An earth-air-space integrated forest and grass resource intelligent monitoring system and method

Abstract

The application discloses a kind of heaven and earth air integration forest and grass resource intelligent supervision system and method, it is related to forest and grass resource supervision technical field;The present application is obtained by image recognition technology from the target area of identification in the supervision area, to track the target area and inspect the target matching several target unmanned aerial vehicles;With target area as the encirclement target, several target unmanned aerial vehicles are planned to track the route;Several target unmanned aerial vehicles are controlled to track the target area according to the tracking route and inspect, while sending tracking information to the inspector.The present application relies on the heaven and earth air integration monitoring architecture, and encircles the tracking instead of traditional single direction inspection, fundamentally solves the problem that forest and grass resource abnormal diffusion direction is unpredictable and easy to lose tracking target;Through multi-machine encirclement covering target area full direction diffusion path, abnormal dynamic such as fire spread, illegal personnel fleeing, etc. can be captured in real time, to avoid missed inspection and tracking failure, guarantee the reliability of forest and grass resource supervision.

Description

Technical Field

[0001] This invention belongs to the field of forestry and grassland resource monitoring technology, specifically an integrated air-ground-space intelligent monitoring system and method for forestry and grassland resources. Background Technology

[0002] Forest and grassland resource supervision is a comprehensive management work that relies on integrated air, land, and space monitoring to conduct routine inspections, dynamic monitoring, risk warnings, and rectification of violations of ecological resources such as forests, grasslands, and wetlands. It can promptly detect problems such as illegal logging, illegal encroachment, fire hazards, vegetation degradation, and the spread of pests and diseases, and comprehensively grasp the quantity, quality, and spatial changes of forest and grassland resources.

[0003] The existing traditional methods for supervising forest and grassland resources mainly rely on a combination of manual ground patrols, regular on-site inspections, scattered video surveillance, and periodic remote sensing spot checks. These methods depend on forest rangers conducting daily patrols in grid-based areas, supplemented by a small number of fixed cameras on-site. They also involve manual comparison and verification of resource changes using quarterly or annual satellite remote sensing images. This approach passively detects and handles issues such as forest fires, illegal logging, illegal land occupation, grassland degradation, and pests and diseases. The overall process is mainly based on manual visual judgment, offline hierarchical reporting, and on-site rectification and investigation. This approach cannot achieve timely tracking of abnormal situations and is difficult to effectively curb the development of abnormal conditions.

[0004] This invention provides an integrated air-ground-space intelligent monitoring system and method for forest and grassland resources to solve the above-mentioned technical problems. Summary of the Invention

[0005] The present invention aims to solve at least one of the technical problems existing in the prior art; to this end, the present invention proposes an integrated air-ground-space intelligent monitoring system and method for forest and grassland resources.

[0006] To achieve the above objectives, a first aspect of the present invention provides an integrated air-ground-space intelligent monitoring method for forest and grassland resources, comprising: The target area is identified from the monitored area using image recognition technology; the target area is an abnormal area that needs to be tracked and inspected. The system aims to match several target drones with the goal of tracking and inspecting the target area; and to plan tracking routes for the target drones by encircling the target area. Control several target drones to track and inspect the target area according to the tracking route, and send the tracking information to the inspection personnel at the same time.

[0007] In one possible implementation, the target area is identified from the monitored area using image recognition technology, including: Based on the analysis of image data, several abnormal areas and their abnormality types were identified within the monitored area; the image data was acquired through remote sensing satellites or inspection drones. Determine whether the anomaly type of the abnormal region belongs to the preset tracking type; if yes, mark the abnormal region as the target region; otherwise, do not mark the abnormal region.

[0008] In one possible implementation, several target drones are matched with the objective of tracking and inspecting a target area, including: The tracking area is expanded based on the circumcircle of the target area; the number of drones required for the tracking area is calculated based on the maximum tracking field of view of the inspection drone; the inspection drones are set up in the gridded monitoring area; A number of inspection drones within the monitored area that meet the requirements are selected; among them, meeting the requirements includes both machine status and mission status meeting the requirements. With the encirclement and tracking area as the target, a number of target drones are selected from a number of inspection drones based on the demand for drones.

