A smart forestry topography surveying and mapping and resource monitoring integrated system

Abstract

The application provides a kind of wisdom forestry topography surveying and mapping and resource monitoring integrated system, comprising: parameter acquisition and preprocessing module: the relevant parameters of forestry surveying and mapping are collected, and the relevant parameters collected are preprocessed;Macroscopic change screening module: generate macroscopic change index through relevant parameters, compare macroscopic change index with preset threshold value;Urgency sorting module: when macroscopic change index is greater than preset threshold value, collect urgency characteristic data, and generate abnormal urgency index;Response decision module, combine weather availability, unmanned aerial vehicle hangar state with macroscopic change index, abnormal urgency index to generate response decision index;Task classification dispatching module: compare response decision index with preset first threshold value and second threshold value.The application can make the system automatically classify and dispatch unmanned aerial vehicles, satellites and artificial patrol tasks through response decision index, thereby improving the utilization efficiency of monitoring resources.

Description

Technical Field

[0001] This invention relates to the field of remote sensing monitoring technology, specifically to an integrated system for intelligent forestry topographic mapping and resource monitoring. Background Technology

[0002] With the deepening of ecological civilization construction, forestry management is gradually transforming from traditional extensive management to refined, digitalized, and intelligent management. Forest resource monitoring, forest land protection, pest and disease control, and forest fire prevention place increasingly higher demands on the timeliness, accuracy, and coverage of geographic information. However, in forestry monitoring, satellite, drone, and manual patrols operate independently, lacking a collaborative mechanism. When changes occur in vegetation, it is difficult to automatically assign tasks based on the urgency of the change and resource availability, resulting in poor response timeliness and low resource utilization efficiency. By constructing an integrated system, the system can automatically assign drone, satellite, or manual patrol tasks according to different levels, thereby improving the efficiency of monitoring resource utilization, shortening emergency response time, and reducing reliance on manual labor.

[0003] The prior art, disclosed in CN120368927B, presents a method and system for remote sensing mapping of forest topography for smart forestry. This technology includes: acquiring remote sensing images of the forest area to be measured; acquiring the elevation values ​​of each monitoring station within the forest area and their corresponding grayscale values ​​in the remote sensing images, and establishing an elevation-grayscale relationship model; determining the vegetation cover density of each zone within the forest area based on the grayscale values ​​of each pixel in the remote sensing image corresponding to that zone; determining the theoretical elevation value corresponding to the grayscale value of each pixel in the remote sensing image corresponding to that zone based on the elevation-grayscale relationship model, and correcting the measured elevation value based on the vegetation cover density and the theoretical elevation value to obtain a weighted elevation value; determining the seasonal weight based on the temperature of the forest area to be measured, and determining the target elevation value of the zone based on the seasonal weight and the weighted elevation value.

[0004] However, in the aforementioned existing technologies, satellites, drones, and manual patrols operate independently during forestry monitoring, lacking a collaborative mechanism. This makes it difficult to automatically prioritize and assign tasks based on the urgency of changes and resource availability, resulting in poor response timeliness and low resource utilization efficiency. Change screening largely relies on manual interpretation or single vegetation index threshold segmentation, leading to low automation and a high rate of missed or false alarms in complex terrain. After detecting suspected changes, there is a lack of a quantitative urgency assessment method that comprehensively considers ecological sensitivity, accessibility, and the frequency of historical disturbances, making it difficult to scientifically determine the priority of response. Furthermore, the lack of integration of meteorological conditions and the availability of resources such as drones during task generation often results in situations where tasks cannot be executed.

[0005] The information disclosed in the background section is only intended to enhance the understanding of the background of this disclosure, and therefore may include information that does not constitute prior art known to those skilled in the art. Summary of the Invention

