Intelligent linkage method and system for fire prevention holder machine in mountainous area based on cooperative verification

Abstract

The invention provides a cooperative verification-based intelligent linkage method and system for a fire prevention holder machine in a mountainous area, and relates to the technical field of fire prevention in the mountainous area, and the method comprises the steps: constructing a dynamic risk assessment system, collecting data, and outputting a unified data base; dividing the power transmission line into grid units and outputting a dynamic fireproof risk thermodynamic diagram; establishing a preset bit space model and constructing a three-dimensional terrain shielding model, calculating an effective monitoring range of a preset bit, performing spatial superposition on the effective monitoring range and the thermodynamic diagram, and outputting a coverage risk mean value and a monitoring redundancy rate; constructing a multi-dimensional weight calculation system in combination with the state of the PTZ equipment, and outputting a comprehensive inspection weight; an emergency constraint inverse proportion model is adopted to convert the weight into an inspection period, and a dynamic inspection scheduling scheme is output in combination with a task conflict scheduling rule and an emergency response mechanism, so that an inspection strategy is dynamically adjusted according to the real-time risk condition and the monitoring resource distribution condition of each section of the power transmission line, the monitoring capability of a high-risk area is enhanced, and the reliability of the power transmission line is improved. And the resource waste of the low-risk area is reduced.

Description

Technical Field

[0001] This invention relates to the field of mountain fire prevention technology, and in particular to a method and system for intelligent linkage of mountain fire prevention PTZ cameras based on collaborative verification. Background Technology

[0002] As an important component of the power system, the safe and stable operation of transmission lines is directly related to the reliability of the power grid.

[0003] Traditional power transmission line inspections primarily rely on manual patrols and fixed-cycle video surveillance, a method with several shortcomings. First, manual inspections are inefficient, heavily limited by terrain and weather conditions, and struggle to achieve 24 / 7 monitoring. They are particularly inadequate for responding promptly to sudden wildfire hazards in mountainous areas, failing to meet the dynamic protection needs of power transmission lines in these regions. Second, fixed-cycle video surveillance uses a uniform inspection frequency, failing to differentiate management based on the actual risk levels of the transmission lines. Especially in complex terrains like mountainous areas, transmission lines face multiple threats such as wildfires, landslides, and icing, with significant differences in risk levels across different sections. Existing inspection methods cannot effectively identify and address these differences. Finally, the preset positions of mountain fire prevention pan-tilt-zoom (PTZ) cameras are often based on experience, lacking a scientific weighting mechanism that considers average coverage risk and monitoring redundancy. This results in high-risk areas not receiving sufficient monitoring, while low-risk areas consume excessive inspection resources, leading to low monitoring efficiency and resource waste.

[0004] Therefore, it is necessary to provide a method and system for intelligent linkage of mountain fire prevention PTZ cameras based on collaborative verification to solve the above-mentioned technical problems. Summary of the Invention

[0005] To address the aforementioned technical problems, this invention provides a method and system for intelligent linkage of pan-tilt-zoom (PTZ) cameras for fire prevention in mountainous areas based on collaborative verification. This system solves the problem that existing technologies cannot dynamically adjust the inspection strategy of the PTG cameras according to the real-time risk status and monitoring resource distribution of each section of the transmission line, resulting in insufficient monitoring in high-risk areas and waste of resources in low-risk areas.

[0006] The present invention provides an intelligent linkage method for mountain fire prevention PTZ cameras based on collaborative verification, the method comprising: Construct a dynamic risk assessment system for mountain fire prevention PTZ cameras, collect historical wildfire fault data, real-time tower environment data, meteorological fire prevention forecast data and high-precision topographic data, perform spatiotemporal alignment and standardization processing, and output a unified data base. Based on the unified data base, the mountain power transmission lines are divided into multiple grid units, and the dynamic fire risk value of each grid unit is calculated to generate a dynamic fire risk heat map. Establish a spatial model of the preset positions of the mountain fire prevention PTZ camera, calibrate the installation three-dimensional coordinates, field of view and maximum monitoring distance of the mountain fire prevention PTZ camera, construct a three-dimensional terrain occlusion model in combination with lidar scanning, calculate the effective monitoring range of each preset position and spatially overlay it with the dynamic fire risk heat map, and output the average coverage risk and monitoring redundancy rate of each preset position. Based on the average coverage risk and monitoring redundancy rate of each preset position, and combined with the real-time device status of the corresponding PTZ machine, a multi-dimensional weight calculation system is constructed to output the comprehensive inspection weight of each preset position. The comprehensive inspection weights of each preset position are converted into inspection cycles using a mountain emergency constraint inverse proportional model. Combined with the gimbal task conflict scheduling rules and the mountain wildfire emergency response mechanism, a dynamic inspection scheduling scheme is output.

[0007] Preferably, the step of dividing mountain power transmission lines into multiple grid units based on the unified data base and calculating the dynamic fire risk value of each grid unit to generate a dynamic fire risk heat map specifically includes: Based on the unified data base, the mountain power transmission line is divided into multiple grid units according to the complexity of the mountain terrain. Extracting the historical wildfire failure probability for each grid cell Current environmental risk factors and future weather threat levels And the current environmental risk factors This includes temperature deviation, humidity deviation, and vegetation temperature perception deviation; A multi-factor weighted risk calculation model for mountainous areas is adopted, based on the historical wildfire failure probability of each grid cell. The aforementioned current environmental risk factors and the aforementioned future weather threat level Calculate the dynamic fire risk value as follows: In the formula, Indicates the probability weight of historical wildfire failures; Indicates the current environmental risk factor weights; Indicates the weight of future weather threats; This indicates the correction factor for wildfire warnings in mountainous areas; like ,but It is a dynamic fire protection low-risk level; if ,but The risk level is dynamic and medium; if ,but It is classified as a dynamic high-risk fire protection level; Different thermal colors are matched to different dynamic fire risk levels, with green corresponding to low dynamic fire risk level, yellow corresponding to medium dynamic fire risk level, and red corresponding to high dynamic fire risk level. The dynamic fire risk value of all grid cells is spatially stitched together with the thermal color matching results of the corresponding dynamic fire risk level to generate the dynamic fire risk heat map.

