly generated according to the evaluation cycle, so as to perform the monitoring level evaluation work on each spatial grid later; the monitoring rating signal is received to determine each spatial grid as a target grid one by one, and the proportion of the time and the number of times the target grid is in the frame in the previous analysis period are counted, so as to calculate the grid monitoring level of the target grid according to the monitoring rating rules, so as to determine the degree of monitoring of the target grid by the monitoring camera; based on the grid monitoring level and distribution of each target grid, the partition monitoring level of each partition in the monitored area is evaluated, so as to facilitate the subsequent adoption of different monitoring strategies for different partition monitoring levels of each monitoring partition. BRIEF DESCRIPTION OF THE DRAWINGS

[0073] Figure 1 It is a flow chart of the regional security monitoring method based on the Internet of Things in Example 1 of the present application.

[0074] Figure 2 It is a principle block diagram of a regional security monitoring system based on the Internet of Things in Example 2 of the present application.

[0075] Figure 3 It is a schematic diagram of the equipment in Example 3 of the present application. DETAILED DESCRIPTION

[0076] The following is combined with Figures 1 to 3 This application is described in further detail.

[0077] Embodiment 1

[0078] Reference Figure 1 The present application discloses a regional security monitoring method based on the Internet of Things, which specifically includes the following steps:

[0079] S10: Obtain a building planning drawing of the area to be monitored to create a monitoring area model, obtain monitoring deployment information, and mark each monitoring camera in the monitoring area model.

[0080] In this embodiment, the building planning drawings record the modeling parameter information of each building in the monitored area, including the location, size, shape, light transmittance and other parameters used for building modeling; the monitoring camera is associated with the corresponding monitoring position information.

[0081] Specifically, the architectural planning drawings of the area to be monitored are obtained, and a monitoring area model is created in a three-dimensional modeling program according to the modeling parameter information of each building in the area to be monitored, so as to facilitate building information modeling processing of the area to be monitored. Preferably, the three-dimensional modeling program can be specifically BIM software; the monitoring deployment information is obtained, and each monitoring camera is marked in the monitoring area model, and each monitoring camera is associated with monitoring orientation information, so as to facilitate subsequent analysis of the monitoring range of each monitoring camera.

[0082] S20: Acquire monitoring parameter information of each monitoring camera in real time, and evaluate the monitoring coverage area of ​​each monitoring camera in the monitoring area model based on the monitoring position information and monitoring parameter information of each monitoring camera.

[0083] Specifically, the monitoring parameter information of each monitoring camera is obtained in real time, combined with the monitoring position information, to evaluate the current monitoring coverage area of ​​each monitoring camera in the monitoring area model, so as to know the coverage and overlap of the monitoring range of each monitoring camera.

[0084] Wherein, in step S20, it includes:

[0085] S21: Acquire monitoring parameter information and monitoring position information of each monitoring camera based on a preset update cycle.

[0086] In this embodiment, the update cycle refers to the period in which a preset application reacquires the current monitoring parameter information. Preferably, the update cycle can be 10 seconds; the monitoring orientation information includes the installation position coordinates and the initial shooting direction of the monitoring camera. The shooting direction refers to the direction of the ray formed by the endpoint at the camera lens along the optical axis; the monitoring parameter information includes the focal length, focal length, field of view, cropping factor, current shooting direction, shooting direction range, and resolution of the monitoring camera.

[0087] Specifically, the current monitoring parameter information and monitoring position information of each monitoring camera are obtained based on the update cycle, so as to subsequently analyze the current shooting range of each monitoring camera.

[0088] S22: Determine the target cameras one by one, determine the imaging cone space of the target camera based on the installation position coordinates, current shooting direction and field of view angle of the target camera, evaluate the clear imaging distance interval based on the focal length and resolution of the target camera, and intercept the clear imaging space from the imaging cone space based on the clear imaging distance interval.

[0089] In this embodiment, the target camera refers to the surveillance camera selected as the evaluation object, and all target objects in this embodiment refer to the objects selected as the analysis targets; the clear imaging distance interval is specifically a length interval, where the distance refers to the distance between the target and the camera lens, and the upper limit of the clear imaging distance interval is determined by parameters related to the camera imaging clarity, and the lower limit of the clear imaging interval is determined by the focal length of the camera. The specific setting rules can be adjusted according to actual needs, and the purpose is to determine the distance range of the camera's clear imaging.

