Monitoring camera site selection method and device, medium and equipment

Abstract

The invention provides a monitoring camera site selection method and device, a medium and equipment, and belongs to the technical field of video monitoring layout, and the method comprises the steps: obtaining geographical constraint data and power supply node coordinate data of a region range to be subjected to site selection; acquiring cost distribution data according to the geographical constraint data and the power supply node coordinate data; and according to the geographical constraint data and the cost distribution data, constructing and solving a multi-objective optimization model, and according to a solving result, generating site selection scheme information of the monitoring camera. According to the method, the actual wiring path difficulty from each candidate position to the adjacent power supply node is calculated, and real engineering obstacles such as topographic relief and gradient are incorporated into the cost model. The optimal path planned by using the Dijkstra algorithm can accurately reflect the engineering quantity and material cost of cable laying, avoids the cost underestimation caused by neglecting the terrain in the traditional method, reduces the total cost estimation error, and significantly improves the economy and feasibility of the site selection scheme.

Description

Technical Field

[0001] This invention belongs to the field of video surveillance layout technology, and particularly relates to a method, device, medium and equipment for selecting surveillance camera locations. Background Technology

[0002] In existing surveillance camera site selection technologies, cost estimation often employs simplified models that fail to adequately consider the impact of terrain and geological differences on deployment costs. Traditional methods typically use horizontal distance or regional average costs for rough calculations, ignoring the significant influence of terrain gradient changes (such as steep slopes and depressions) and geological conditions (such as rock layers and loose soil) on construction difficulty. For example, installing cameras in areas with steep slopes requires additional foundation reinforcement costs, while complex geological conditions may increase the difficulty of equipment fixing and cable laying, leading to actual construction costs far exceeding the budget and causing a disconnect between the economics and feasibility of the site selection plan.

[0003] Meanwhile, current technologies often rely primarily on straight-line distance for cabling cost assessments, failing to incorporate detailed analysis using terrain height grid data. In actual deployments, cabling paths between cameras and power supply nodes may traverse complex terrains such as rivers and canyons, significantly increasing cabling difficulty and material consumption. Traditional methods, lacking quantitative analysis of these terrain factors, lead to substantial deviations in cabling cost estimates, and in some cases, the need to abandon site selection due to cabling difficulties, impacting the overall coverage and construction efficiency of the surveillance network. Summary of the Invention

[0004] In view of the shortcomings of the prior art, the present invention provides a method, apparatus, medium and device for selecting the location of surveillance cameras.

[0005] Firstly, the method includes, Obtain geographical constraint data and power supply node coordinate data for the area to be selected; Cost distribution data is obtained based on geographical constraint data and power supply node coordinate data; Based on geographical constraint data and cost distribution data, a multi-objective optimization model is constructed and solved, and the location scheme information of surveillance cameras is generated based on the solution results.

[0006] Furthermore, the geographic constraint data is acquired through multi-source information collection, specifically including: terrain height raster data, terrain gradient raster data, and geological raster data; The power supply node coordinate data is collected through the power sector's infrastructure archives, specifically including the precise geographical coordinates of the power supply facilities.

[0007] Furthermore, the acquisition of cost distribution data specifically includes acquiring location cost grid data and acquiring wiring difficulty grid data, and generating cost distribution data based on the location cost grid data and wiring difficulty grid data; The acquisition of location cost raster data includes, The terrain gradient raster data is normalized; the normalized terrain gradient raster data is multiplied by a third preset weight to obtain terrain cost raster data; the geological raster data is normalized; the normalized geological raster data is multiplied by a fourth preset weight to obtain geological cost raster data; the terrain cost raster data and the geological cost raster data are added together to generate location cost raster data. The acquisition of wiring difficulty raster data includes, Based on the coordinates of each grid cell in the terrain height raster data and the coordinates of the power supply nodes, the Euclidean distance from each grid cell to all power supply nodes is calculated, and the nearest node is selected as the nearest power supply node. Based on the terrain height and gradient data, the Dijkstra algorithm is used to plan the optimal cabling path from the grid cell to the nearest power supply node, and a set of path coordinate data is obtained. The terrain height corresponding to all coordinates in the path coordinate data set is multiplied by the terrain gradient data and then summed to generate the cabling difficulty coefficient corresponding to each grid cell. The cabling difficulty coefficients corresponding to all grid cells are arranged according to their geographical coordinates to form cabling difficulty raster data.