[0008] Preferably, the step of establishing a spatial model of the preset positions of the mountain fire prevention pan-tilt-zoom (PTZ) camera, calibrating the installation three-dimensional coordinates, field of view, and maximum monitoring distance of the mountain fire prevention PTZ camera, constructing a three-dimensional terrain occlusion model in conjunction with lidar scanning, calculating the effective monitoring range of each preset position, spatially overlaying it with the dynamic fire risk heat map, and outputting the average coverage risk and monitoring redundancy rate of each preset position, specifically includes: Establish a preset position spatial model of the mountain fire prevention PTZ camera, obtain the installation three-dimensional coordinates of the mountain fire prevention PTZ camera through GPS positioning and laser ranging, and measure the field of view of the mountain fire prevention PTZ camera, including the horizontal field of view and the vertical field of view, as well as the maximum monitoring distance; The terrain within the field of view of the mountain fire prevention PTZ camera is scanned using a lidar to obtain altitude distribution data. Combined with the installation three-dimensional coordinates, the field of view, and the maximum monitoring distance, the three-dimensional terrain occlusion model is constructed. The theoretical monitoring area of ​​each preset position is calculated using the principles of geometric optics. as follows: In the formula, Indicates the maximum monitoring distance; Indicates the horizontal field of view; Indicates the vertical field of view; The terrain occlusion rate of each preset location is calculated based on the three-dimensional terrain occlusion model. With vegetation shading rate The effective monitoring area of ​​each preset position is calculated using a mountainous field-of-view occlusion compensation model. as follows: The effective monitoring area of ​​each preset location is mapped to a geographic coordinate system to determine the boundary coordinates of the effective monitoring range. This coordinates are then spatially overlaid with the dynamic fire risk heat map to calculate the average coverage risk of each preset location. and the monitoring redundancy rate as follows: In the formula, n represents the number of grid cells covered by the preset position; This represents the dynamic fire risk value of the i-th grid cell covered by the preset position; This represents the area of ​​the i-th grid cell covered by the preset position; This represents the monitoring overlap area between the x-th and y-th preset positions; This represents the effective monitoring area of ​​the x-th preset position.

[0009] Preferably, the percentage of grid cells with a dynamic fire risk value of "high dynamic fire risk" within the coverage area of ​​each preset location is counted. ; Obtain the enhancement coefficient of high risk in mountainous areas ,like ,but ;like ,but ;like ,but ; The mean coverage risk was calculated using a high-risk nonlinear mapping model for mountainous areas. Corresponding risk weights as follows: In the formula, This represents the risk sensitivity coefficient; This indicates the risk threshold offset.

[0010] Preferably, the unique terrain areas in the mountainous region are identified, and the monitoring redundancy rate is marked to cover the unique terrain areas in the mountainous region. Less than 10% of the preset positions are unique perspective preset positions; The redundancy weights corresponding to the monitoring redundancy rate are calculated using a mountainous area-specific perspective-first model. as follows: In the formula, Indicates the redundancy compensation coefficient; This represents the reward coefficient for unique perspectives.

[0011] Preferably, the device status weight corresponding to the real-time device status of the gimbal is... The calculation formula is as follows: In the formula, G represents the health status value of the gimbal; This indicates the cumulative number of gimbal malfunctions. This indicates the total number of times the gimbal has been run; Indicates the time since the last maintenance; J represents the standard maintenance cycle; Q represents the PTZ device's battery status value, i.e., the remaining battery percentage of the PTZ device; Q represents the PTZ device's communication status value. Indicates the current signal strength of the gimbal; This indicates the maximum signal strength of the gimbal. This indicates the data packet loss rate of the gimbal; This indicates the mountain communication correction factor, which is set based on the altitude of the mountainous area where the mountain fire prevention PTZ unit is located. Based on the risk weight The redundant weights and the device state weights The comprehensive inspection weight is calculated using a variable coefficient fusion model for mountainous scenes. as follows: In the formula, They represent risk weights respectively. Redundant weights Equipment status weights The corresponding fusion coefficient.

[0012] Preferably, the comprehensive inspection weights of each preset position are calculated using the mountain emergency constraint inverse proportional model. Converting this to the inspection cycle T, the corresponding calculation formula is as follows: In the formula, Indicates the minimum inspection cycle; Indicates the basic inspection cycle; Indicates emergency response factors; Indicates taking and The larger value in the range.

[0013] A collaborative verification-based intelligent linkage system for mountain fire prevention PTZ cameras, comprising: The base output module is used to build a dynamic risk assessment system for mountain fire prevention PTZ cameras. It collects historical wildfire fault data, real-time tower environment data, meteorological fire prevention forecast data and high-precision topographic data, and performs spatiotemporal alignment and standardization processing to output a unified data base. The heat map generation module is used to divide the mountain power transmission line into multiple grid units based on the unified data base, and calculate the dynamic fire risk value of each grid unit to generate a dynamic fire risk heat map. The spatial overlay module is used to establish a spatial model of the preset positions of the mountain fire prevention PTZ camera, calibrate the installation three-dimensional coordinates, field of view and maximum monitoring distance of the mountain fire prevention PTZ camera, construct a three-dimensional terrain occlusion model in combination with lidar scanning, calculate the effective monitoring range of each preset position and spatially overlay it with the dynamic fire risk heat map, and output the average coverage risk and monitoring redundancy rate of each preset position. The weight calculation module is used to construct a multi-dimensional weight calculation system based on the average coverage risk and monitoring redundancy rate of each preset position, combined with the real-time device status of the corresponding PTZ machine, and output the comprehensive inspection weight of each preset position. The scheme determination module is used to convert the comprehensive inspection weight of each preset position into an inspection cycle using a mountain emergency constraint inverse proportional model, and output a dynamic inspection scheduling scheme by combining the gimbal task conflict scheduling rules and the mountain wildfire emergency response mechanism.

[0014] An electronic device includes a memory and a processor, wherein the memory stores a computer program, and when the processor runs the computer program stored in the memory, the processor executes the steps of the intelligent linkage method for mountain fire prevention PTZ cameras based on collaborative verification as described above.

[0015] A readable storage medium storing a computer program, which, when executed by a processor, is used to implement the steps of the intelligent linkage method for mountain fire prevention PTZ cameras based on collaborative verification as described above.

[0016] Compared with related technologies, the intelligent linkage method and system for mountain fire prevention PTZ cameras based on collaborative verification provided by this invention has the following beneficial effects: This invention constructs a dynamic risk assessment system for mountain fire prevention PTZ cameras. It collects historical wildfire fault data, real-time tower environment data, meteorological fire forecast data, and high-precision topographic data, performing spatiotemporal alignment and standardization to output a unified data base. Based on this unified data base, mountain transmission lines are divided into multiple grid units, and the dynamic fire risk value of each grid unit is calculated to generate a dynamic fire risk heat map. A pre-positioned spatial model of the mountain fire prevention PTZ camera is established, calibrating the installation three-dimensional coordinates, field of view, and maximum monitoring distance. A three-dimensional terrain occlusion model is constructed using lidar scanning, and the effective monitoring range of each pre-positioned location is calculated and compared with the dynamic fire risk heat map. The system aims to perform spatial overlay to output the average coverage risk and monitoring redundancy rate of each preset location. Based on the average coverage risk and monitoring redundancy rate of each preset location, combined with the real-time equipment status of the corresponding PTZ cameras, a multi-dimensional weight calculation system is constructed to output the comprehensive inspection weight of each preset location. A mountain emergency constraint inverse proportional model is adopted to convert the comprehensive inspection weight of each preset location into an inspection cycle. Combined with the PTZ camera task conflict scheduling rules and the mountain wildfire emergency response mechanism, a dynamic inspection scheduling scheme is output. This allows for dynamic adjustment of the PTZ camera inspection strategy based on the real-time risk status and monitoring resource distribution of each section of the transmission line, enhancing the monitoring capabilities of high-risk areas and reducing resource waste in low-risk areas.