[0090] Specifically, the target cameras are determined one by one, and the imaging cone space of the target camera is determined based on the installation position coordinates, current shooting direction and field of view angle of the target camera. Based on the focal length and resolution of the target camera, the clear imaging distance range is evaluated to intercept the clear imaging space from the imaging cone space to obtain the range in which the target camera can capture clearly.

[0091] S23: Determine the monitoring coverage area in the monitoring area model based on the superposition results of the clear imaging spaces of each target camera.

[0092] Specifically, the clear imaging space of each target camera is superimposed to determine the monitoring coverage area in the monitoring area model.

[0093] S30: Based on the monitoring coverage of each area in the monitoring area model and the preset monitoring rating rules, the zone monitoring level of each monitoring zone in the area to be monitored is evaluated.

[0094] Specifically, according to the monitoring coverage of each area in the monitoring area model and the monitoring rating rules, the partition monitoring level of each monitoring partition is evaluated to obtain the monitoring degree of each partition relative to the monitoring camera.

[0095] Wherein, in step S30, it includes:

[0096] S31: Divide a number of spatial grids based on the common area in the monitoring area model, and generate a monitoring rating signal based on a preset evaluation cycle.

[0097] Specifically, a number of space grids are divided based on the common area in the monitoring area model, and monitoring rating signals are regularly generated according to the evaluation cycle, so as to perform the monitoring level evaluation work on each space grid later.

[0098] S32: receiving a monitoring rating signal, determining target squares one by one, counting the percentage of the target square's in-frame time, the number of in-frame times, and the monitoring rating rules in a previously preset analysis period, and calculating the square monitoring level of the target square.

[0099] In this embodiment, the target square refers to the spatial square selected as the analysis target; when more than half of the space in the target square is within the clear imaging range, the target square is in the frame state; when the target square reaches a preset frame time in the frame state, an frame count is accumulated; the monitoring rating rules include a calculation formula for the square monitoring level; the monitoring partition is an area in a public area divided according to function and including several spatial squares, such as a street, an alley, a square or an open space, etc.; the square monitoring level includes several integer levels.

[0100] Among them, the calculation formula of the grid monitoring level is:

[0101]

[0102] i is the identification information of the spatial grid, L Ui is the grid monitoring level of spatial grid i, R i is the proportion of the frame duration corresponding to spatial grid i, F i is the number of shots corresponding to spatial grid i. When counting the shot duration and shot frequency, it is necessary to superimpose the shot duration and shot frequency detected by all surveillance cameras. i 、F i Both have upper limits, k R , k F is the weight coefficient corresponding to the proportion of the duration of the scene and the number of scenes, and L0 is the base number for the level evaluation; So The floor rounding expression for the value to be rounded.

[0103] Specifically, a monitoring rating signal is received to identify each spatial grid as a target grid one by one, and the percentage of time and the number of times the target grid is in the frame in the previous analysis period are counted, so as to calculate the grid monitoring level of the target grid according to the monitoring rating rules, so as to determine the degree of monitoring of the target grid by the surveillance camera.

[0104] S33: Based on the grid monitoring level and distribution of each target grid, the partition monitoring level of each monitoring partition in the area to be monitored is evaluated.

[0105] Specifically, based on the grid monitoring level and distribution of each target grid, the partition monitoring level of each partition in the area to be monitored is evaluated, so that different monitoring strategies can be adopted according to the different partition monitoring levels of each monitoring partition.

[0106] Before step S33, the following steps are included:

[0107] S331: Based on the historical monitoring images of the area to be monitored, the number and position of personnel units in the historical monitoring images are identified through an image recognition algorithm, so as to count the time period area flow of people entering each monitoring partition by time period unit.

[0108] In this embodiment, the time period unit refers to the unit time set for evaluating the flow of people in different time periods. Preferably, one time period unit is 1 hour; the flow of people in the time period area refers to the flow of people that has appeared in a specific monitoring area in a specific time period unit, among which a pedestrian, a motor vehicle or a non-motor vehicle is counted as one person.

[0109] Specifically, before evaluating the partition monitoring level of the monitoring partition, the image recognition algorithm is used to process the historical monitoring images of the monitored area to identify the number and location of personnel units in the historical monitoring images, and then the time period flow of people entering each monitoring partition is counted by time period unit, so as to facilitate the analysis of the flow of people in each monitoring partition in the monitored area at different time periods.