[0009] In one possible implementation, several inspection drones are deployed within the regulated area, including: The regulatory area is divided into grids to obtain several inspection areas; Several inspection areas are equipped with inspection drones, and the inspection drones are set up in the inspection areas; the inspection drones are used to carry out routine inspections of the inspection areas.

[0010] In one possible implementation, the tracking region is obtained by expanding the circumcircle of the target region, including: Obtain the circumcircle of the target region; The tracking area is obtained by expanding the outer circle according to the preset radius expansion value.

[0011] In one possible implementation, the drone demand in the tracking area is calculated based on the maximum tracking field of view of the inspection drone, including: Retrieve the maximum tracking field of view of the inspection drone; where maximum tracking field of view refers to the maximum range of ground targets that the inspection drone can identify. With the goal of covering the boundary of the tracking area, the demand for drones in the tracking area is calculated by combining the maximum tracking field of view.

[0012] In one possible implementation, a number of target drones are determined from a pool of inspection drones based on the demand for drones, including: The inspection drone closest to the boundary of the tracking area is used as the reference drone; the intersection of the line connecting the reference drone and the boundary of the tracking area is used as the reference point. Based on the reference points and the maximum tracking field of view, several reference points are sequentially determined on the boundary of the tracking area; the number of reference points is consistent with the number of drones required. The nearest inspection drone is matched to each reference point in turn; the inspection drones matched to several reference points are marked as target drones, and the target drones are associated with the reference points.

[0013] In one possible implementation, tracking routes are planned for several target drones, including: Retrieve the target drone and its associated reference points; use the center of the tracking area as the tracking endpoint; Plan route segment one between the real-time location of the target UAV and the reference point, and plan route segment two between the reference point and the tracking endpoint; then combine route segment one and route segment two to generate the tracking route.

[0014] In one possible implementation, when the target UAV is tracking and inspecting along route segment two, it adjusts its tracking altitude in real time, including: Determine the boundary of the tracking area covered by the maximum tracking field of view of the target UAV, and use the boundary of the tracking area and the center of the tracking area to determine the tracking target area; wherein, the tracking target area is a fan-shaped area; Adjust the tracking altitude of the target drone according to the target area to ensure that the target drone's field of vision always covers the target area.

[0015] The second aspect of the present invention provides an integrated air-ground-land intelligent monitoring system for forest and grassland resources, including a central processing module and several inspection drones; Central processing module: used to identify target areas from the monitored area using image recognition technology; where the target area is an abnormal area that needs to be tracked and inspected; Used for matching several target drones with the goal of tracking and inspecting a target area; planning tracking routes for several target drones with the target area as an encirclement target; and... This is used to control several target drones to track and inspect target areas according to the tracking route, while sending tracking information to inspection personnel.

[0016] Compared with the prior art, the beneficial effects of the present invention are: 1. This invention first identifies the target area from the monitored area using image recognition technology, and then matches several target drones with the target area as the target for tracking and inspection. Using the target area as the encirclement target, tracking routes are planned for the target drones. The drones are then controlled to track and inspect the target area according to the tracking routes, while simultaneously sending tracking information to the inspection personnel. This invention relies on an integrated air-ground-space monitoring architecture, replacing traditional single-direction inspections with encirclement tracking, fundamentally solving the problems of unpredictable abnormal spread of forest and grassland resources and the easy loss of tracking targets. By using multiple drones to encircle and cover the entire spread path of the target area, it can capture abnormal dynamics such as fire spread and escape of violators in real time, avoiding missed detections and tracking failures, and ensuring the reliability of forest and grassland resource supervision.