[0017] This invention, relying on a dynamic risk assessment system and a unified data foundation, combined with a multi-factor weighted risk calculation model for mountainous areas, quantifies and integrates historical wildfire failure probabilities, current environmental risk factors, and future meteorological threat levels to generate a dynamic fire risk heat map. This achieves precise risk classification at the grid unit level, avoiding the shortcomings of traditional risk assessments that rely on experience and are highly subjective. This invention uses a pre-set spatial model and a three-dimensional terrain occlusion model constructed with lidar, combined with geometric optics principles, to calculate the effective monitoring range. This range is then overlaid with the heat map to obtain the average coverage risk and monitoring redundancy rate, accurately avoiding monitoring blind spots caused by mountainous terrain and vegetation obstruction. Simultaneously, it identifies low-redundancy, unique-view pre-set locations, solving the problems of unreasonable pre-set location settings and unbalanced monitoring coverage in traditional methods, and optimizing the spatial distribution of monitoring resources. Based on a multi-dimensional weight calculation system and a mountainous emergency constraint inverse proportional model, this invention dynamically converts comprehensive inspection weights into inspection cycles. Combined with task conflict scheduling and emergency response mechanisms, it enables on-demand adjustment of inspection strategies, increasing the inspection frequency in high-risk areas and saving inspection resources in low-risk areas, completely changing the traditional one-size-fits-all approach of fixed-cycle inspections. Attached Figure Description

[0018] Figure 1 A flowchart of a method for intelligent linkage of mountain fire prevention PTZ cameras based on collaborative verification, provided in an embodiment of the present invention; Figure 2 This is a system block diagram of an intelligent linkage system for mountain fire prevention PTZ cameras based on collaborative verification, provided in an embodiment of the present invention. Figure 3 This is a schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present invention. Detailed Implementation

[0019] 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, and 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.

[0020] like Figure 1 The diagram shown is a flowchart of the intelligent linkage method for mountain fire prevention PTZ cameras based on collaborative verification provided in an embodiment of the present invention. Figure 1The execution entity of the method shown can be a software and / or hardware device. The execution entity of this application can include, but is not limited to, at least one of the following: user equipment, network equipment, etc. User equipment can include, but is not limited to, computers, smartphones, personal digital assistants (PDAs), and the aforementioned electronic devices. Network equipment can include, but is not limited to, a single network server, a server group consisting of multiple network servers, or a cloud based on cloud computing consisting of a large number of computers or network servers. Cloud computing is a type of distributed computing, consisting of a super virtual computer composed of a group of loosely coupled computers. This embodiment does not limit this. Steps S1 to S5 are detailed as follows: S1, construct a dynamic risk assessment system for mountain fire prevention PTZ cameras, collect historical wildfire fault data, real-time tower environment data, meteorological fire prevention forecast data and high-precision topographic data, and perform spatiotemporal alignment and standardization processing to output a unified data base. The historical wildfire fault data specifically covers the occurrence time, corresponding tower number, and fault cause information of past wildfire faults along power transmission lines in mountainous areas. Real-time tower environmental data focuses on temperature deviations, humidity deviations, and vegetation temperature sensitivity deviations around the towers. Meteorological fire prevention forecast data includes fire-related meteorological indicators such as temperature, precipitation probability, and wind speed for a preset future period. High-precision topographic data includes the altitude, slope, and terrain type characteristics along the power transmission lines.

[0021] Understandably, spatiotemporal alignment uses a unified geographic coordinate system to match the spatial location of various data types, and simultaneously calibrates the time dimension of the data based on standard timestamps. Standardization ensures consistency in data structure and dimensions by unifying data formats and correcting outliers during data collection.

[0022] S2, Based on the unified data base, the mountain power transmission line is divided into multiple grid units, and the dynamic fire risk value of each grid unit is calculated to generate a dynamic fire risk heat map; The process of dividing mountain power transmission lines into multiple grid units based on the unified data base and calculating the dynamic fire risk value of each grid unit to generate a dynamic fire risk heat map specifically includes: Based on the unified data base, the mountain power transmission line is divided into multiple grid units according to the complexity of the mountain terrain. Extracting the historical wildfire failure probability for each grid cell Current environmental risk factors and future weather threat levels And the current environmental risk factors This includes temperature deviation, humidity deviation, and vegetation temperature perception deviation; A multi-factor weighted risk calculation model for mountainous areas is adopted, based on the historical wildfire failure probability of each grid cell. The aforementioned current environmental risk factors and the aforementioned future weather threat level Calculate the dynamic fire risk value as follows: In the formula, Indicates the probability weight of historical wildfire failures; Indicates the current environmental risk factor weights; Indicates the weight of future weather threats; This indicates the correction factor for wildfire warnings in mountainous areas; like ,but It is a dynamic fire protection low-risk level; if ,but The risk level is dynamic and medium; if ,but It is classified as a dynamic high-risk fire protection level; Different thermal colors are matched to different dynamic fire risk levels, with green corresponding to low dynamic fire risk level, yellow corresponding to medium dynamic fire risk level, and red corresponding to high dynamic fire risk level. The dynamic fire risk value of all grid cells is spatially stitched together with the thermal color matching results of the corresponding dynamic fire risk level to generate the dynamic fire risk heat map.

[0023] When dividing grid units according to the complexity of mountainous terrain, high-precision topographic data in a unified data base is used as a reference, along with features such as terrain slope, elevation undulation, and landform type, to ensure that the spatial scale of the grid units is compatible with the complexity of the terrain. This avoids the situation where local high-risk areas are obscured due to overly coarse division, or where overly fine division increases data processing redundancy.

[0024] Historical wildfire failure probabilities are extracted based on the spatial range of grid cells, and statistical analysis is performed by associating failure records of corresponding areas in historical wildfire failure data. Current environmental risk factors are obtained by comparing sensor values ​​collected within the coverage area of ​​each grid cell in real-time pole environmental data with preset standard environmental benchmarks. These current environmental risk factors specifically include calculated temperature deviation, humidity deviation, and vegetation temperature sensitivity deviation. Future meteorological threat levels are converted based on the forecast results for the corresponding grid cell area in the meteorological fire prevention forecast data.

[0025] The weights for historical wildfire failure probabilities, current environmental risk factors, and future meteorological threats in the multi-factor weighted risk calculation model for mountainous areas are determined based on the analysis of the contribution of each factor to the occurrence of past wildfire accidents in mountainous areas. The mountainous fire early warning correction factor is dynamically adjusted in conjunction with the microclimate and vegetation flammability characteristics of mountainous areas. The dynamic fire risk level classification clearly defines the risk threshold range for each level, ensuring differentiation between different levels.