[0008] Furthermore, the step of generating cost distribution data based on location cost raster data and wiring difficulty raster data specifically includes: Multiply the location cost raster data by the first preset weight to obtain weighted location cost raster data; Multiply the wiring difficulty raster data by the second preset weight to obtain the weighted wiring difficulty raster data; The weighted location cost raster data is added to the weighted wiring difficulty raster data to generate cost distribution data.

[0009] Furthermore, the step of solving the multi-objective optimization model based on geographical constraint data and cost distribution data specifically includes: Define an optimization objective set and a constraint set; wherein the optimization objective set includes: monitoring field of view coverage, total deployment cost, and overlap coverage; the constraints include: camera installation location constraints, installation spacing constraints, and overlap coverage constraints. A multi-objective optimization model is constructed based on the set of optimization objectives and the set of constraints.

[0010] Furthermore, the multi-objective optimization model constructed by solving specifically includes, The multi-objective optimization model randomly generates an initial set of camera locations and evaluates the fitness of each location to generate a set of fitness values. Perform non-dominated sorting and elite selection on each fitness value in the fitness value set to generate an elite selection set; Perform crossover and mutation operations on the elite selection set to generate an updated set of camera locations; Determine whether the termination condition is met. If the termination condition is met, output the optimal solution; otherwise, re-solve the multi-objective optimization model until the termination condition is met.

[0011] Secondly, a surveillance camera location selection system, the system comprising: a data acquisition module, a cost data calculation module, and a location scheme generation module; The data acquisition module is used to acquire geographical constraint data and power supply node coordinate data of the area to be selected; The cost data calculation module is used to obtain cost distribution data based on geographical constraint data and power supply node coordinate data; The site selection scheme generation module is used to construct and solve a multi-objective optimization model based on geographical constraint data and cost distribution data, and generate site selection scheme information for surveillance cameras based on the solution results.

[0012] Furthermore, the geographic constraint data is acquired through multi-source information collection, specifically including: terrain height raster data, terrain gradient raster data, and geological raster data; The power supply node coordinate data is collected through the power sector's infrastructure archives, specifically including the precise geographical coordinates of the power supply facilities.

[0013] Furthermore, the cost data calculation module is specifically used to acquire location cost grid data and wiring difficulty grid data, and generate cost distribution data based on the location cost grid data and wiring difficulty grid data; The cost data calculation module is also used for, The terrain gradient raster data is normalized; the normalized terrain gradient raster data is multiplied by a third preset weight to obtain terrain cost raster data; the geological raster data is normalized; the normalized geological raster data is multiplied by a fourth preset weight to obtain geological cost raster data; the terrain cost raster data and the geological cost raster data are added together to generate location cost raster data. The cost data calculation module is also used for, Based on the coordinates of each grid cell in the terrain height raster data and the coordinates of the power supply nodes, the Euclidean distance from each grid cell to all power supply nodes is calculated, and the nearest node is selected as the nearest power supply node. Based on the terrain height and gradient data, the Dijkstra algorithm is used to plan the optimal cabling path from the grid cell to the nearest power supply node, and a set of path coordinate data is obtained. The terrain height corresponding to all coordinates in the path coordinate data set is multiplied by the terrain gradient data and then summed to generate the cabling difficulty coefficient corresponding to each grid cell. The cabling difficulty coefficients corresponding to all grid cells are arranged according to their geographical coordinates to form cabling difficulty raster data.

[0014] Furthermore, the cost data calculation module is specifically used for: Multiply the location cost raster data by the first preset weight to obtain weighted location cost raster data; Multiply the wiring difficulty raster data by the second preset weight to obtain the weighted wiring difficulty raster data; The weighted location cost raster data is added to the weighted wiring difficulty raster data to generate cost distribution data.