[0110] S332: Calculate the crowd flow impact coefficient corresponding to each monitoring zone based on the crowd flow in the time period area.

[0111] In this embodiment, j is the identification information of the monitoring partition, L Dj is the partition monitoring level of monitoring partition j, xj is the identification information of the spatial grid in monitoring partition j, xj∈i, L Uxj is the monitoring level of the spatial grid xj, λ1 is the flow influence coefficient, k1 is the flow influence assessment coefficient, P is the flow of people in the time period, λ2 is the adjacent influence parameter, k2 is the adjacent influence assessment coefficient, minadj{L Uxj} is the minimum cell monitoring level among the adjacent cells of the spatial cell xj, AL UxjAssign a value to the monitoring level of the spatial grid xj, N xj To monitor the number of spatial grids in partition j.

[0112] The calculation formula of the flow impact parameter is:

[0113] λ1=k1P

[0114] Specifically, based on the regional pedestrian flow in the time period, the corresponding pedestrian flow impact coefficient of each monitoring zone is calculated to facilitate the subsequent evaluation of the impact of the pedestrian flow on the safety of the monitoring zone.

[0115] S333: When the cell monitoring level of the target cell is lower than the first threshold, the cell monitoring levels of several corresponding adjacent cells are obtained, and the adjacent influence parameter is determined based on the lowest cell monitoring level.

[0116] In this embodiment, the first threshold refers to a threshold used to evaluate whether the grid monitoring level is too low. Preferably, the first threshold can be set to 0.9;

[0117] The calculation formula of the adjacency influence parameter is:

[0118] λ2=k2minadj{L Uxj}

[0119] Specifically, since there may be some spatial grids within the monitoring range at the edge of the monitoring range of the surveillance camera, and the inflow and outflow of personnel in these spatial grids can be analyzed based on the flow of personnel within the monitoring range, when the grid monitoring level of the target grid is lower than the first threshold, the adjacency influence coefficient of the target grid is determined according to the lowest grid monitoring level among several adjacent grids, so as to facilitate a more scientific evaluation of the degree of monitoring of the spatial grids at the edge of the monitoring range in the future.

[0120] S334: Based on the adjacency influence parameter of the target square and the crowd flow influence coefficient of the monitoring zone, the corresponding square monitoring level value is calculated.

[0121] In this embodiment, the calculation formula for assigning the grid monitoring level is:

[0122] AL Uxj =λ1(L Uxj +λ2)

[0123] The calculation formula for the partition monitoring level is:

[0124]

[0125] Among them, the superscript and subscript values ​​of the summation formula can be set according to actual needs, and the numbering rules of the identification information can also be set and adjusted according to actual needs; the partition monitoring level can be a non-integer, such as level 0.1, and the specific grading order of magnitude can be determined according to actual needs.

[0126] Specifically, based on the adjacency influence parameter and the crowd flow influence coefficient of the target square, the square monitoring level assignment of the target square is calculated, so as to more scientifically evaluate the monitoring degree of the target square.

[0127] S40: Generate corresponding warning instructions based on the partition monitoring level and match the corresponding inspection plan.

[0128] Specifically, an early warning instruction is generated according to the partition monitoring level and a corresponding inspection plan is matched, so as to inform the security guards to focus on manual inspections of areas with low monitoring levels.

[0129] Wherein, in step S40, it includes:

[0130] S41: Compare the monitoring level of each partition with a preset inspection threshold, define the monitoring partition whose monitoring level is less than the inspection threshold as a partition to be inspected and send it to the inspection terminal.

[0131] In this embodiment, the inspection threshold refers to a threshold used to determine whether the monitored degree corresponding to the partition monitoring level has reached a standard requiring manual inspection.

[0132] Specifically, the monitoring partitions whose partition monitoring levels are less than the inspection threshold are defined as partitions to be inspected and sent to the inspection terminal, so as to prompt the inspection personnel to perform targeted inspection work on the monitoring partitions with a low degree of monitoring.

[0133] S42: When a sudden change in the partition monitoring level is detected, a corresponding monitoring image detection instruction is generated to evaluate the image anomaly type of each monitoring camera through an image recognition algorithm.