[0026] The matching of thermal colors follows the principle of visual recognition, with the color gradations of green, yellow, and red meeting the clarity requirements for long-distance observation and digital display. The spatial stitching process uses the geographic coordinate system in the unified data base as a reference to calibrate the coordinates of the thermal color information of each grid unit, ensuring that the thermal color transition between adjacent grid units is natural and the spatial positions correspond accurately. The resulting dynamic fire risk heat map fully covers the entire area of ​​mountain power transmission lines and can intuitively reflect the risk differences in different areas.

[0027] S3, establish a spatial model of the preset positions of the mountain fire prevention PTZ camera, calibrate the installation three-dimensional coordinates, field of view and maximum monitoring distance of the mountain fire prevention PTZ camera, construct a three-dimensional terrain occlusion model in combination with lidar scanning, calculate the effective monitoring range of each preset position and spatially overlay it with the dynamic fire risk heat map, and output the average coverage risk and monitoring redundancy rate of each preset position. The process involves establishing a spatial model of the pre-positioned fire prevention pan-tilt-zoom (PTZ) camera for mountainous areas, calibrating the 3D coordinates, field of view, and maximum monitoring distance of the PTG camera, constructing a 3D terrain occlusion model using lidar scanning, calculating the effective monitoring range of each pre-positioned location, spatially overlaying it with the dynamic fire risk heat map, and outputting the average coverage risk and monitoring redundancy rate for each pre-positioned location. Specifically, this includes: Establish a preset position spatial model of the mountain fire prevention PTZ camera, obtain the installation three-dimensional coordinates of the mountain fire prevention PTZ camera through GPS positioning and laser ranging, and measure the field of view of the mountain fire prevention PTZ camera, including the horizontal field of view and the vertical field of view, as well as the maximum monitoring distance; The terrain within the field of view of the mountain fire prevention PTZ camera is scanned using a lidar to obtain altitude distribution data. Combined with the installation three-dimensional coordinates, the field of view, and the maximum monitoring distance, the three-dimensional terrain occlusion model is constructed. The theoretical monitoring area of ​​each preset position is calculated using the principles of geometric optics. as follows: In the formula, Indicates the maximum monitoring distance; Indicates the horizontal field of view; Indicates the vertical field of view; The terrain occlusion rate of each preset location is calculated based on the three-dimensional terrain occlusion model. With vegetation shading rate The effective monitoring area of ​​each preset position is calculated using a mountainous field-of-view occlusion compensation model. as follows: The effective monitoring area of ​​each preset location is mapped to a geographic coordinate system to determine the boundary coordinates of the effective monitoring range. This coordinates are then spatially overlaid with the dynamic fire risk heat map to calculate the average coverage risk of each preset location. and the monitoring redundancy rate as follows: In the formula, n represents the number of grid cells covered by the preset position; This represents the dynamic fire risk value of the i-th grid cell covered by the preset position; This represents the area of ​​the i-th grid cell covered by the preset position; This represents the monitoring overlap area between the x-th and y-th preset positions; This represents the effective monitoring area of ​​the x-th preset position.

[0028] The pre-set spatial model is a spatial parameter model constructed specifically for mountain fire prevention pan-tilt units. It obtains the 3D coordinates of the pan-tilt unit's installation using GPS positioning and laser ranging, and measures the horizontal and vertical field of view, as well as the maximum monitoring distance. When obtaining the 3D coordinates via GPS positioning, the geographic coordinate system of the unified data base is used as a reference, and coordinate corrections are made based on the mountainous terrain features to avoid positioning deviations caused by terrain obstruction. Laser ranging is performed on the actual fixed point of the pan-tilt unit's mounting base to ensure that the measurement results perfectly match the physical coordinates of the installation location. During the field of view measurement, the horizontal and vertical field of view are calibrated using optical measurement equipment under normal operating conditions of the pan-tilt unit's lens to eliminate the influence of lens distortion on the angle data. The maximum monitoring distance is determined after on-site testing and verification, taking into account the pan-tilt unit's lens resolution, atmospheric visibility in mountainous areas, and target recognition requirements, ensuring that the data conforms to the actual monitoring scenario.

[0029] When scanning the terrain within the field of view of the lidar, the scanning resolution and sampling interval are preset. Key information such as terrain protrusions, gullies, and vegetation distribution within the pan-tilt-zoom (PTZ) camera's field of view is collected. Elevation distribution data is cross-validated with high-precision terrain data from a unified data base to ensure data accuracy. When constructing a 3D terrain occlusion model, the PTZ camera's installation 3D coordinates are used as the origin. Combined with the angular boundaries of the field of view and the spatial boundaries of the maximum monitoring distance, occlusion factors such as terrain protrusion height and vegetation height are transformed into spatial occlusion areas, clearly marking the degree of occlusion in each area.

[0030] When calculating the theoretical monitoring area using geometric optics principles, the calibrated horizontal and vertical field of view angles and the actual maximum monitoring distance are substituted to avoid calculation errors caused by using theoretical lens parameters. When calculating the effective monitoring area using the mountainous field-of-view occlusion compensation model, the terrain occlusion rate is determined based on the proportion of the occluded area within the theoretical monitoring area in the 3D terrain occlusion model. The vegetation occlusion rate is calculated by combining vegetation cover density and height data obtained from lidar scanning, ensuring that both types of occlusion rates accurately reflect the actual field-of-view occlusion situation.

[0031] When mapping the effective monitoring area to a geographic coordinate system, it is necessary to maintain consistency with the coordinate system of the dynamic fire risk heat map, with boundary coordinates accurate to the vertex position of the grid cell to avoid misalignment during spatial overlay. When calculating the average coverage risk, all grid cells covered by the effective monitoring range of the preset locations should be accurately extracted, ensuring that the dynamic fire risk value and area data of each grid cell come from a unified data base. When calculating the monitoring redundancy rate, overlapping areas of the effective monitoring ranges of different preset locations should be identified, and the overlapping area should be determined through spatial intersection operations to ensure that the redundancy rate calculation results objectively reflect the duplicate coverage of monitoring resources.

[0032] S4. Based on the average coverage risk and monitoring redundancy rate of each preset position, and combined with the real-time device status of the corresponding PTZ machine, a multi-dimensional weight calculation system is constructed to output the comprehensive inspection weight of each preset position. Statistically determine the percentage of grid cells within each preset location's coverage area that have a dynamic fire risk value classified as high-risk for dynamic fire protection. ; Obtain the enhancement coefficient of high risk in mountainous areas ,like ,but ;like ,but ;like ,but ; The mean coverage risk was calculated using a high-risk nonlinear mapping model for mountainous areas. Corresponding risk weights as follows: In the formula, This represents the risk sensitivity coefficient; This indicates the risk threshold offset.