[0015] Furthermore, the location scheme generation module is specifically used for, Define an optimization objective set and a constraint set; wherein the optimization objective set includes: monitoring field of view coverage, total deployment cost, and overlap coverage; the constraints include: camera installation location constraints, installation spacing constraints, and overlap coverage constraints. A multi-objective optimization model is constructed based on the set of optimization objectives and the set of constraints.

[0016] Furthermore, the location scheme generation module is specifically used for, The multi-objective optimization model randomly generates an initial set of camera locations and evaluates the fitness of each location to generate a set of fitness values. Perform non-dominated sorting and elite selection on each fitness value in the fitness value set to generate an elite selection set; Perform crossover and mutation operations on the elite selection set to generate an updated set of camera locations; Determine whether the termination condition is met. If the termination condition is met, output the optimal solution; otherwise, re-solve the multi-objective optimization model until the termination condition is met.

[0017] Thirdly, a computer-readable storage medium storing a computer program that, when executed by a processor, implements any of the steps of the surveillance camera location method described above.

[0018] Fourthly, an electronic device includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus. Memory, used to store computer programs; When the processor executes the program stored in the memory, it implements any of the steps of the surveillance camera location method described above.

[0019] Compared with the prior art, the present invention has the following advantages: This invention incorporates real engineering obstacles such as terrain undulations and slope gradients into the cost model by calculating the actual wiring path difficulty (rather than simple straight-line distance) from each candidate location to the nearest power supply node. The optimal path planned using Dijkstra's algorithm can accurately reflect the engineering workload and material costs of cable laying, avoiding the cost underestimation caused by ignoring terrain in traditional methods. This reduces the error in total cost estimation and significantly improves the economy and feasibility of the site selection scheme.

[0020] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention may be realized and obtained by means of the structures pointed out in the description, claims and drawings. Attached Figure Description

[0021] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0022] Figure 1 A schematic flowchart of a surveillance camera location selection method according to the present invention is shown.

[0023] Figure 2 A schematic diagram of a surveillance camera location selection system module according to the present invention is shown. Detailed Implementation

[0024] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0025] In one embodiment of the present invention, such as Figure 1 As shown, a method for selecting the location of a surveillance camera includes the following steps: like Figure 1 As shown, this embodiment of the invention provides a method for selecting the location of a surveillance camera, including the following steps: S1. Obtain the geographical constraint data and power supply node coordinate data of the area to be selected.

[0026] In this implementation, the area to be selected needs to be defined according to actual monitoring requirements, and the spatial boundaries are usually defined by latitude and longitude coordinates or administrative boundaries. Among them, 1. Geographic constraint data is obtained through multi-source information collection, specifically including: (1) Terrain height raster data: The region is divided into equal grid cells, each cell recording basic terrain information such as elevation, reflecting the region's topographic relief characteristics. Data sources may include digital elevation models (DEM), lidar (LiDAR), etc.

[0027] (2) Terrain gradient raster data: Based on terrain height data, the slope or gradient index of each grid is recorded to reflect the steepness and trend of terrain.

[0028] (3) Geological grid data: The geological attributes such as soil type, rock distribution, and foundation bearing capacity of each grid are marked. These can be obtained from geological exploration reports or soil type maps.

[0029] 2. Power supply node coordinate data is collected from the power sector's infrastructure archives, including the precise geographical coordinates of power supply facilities such as substations and distribution boxes, providing a benchmark for subsequent cabling cost analysis.

[0030] Optionally, all raster data should maintain a consistent resolution (e.g., 10 meters × 10 meters) for subsequent calculations.

[0031] S2. Obtain cost distribution data based on geographical constraint data and power supply node coordinate data.

[0032] In this embodiment, the cost distribution data includes location cost grid data and wiring difficulty grid data, and the acquisition process includes: S2.1 Obtain location cost raster data.

[0033] Location cost raster data is obtained by quantifying the impact of terrain gradients and geological conditions on deployment costs. Specific steps include: S2.1.1 Normalize the terrain gradient raster data, mapping the original slope values ​​to the [0,1] interval. For example, if the slope range is 0° to 60°, then a 30° slope in a certain raster will be normalized to 0.5.