[0134] In this embodiment, the level mutation can be determined by comparing the change in the partition monitoring level per unit time with a preset specific threshold. For example, when the change in the partition monitoring level per unit time is greater than 0.5 levels, it is judged that a level mutation has occurred; the monitoring image detection instruction refers to an instruction used to execute an image recognition algorithm to identify whether there are abnormal phenomena such as missing or blurred images in the monitoring image.

[0135] Specifically, when a sudden change in the partition monitoring level is detected, it is considered that the camera is damaged, and a monitoring image detection instruction is generated to identify whether there is an abnormality in the monitoring image through an image recognition algorithm and determine the type of image abnormality.

[0136] S43: If the image abnormality type is device damage, the monitoring camera based on the device damage generates device inspection information and sends it to the inspection terminal.

[0137] Specifically, when the image anomaly type is equipment damage, equipment inspection information is generated based on the damaged surveillance camera and sent to the inspection terminal, so as to inform the inspection personnel to check the cause of the damage of the surveillance camera during the inspection.

[0138] Wherein, after step S41, the regional security monitoring method based on the Internet of Things further includes:

[0139] S411: Mark the partitions to be inspected and the high-definition cameras in the monitoring area model.

[0140] In this embodiment, a high-definition camera refers to a monitoring camera whose monitoring parameter information meets a preset high-definition standard, wherein the high-definition standard can be set according to actual needs.

[0141] Specifically, high-definition cameras are selected from various surveillance cameras through preset high-definition standards, and the locations of the partitions to be inspected and the high-definition cameras are marked in the monitoring area model to facilitate subsequent analysis and optimization of the monitoring expansion plan.

[0142] S412: Determine the target partitions to be inspected one by one, and based on the target partitions to be inspected and the installation position coordinates and shooting direction range of each high-definition camera, analyze the high-definition camera whose optical axis can point to the target partitions to be inspected after one refraction and mark it as the corresponding alternative camera, and mark the corresponding refraction position of the alternative camera in the monitoring area model.

[0143] In this embodiment, when performing the optical axis refraction analysis, the refraction angle has a value range of 15-75°, and the refraction position is located on the building wall.

[0144] Specifically, the target partitions to be inspected are determined one by one. Based on the position of the partition to be inspected and the installation position coordinates and shooting direction range of each high-definition camera, an optical analysis plug-in is used to analyze the high-definition camera that can point to the target partition to be inspected after one refraction. These high-definition cameras are marked as alternative cameras corresponding to the target partition to be inspected, and the alternative cameras and the corresponding refraction positions are marked in the monitoring area model.

[0145] S413: Simulate the setting of reflectors at various refraction positions in the monitoring area model, set the optimization goal of maximizing the monitoring of the partition to be inspected, evaluate the installation angles of the candidate cameras and the corresponding reflectors through the automatic optimization algorithm, determine the optimal reflection combination of the candidate cameras and the reflectors, generate monitoring optimization information based on the reflection combination that maximizes the monitoring of the partition to be inspected, and send it to the inspection terminal.

[0146] Specifically, the setting of reflectors at various refraction positions is simulated in the monitoring area model, and the optimization goal of maximizing the monitoring of the partition to be inspected is set. The installation angles of the alternative cameras and the corresponding reflectors are discarded through an automatic optimization algorithm so as to select the optimal reflection combination from several reflection combinations consisting of alternative cameras and reflectors. Monitoring optimization information is generated according to the optimal reflection combination and sent to the inspection terminal, so that the inspection personnel can increase the monitoring range of the monitoring camera by setting reflectors in the area to be monitored and adjusting the camera angle, thereby reducing the area that requires regular manual inspections and improving the detection rate of safety risks.

[0147] It should be understood that the serial numbers of the steps in the above embodiments do not imply a sequence of execution. The execution sequence 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 the present application.

[0148] Embodiment 2

[0149] A regional security monitoring system based on the Internet of Things, which corresponds to the regional security monitoring method based on the Internet of Things in the above embodiment.