[0006] The purpose of this invention is to provide an integrated system for intelligent forestry topographic mapping and resource monitoring to address the problems mentioned in the background section. This invention achieves automatic screening of change areas through a macro-change index and adaptive thresholds, reducing missed detections and false alarms; it prioritizes high-risk areas by using an anomaly urgency index that integrates area, ecological red line, accessibility, and historical disturbances; it generates a response decision index by combining weather availability and UAV resource status, automatically assigning tasks to UAVs, satellites, or human terminals to achieve on-demand resource scheduling; and it dynamically updates historical data through verification results, forming a closed-loop optimization, significantly improving the timeliness and intelligence level of intelligent forestry monitoring. To achieve the above objectives, the present invention provides the following technical solution: An integrated intelligent forestry topographic mapping and resource monitoring system includes: Parameter acquisition and preprocessing module: Acquires relevant parameters for forestry surveying, including the current phase normalized vegetation index, historical baseline values ​​of the normalized vegetation index, and texture difference values; preprocesses the acquired parameters, including geometric registration, atmospheric correction, and radiometric normalization. Macroeconomic Change Screening Module: After preprocessing the relevant parameters, a macroeconomic change index is generated based on the relevant parameters. The macroeconomic change index is used to quickly screen and identify areas of change. A preset threshold is set, and the macroeconomic change index is compared with the preset threshold. Urgency ranking module: When the macro-change index exceeds a preset threshold, urgency feature data is collected. This urgency feature data includes the area of ​​change, distance to the ecological red line, road distance, and historical disturbance frequency. An abnormal urgency index is generated from this urgency feature data. The abnormal urgency index is used to comprehensively quantify the spatial scale, ecological sensitivity, traffic accessibility, and historical disturbance degree of suspected change areas, thereby ranking and determining the priority of handling change areas and obtaining a priority list. Response Decision Module: Analyzes weather conditions based on wind speed, rainfall, and cloud cover to generate weather availability and retrieves drone hangar status; combines weather availability, drone hangar status, macroeconomic change index, and anomaly urgency index to generate a response decision index; Task tiered dispatch module: The response decision index is compared with a preset first threshold and a second threshold. When the response decision index is greater than or equal to the first threshold, a high-precision UAV acquisition task is automatically generated and dispatched to the mapping and sensing unit. When the response decision index is between the second threshold and the first threshold, a high-resolution satellite image ordering instruction is automatically generated. When the comprehensive decision value is less than or equal to the second threshold, a manual patrol and verification task is automatically generated and pushed to the patrol terminal.

[0007] Furthermore, the preprocessing includes geometric registration, atmospheric correction, and radiometric normalization. Geometric registration includes: using historical reference images as a reference, extracting corresponding control points between the current time-phase image and the historical reference image, performing spatial coordinate transformation using a quadratic polynomial transformation model, and resampling using bilinear interpolation to ensure that the current time-phase image and the historical reference image are precisely aligned pixel by pixel in spatial position, with the registration error controlled within 0.5 pixels. Atmospheric correction includes: using a radiative transfer model to convert the original digital quantization values ​​of the remote sensing image into surface reflectance, eliminating the influence of atmospheric scattering, absorption, and aerosols on surface reflectance information. Radiometric normalization includes: using historical reference images as a reference, selecting pseudo-invariant feature regions, and performing radiometric normalization processing on the current time-phase image using a histogram matching method to ensure that the historical reference image and the current time-phase image have a consistent radiometric reference.

[0008] Furthermore, after preprocessing the relevant parameters, a macroeconomic change index is generated using these parameters. This macroeconomic change index is calculated using the following formula: ; in: This is a macroeconomic change index; The normalized vegetation index for the current time phase; This is the historical baseline value for the Normalized Difference Vegetation Index; This represents the texture difference value; Represents the relative vegetation change rate; α and β are the weighting coefficients for the relative vegetation change rate and texture difference value, respectively. , ; It is a stable constant that prevents mathematical anomalies caused by a denominator of zero and controls the numerical stability of exponent calculations.

[0009] Furthermore, the macro-change index is compared with a preset threshold, which is statistically determined based on the distribution characteristics of the macro-change index in historically changed and unchanged areas. Several known stable areas without change are selected as training samples, and the macro-change index value of each sample is calculated. The 95th percentile of the macro-change index value is taken as the preset threshold to ensure that the false positive rate is controlled within 5%. The threshold is dynamically adjusted according to the management objectives and seasonal characteristics of the monitoring area. During the fire prevention period and the high incidence of illegal logging, the preset threshold is lowered to improve monitoring sensitivity, while the standard threshold is maintained during the regular monitoring period to balance accuracy and efficiency. The macro-change index is compared with the preset threshold pixel by pixel: if the macro-change index is greater than or equal to the preset threshold, the patch is determined to be a suspected change area, and its spatial location, change intensity, and geometric features are extracted to generate a list of suspected change patches; if the macro-change index is less than the preset threshold, it is marked as a stable area and no further processing is performed.

[0010] Furthermore, when the macro-change index is greater than or equal to a preset threshold, the system identifies the corresponding map patch as a suspected change map patch and triggers the calculation process of the abnormal urgency index. For each suspected change map patch, the system automatically extracts four urgency feature data from the integrated spatial database: change area, distance to ecological red line, road distance, and historical disturbance frequency. These four data points are then substituted into the abnormal urgency index formula, and weighted and fused using preset weighting coefficients to calculate the abnormal urgency index for each map patch. The abnormal urgency index is calculated using the following formula: ; in: An exceptionally urgent index; A represents the area of ​​change; Distance to the ecological red line; Road distance; Frequency of historical disturbances; These are the weighting coefficients for the area of ​​change, distance from the ecological red line, distance from the road, and frequency of historical disturbances, respectively. The relationship between the weighting coefficients is as follows: .