[0017] 2. This invention first divides the regulatory area into grids and configures fixed inspection drones in each grid for routine daily inspections. The tracking area is then expanded using the circumcircle of the target area. The maximum tracking field of view of the drones is retrieved, and the required number of drones is accurately calculated based on complete coverage of the tracking area boundary. Using the drone closest to the tracking area boundary as a benchmark, boundary reference points are determined. The nearest inspection drone is then matched to each reference point and marked as the target drone, completing the association and binding with the reference point. This invention achieves refined scheduling and optimal configuration of inspection drone resources, avoiding resource waste caused by blind drone deployment. Based on grid-based deployment, drones are matched to the nearest available location, significantly shortening the time to reach the task area and improving tracking response speed. The requirement is calculated based on the maximum tracking field of view, ensuring accurate quantity matching, meeting both encirclement and coverage requirements without redundant configuration. Overall, it achieves the coordinated reuse of drone resources for routine inspections and emergency tracking, improving the overall operational efficiency of the forestry and grassland regulatory system, reducing scheduling costs and equipment wear, and providing stable and reliable aerial execution capabilities for integrated air-ground intelligent regulatory. Attached Figure Description

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0019] Figure 1 This is a schematic diagram of the method flow for the intelligent monitoring method of forest and grassland resources in an embodiment of the present invention; Figure 2 This is a schematic diagram illustrating the principle of identifying the target area from the regulatory area in an embodiment of the present invention; Figure 3 This is a schematic diagram illustrating the principle of setting up several inspection drones in a monitored area in an embodiment of the present invention; Figure 4 This is a schematic diagram illustrating the principle of expanding the tracking area based on the circumcircle of the target area in an embodiment of the present invention; Figure 5 This is a schematic diagram illustrating the principle of calculating the demand for drones in the tracking area in an embodiment of the present invention; Figure 6 This is a schematic diagram illustrating the principle of planning tracking routes for several target drones in an embodiment of the present invention; Figure 7 This is a schematic diagram illustrating the principle of controlling several target drones to track and inspect a target area according to a tracking route in an embodiment of the present invention. Detailed Implementation

[0020] The technical solution of the present invention will be clearly and completely described below with reference to the embodiments. 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.

[0021] Please see Figure 1 The first aspect of the present invention provides an integrated air-ground-land intelligent monitoring method for forest and grassland resources, comprising: identifying a target area from a monitored area using image recognition technology; wherein the target area is an abnormal area that needs to be tracked and inspected; matching several target drones with the target area as the target for tracking and inspection; planning tracking routes for the several target drones with the target area as the encirclement target; controlling the several target drones to track and inspect the target area according to the tracking routes, while sending tracking information to the inspection personnel.

[0022] Forestry and grassland resource supervision is a comprehensive management task involving routine inspections, dynamic monitoring, risk warnings, and rectification of violations of ecological resources such as forests, grasslands, and wetlands. It can promptly detect problems such as illegal logging, illegal encroachment, fire hazards, vegetation degradation, and the spread of pests and diseases. In the process of forestry and grassland resource supervision, it is necessary not only to identify existing problems but also to track specific issues in a timely manner, such as illegal logging and fire hazards, so as to address them promptly. The implementation process of the integrated air-ground-space intelligent supervision method for forestry and grassland resources provided by this invention is as follows: A01: The target area is identified from the monitored area using image recognition technology; the target area is an abnormal area that needs to be tracked and inspected. The target area is selected from the abnormal areas within the monitored areas, which are regions requiring forestry and grassland resource monitoring. After identifying several abnormal areas from the monitored areas, if the abnormal type corresponding to the abnormal area needs to be tracked, the abnormal area is marked as the target area, and each target area is associated with an abnormal type. If tracking of abnormal areas is not required, image data of the abnormal areas can be collected according to the preset inspection plan. The abnormal types corresponding to the abnormal areas include illegal logging, illegal encroachment, fire hazards, vegetation degradation, and pests and diseases, and custom abnormal types can also be defined for specific needs.