[0150] like Figure 2 As shown in the figure, the regional security monitoring system based on the Internet of Things includes a monitoring area model creation module, a monitoring coverage area evaluation module, a partition monitoring level evaluation module and an inspection plan matching module. The detailed description of each functional module is as follows:

[0151] A monitoring area model creation module is used to obtain the architectural planning drawings of the area to be monitored to create a monitoring area model, obtain monitoring deployment information, and mark each monitoring camera in the monitoring area model;

[0152] A monitoring coverage area evaluation module is used to obtain monitoring parameter information of each monitoring camera in real time, and evaluate the monitoring coverage area of ​​each monitoring camera in the monitoring area model based on the monitoring position information and monitoring parameter information of each monitoring camera;

[0153] A zone monitoring level assessment module is used to assess the zone monitoring level of each monitoring zone in the monitored area based on the monitoring coverage of each zone in the monitoring area model and preset monitoring rating rules;

[0154] The inspection plan matching module is used to generate corresponding early warning instructions based on the partition monitoring level and match the corresponding inspection plan.

[0155] Among them, the monitoring coverage area assessment module also includes:

[0156] The camera information analysis submodule is used to obtain the monitoring parameter information and monitoring position information of each monitoring camera based on a preset update cycle;

[0157] A clear imaging space determination submodule is used to determine the target cameras one by one, determine the imaging cone space of the target camera based on the installation position coordinates, current shooting direction and field angle of the target camera, evaluate the clear imaging distance interval based on the focal length and resolution of the target camera, and intercept the clear imaging space from the imaging cone space based on the clear imaging distance interval;

[0158] The clear imaging space superposition submodule is used to determine the monitoring coverage area in the monitoring area model based on the superposition results of the clear imaging spaces of each target camera.

[0159] Among them, the zoning monitoring level assessment module also includes:

[0160] A monitoring rating signal generation submodule, used to divide a number of spatial grids based on a common area in the monitoring area model, and generate a monitoring rating signal based on a preset evaluation period;

[0161] The grid monitoring level calculation submodule is used to receive the monitoring rating signal, determine the target grids one by one, count the proportion of the target grid in the frame time, the number of times the target grid is in the frame and the monitoring rating rules in the previous preset analysis period, and calculate the grid monitoring level of the target grid;

[0162] The partition monitoring level calculation submodule is used to evaluate the partition monitoring level of each monitoring partition in the monitored area based on the grid monitoring level and distribution of each target grid.

[0163] Among them, the partition monitoring level calculation submodule also includes:

[0164] The time period area human flow statistics submodule is used to identify the number and location of personnel units in the historical monitoring images of the monitored area through an image recognition algorithm based on the historical monitoring images of the monitored area, so as to count the time period area human flow entering each monitoring zone by time period unit;

[0165] The crowd flow impact coefficient calculation submodule is used to calculate the crowd flow impact coefficient corresponding to each monitoring zone based on the crowd flow in the time period area;

[0166] The adjacency influence parameter determination submodule is used to obtain the corresponding grid monitoring levels of several adjacent grids when the grid monitoring level of the target grid is lower than the first threshold, and determine the adjacency influence parameter based on the lowest grid monitoring level;

[0167] The grid monitoring level assignment calculation submodule is used to calculate the corresponding grid monitoring level assignment based on the adjacency influence parameter of the target grid and the crowd influence coefficient of the monitoring zone in which it is located.

[0168] Among them, the inspection plan matching module also includes:

[0169] The submodule for defining the partitions to be inspected is used to compare the monitoring level of each partition with the preset inspection threshold, define the monitoring partitions whose monitoring level is less than the inspection threshold as the partitions to be inspected and send them to the inspection terminal;

[0170] The image anomaly type assessment submodule is used to generate corresponding monitoring image detection instructions when a sudden change in the partition monitoring level is detected, so as to assess the image anomaly type of each monitoring camera through an image recognition algorithm;

[0171] The equipment inspection information generation submodule is used to generate equipment inspection information based on the monitoring camera of the damaged equipment and send it to the inspection terminal if the image abnormality type is equipment damage.

[0172] The submodule for defining the partition to be inspected also includes:

[0173] Monitoring optimization pre-marking submodule, used to mark the partitions to be inspected and high-definition cameras in the monitoring area model;

[0174] The refraction position analysis submodule is used to determine the target partitions to be inspected one by one, and based on the target partitions to be inspected and the installation position coordinates and shooting direction range of each high-definition camera, analyze the high-definition camera whose optical axis can point to the target partitions to be inspected after one refraction and mark it as the corresponding candidate camera, and mark the refraction position corresponding to the candidate camera in the monitoring area model;

[0175] The monitoring optimization information generation submodule is used to simulate the setting of reflectors at various refraction positions in the monitoring area model, set the optimization goal of maximizing the monitoring of the partition to be inspected, evaluate the installation angles of each alternative camera and the corresponding reflector through an automatic optimization algorithm, determine the optimal reflection combination of the alternative camera and the reflector, and generate monitoring optimization information based on the reflection combination that maximizes the monitoring of the partition to be inspected and send it to the inspection terminal.