[0011] Furthermore, after calculating the urgency index for all suspected changed map features, the system sorts them in descending order of urgency index, generates a priority list, and transmits the priority list along with the macro-change index value to the response decision module. After subsequent monitoring tasks are completed, the system updates the historical disturbance frequency based on the verification results: if the verification confirms a real change, the historical disturbance frequency of the corresponding map feature is incremented by one; if the verification is a false alarm, the historical disturbance frequency remains unchanged. The updated historical disturbance frequency will participate in the calculation of the abnormal urgency index for the next cycle.

[0012] Furthermore, the system collects three meteorological factors in real time: wind force level, rainfall intensity, and cloud cover. Based on preset meteorological scoring rules, each factor is assigned a score between 0 and 1. Specifically, wind force level 3 or lower is scored as 1.0, level 4 as 0.5, and level 5 or higher as 0; no rain is scored as 1.0, light rain as 0.3, and moderate rain or higher as 0; cloud cover below 30% is scored as 1.0, between 30% and 70% as 0.5, and above 70% as 0.2. The three scores are then weighted and summed according to preset weights to generate a weather availability parameter, ranging from 0 to 1, with higher values ​​indicating greater suitability for drone operations. Simultaneously, the system retrieves the drone hangar status recorded in the drone equipment management system to obtain the number of currently available drones, truncating it to an integer between 0 and 2. 0 indicates no available drones, 1 indicates one available drone, and 2 or higher indicates two or more available drones.

[0013] Furthermore, the formula for calculating weather availability is: ; in: Weather availability; Wind force rating; Score the rainfall; Rate cloud cover; These are the weighting coefficients for wind force score, rainfall score, and cloud cover score, respectively. , .

[0014] Furthermore, the response decision index is calculated using the following formula: ; in: In response to the decision index; The drone hangar is in operation. This is the execution capability item, reflecting the impact of execution capability on decision-making; These are the weighting coefficients for the macroeconomic change index, the abnormal urgency index, and the execution capability item, respectively. , .

[0015] Furthermore, the response decision index is compared with a preset first threshold and a second threshold, where the first threshold is greater than the second threshold. When the response decision index is greater than or equal to the first threshold, it is determined to be a high-priority response state, and the system automatically generates a high-precision UAV acquisition task, including the geographic coordinates of the target patch, the acquisition area, the required payload type, and preset flight path parameters, and dispatches the high-precision acquisition task instruction to the mapping and sensing unit for execution. When the response decision index is between the second threshold and the first threshold, it is determined to be a medium-priority response state, and the system automatically generates a high-resolution satellite image ordering instruction, which includes the geographic coordinate range of the suspected changed patch, the spatial resolution requirement of better than 1 meter, and the current temporal acquisition time window, and sends it to the satellite data service provider interface through the cloud collaborative processing platform. When the response decision index is less than or equal to the second threshold, it is determined to be a low-priority response state, and the system automatically generates a manual patrol and verification task, which includes the patch location, the preset verification route, and the content to be verified, and pushes it to the patrol terminal for forest rangers to verify during daily patrols.

[0016] Compared with existing technologies, the beneficial effects of this invention are as follows: It achieves automated and accurate screening of changed areas through a macro-change index and adaptive thresholds, effectively reducing the rates of missed detections and false alarms. By comprehensively assessing the changed area, distance to ecological red lines, road accessibility, and historical disturbance frequency using an anomaly urgency index, it scientifically prioritizes suspected changed areas, ensuring that high-ecological-risk areas are addressed first. Furthermore, the system incorporates weather availability and drone resource status to generate a response decision index and automatically assigns tasks to drones, satellites, or manual patrol terminals, solving the problem of monitoring resource mismatch and achieving on-demand scheduling. Simultaneously, by dynamically updating historical disturbance frequencies through verification results, a closed-loop optimization mechanism is formed, enabling the system to have self-learning capabilities and significantly improving the timeliness, intelligence level, and resource utilization efficiency of smart forestry monitoring. Attached Figure Description

[0017] Figure 1 This is a system block diagram of an integrated intelligent forestry topographic mapping and resource monitoring system. Figure 2 This is a flowchart illustrating the integrated system for intelligent forestry topographic mapping and resource monitoring according to the present invention. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this invention clearer, the invention will be further described in detail below with reference to specific embodiments.

[0019] It should be noted that, unless otherwise defined, the technical or scientific terms used in this invention should have the ordinary meaning understood by one of ordinary skill in the art to which this invention pertains. The terms "first," "second," and similar terms used in this invention do not indicate any order, quantity, or importance, but are merely used to distinguish different components. Terms such as "comprising" or "including" mean that the element or object preceding the word encompasses the elements or objects listed following the word and their equivalents, without excluding other elements or objects. Terms such as "connected" or "linked" are not limited to physical or mechanical connections, but can include electrical connections, whether direct or indirect. Terms such as "upper," "lower," "left," and "right" are used only to indicate relative positional relationships; when the absolute position of the described object changes, the relative positional relationship may also change accordingly.