[0023] A02: Match several target drones with the goal of tracking and inspecting the target area; plan tracking routes for several target drones with the target area as the encirclement target. Tracking and inspecting a target area means not only collecting inspection data of the target area, but also tracking the factors that cause anomalies in the target area in order to effectively curb the spread of abnormal conditions. For example, when a fire hazard is identified in a target area, it is necessary to track the development of the fire; when illegal logging is identified in a target area, it is necessary to track the relevant personnel who carried out the illegal logging.

[0024] The spread of anomalies in the target area is closely related to the anomaly type, meteorological environment, and terrain environment. The direction of spread cannot be accurately predicted in advance, and tracking in a single direction may result in losing the target. Therefore, the target area is used as an encirclement target for tracking. Specifically, several target drones are selected from the several inspection drones deployed in the monitored area. These target drones are used to conduct encirclement inspections of the possible spread directions of anomalies in the target area to achieve timely tracking.

[0025] Similarly, the target area is used as the encirclement target for several target drones to plan the tracking route to ensure that the tracking route can cover the target area and its abnormal spread area. This can achieve all-round tracking and minimize the loss of the tracked target.

[0026] A03: Control several target drones to track and inspect the target area according to the tracking route, and send the tracking information to the inspection personnel at the same time.

[0027] When multiple target drones conduct tracking and inspection along a planned route, they can achieve encirclement inspection of the target area. If an abnormal state in the target area or the factors causing the abnormal state spreads, the encirclement inspection by multiple target drones can obtain real-time tracking information such as the direction and speed of spread. After identifying the target, continuous tracking is also possible. For example, if illegal logging is identified during the encirclement inspection, the target drones can be used to continuously track the perpetrators.

[0028] The tracking information will be promptly synchronized with the inspection personnel, who can then promptly address any abnormal conditions in the target area and prevent the recurrence of such conditions, thus achieving effective supervision of forest and grassland resources.

[0029] The coverage area of ​​monitored areas is generally large, making it impossible to accurately identify abnormal areas using a single image recognition technology. Furthermore, some abnormal areas do not expand rapidly, eliminating the need for tracking and inspection of all abnormal areas. This invention uses image recognition technology to identify several abnormal areas within a monitored area, and then filters out target areas from these abnormal areas by determining the type of anomaly, thus accurately identifying the abnormal areas that require timely tracking and inspection. The implementation process of this invention to identify target areas from monitored areas using image recognition technology is as follows: B01: Based on image data analysis, several abnormal areas and their abnormality types are identified within the monitored area; the image data is acquired via remote sensing satellites or inspection drones. Image data can be remote sensing images acquired by remote sensing satellites or inspection images acquired by inspection drones. Remote sensing images have a large coverage area, but are limited by the flight trajectory of remote sensing satellites, making it difficult to cover the entire monitored area. Inspection drones have high mobility, but their inspection range is relatively small due to environmental and energy constraints. This invention uses a combination of remote sensing satellites and inspection drones to acquire image data, ensuring both coverage and timeliness.

[0030] Image analysis models are used to identify anomalous regions and their corresponding anomaly types from image data. Anomalous regions include areas corresponding to types such as deforestation, illegal encroachment, fire hazards, vegetation degradation, and pests and diseases. The image analysis model can be built and trained based on an artificial intelligence model, which can be a deep convolutional neural network. The training and construction process of artificial intelligence models is widely disclosed in existing solutions and will not be elaborated upon here.

[0031] B02: Determine whether the anomaly type of the abnormal region belongs to the preset tracking type; if yes, mark the abnormal region as the target region; otherwise, do not mark the abnormal region.

[0032] The tracking type is preset, mainly based on whether tracking is needed to collect more and more reliable data after an anomaly type is identified. It can be set according to experience.