[0033] When calculating the proportion of grid units with dynamic high-risk levels, the boundary of the effective monitoring range mapped to the geographic coordinate system is used as the benchmark. Only grid units that fall completely or partially within this boundary and whose dynamic fire risk value meets the high-risk level are included to ensure... It can accurately reflect the concentration of high-risk areas within the pre-set coverage area. When obtaining the high-risk enhancement coefficient in mountainous areas, it uses... The actual statistical results are used as the basis for judgment to clarify different The coefficient values ​​corresponding to the intervals are selected to ensure that the coefficients can reasonably strengthen and adjust the risk weights according to the differences in the proportion of high-risk grids.

[0034] In the high-risk nonlinear mapping model for mountainous areas, the risk sensitivity coefficient is set based on the correlation between the average coverage risk and the actual probability of wildfire hazards in past wildfire accident cases in mountainous areas. This ensures that even small changes in the average risk value can reflect differences in risk weight calculation that meet actual prevention and control needs. The risk threshold offset is adjusted with reference to the average coverage risk value corresponding to historical high-risk events occurring along mountain transmission lines. This ensures that the risk weights calculated by the high-risk nonlinear mapping model for mountainous areas accurately match the actual risk characteristics of mountain transmission lines, avoiding a disconnect between weights and actual risk priorities due to risk threshold deviations.

[0035] Identify unique mountainous terrain areas, mark areas covering these unique terrain areas, and specify the monitoring redundancy rate. Less than 10% of the preset positions are unique perspective preset positions; The redundancy weights corresponding to the monitoring redundancy rate are calculated using a mountainous area-specific perspective-first model. as follows: In the formula, Indicates the redundancy compensation coefficient; This represents the reward coefficient for unique perspectives.

[0036] When identifying unique terrain areas in mountainous regions, based on high-precision topographic data in a unified data base, the focus is on terrain types that have a special impact on the safety of transmission lines, such as steep canyon sections, the area around isolated mountains, abrupt changes in terrain slope, and key sections where transmission lines cross deep ravines. Through terrain feature extraction and spatial range definition, the geographical coordinate boundaries of each unique terrain area are clarified to ensure that the identification results are consistent with the actual terrain risk scenarios of transmission lines in mountainous areas.

[0037] When marking unique viewpoint preset positions, both "covering unique terrain areas" and "monitoring redundancy rate" must be satisfied. The two conditions, "less than 10%", are: first, determine whether the effective monitoring range of the preset position has spatial intersection with the unique terrain area; and second, verify whether the redundancy rate calculated from the monitoring overlap area with other preset positions is lower than the threshold. Only when both conditions are met can it be marked, so as to avoid the lack of monitoring of unique terrain areas due to only focusing on redundancy rate or coverage.

[0038] In the mountainous area unique perspective priority model, the redundancy compensation coefficient is set in conjunction with the overall distribution of monitoring resources in the mountainous area. Its purpose is to avoid extreme fluctuations in the calculation of redundancy weight when the monitoring redundancy rate is too low, and to ensure that the trend of redundancy weight changes conforms to the actual monitoring resource allocation needs. The unique perspective reward coefficient is used to increase the inspection priority of pre-positioned locations covering unique terrain areas. Its value is based on the degree of impact of unique terrain areas on the safety of transmission lines. For example, terrain abrupt changes can easily cause instability in tower foundations, and steep canyon sections can cause rapid spread of wildfires. By rewarding with coefficients, the weight ratio of such pre-positioned locations is strengthened, ultimately ensuring that the redundancy weight can accurately reflect the degree of monitoring redundancy and the necessity of unique terrain coverage.

[0039] The device status weight corresponding to the real-time device status of the gimbal The calculation formula is as follows: In the formula, G represents the health status value of the gimbal; This indicates the cumulative number of gimbal malfunctions. This indicates the total number of times the gimbal has been run; Indicates the time since the last maintenance; J represents the standard maintenance cycle; Q represents the PTZ device's battery status value, i.e., the remaining battery percentage of the PTZ device; Q represents the PTZ device's communication status value. Indicates the current signal strength of the gimbal; This indicates the maximum signal strength of the gimbal. This indicates the data packet loss rate of the gimbal; This indicates the mountain communication correction factor, which is set based on the altitude of the mountainous area where the mountain fire prevention PTZ unit is located. Based on the risk weight The redundant weights and the device state weights The comprehensive inspection weight is calculated using a variable coefficient fusion model for mountainous scenes. as follows: In the formula, They represent risk weights respectively. Redundant weights Equipment status weights The corresponding fusion coefficient.

[0040] When calculating the health status value of the gimbal, the cumulative number of faults is counted based on the number of various functional fault records since the equipment was put into operation, and the total number of operations is the total number of times the equipment has been started normally and performed inspection tasks during the same period, ensuring that the statistical periods for the two types of data are consistent. The time since the last maintenance is calculated from the most recent maintenance completion timestamp recorded in the equipment maintenance file. The standard maintenance cycle is adjusted and set in combination with the degree of wear and tear on the equipment in the mountainous environment, such as the aging rate of components caused by high humidity and dust, to ensure that the health status value of the gimbal accurately reflects the health degradation of the equipment.

[0041] The PTZ camera's battery status value, i.e., the remaining battery percentage, is collected in real-time by the device's built-in battery sensor and converted into a percentage value, avoiding the use of lagging battery data that could affect the accuracy of the device status weight calculation. When calculating the communication status value, the PTZ camera's current signal strength is taken as the average value collected within 5-10 minutes prior to the calculation time. The PTZ camera's maximum signal strength is the peak signal strength calibrated by the device in an ideal environment in mountainous areas without terrain or vegetation obstruction. The PTZ camera's data packet loss rate is calculated as the ratio of total data packets transmitted from the device to the backend during the same period to the number of lost data packets. The mountainous communication correction factor is set according to the device's altitude; the higher the altitude, the stronger the signal transmission is affected by terrain obstruction and electromagnetic interference, and the mountainous communication correction factor value is adjusted accordingly to compensate for the adverse effects of high altitude on communication status.

[0042] In the variable coefficient fusion model for mountainous scenarios, the values ​​of the fusion coefficients are determined based on the priority settings of different operation and maintenance scenarios for power transmission lines in mountainous areas. For example, during peak wildfire seasons, the proportion of the fusion coefficient for risk weights can be increased to prioritize the impact of risk dimensions on the overall weight. In sections with dense monitoring resources and high redundancy rates, the proportion of the fusion coefficient for redundancy weights can be increased to optimize resource allocation efficiency. When some PTZ cameras have health risks or insufficient power, the proportion of the fusion coefficient for equipment status weights can be appropriately increased to avoid inspection interruptions caused by equipment failures. This ensures that the weights of the three dimensions—risk, redundancy, and equipment status—can be reasonably integrated according to actual needs, so that the overall inspection weight reflects both the regional risk priority and the necessity of monitoring and the operational capacity of the equipment.