[0020] Example: Please refer to Figures 1-2 The present invention provides a technical solution: An integrated intelligent forestry topographic mapping and resource monitoring system includes: Parameter Acquisition and Preprocessing Module: This module acquires relevant parameters from forestry surveying, including the current temporal normalized vegetation index (NVR), historical NVR baseline values, and texture difference values. The current temporal NVR is obtained by acquiring the surface reflectance in the red and near-infrared bands of the current temporal satellite remote sensing image and calculating it pixel-by-pixel using the NVR calculation formula. The historical NVR baseline value is a reference value retrieved from the integrated spatial database for the same area during the same historical period or the previous monitoring cycle. The texture difference value is obtained by extracting the near-infrared bands of the current temporal and historical baseline images, calculating contrast, entropy, and homogeneity texture features using a gray-level co-occurrence matrix, and calculating the Euclidean distance between the two sets of texture feature vectors. This value is used to characterize the degree of change in the spatial structure of land cover. The collected parameters are preprocessed, including geometric registration, atmospheric correction, and radiometric normalization. Specifically, geometric registration involves: using historical reference images as a reference, and combining automatic feature point extraction algorithms with manual correction to obtain uniformly distributed and accurately positioned corresponding control points between the current temporal image and the historical reference image; employing a quadratic polynomial transformation model to perform spatial coordinate transformation on the current temporal image to correct geometric deformations caused by sensor attitude, orbital drift, and terrain undulations; and using bilinear interpolation for grayscale resampling to ensure pixel-by-pixel precise alignment between the current temporal image and the historical reference image while maintaining the continuity of image radiometric information, with registration errors controlled within 0.5 pixels, ensuring a one-to-one correspondence of pixels between the two images at the same geographic coordinates.

[0021] Atmospheric correction specifically involves using a radiative transfer model, combined with metadata parameters such as solar geometric parameters, atmospheric aerosol optical thickness, and water vapor content during image imaging, to convert the raw digital quantization values ​​of remote sensing images into surface reflectance. Through atmospheric correction, the influence of atmospheric molecular scattering, aerosol scattering, and water vapor absorption on surface reflectance information is eliminated, ensuring that image pixel values ​​truly reflect the physical reflectance characteristics of surface cover and guaranteeing physical comparability of images from different time phases in the radiative dimension.

[0022] Radiation normalization specifically involves: using historical baseline imagery as the radiation reference standard, firstly, selecting land cover types with relatively stable radiation characteristics over time as pseudo-invariant feature regions. These pseudo-invariant feature regions include deep water bodies, exposed rocks, artificial structures, or large roofs. Then, statistically analyzing the cumulative histogram distributions of the baseline imagery and the current temporal imagery within these pseudo-invariant feature regions, a grayscale mapping function is constructed. Using a histogram matching method, the grayscale distribution of the current temporal imagery is mapped to the grayscale distribution of the baseline imagery, ensuring a consistent radiation baseline between the two images. Through radiation normalization, the overall brightness deviation caused by changes in illumination conditions, differences in sensor response, and residual errors in atmospheric correction is eliminated, making the two images comparable in radiation dimension. The construction of this integrated spatial database and the spatial correlation matching of multi-source data break down the barriers between static surveying data and dynamic monitoring data, enabling deep integration of these two types of data within a unified geographical framework, providing a solid data foundation for a complete closed loop from perception to decision-making.

[0023] Macroeconomic Change Screening Module: After preprocessing the relevant parameters, a macroeconomic change index is generated based on the relevant parameters. The macroeconomic change index is calculated using the following formula: ; in: This is a macroeconomic change index; The normalized vegetation index for the current time phase; This is the historical baseline value for the Normalized Difference Vegetation Index; This represents the texture difference value; Representing the relative vegetation change rate, this term increases when the normalized vegetation index (NDI) decreases significantly or increases abnormally. Using relative values ​​instead of absolute values ​​can eliminate the influence of differences in vegetation background across different regions; the same absolute change is more indicative in low-vegetation areas than in high-vegetation areas. α and β are the weighting coefficients for the relative vegetation change rate and texture difference value, respectively. , The stability constant It is a small positive constant whose function is: when the historical benchmark value When the denominator approaches zero, It is always greater than zero, thus effectively preventing mathematical calculation anomalies caused by a denominator of zero; at the same time, by setting an appropriate lower limit, it avoids the phenomenon of a sharp amplification of the ratio term caused by small changes in low vegetation cover areas, suppresses the generation of false high values, and ensures the numerical stability and calculation reliability of the macro change index in the whole domain. The macro-change index is compared with a preset threshold, which is determined statistically based on the distribution characteristics of the macro-change index in historically changed and unchanged areas. Several stable areas within the forest area that have been confirmed to have no changes over a long period of time are selected as training samples. These stable areas include the core area of ​​the ecological red line, long-term closed forest areas, and artificially fixed sample plots. The macro-change index value of each sample is calculated, and its distribution characteristics are statistically analyzed. The 95th percentile of the macro-change index value is taken as the basic preset threshold to ensure that the false positive rate is controlled within 5% under normal conditions, that is, at most 5 out of 100 unchanged pixels are misjudged as suspected changes.