[0176] For the specific limitations of the regional security monitoring system based on the Internet of Things, please refer to the limitations of the regional security monitoring method based on the Internet of Things in the above text, which will not be repeated here; the various modules in the above-mentioned regional security monitoring system based on the Internet of Things can be implemented in whole or in part through software, hardware and their combination; the above-mentioned modules can be embedded in or independent of the processor in the computer device in the form of hardware, or can be stored in the memory of the computer device in the form of software, so that the processor can call and execute the corresponding operations of the above modules.

[0177] Embodiment 3

[0178] A computer device, which may be a server, may have an internal structure as shown in Figure 3As shown. The computer device includes a processor, a memory, a network interface and a database connected through a system bus. Among them, 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 the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as building planning drawings, monitoring area models, monitoring deployment information, monitoring parameter information, monitoring orientation information, monitoring parameter information, monitoring coverage areas, monitoring coverage conditions, monitoring rating rules, partition monitoring levels, early warning instructions and inspection plans. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, a regional security monitoring method based on the Internet of Things is implemented.

[0179] 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, wherein the processor implements the following steps when executing the computer program:

[0180] S10: Obtaining a building planning drawing of the area to be monitored to create a monitoring area model, and obtaining monitoring deployment information to mark each monitoring camera in the monitoring area model;

[0181] S20: acquiring monitoring parameter information of each monitoring camera in real time, and evaluating the monitoring coverage area of ​​each monitoring camera in the monitoring area model based on the monitoring position information and monitoring parameter information of each monitoring camera;

[0182] S30: Based on the monitoring coverage of each area in the monitoring area model and the preset monitoring rating rules, the monitoring level of each monitoring area in the area to be monitored is evaluated;

[0183] S40: Generate corresponding warning instructions based on the partition monitoring level and match the corresponding inspection plan.

[0184] In one embodiment, a computer readable storage medium is provided, on which a computer program is stored, and when the computer program is executed by a processor, the following steps are implemented:

[0185] S10: Obtaining a building planning drawing of the area to be monitored to create a monitoring area model, and obtaining monitoring deployment information to mark each monitoring camera in the monitoring area model;

[0186] S20: acquiring monitoring parameter information of each monitoring camera in real time, and evaluating the monitoring coverage area of ​​each monitoring camera in the monitoring area model based on the monitoring position information and monitoring parameter information of each monitoring camera;

[0187] S30: Based on the monitoring coverage of each area in the monitoring area model and the preset monitoring rating rules, the monitoring level of each monitoring area in the area to be monitored is evaluated;

[0188] S40: Generate corresponding warning instructions based on the partition monitoring level and match the corresponding inspection plan.

[0189] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and 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 the present 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. As an illustration and not limitation, RAM is available in many 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).

[0190] Those skilled in the art can clearly understand that for the convenience and simplicity 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.

[0191] The embodiments described above 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, it should be understood by those skilled in the art that the technical solutions described in the aforementioned embodiments may still be modified, or some of the features thereof may be replaced by equivalents. Such modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application, and should all be included in the protection scope of the present application.

Claims

1. A regional security monitoring method based on the Internet of Things, characterized in that: include: Obtain architectural planning drawings of the area to be monitored to create a monitoring area model, obtain monitoring deployment information, and mark each monitoring camera in the monitoring area model; Acquire the monitoring parameter information of each monitoring camera in real time, and evaluate the monitoring coverage area of ​​each monitoring camera in the monitoring area model based on the monitoring position information and monitoring parameter information of each monitoring camera; Based on the monitoring coverage of each area in the monitoring area model and the preset monitoring rating rules, the monitoring level of each monitoring area in the area to be monitored is evaluated; Generate corresponding warning instructions based on the partition monitoring level and match the corresponding inspection plan; The building planning drawings record the modeling parameter information of each building in the area to be monitored; The monitoring camera is associated with corresponding monitoring position information.