[0034] S2.1.2 Multiply the normalized terrain gradient raster data by a third preset weight (e.g., 0.3) to obtain the terrain cost raster data. For example, a normalized value of 0.5 multiplied by a weight of 0.3 results in a terrain cost of 0.15.

[0035] S2.1.3 Normalize the geological raster data; if the original data is a classification value (e.g., soil types are divided into soft soil, clay, sandy soil, and rock layer), cost impact level must be assigned first (e.g., soft soil = 4, rock layer = 1), and then normalized according to the formula (category level - lowest level) / (highest level - lowest level).

[0036] S2.1.4 Multiply the normalized geological raster data by the fourth preset weight (e.g., 0.25) to obtain the geological cost raster data; for example, the normalized value of soft soil is 1, and the geological cost is 0.25 after multiplying by the weight of 0.25.

[0037] S2.1.5 Add the terrain cost raster data and the geological cost raster data to generate the location cost raster data; for example, if the terrain cost of a certain raster is 0.15 and the geological cost is 0.25, then the location cost is 0.4.

[0038] S2.2 Obtain wiring difficulty grid data In this embodiment, the wiring difficulty grid data is obtained by analyzing the path terrain complexity from each grid to the nearest power supply node. Specific steps include: S2.2.1 Based on the coordinates of each grid cell in the terrain height grid data and the coordinates of the power supply nodes, calculate the Euclidean distance from each grid cell to all power supply nodes, and select the nearest node as the nearest power supply node.

[0039] S2.2.2 Based on terrain height and gradient data, the Dijkstra algorithm is used to plan the optimal wiring path from the grid to the nearest power supply node and obtain the path coordinate data set.

[0040] S2.2.3 Multiply the terrain height and terrain gradient data corresponding to all coordinates in the path coordinate data set and sum them to generate the wiring difficulty coefficient for each grid. For example, if a path contains 6 coordinate points with corresponding terrain height data of [10,11,12,23,24,30] and terrain gradient data of [1,1,1,11,1,6], then the wiring difficulty coefficient is 10×1+11×1+12×1+23×11+24×1+30×6=490.

[0041] S2.2.4 Arrange the wiring difficulty coefficients corresponding to all grids according to their geographical coordinates to form wiring difficulty grid data.

[0042] S2.3. Generate cost distribution data based on location cost raster data and wiring difficulty raster data.

[0043] S2.3.1 Multiply the location cost raster data by the first preset weight (e.g., 0.6) to obtain the weighted location cost raster data.

[0044] S2.3.2 Multiply the wiring difficulty grid data by the second preset weight (e.g., 0.4) to obtain the weighted wiring difficulty grid data.

[0045] S2.3.3. Add the weighted location cost raster data and the weighted routing difficulty raster data to generate cost distribution data. For example, if the weighted location cost of a certain raster is 0.24 and the weighted routing difficulty is 196, then the total cost is 196.24.

[0046] S3. Based on geographical constraint data and cost distribution data, construct and solve a multi-objective optimization model, and generate location scheme information for surveillance cameras based on the solution results.

[0047] S3.1 Construct a multi-objective optimization model based on geographical constraint data and cost distribution data.

[0048] S3.1.1 Define the optimization objective set, which includes: 1. Surveillance field of view coverage: Calculate the effective coverage grid ratio by combining camera parameters (field of view, installation height) and terrain height data.

[0049] 2. Total deployment cost: including location cost, cabling cost and equipment cost.

[0050] 3. Overlap Coverage: Statistically measure the proportion of grid cells covered by multiple cameras to control redundancy.

[0051] S3.1.2 Define a set of constraints, where the constraints include: 1. Camera installation location constraints: Exclude areas where the terrain gradient exceeds the threshold (e.g., ≥0.8 after normalization) or where the geological conditions are unstable.

[0052] 2. Installation spacing constraints: Set the minimum and maximum spacing based on the camera's field of view and monitoring distance.