[0024] Furthermore, the preset threshold is dynamically adjusted according to the management objectives and seasonal characteristics of the monitoring area: during the fire prevention period or the peak period of illegal logging, in order to improve the monitoring sensitivity of potential fires and illegal logging activities, the preset threshold is reduced by 10% to 15% based on the basic threshold to reduce the false negative rate; during the regular monitoring period, the basic threshold is maintained to balance monitoring accuracy and data processing efficiency; during the period of vigorous vegetation growth, due to the large fluctuations in the normalized vegetation index, the preset threshold is appropriately increased by 5% to 10% to suppress false alarms caused by phenological changes.

[0025] The macro-change index is compared pixel-by-pixel with a preset threshold. If the macro-change index is greater than or equal to the preset threshold, the pixel or set of pixels is identified as a suspected change area. Its spatial coordinates and macro-change index value are automatically extracted as change intensity indicators. Geometric features of the patch, including patch area, perimeter, and shape index, are extracted through connected component analysis, generating a list of suspected change patches containing patch number, spatial location, change intensity, and geometric features. If the macro-change index is less than the preset threshold, it is marked as a stable area and no further processing is performed, thus achieving rapid initial screening and identification of change areas. By fusing the macro-change index with vegetation index and texture differences, efficient and automated screening of change areas is achieved, effectively reducing the false negative and false positive rates and significantly improving the scientific rigor and operational efficiency of the monitoring network.

[0026] Urgency Ranking Module: When the macro-change index is greater than or equal to a preset threshold, the system identifies the patch as a suspected change patch and triggers the calculation process of the abnormal urgency index, marking the transition from the change screening stage to the urgency evaluation stage. For each suspected change patch, the system automatically extracts four urgency feature data from the integrated spatial database: change area, obtained by multiplying the number of pixels covered by the patch by the area of ​​a single pixel, in hectares; ecological red line distance, calculated through spatial analysis to the minimum Euclidean distance from the patch centroid to the nearest ecological red line boundary, in meters; road distance, calculated through spatial analysis to the minimum Euclidean distance from the patch centroid to the nearest forest road, in meters; and historical disturbance frequency, calculated from historical monitoring records to count the cumulative number of times the patch and its surrounding 200-meter buffer zone have been marked as changed in the past three years. Substituting the above four data points into the abnormal urgency index formula, and using preset weighting coefficients for weighted fusion, the abnormal urgency index is calculated for each map patch, thereby achieving a quantitative evaluation of the urgency level of suspected changed map patches. The abnormal urgency index is calculated using the following formula: ; in: An exceptionally urgent index; A represents the area of ​​change; Distance to the ecological red line; Road distance; Frequency of historical disturbances; These are the weighting coefficients for the area of ​​change, distance from the ecological red line, distance from the road, and frequency of historical disturbances, respectively. The relationship between the weighting coefficients is as follows: The area of ​​change, as the most direct indicator reflecting the scale of disturbance, is given the highest weight to ensure that large-scale changes are addressed first; the distance to the ecological red line is given the second highest weight to reflect the focus on ecologically sensitive areas; the road distance is given the third highest weight as a reference for accessibility and the risk of human interference; and the frequency of historical disturbances is given the lowest weight as a supplementary reference factor to avoid the excessive influence of historical records on the assessment of the urgency of current changes. After calculating the anomaly urgency index for all suspected changed map patches, the system sorts them in descending order of anomaly urgency index, generating a list reflecting the priority of handling. This priority list includes at least key information such as map patch number, spatial coordinates, anomaly urgency index value, changed area, distance to ecological red line, road distance, and historical disturbance frequency. Furthermore, after subsequent monitoring tasks are completed, the system dynamically updates the historical disturbance frequency based on verification results from UAV checks, satellite image reviews, or manual patrols: if verification confirms a real change, including logging, pests and diseases, illegal land occupation, and road construction, the historical disturbance frequency of the corresponding map patch is incremented by one; if the verification result is a false alarm, the historical disturbance frequency remains unchanged. The updated historical disturbance frequency is stored in the integrated spatial database and participates in the calculation of the anomaly urgency index for the next cycle, ensuring that hotspots with high historical disturbance frequencies continue to receive high urgency scores, thus dynamically tilting monitoring resources towards areas with high problem incidence. By comprehensively and quantitatively evaluating the area of ​​change, distance from the ecological red line, road accessibility, and historical disturbances, a scientific ranking of the urgency of suspected change areas has been achieved, enabling early warning to evolve from regional averages to precise grading based on multi-dimensional characteristics, ensuring that high-risk areas are given priority in handling.