[0043] S5 uses a mountain emergency constraint inverse proportional model to convert the comprehensive inspection weight of each preset position into an inspection cycle, and combines the gimbal machine task conflict scheduling rules and mountain wildfire emergency response mechanism to output a dynamic inspection scheduling scheme.

[0044] The method employs an inverse proportional model based on mountain emergency constraints to assign comprehensive inspection weights to each preset location. Converting this to the inspection cycle T, the corresponding calculation formula is as follows: In the formula, Indicates the minimum inspection cycle; Indicates the basic inspection cycle; Indicates emergency response factors; Indicates taking and The larger value in the range.

[0045] The minimum inspection cycle is set by taking into account the shortest response window for mountain fire emergency response, the continuous operation tolerance of the PTZ machine's mechanical components, and the load limit of the data transmission link. This avoids excessive wear and tear on the equipment or data transmission congestion due to an excessively short cycle, while ensuring that potential wildfire hazards can be detected within the effective prevention and control time. The basic inspection cycle is based on the historical inspection interval of routine maintenance of power transmission lines in mountainous areas, the average dynamic fire risk level of grid units, and the daily maintenance cost of the PTZ machine. This ensures that the routine fire monitoring needs of the lines can be met when there are no emergency situations, and that it is compatible with the normal operating life of the equipment.

[0046] The values ​​of the emergency response factor are linked to the early warning levels of the mountain fire emergency response mechanism. For example, when meteorological fire prevention forecast data indicates a high fire risk level, or when signs of wildfires are detected in the area, the emergency response factor is increased to strengthen the emergency constraint effect and promote a shorter inspection cycle; if the risk level in the area drops to low risk, the emergency response factor can be appropriately reduced to allow the inspection cycle to return to normal levels, ensuring that the emergency response factor can accurately match actual emergency needs.

[0047] Use the max function to get and The larger value in the calculation is used to balance emergency prevention and control needs with equipment operational feasibility. When the comprehensive inspection weight is too high and the emergency response factor is too large, it leads to... Less than At that time, with This is the final inspection cycle to prevent equipment from exceeding its operating load. When The calculated value is greater than At that time, with The calculated value is the standard, ensuring that the inspection cycle can be dynamically adjusted according to the comprehensive inspection weight and emergency needs. This avoids wasting monitoring resources and meets the high-frequency inspection needs of high-risk areas, ultimately providing reasonable and feasible cycle parameters to support the output of the dynamic inspection scheduling scheme.

[0048] In practical applications, the early warning level of the mountain fire emergency response mechanism is first linked to the emergency response factor of the mountain emergency constraint inverse proportional model to ensure that the model can output an inspection cycle that matches the risk under emergency conditions. When handling gimbal task conflicts, the comprehensive inspection weight is used as the core judgment criterion, and inspection tasks with high weight preset positions are executed first. If multiple tasks conflict on the same gimbal, time-staggered scheduling is carried out in combination with its real-time equipment status to avoid task backlog. After the dynamic inspection scheduling plan is output, it is synchronized to each gimbal control terminal, and the plan is adapted and adjusted in real time. For example, when the mountain fire emergency response mechanism triggers a higher warning, or when the preset comprehensive inspection weight is updated due to risk changes, the dynamic inspection scheduling plan needs to be adjusted immediately to ensure that inspection resources are tilted towards high-risk areas and emergency needs.

[0049] like Figure 2 The diagram shown is a system block diagram of an intelligent linkage system for mountain fire prevention PTZ cameras based on collaborative verification, provided in an embodiment of the present invention. The system includes: The base output module is used to build a dynamic risk assessment system for mountain fire prevention PTZ cameras. It collects historical wildfire fault data, real-time tower environment data, meteorological fire prevention forecast data and high-precision topographic data, and performs spatiotemporal alignment and standardization processing to output a unified data base. The heat map generation module is used to divide the mountain power transmission line into multiple grid units based on the unified data base, and calculate the dynamic fire risk value of each grid unit to generate a dynamic fire risk heat map. The spatial overlay module is used to establish a spatial model of the preset positions of the mountain fire prevention PTZ camera, calibrate the installation three-dimensional coordinates, field of view and maximum monitoring distance of the mountain fire prevention PTZ camera, construct a three-dimensional terrain occlusion model in combination with lidar scanning, calculate the effective monitoring range of each preset position and spatially overlay it with the dynamic fire risk heat map, and output the average coverage risk and monitoring redundancy rate of each preset position. The weight calculation module is used to construct a multi-dimensional weight calculation system based on the average coverage risk and monitoring redundancy rate of each preset position, combined with the real-time device status of the corresponding PTZ machine, and output the comprehensive inspection weight of each preset position. The scheme determination module is used to convert the comprehensive inspection weight of each preset position into an inspection cycle using a mountain emergency constraint inverse proportional model, and output a dynamic inspection scheduling scheme by combining the gimbal task conflict scheduling rules and the mountain wildfire emergency response mechanism.

[0050] Figure 2 The apparatus of the illustrated embodiment can be used to perform corresponding actions. Figure 1 The steps in the method embodiments shown are implemented in a similar manner and have similar technical effects, and will not be repeated here.

[0051] An electronic device includes a memory and a processor, wherein the memory stores a computer program, and when the processor runs the computer program stored in the memory, the processor executes the steps of the intelligent linkage method for mountain fire prevention PTZ cameras based on collaborative verification as described above.

[0052] like Figure 3 The diagram shown is a hardware structure schematic of an electronic device according to an embodiment of the present invention. The electronic device 30 includes: a processor 31, a memory 32, and a computer program; wherein... The memory 32 is used to store the computer program, and the memory may also be flash memory. The computer program is, for example, an application program or functional module that implements the above method.

[0053] The processor 31 is configured to execute the computer program stored in the memory to implement the various steps performed by the device in the above method. For details, please refer to the relevant descriptions in the preceding method embodiments.

[0054] Alternatively, the memory 32 can be either standalone or integrated with the processor 31.

[0055] When the memory 32 is a device independent of the processor 31, the device may further include: Bus 33 is used to connect the memory 32 and the processor 31.

[0056] A readable storage medium storing a computer program, which, when executed by a processor, is used to implement the steps of the intelligent linkage method for mountain fire prevention PTZ cameras based on collaborative verification as described above.

[0057] The readable storage medium can be a computer storage medium or a communication medium. A communication medium includes any medium that facilitates the transfer of computer programs from one location to another. A computer storage medium can be any available medium accessible to a general-purpose or special-purpose computer. For example, a readable storage medium is coupled to a processor, enabling the processor to read information from and write information to the readable storage medium. Of course, the readable storage medium can also be a component of the processor. The processor and the readable storage medium can reside in an Application-Specific Integrated Circuit (ASIC). Alternatively, the ASIC can be located in a user equipment. Of course, the processor and the readable storage medium can also exist as discrete components in a communication device. The readable storage medium can be a read-only memory (ROM), random access memory (RAM), CD-ROM, magnetic tape, floppy disk, and optical data storage device, etc.