[0053] 3. Overlapping Coverage Constraints: Set upper and lower limits for overlap rate based on regional importance.

[0054] S3.1.3 Construct a multi-objective optimization model based on the set of optimization objectives and the set of constraints.

[0055] S3.2 Solve the constructed multi-objective optimization model.

[0056] S3.2.1 The multi-objective optimization model randomly generates an initial set of camera locations and performs fitness evaluation on each location to generate a set of fitness values.

[0057] S3.2.2 Perform non-dominated sorting and elite selection on each fitness value in the fitness value set to generate an elite selection set.

[0058] S3.2.3 Perform crossover and mutation operations on the elite selection set to generate an updated set of camera locations.

[0059] S3.2.4 Determine whether the termination condition is met (such as the elite set being stable or the maximum number of iterations being reached). If the termination condition is met, output the optimal solution; otherwise, re-solve the multi-objective optimization model until the termination condition is met.

[0060] S3.3 Based on the solution results, the generated site selection scheme information includes a list of geographic coordinates of camera locations, a cost list, a field of view coverage heatmap, and an overlap coverage distribution map.

[0061] In another embodiment of the invention, such as Figure 2 As shown, a surveillance camera location selection system includes the following steps: like Figure 2 As shown, this embodiment of the invention provides a surveillance camera location selection system, which includes: a data acquisition module, a cost data calculation module, and a location selection scheme generation module.

[0062] 1. The data acquisition module is used to acquire the geographical constraint data and power supply node coordinate data of the area to be selected.

[0063] In this implementation, the area to be selected needs to be defined according to actual monitoring requirements, and the spatial boundaries are usually defined by latitude and longitude coordinates or administrative boundaries. The geographic constraint data is obtained through multi-source information collection, specifically including: (1) Terrain height raster data: The region is divided into equal grid cells, each cell recording basic terrain information such as elevation, reflecting the region's topographic relief characteristics. Data sources may include digital elevation models (DEM), lidar (LiDAR), etc.

[0064] (2) Terrain gradient raster data: Based on terrain height data, the slope or gradient index of each grid is recorded to reflect the steepness and trend of terrain.

[0065] (3) Geological grid data: The geological attributes such as soil type, rock distribution, and foundation bearing capacity of each grid are marked. These can be obtained from geological exploration reports or soil type maps.

[0066] The power supply node coordinate data is collected from the power sector's infrastructure archives and includes the precise geographical coordinates of power supply facilities such as substations and distribution boxes, providing a benchmark for subsequent cabling cost analysis.

[0067] Optionally, all raster data should maintain a consistent resolution (e.g., 10 meters × 10 meters) for subsequent calculations.

[0068] 2. The cost data calculation module is used to obtain cost distribution data based on geographical constraint data and power supply node coordinate data.

[0069] In this embodiment, the cost distribution data includes location cost grid data and wiring difficulty grid data, and the acquisition process includes: (1) Obtain location cost raster data.

[0070] Location cost raster data is obtained by quantifying the impact of terrain gradients and geological conditions on deployment costs. Specific steps include: (1.1) Normalize the terrain gradient raster data and map the original slope values ​​to the [0,1] interval. For example, if the slope range is 0° to 60°, then a 30° slope in a certain raster will be normalized to 0.5.

[0071] (1.2) Multiply the normalized terrain gradient raster data by a third preset weight (e.g., 0.3) to obtain the terrain cost raster data. For example, a normalized value of 0.5 multiplied by a weight of 0.3 results in a terrain cost of 0.15.

[0072] (1.3) Normalize the geological raster data; if the original data is a classification value (such as soil type is divided into soft soil, clay, sandy soil and rock layer), it is necessary to first assign a cost impact level (such as soft soil = 4, rock layer = 1), and then normalize it according to the formula (category level - lowest level) / (highest level - lowest level).

[0073] (1.4) Multiply the normalized geological raster data by the fourth preset weight (e.g., 0.25) to obtain the geological cost raster data; for example, the normalized value of soft soil is 1, and the geological cost is 0.25 after multiplying by the weight of 0.25.