[0027] The response decision module collects three meteorological factors in real time: wind force level, rainfall intensity, and cloud cover. Based on preset meteorological scoring rules, it assigns a score between 0 and 1 to each factor. Wind force level is assessed according to the Beaufort scale: when the wind force is less than or equal to level 3 (wind speed not exceeding 5.5 meters per second), it is rated as suitable for flight with a score of 1.0; when the wind force is level 4 (wind speed between 5.5 and 8.0 meters per second), it is rated as critical for flight with a score of 0.5; and when the wind force is greater than or equal to level 5 (wind speed exceeding 8.0 meters per second), it is rated as prohibited from flight with a score of 0. Rainfall intensity is assessed based on hourly precipitation: 1.0 for no rain; 0.3 for light rain (less than 2.5 mm per hour); and 0 for moderate rain or above (2.5 mm or more per hour). Cloud cover is assessed based on cloud cover percentage: 1.0 for cloud cover below 30%; 0.5 for cloud cover between 30% and 70%; and 0.2 for cloud cover above 70%. The weather availability score is generated by weighting and summing these three scores according to preset weights. The formula for calculating weather availability is: ; in: Weather availability; Wind force rating; Score the rainfall; Rate cloud cover; These are the weighting coefficients for wind force score, rainfall score, and cloud cover score, respectively. , Wind speed has the highest weight because it directly affects the stability of the drone's flight attitude and its endurance, making it a core factor in determining flight safety. Rainfall has a medium weight because it not only affects the waterproof performance of the equipment but also significantly interferes with the imaging quality of optical sensors, making it an important factor affecting operational feasibility. Cloud cover has the lowest weight because it mainly affects image clarity rather than flight safety, and is therefore used as an auxiliary reference factor in the overall score. A response decision index is generated by combining weather availability, drone hangar status, macroeconomic change index, and anomaly urgency index. The response decision index is calculated using the following formula: ; in: In response to the decision index; The drone hangar is in operation. This is the execution capability item, reflecting the impact of execution capability on decision-making; weighting coefficient. These correspond to the contribution levels of the macroeconomic change index, the abnormal urgency index, and the execution capability index, respectively, and all three satisfy the normalization constraint. And strictly follow The size relationship; among which, The highest value reflects the primary importance of the intensity of change in decision-making; The value should be centered to reflect the importance of urgency as a key reference factor. The lowest value is used to reflect the execution capability as a supplementary basis for feasibility constraints, avoiding excessive influence of resource conditions on response decisions in areas of significant change. By incorporating meteorological conditions and UAV resource status into the decision-making model, on-demand and precise scheduling of monitoring resources is achieved, effectively solving the resource mismatch problem and significantly improving the timeliness and success rate of emergency response.

[0028] The task tiered dispatch module compares the response decision index with a preset first threshold and a second threshold, where the first threshold is greater than the second threshold. When the response decision index is greater than or equal to the first threshold, it is determined to be a high-priority response state. The system automatically generates a high-precision UAV data acquisition task and links it with the intelligent emergency response module. The task includes at least the geographic coordinates of the target patch, the data acquisition area, the required payload type, and preset flight path parameters. The required payload type is automatically matched according to the type of change; for vegetation changes, a multispectral or lidar payload is configured, and for structural changes, a visible light oblique photography payload is configured. The system dispatches the task instructions to the mapping and sensing unit for execution. Simultaneously, it automatically plans the UAV's approach verification flight path based on the terrain data surrounding the target patch. It can also guide the nearest fire camera to automatically turn to the target area for continuous tracking through gimbal control, achieving air-ground collaborative monitoring. Through this mechanism, fire location can be improved from approximate location to precise three-dimensional coordinates, and emergency response can be transformed from manual path finding to automatic optimal path planning and UAV verification by the system, greatly improving the accuracy and speed of early warning and response.

[0029] When the response decision index is between the second threshold and the first threshold, it is determined to be a medium-priority response state. The system automatically generates a high-resolution satellite image ordering instruction: the instruction includes the geographic coordinate range of the suspected changed patch, the spatial resolution requirement of better than 1 meter, and the current time window for acquisition, and sends it to the satellite data service provider interface through the cloud collaborative processing platform; after the ordered image data is received, it is automatically stored in the database and compared with historical images in the integrated spatial database for further confirmation of suspected changed areas and identification of change types.

[0030] When the response decision index is less than or equal to the second threshold, it is determined to be a low-priority response state. The system automatically generates a manual patrol and verification task: the task includes the location of the map patch, the preset verification route and the content to be verified, and pushes it to the patrol terminal for forest rangers to verify along the way during daily patrols; the verification results are transmitted back in real time through the mobile terminal, and after being processed by the dynamic data fusion and correction engine, the historical disturbance frequency records in the integrated spatial database are updated to provide data support for the subsequent calculation of the abnormal urgency index.