[0058] The present invention also provides a program product including executable instructions stored in a readable storage medium. At least one processor of the device can read the executable instructions from the readable storage medium, and the at least one processor executes the executable instructions to cause the device to implement the methods provided in the various embodiments described above.

[0059] In the embodiments of the above-described device, it should be understood that the processor can be a Central Processing Unit (CPU), or other general-purpose processors, digital signal processors (DSPs), application-specific integrated circuits (ASICs), etc. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the method disclosed in this invention can be directly manifested as execution by a hardware processor, or execution by a combination of hardware and software modules within the processor.

[0060] Through the above embodiments, this invention, through a collaborative verification-based intelligent linkage method and system for mountain fire prevention PTZ cameras, constructs a dynamic risk assessment system for mountain fire prevention PTZ cameras. It collects historical wildfire fault data, real-time tower environment data, meteorological fire forecast data, and high-precision topographic data, performs spatiotemporal alignment and standardization processing, and outputs a unified data base. Based on this unified data base, it divides mountain transmission lines into multiple grid units and calculates the dynamic fire risk value of each grid unit to generate a dynamic fire risk heat map. It establishes a pre-positioned spatial model for the mountain fire prevention PTZ camera, calibrates the installation three-dimensional coordinates, field of view, and maximum monitoring distance of the camera, and constructs a three-dimensional terrain occlusion model using lidar scanning to calculate the risk of each... The effective monitoring range of the preset locations is spatially overlaid with a dynamic fire risk heat map to output the average coverage risk and monitoring redundancy rate of each preset location. Based on the average coverage risk and monitoring redundancy rate of each preset location, combined with the real-time equipment status of the corresponding PTZ cameras, a multi-dimensional weight calculation system is constructed to output the comprehensive inspection weight of each preset location. A mountain emergency constraint inverse proportional model is adopted to convert the comprehensive inspection weight of each preset location into an inspection cycle. Combined with the PTZ camera task conflict scheduling rules and the mountain wildfire emergency response mechanism, a dynamic inspection scheduling scheme is output. This allows for dynamic adjustment of the PTZ camera inspection strategy based on the real-time risk status and monitoring resource distribution of each section of the transmission line, enhancing the monitoring capabilities of high-risk areas and reducing resource waste in low-risk areas.

[0061] This invention, relying on a dynamic risk assessment system and a unified data foundation, combined with a multi-factor weighted risk calculation model for mountainous areas, quantifies and integrates historical wildfire failure probabilities, current environmental risk factors, and future meteorological threat levels to generate a dynamic fire risk heat map. This achieves precise risk classification at the grid unit level, avoiding the shortcomings of traditional risk assessments that rely on experience and are highly subjective. This invention uses a pre-set spatial model and a three-dimensional terrain occlusion model constructed with lidar, combined with geometric optics principles, to calculate the effective monitoring range. This range is then overlaid with the heat map to obtain the average coverage risk and monitoring redundancy rate, accurately avoiding monitoring blind spots caused by mountainous terrain and vegetation obstruction. Simultaneously, it identifies low-redundancy, unique-view pre-set locations, solving the problems of unreasonable pre-set location settings and unbalanced monitoring coverage in traditional methods, and optimizing the spatial distribution of monitoring resources. Based on a multi-dimensional weight calculation system and a mountainous emergency constraint inverse proportional model, this invention dynamically converts comprehensive inspection weights into inspection cycles. Combined with task conflict scheduling and emergency response mechanisms, it enables on-demand adjustment of inspection strategies, increasing the inspection frequency in high-risk areas and saving inspection resources in low-risk areas, completely changing the traditional one-size-fits-all approach of fixed-cycle inspections.

[0062] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, and not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some or all of the technical features; and these modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for intelligent linkage of pan-tilt-zoom (PTZ) fire prevention systems in mountainous areas based on collaborative verification, characterized in that: The method includes: Construct a dynamic risk assessment system for mountain fire prevention PTZ cameras, collect historical wildfire fault data, real-time tower environment data, meteorological fire prevention forecast data and high-precision topographic data, perform spatiotemporal alignment and standardization processing, and output a unified data base. Based on the unified data base, the mountain power transmission lines are divided into multiple grid units, and the dynamic fire risk value of each grid unit is calculated to generate a dynamic fire risk heat map. Establish a spatial model of the preset positions of the mountain fire prevention PTZ camera, calibrate the installation three-dimensional coordinates, field of view and maximum monitoring distance of the mountain fire prevention PTZ camera, construct a three-dimensional terrain occlusion model in combination with lidar scanning, calculate the effective monitoring range of each preset position and spatially overlay it with the dynamic fire risk heat map, and output the average coverage risk and monitoring redundancy rate of each preset position. Based on the average coverage risk and monitoring redundancy rate of each preset position, and combined with the real-time device status of the corresponding PTZ machine, a multi-dimensional weight calculation system is constructed to output the comprehensive inspection weight of each preset position. The comprehensive inspection weights of each preset position are converted into inspection cycles using a mountain emergency constraint inverse proportional model. Combined with the gimbal task conflict scheduling rules and the mountain wildfire emergency response mechanism, a dynamic inspection scheduling scheme is output.

2. The intelligent linkage method for mountain fire prevention PTZ cameras based on collaborative verification according to claim 1, characterized in that, The process of dividing mountain power transmission lines into multiple grid units based on the unified data base and calculating the dynamic fire risk value of each grid unit to generate a dynamic fire risk heat map specifically includes: Based on the unified data base, the mountain power transmission line is divided into multiple grid units according to the complexity of the mountain terrain. Extracting the historical wildfire failure probability for each grid cell Current environmental risk factors and future weather threat levels And the current environmental risk factors This includes temperature deviation, humidity deviation, and vegetation temperature perception deviation; A multi-factor weighted risk calculation model for mountainous areas is adopted, based on the historical wildfire failure probability of each grid cell. The aforementioned current environmental risk factors and the aforementioned future weather threat level Calculate the dynamic fire risk value as follows: In the formula, Indicates the probability weight of historical wildfire failures; Indicates the current environmental risk factor weights; Indicates the weight of future weather threats; This indicates the correction factor for wildfire warnings in mountainous areas; like ,but It is a dynamic fire protection low-risk level; if ,but The risk level is dynamic and medium; if ,but It is classified as a dynamic high-risk fire protection level; Different thermal colors are matched to different dynamic fire risk levels, with green corresponding to low dynamic fire risk level, yellow corresponding to medium dynamic fire risk level, and red corresponding to high dynamic fire risk level. The dynamic fire risk value of all grid cells is spatially stitched together with the thermal color matching results of the corresponding dynamic fire risk level to generate the dynamic fire risk heat map.