[0074] (1.5) Add the terrain cost raster data and the geological cost raster data to generate the location cost raster data; for example, if the terrain cost of a certain raster is 0.15 and the geological cost is 0.25, then the location cost is 0.4.

[0075] (2) Obtaining wiring difficulty grid data In this embodiment, the wiring difficulty grid data is obtained by analyzing the path terrain complexity from each grid to the nearest power supply node. Specific steps include: (2.1) Based on the coordinates of each grid in the terrain height grid data and the coordinates of the power supply nodes, calculate the Euclidean distance from each grid to all power supply nodes, and select the nearest node as the nearest power supply node.

[0076] (2.2) Based on terrain height and gradient data, the Dijkstra algorithm is used to plan the optimal wiring path from the grid to the nearest power supply node and obtain the path coordinate data set.

[0077] (2.3) Multiply the terrain height and terrain gradient data corresponding to all coordinates in the path coordinate data set and sum them to generate the wiring difficulty coefficient for each grid. For example, if a path contains 6 coordinate points with terrain height data of [10,11,12,23,24,30] and terrain gradient data of [1,1,1,11,1,6], then the wiring difficulty coefficient is 10×1+11×1+12×1+23×11+24×1+30×6=490.

[0078] (2.4) Arrange the wiring difficulty coefficients corresponding to all grids according to their geographical coordinates to form wiring difficulty grid data.

[0079] (3) Generate cost distribution data based on location cost raster data and wiring difficulty raster data.

[0080] (3.1) Multiply the location cost raster data by the first preset weight (e.g., 0.6) to obtain the weighted location cost raster data.

[0081] (3.2) Multiply the wiring difficulty grid data by the second preset weight (e.g., 0.4) to obtain the weighted wiring difficulty grid data.

[0082] (3.3) Add the weighted location cost raster data and the weighted wiring difficulty raster data to generate cost distribution data. For example, if the weighted location cost of a certain raster is 0.24 and the weighted wiring difficulty is 196, then the total cost is 196.24.

[0083] 3. The site selection scheme generation module is used to construct and solve a multi-objective optimization model based on geographical constraint data and cost distribution data, and generate site selection scheme information for surveillance cameras based on the solution results.

[0084] (1) Construct a multi-objective optimization model based on geographical constraint data and cost distribution data.

[0085] (1.1) Define the set of optimization objectives, wherein the optimization objectives include: Surveillance field of view coverage: Calculate the effective coverage grid ratio by combining camera parameters (field of view, installation height) and terrain height data.

[0086] Total deployment cost: includes location cost, cabling cost, and equipment cost.

[0087] Overlap coverage: Statistically calculates the proportion of grid cells covered by multiple cameras to control redundancy.

[0088] (1.2) Define a set of constraints, wherein the constraints include: Camera installation location constraints: exclude areas where the terrain gradient exceeds the threshold (e.g., ≥0.8 after normalization) or where the geological conditions are unstable.

[0089] Installation spacing constraints: Set the minimum and maximum spacing based on the camera's field of view and monitoring distance.

[0090] Overlapping constraint: Set upper and lower limits for overlap rate based on regional importance.

[0091] (1.3) Construct a multi-objective optimization model based on the set of optimization objectives and the set of constraints.

[0092] (2) Solve the constructed multi-objective optimization model.

[0093] (2.1) Randomly generate an initial set of camera locations and evaluate the fitness of each location to generate a set of fitness values.

[0094] (2.2) Perform non-dominated sorting and elite selection on each fitness value in the fitness value set to generate an elite selection set.

[0095] (2.3) Perform crossover and mutation operations on the elite selection set to generate an updated set of camera locations.

[0096] (2.4) Determine whether the termination condition is met (such as the elite set being stable or the maximum number of iterations being reached). If it is met, output the optimal solution.

[0097] (3) Based on the solution results, the generated site selection scheme information includes a list of geographic coordinates of camera locations, a cost list, a heat map of field of view coverage, and a map of overlapping coverage distribution.

[0098] Based on the above disclosure, the present invention also provides an electronic device. The electronic device of this embodiment includes at least one processor and at least one storage medium electrically connected to the processor. The storage medium is electrically connected to the processor, wherein the storage medium stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method described above.