[0031] Through the aforementioned tiered response mechanism, the system achieves coordinated configuration of multi-level monitoring methods, from high-priority UAV emergency verification and medium-priority satellite imagery supplementation to low-priority manual patrol verification. This ensures that monitoring resources are allocated as needed, and that response time matches the urgency of changes, forming a closed-loop smart forestry monitoring system covering the entire area and providing layered responses. As a result, the system breaks down data barriers between surveying and monitoring, enabling deep integration of static spatial data and dynamic monitoring data within a unified geographical framework. This achieves data fusion and business collaboration, supporting a complete closed loop from perception to decision-making. Simultaneously, the optimized deployment of monitoring equipment based on terrain data reduces blind spots at the source, improves the monitoring efficiency of individual devices, and lowers the cost of blind deployment. Ultimately, by integrating all dynamic and static information, the system provides managers with unprecedented global situational awareness and precise decision support tools, enhancing the visualization and intelligence of management.

[0032] The above embodiments can be implemented, in whole or in part, by software, hardware, firmware, or any other combination thereof. When implemented in software, the above embodiments can be implemented, in whole or in part, as a computer program product. Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented by electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution.

[0033] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment, depending on actual needs.

[0034] The above description is merely a specific embodiment of this application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the scope of the technology disclosed in this application should be included within the scope of protection of this application.

Claims

1. An integrated system for intelligent forestry topographic mapping and resource monitoring, characterized in that, include: Parameter acquisition and preprocessing module: Acquires relevant parameters for forestry surveying, including the current phase normalized vegetation index, historical baseline values ​​of the normalized vegetation index, and texture difference values; preprocesses the acquired parameters, including geometric registration, atmospheric correction, and radiometric normalization. Macro-change screening module: After preprocessing the relevant parameters, a macro-change index is generated based on the relevant parameters. The macro-change index is used to achieve rapid initial screening and identification of areas of change. The macroeconomic change index is calculated using the following formula: ； in: This is a macroeconomic change index; The normalized vegetation index for the current time phase; This is the historical baseline value for the Normalized Difference Vegetation Index; This represents the texture difference value; Represents the relative vegetation change rate; α and β are the weighting coefficients for the relative vegetation change rate and texture difference value, respectively. , ; It is a stable constant that prevents mathematical anomalies caused by a denominator of zero and controls the numerical stability of exponent calculations. A preset threshold is established, and the macro-change index is compared with the preset threshold. The preset threshold is determined statistically based on the distribution characteristics of the macro-change index in historically changed and unchanged areas. Several known stable areas without change are selected as training samples, and the macro-change index value of each sample is calculated. The 95th percentile of the macro-change index value is taken as the preset threshold to ensure that the false positive rate is controlled within 5%. The preset threshold is dynamically adjusted according to the management objectives and seasonal characteristics of the monitoring area. During the fire prevention period and the high incidence of illegal logging, the preset threshold is lowered to improve monitoring sensitivity, while the standard threshold is maintained during the regular monitoring period to balance accuracy and efficiency. The macro-change index is compared with the preset threshold pixel by pixel: if the macro-change index is greater than or equal to the preset threshold, the patch is determined to be a suspected change area, and its spatial location, change intensity, and geometric features are extracted to generate a list of suspected change patches; if the macro-change index is less than the preset threshold, it is marked as a stable area and no further processing is performed. Urgency ranking module: When the macro-change index exceeds a preset threshold, urgency feature data is collected. This urgency feature data includes the area of ​​change, distance to the ecological red line, road distance, and historical disturbance frequency. An abnormal urgency index is generated from this urgency feature data. The abnormal urgency index is used to comprehensively quantify the spatial scale, ecological sensitivity, traffic accessibility, and historical disturbance degree of suspected change areas, thereby ranking and determining the priority of handling change areas and obtaining a priority list. Response Decision Module: Analyzes weather conditions based on wind speed, rainfall, and cloud cover to generate weather availability and retrieves drone hangar status; combines weather availability, drone hangar status, macroeconomic change index, and anomaly urgency index to generate a response decision index; Task tiered dispatch module: The response decision index is compared with a preset first threshold and a second threshold. When the response decision index is greater than or equal to the first threshold, a high-precision UAV acquisition task is automatically generated and dispatched to the mapping and sensing unit. When the response decision index is between the second threshold and the first threshold, a high-resolution satellite image ordering instruction is automatically generated. When the comprehensive decision value is less than or equal to the second threshold, a manual patrol and verification task is automatically generated and pushed to the patrol terminal.

2. The integrated system for intelligent forestry topographic mapping and resource monitoring according to claim 1, characterized in that: The preprocessing includes geometric registration, atmospheric correction, and radiometric normalization. Geometric registration involves extracting corresponding control points between the current time-phase image and the historical reference image, using a quadratic polynomial transformation model for spatial coordinate transformation, and resampling via bilinear interpolation to ensure precise pixel-by-pixel alignment between the current time-phase image and the historical reference image, with registration errors controlled within 0.5 pixels. Atmospheric correction involves converting the raw digital quantization values ​​of the remote sensing image into surface reflectance using a radiative transfer model to eliminate the influence of atmospheric scattering, absorption, and aerosols on surface reflectance information. Radiometric normalization involves selecting pseudo-invariant feature regions based on the historical reference image and performing radiometric normalization processing on the current time-phase image using a histogram matching method to ensure that the historical reference image and the current time-phase image have a consistent radiometric reference.