2. The method for regional security monitoring based on the Internet of Things according to claim 1, characterized in that: The monitoring position information includes the installation position coordinates and the initial shooting direction of the monitoring camera; the monitoring parameter information includes the focal length, focal length, field of view, cropping factor, current shooting direction, shooting direction range, and resolution of the monitoring camera; The real-time acquisition of monitoring parameter information of each monitoring camera, and based on the monitoring position information and monitoring parameter information of each monitoring camera, evaluating the monitoring coverage area of ​​each monitoring camera in the monitoring area model, includes: Acquire monitoring parameter information and monitoring position information of each monitoring camera based on a preset update cycle; Determine the target cameras one by one, determine the imaging cone space of the target cameras based on the installation position coordinates, current shooting direction and field of view angle of the target cameras, evaluate the clear imaging distance interval based on the focal length and resolution of the target cameras, and intercept the clear imaging space from the imaging cone space based on the clear imaging distance interval; The monitoring coverage area is determined in the monitoring area model based on the superposition results of the clear imaging space of each target camera.

3. The method for regional security monitoring based on the Internet of Things according to claim 1, characterized in that: The step of evaluating the zone monitoring level of each monitoring zone in the monitored area based on the monitoring coverage of each zone in the monitoring area model and the preset monitoring rating rules includes: Divide a number of spatial grids based on the common areas in the monitoring area model, and generate monitoring rating signals based on a preset evaluation cycle; Receive the monitoring rating signal, determine the target squares one by one, count the percentage of the target squares in the frame during a previously preset analysis period, the number of times they are in the frame, and the monitoring rating rules, and calculate the square monitoring level of the target squares; Based on the grid monitoring level and distribution of each target grid, evaluate the sub-district monitoring level of each monitoring sub-district in the area to be monitored; When more than half of the space in the target square is within the clear imaging range, the target square is in the frame state; when the target square reaches a preset frame time in the frame state, an frame count is accumulated; the monitoring rating rule includes a calculation formula for the square monitoring level; the monitoring partition is an area including several space squares divided according to functions in the public area; The calculation formula of the grid monitoring level is: i is the identification information of the spatial grid, L Ui is the grid monitoring level of spatial grid i, R i is the proportion of the frame duration corresponding to spatial grid i, F i is the number of shots corresponding to spatial grid i. When counting the shot duration and shot frequency, it is necessary to superimpose the shot duration and shot frequency detected by all surveillance cameras. i 、F i Both have upper limits, k R , k F is the weight coefficient corresponding to the proportion of the duration of the scene and the number of scenes, and L0 is the base number for the level evaluation; So The floor rounding expression for the value to be rounded.

4. The method for regional security monitoring based on the Internet of Things according to claim 3 is characterized in that: Before evaluating the partition monitoring level of each monitoring partition in the to-be-monitored area based on the grid monitoring level and distribution of each target grid, the following steps are included: Based on the historical surveillance images of the area to be monitored, the number and location of personnel units in the historical surveillance images are identified through image recognition algorithms, so as to count the time period area flow of people entering each monitoring zone by time period unit; Based on the flow of people in the time period area, calculate the flow impact coefficient corresponding to each monitoring zone; When the cell monitoring level of the target cell is lower than the first threshold, obtaining the cell monitoring levels of several corresponding adjacent cells, and determining the adjacent influence parameter based on the lowest cell monitoring level; Based on the adjacent influence parameters of the target square and the crowd influence coefficient of the monitoring zone, the corresponding square monitoring level is calculated; The calculation formula of the flow influencing parameter is: λ1=k1P The calculation formula of the adjacency influence parameter is: λ2=k1minadj{L Uxj } The calculation formula for assigning the grid monitoring level is: AL Uxj =λ1(L Uxj +λ2) The calculation formula of the partition monitoring level is: j is the identification information of the monitoring partition, L Dj is the partition monitoring level of monitoring partition j, xj is the identification information of the spatial grid in monitoring partition j, xj∈i, L Uxj is the monitoring level of the spatial grid xj, λ1 is the flow influence coefficient, k1 is the flow influence assessment coefficient, P is the flow of people in the time period, λ2 is the adjacent influence parameter, k2 is the adjacent influence assessment coefficient, minadj{L Uxj } is the minimum cell monitoring level among the adjacent cells of the spatial cell xj, AL Uxj Assign a value to the monitoring level of the spatial grid xj, N xj To monitor the number of spatial grids in partition j.