[0099] Based on the same inventive concept, the present invention also provides a storage medium storing instructions executable by the at least one processor, the instructions being executed by the at least one processor to enable the at least one processor to perform the method as described above.

[0100] The foregoing description and accompanying drawings fully illustrate embodiments of the invention to enable those skilled in the art to practice them. Other embodiments may include structural and other changes. The embodiments represent only possible variations. Individual components and functions are optional unless explicitly required, and the order of operation may vary. Some portions and features of some embodiments may be included or substituted for portions and features of other embodiments. Embodiments of the invention are not limited to the structures described above and shown in the accompanying drawings, and various modifications and changes may be made without departing from their scope. The scope of the invention is limited only by the appended claims.

Claims

1. A method for selecting the location of a surveillance camera, characterized in that, The method includes, Obtain geographical constraint data and power supply node coordinate data for the area to be selected; Cost distribution data is obtained based on geographical constraint data and power supply node coordinate data; Based on geographical constraint data and cost distribution data, a multi-objective optimization model is constructed and solved, and the location scheme information of surveillance cameras is generated based on the solution results.

2. The method for selecting a location for a surveillance camera according to claim 1, characterized in that, The geographic constraint data is acquired through multi-source information collection, specifically including: terrain height raster data, terrain gradient raster data, and geological raster data; The power supply node coordinate data is collected through the power sector's infrastructure archives, specifically including the precise geographical coordinates of the power supply facilities.

3. The method for selecting a location for a surveillance camera according to claim 1, characterized in that, The acquisition of cost distribution data specifically includes acquiring location cost grid data and wiring difficulty grid data, and generating cost distribution data based on the location cost grid data and wiring difficulty grid data; The acquisition of location cost raster data includes, Normalize the terrain gradient raster data; The normalized terrain gradient raster data is multiplied by the third preset weight to obtain the terrain cost raster data; the geological raster data is normalized; the normalized geological raster data is multiplied by the fourth preset weight to obtain the geological cost raster data; the terrain cost raster data and the geological cost raster data are added together to generate the location cost raster data. The acquisition of wiring difficulty raster data includes, Based on the coordinates of each grid cell in the terrain height grid data and the coordinates of the power supply nodes, calculate the Euclidean distance from each grid cell to all power supply nodes, and select the nearest node as the nearest power supply node. Based on terrain height and gradient data, the Dijkstra algorithm is used to plan the optimal wiring path from the grid to the nearest power supply node, and a set of path coordinate data is obtained. The terrain height corresponding to all coordinates in the set of path coordinate data is multiplied by the terrain gradient data and then summed to generate the wiring difficulty coefficient corresponding to each grid. The wiring difficulty coefficients corresponding to all grids are arranged according to their geographical coordinates to form wiring difficulty grid data.

4. The method for selecting a location for a surveillance camera according to claim 3, characterized in that, The process of generating cost distribution data based on location cost raster data and wiring difficulty raster data specifically includes: Multiply the location cost raster data by the first preset weight to obtain weighted location cost raster data; Multiply the wiring difficulty raster data by the second preset weight to obtain the weighted wiring difficulty raster data; The weighted location cost raster data is added to the weighted wiring difficulty raster data to generate cost distribution data.

5. The method for selecting a location for a surveillance camera according to claim 1, characterized in that, The process of solving the multi-objective optimization model based on geographical constraint data and cost distribution data specifically includes: Define an optimization objective set and a constraint set; wherein the optimization objective set includes: monitoring field of view coverage, total deployment cost, and overlap coverage; the constraints include: camera installation location constraints, installation spacing constraints, and overlap coverage constraints. A multi-objective optimization model is constructed based on the set of optimization objectives and the set of constraints.