3. The integrated system for intelligent forestry topographic mapping and resource monitoring according to claim 1, characterized in that: When the macro-change index is greater than or equal to a preset threshold, the system identifies the corresponding map patch as a suspected change map patch and triggers the calculation process of the abnormal urgency index. For each suspected change map patch, the system automatically extracts four urgency feature data from the integrated spatial database: change area, distance to ecological red line, road distance, and historical disturbance frequency. These four data points are then substituted into the abnormal urgency index formula, and weighted and fused using preset weighting coefficients to calculate the abnormal urgency index for each map patch. The abnormal urgency index is calculated using the following formula: ； in: An exceptionally urgent index; A represents the area of ​​change; Distance to the ecological red line; Road distance; Frequency of historical disturbances; These are the weighting coefficients for the changed area, distance to the ecological red line, road distance, and frequency of historical disturbances, respectively. The relationship between the weighting coefficients is as follows: .

4. The integrated system for intelligent forestry topographic mapping and resource monitoring according to claim 3, characterized in that: After calculating the urgency index for all suspected changed map features, the system sorts them in descending order of urgency index, generates a priority list, and transmits the priority list along with the macro-change index value to the response decision module. After subsequent monitoring tasks are completed, the system updates the historical disturbance frequency based on the verification results: if the verification confirms a real change, the historical disturbance frequency of the corresponding map feature is incremented by one; if the verification is a false alarm, the historical disturbance frequency remains unchanged. The updated historical disturbance frequency will participate in the calculation of the abnormal urgency index for the next cycle.

5. The integrated system for intelligent forestry topographic mapping and resource monitoring according to claim 1, characterized in that: The system collects three meteorological factors in real time: wind force, rainfall intensity, and cloud cover. Based on preset meteorological scoring rules, each factor is assigned a score between 0 and 1. Specifically, wind force is 1.0 for wind speed less than or equal to level 3, 0.5 for level 4, and 0 for level 5 and above; no rain is 1.0, light rain is 0.3, and moderate rain or above is 0; cloud cover is 1.0 for cloud cover below 30%, 0.5 for cloud cover between 30% and 70%, and 0.2 for cloud cover above 70%. The three scores are then weighted and summed according to preset weights to generate a weather availability parameter, ranging from 0 to 1, with higher values ​​indicating greater suitability for drone operations. Simultaneously, the system retrieves the drone hangar status recorded in the drone equipment management system to obtain the number of currently available drones, truncating the result to an integer between 0 and 2. 0 indicates no available drones, 1 indicates one available drone, and 2 or higher indicates two or more available drones.

6. The integrated system for intelligent forestry topographic mapping and resource monitoring according to claim 5, characterized in that: The formula for calculating weather availability is: ； in: Weather availability; Wind force rating; Score the rainfall; Rate cloud cover; These are the weighting coefficients for wind force score, rainfall score, and cloud cover score, respectively. , .

7. The integrated system for intelligent forestry topographic mapping and resource monitoring according to claim 6, characterized in that: The response decision index is calculated using the following formula: ； in: In response to the decision index; The drone hangar is in operation. This is the execution capability item, reflecting the impact of execution capability on decision-making; These are the weighting coefficients for the macroeconomic change index, the abnormal urgency index, and the execution capability item, respectively. , .

8. The integrated system for intelligent forestry topographic mapping and resource monitoring according to claim 7, characterized in that: The response decision index is compared with a preset first threshold and a second threshold, wherein the first threshold is greater than the second threshold; When the response decision index is greater than or equal to the first threshold, it is determined to be a high-priority response state. The system automatically generates a high-precision UAV acquisition task, including the geographic coordinates of the target patch, the acquisition area, the required payload type, and the preset flight path parameters. The high-precision acquisition task instruction is then dispatched to the mapping and sensing unit for execution. When the response decision index is between the second threshold and the first threshold, it is determined to be a medium-priority response state. The system automatically generates a high-resolution satellite image ordering instruction, which includes the geographic coordinate range of the suspected changed patch, the spatial resolution requirement of better than 1 meter, and the current time acquisition window. This instruction is then sent to the satellite data service provider interface through the cloud collaborative processing platform. When the response decision index is less than or equal to the second threshold, it is determined to be a low-priority response state. The system automatically generates a manual patrol and verification task. The patrol and verification task includes the location of the map patch, the preset verification route and the content to be verified, and pushes it to the patrol terminal for forest rangers to verify during daily patrols.

Images