3. The intelligent linkage method for mountain fire prevention PTZ cameras based on collaborative verification according to claim 1, characterized in that, The process involves establishing a spatial model of the pre-positioned fire prevention pan-tilt-zoom (PTZ) camera for mountainous areas, calibrating the 3D coordinates, field of view, and maximum monitoring distance of the PTG camera, constructing a 3D terrain occlusion model using lidar scanning, calculating the effective monitoring range of each pre-positioned location, spatially overlaying it with the dynamic fire risk heat map, and outputting the average coverage risk and monitoring redundancy rate for each pre-positioned location. Specifically, this includes: Establish a preset position spatial model of the mountain fire prevention PTZ camera, obtain the installation three-dimensional coordinates of the mountain fire prevention PTZ camera through GPS positioning and laser ranging, and measure the field of view of the mountain fire prevention PTZ camera, including the horizontal field of view and the vertical field of view, as well as the maximum monitoring distance; The terrain within the field of view of the mountain fire prevention PTZ camera is scanned using a lidar to obtain altitude distribution data. Combined with the installation three-dimensional coordinates, the field of view, and the maximum monitoring distance, the three-dimensional terrain occlusion model is constructed. The theoretical monitoring area of ​​each preset position is calculated using the principles of geometric optics. as follows: In the formula, Indicates the maximum monitoring distance; Indicates the horizontal field of view; Indicates the vertical field of view; The terrain occlusion rate of each preset location is calculated based on the three-dimensional terrain occlusion model. With vegetation shading rate The effective monitoring area of ​​each preset position is calculated using a mountainous field-of-view occlusion compensation model. as follows: The effective monitoring area of ​​each preset location is mapped to a geographic coordinate system to determine the boundary coordinates of the effective monitoring range. This coordinates are then spatially overlaid with the dynamic fire risk heat map to calculate the average coverage risk of each preset location. and the monitoring redundancy rate as follows: In the formula, n represents the number of grid cells covered by the preset position; This represents the dynamic fire risk value of the i-th grid cell covered by the preset position; This represents the area of ​​the i-th grid cell covered by the preset position; This represents the monitoring overlap area between the x-th and y-th preset positions; This represents the effective monitoring area of ​​the x-th preset position.

4. The intelligent linkage method for mountain fire prevention PTZ cameras based on collaborative verification according to claim 1, characterized in that, Statistically determine the percentage of grid cells within each preset location's coverage area that have a dynamic fire risk value classified as high-risk for dynamic fire protection. ; Obtain the enhancement coefficient of high risk in mountainous areas ,like ,but ;like ,but ;like ,but ; The mean coverage risk was calculated using a high-risk nonlinear mapping model for mountainous areas. Corresponding risk weights as follows: In the formula, This represents the risk sensitivity coefficient; This indicates the risk threshold offset.

5. The intelligent linkage method for mountain fire prevention PTZ cameras based on collaborative verification according to claim 4, characterized in that, Identify unique mountainous terrain areas, mark areas covering these unique terrain areas, and specify the monitoring redundancy rate. Less than 10% of the preset positions are unique perspective preset positions; The redundancy weights corresponding to the monitoring redundancy rate are calculated using a mountainous area-specific perspective-first model. as follows: In the formula, Indicates the redundancy compensation coefficient; This represents the reward coefficient for unique perspectives.

6. The intelligent linkage method for mountain fire prevention PTZ cameras based on collaborative verification according to claim 5, characterized in that, The device status weight corresponding to the real-time device status of the gimbal The calculation formula is as follows: In the formula, G represents the health status value of the gimbal; This indicates the cumulative number of gimbal malfunctions. This indicates the total number of times the gimbal has been run; Indicates the time since the last maintenance; J represents the standard maintenance cycle; Q represents the PTZ device's battery status value, i.e., the remaining battery percentage of the PTZ device; Q represents the PTZ device's communication status value. Indicates the current signal strength of the gimbal; This indicates the maximum signal strength of the gimbal. This indicates the data packet loss rate of the gimbal; This indicates the mountain communication correction factor, which is set based on the altitude of the mountainous area where the mountain fire prevention PTZ unit is located. Based on the risk weight The redundant weights and the device state weights The comprehensive inspection weight is calculated using a variable coefficient fusion model for mountainous scenes. as follows: In the formula, They represent risk weights respectively. Redundant weights Equipment status weights The corresponding fusion coefficient.

7. The intelligent linkage method for mountain fire prevention PTZ cameras based on collaborative verification according to claim 1, characterized in that, The method employs an inverse proportional model based on mountain emergency constraints to assign comprehensive inspection weights to each preset location. Converting this to the inspection cycle T, the corresponding calculation formula is as follows: In the formula, Indicates the minimum inspection cycle; Indicates the basic inspection cycle; Indicates emergency response factors; Indicates taking and The larger value in the range.

8. A collaborative verification-based intelligent linkage system for mountain fire prevention PTZ cameras, applied to the collaborative verification-based intelligent linkage method for mountain fire prevention PTZ cameras as described in any one of claims 1-7, characterized in that, The system includes: The base output module is used to build a dynamic risk assessment system for mountain fire prevention PTZ cameras. It collects historical wildfire fault data, real-time tower environment data, meteorological fire prevention forecast data and high-precision topographic data, and performs spatiotemporal alignment and standardization processing to output a unified data base. The heat map generation module is used to divide the mountain power transmission line into multiple grid units based on the unified data base, and calculate the dynamic fire risk value of each grid unit to generate a dynamic fire risk heat map. The spatial overlay module is used to establish a spatial model of the preset positions of the mountain fire prevention PTZ camera, calibrate the installation three-dimensional coordinates, field of view and maximum monitoring distance of the mountain fire prevention PTZ camera, construct a three-dimensional terrain occlusion model in combination with lidar scanning, calculate the effective monitoring range of each preset position and spatially overlay it with the dynamic fire risk heat map, and output the average coverage risk and monitoring redundancy rate of each preset position. The weight calculation module is used to construct a multi-dimensional weight calculation system based on the average coverage risk and monitoring redundancy rate of each preset position, combined with the real-time device status of the corresponding PTZ machine, and output the comprehensive inspection weight of each preset position. The scheme determination module is used to convert the comprehensive inspection weight of each preset position into an inspection cycle using a mountain emergency constraint inverse proportional model, and output a dynamic inspection scheduling scheme by combining the gimbal task conflict scheduling rules and the mountain wildfire emergency response mechanism.

9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program, characterized in that, When the processor runs the computer program stored in the memory, the processor executes the steps of the intelligent linkage method for mountain fire prevention PTZ cameras based on collaborative verification as described in any one of claims 1-7.

10. A readable storage medium storing a computer program, characterized in that, When the computer program is executed by the processor, it is used to implement the steps of the intelligent linkage method for mountain fire prevention PTZ cameras based on collaborative verification as described in any one of claims 1-7.

Images