6. The method for selecting a location for a surveillance camera according to claim 1, characterized in that, The multi-objective optimization model constructed by solving the problem specifically includes... The multi-objective optimization model randomly generates an initial set of camera locations and evaluates the fitness of each location to generate a set of fitness values. Perform non-dominated sorting and elite selection on each fitness value in the fitness value set to generate an elite selection set; Perform crossover and mutation operations on the elite selection set to generate an updated set of camera locations; Determine if the termination condition is met; if the termination condition is met, output the optimal solution. Conversely, the multi-objective optimization model is solved again until the termination condition is met.

7. A surveillance camera location selection system, characterized in that, The system includes: a data acquisition module, a cost data calculation module, and a site selection scheme generation module; The data acquisition module is used to acquire geographical constraint data and power supply node coordinate data of the area to be selected; The cost data calculation module is used to obtain cost distribution data based on geographical constraint data and power supply node coordinate data; The site selection scheme generation module is used to construct and solve a multi-objective optimization model based on geographical constraint data and cost distribution data, and generate site selection scheme information for surveillance cameras based on the solution results.

8. The surveillance camera location selection system according to claim 7, characterized in that, The geographic constraint data is acquired through multi-source information collection, specifically including: terrain height raster data, terrain gradient raster data, and geological raster data; The power supply node coordinate data is collected through the power sector's infrastructure archives, specifically including the precise geographical coordinates of the power supply facilities.

9. The surveillance camera location selection system according to claim 7, characterized in that, The cost data calculation module is specifically used to acquire location cost grid data and wiring difficulty grid data, and generate cost distribution data based on the location cost grid data and wiring difficulty grid data. The cost data calculation module is also used for, The terrain gradient raster data is normalized; the normalized terrain gradient raster data is multiplied by a third preset weight to obtain terrain cost raster data; the geological raster data is normalized; the normalized geological raster data is multiplied by a fourth preset weight to obtain geological cost raster data; the terrain cost raster data and the geological cost raster data are added together to generate location cost raster data. The cost data calculation module is also used for, Based on the coordinates of each grid cell in the terrain height grid data and the coordinates of the power supply nodes, calculate the Euclidean distance from each grid cell to all power supply nodes, and select the nearest node as the nearest power supply node. Based on terrain height and gradient data, the Dijkstra algorithm is used to plan the optimal wiring path from the grid to the nearest power supply node, and a set of path coordinate data is obtained. The terrain height corresponding to all coordinates in the set of path coordinate data is multiplied by the terrain gradient data and then summed to generate the wiring difficulty coefficient corresponding to each grid. The wiring difficulty coefficients corresponding to all grids are arranged according to their geographical coordinates to form wiring difficulty grid data.

10. The surveillance camera location selection system according to claim 9, characterized in that, The cost data calculation module is specifically used for, Multiply the location cost raster data by the first preset weight to obtain weighted location cost raster data; Multiply the wiring difficulty raster data by the second preset weight to obtain the weighted wiring difficulty raster data; The weighted location cost raster data is added to the weighted wiring difficulty raster data to generate cost distribution data.

11. The surveillance camera location selection system according to claim 7, characterized in that, The location selection scheme generation module is specifically used for, Define an optimization objective set and a constraint set; wherein the optimization objective set includes: monitoring field of view coverage, total deployment cost, and overlap coverage; the constraints include: camera installation location constraints, installation spacing constraints, and overlap coverage constraints. A multi-objective optimization model is constructed based on the set of optimization objectives and the set of constraints.

12. The surveillance camera location selection system according to claim 7, characterized in that, The location selection scheme generation module is specifically used for, The multi-objective optimization model randomly generates an initial set of camera locations and evaluates the fitness of each location to generate a set of fitness values. Perform non-dominated sorting and elite selection on each fitness value in the fitness value set to generate an elite selection set; Perform crossover and mutation operations on the elite selection set to generate an updated set of camera locations; Determine if the termination condition is met; if the termination condition is met, output the optimal solution. Conversely, the multi-objective optimization model is solved again until the termination condition is met.

13. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the surveillance camera location method according to any one of claims 1-6.

14. An electronic device, characterized in that, It includes a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other through the communication bus; Memory, used to store computer programs; When a processor executes a program stored in memory, it implements the steps of the surveillance camera location method according to any one of claims 1-6.

Images