5. The regional security monitoring method based on the Internet of Things according to claim 1 is characterized in that: The generating of corresponding warning instructions based on the partition monitoring level and matching corresponding inspection plans include: Compare the monitoring level of each partition with the preset inspection threshold, define the monitoring partition whose monitoring level is less than the inspection threshold as the partition to be inspected and send it to the inspection terminal; When a sudden change in the partition monitoring level is detected, a corresponding monitoring image detection instruction is generated to evaluate the image anomaly type of each monitoring camera through an image recognition algorithm; If the image anomaly type is equipment damage, the monitoring camera based on the equipment damage generates equipment inspection information and sends it to the inspection terminal.

6. The regional security monitoring method based on the Internet of Things according to claim 5 is characterized in that: The step of comparing the monitoring level of each partition with a preset inspection threshold and defining the monitoring partition whose monitoring level is less than the inspection threshold as the partition to be inspected includes: Mark the areas to be inspected and the HD cameras in the monitoring area model; Determine the target inspection zones one by one, and based on the target inspection zones and the installation position coordinates and shooting direction range of each HD camera, analyze the HD cameras whose optical axes can point to the target inspection zones after one refraction and mark them as corresponding candidate cameras, and mark the corresponding refraction positions of the candidate cameras in the monitoring area model; In the monitoring area model, it is simulated to set up reflectors at various refraction positions, set the optimization goal of maximizing the monitoring of the partition to be inspected, evaluate the installation angles of each candidate camera and the corresponding reflector through the automatic optimization algorithm, determine the optimal reflection combination of the candidate camera and the reflector, and generate monitoring optimization information based on the reflection combination of the partition to be inspected that maximizes the monitoring and sends it to the inspection terminal; The high-definition camera refers to a monitoring camera whose monitoring parameter information meets the preset high-definition standard; when performing optical axis refraction analysis, the refraction angle ranges from 15 to 75°, and the refraction position is located on the building wall.

7. A regional security monitoring system based on the Internet of Things, characterized in that: The regional security monitoring method based on the Internet of Things applied to any one of claims 1 to 6 comprises: A monitoring area model creation module is used to obtain the architectural planning drawings of the area to be monitored to create a monitoring area model, obtain monitoring deployment information, and mark each monitoring camera in the monitoring area model; A monitoring coverage area evaluation module is used to obtain monitoring parameter information of each monitoring camera in real time, and evaluate the monitoring coverage area of ​​each monitoring camera in the monitoring area model based on the monitoring position information and monitoring parameter information of each monitoring camera; A zone monitoring level assessment module is used to assess the zone monitoring level of each monitoring zone in the monitored area based on the monitoring coverage of each zone in the monitoring area model and preset monitoring rating rules; Inspection plan matching module, used to generate corresponding warning instructions based on the partition monitoring level and match the corresponding inspection plan; The building planning drawings record the modeling parameter information of each building in the area to be monitored; the monitoring cameras are associated with corresponding monitoring position information.

8. The regional security monitoring system based on the Internet of Things according to claim 7 is characterized in that: The monitoring coverage area assessment module includes: The camera information analysis submodule is used to obtain the monitoring parameter information and monitoring position information of each monitoring camera based on a preset update cycle; A clear imaging space determination submodule is used to determine the target cameras one by one, determine the imaging cone space of the target camera based on the installation position coordinates, current shooting direction and field angle of the target camera, evaluate the clear imaging distance interval based on the focal length and resolution of the target camera, and intercept the clear imaging space from the imaging cone space based on the clear imaging distance interval; A clear imaging space superposition submodule, used to determine the monitoring coverage area in the monitoring area model based on the superposition results of the clear imaging spaces of each target camera; The monitoring position information includes the installation position coordinates and initial shooting direction of the monitoring camera; the monitoring parameter information includes the focal length, focal length, field of view, cropping factor, current shooting direction, shooting direction range, and resolution of the monitoring camera.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the steps of the regional security monitoring method based on the Internet of Things are implemented as described in any one of claims 1 to 6.

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 regional security monitoring method based on the Internet of Things are implemented as described in any one of claims 1 to 6.

Images