[0033] For example, taking five anomaly types—illegal logging, illegal encroachment, fire hazards, vegetation degradation, and pests and diseases—as examples, illegal encroachment, vegetation degradation, and pests and diseases do not require immediate tracking after identification; reliable data can be collected according to the established inspection plan. However, illegal logging and fire hazards require immediate tracking after identification. Just as a fire in a forest needs to be tracked immediately to allow firefighters to handle it accurately, illegal logging also requires immediate tracking of relevant personnel after identification to effectively curb its occurrence. Therefore, illegal logging and fire hazards are designated as preset tracking types.

[0034] The abnormality type in the abnormal area is compared with the tracking type. If the abnormality type in the abnormal area matches any of the preset tracking types, the abnormal area is marked as the target area; otherwise, the abnormal area is not marked, and the inspection data of the abnormal area is collected according to the preset inspection plan.

[0035] It should be noted that if there are multiple anomaly types in the same area, as long as one of the anomaly types belongs to the preset tracking type, the area will be marked as the target area or as part of the target area.

[0036] like Figure 2 As shown, it is assumed that the preset tracking types include two types: illegal logging and fire hazards. Figure 2 Triangular region A and elliptical region B are two abnormal regions identified within the monitored area. The anomaly type of triangular region A is illegal encroachment, and the anomaly type of elliptical region B is illegal logging. Mixed region C includes illegal logging in the elliptical region and illegal encroachment in the triangular region. Since illegal logging in elliptical region B and illegal logging in mixed region C belong to the preset tracking type, the elliptical regions in elliptical region B and mixed region C are marked as target regions.

[0037] To achieve effective tracking and inspection of a target area, relying on a single inspection drone is insufficient. Therefore, it is necessary to determine a sufficient number of inspection drones as target drones based on the coverage area of ​​the target area. Tracking reliability can be ensured by using these target drones to track the target area from multiple angles. This invention expands the tracking area based on the target area, and matches several target drones to this encircling tracking area. The implementation process of matching several target drones to track and inspect the target area in this invention is as follows: C01: The tracking area is obtained by expanding the circumcircle of the target area; the number of drones required for the tracking area is calculated based on the maximum tracking field of view of the inspection drone; the inspection drones are set up in the gridded monitoring area; The tracking area is the outer circle of the target area, and the outer circle contains the target area. The expansion of the tracking area relative to the target area is to prevent the target from rapidly spreading and rendering the tracking meaningless. For example, if the perpetrators of illegal logging have left the target area, they cannot be tracked if the target area is still used as the tracking area.

[0038] After determining the tracking area, the number of drones required for simultaneous tracking and inspection is calculated based on the maximum tracking field of view. Simultaneous tracking by inspection drones means that all drones patrol along a straight line from the boundary of the tracking area to its center. Covering the tracking area with a sufficient number of target drones improves the reliability of the tracking and inspection.

[0039] C02: Select a number of inspection drones in the monitored area whose status meets the requirements; where the status meets the requirements includes both the machine status and the mission status. Several inspection drones are pre-positioned within the monitored area to perform routine inspections. During the selection process, the machine status and task status of several inspection drones are extracted in real time. The machine status determines whether the drone can perform the task, such as whether it is malfunctioning or has sufficient battery power. The task status determines whether the drone can be prioritized for tracking and inspection, which mainly depends on whether the drone has been assigned a higher-priority task. For example, if a higher-priority task exists in the drone's task queue, that drone will not be selected as a target drone.

[0040] C03: With the encirclement and tracking area as the target, select a number of target drones from a number of inspection drones based on the demand for drones.

[0041] When there are too many inspection drones in the monitored area that meet the requirements, a portion of these drones can be selected as target drones, with the number of target drones equal to the required number of drones. If there are insufficient inspection drones in the monitored area that meet the requirements, backup drones can be used to supplement the number of target drones to ensure that there are enough.

[0042] In order to achieve effective supervision of forest and grassland resources in the regulatory area and ensure the convenience of target drone dispatch during tracking and inspection, this invention sets up several inspection drones in the gridded regulatory area. After deployment, the inspection drones will perform daily inspections of the corresponding gridded area according to a predetermined procedure. When tracking and inspection are required, they can be marked as target drones to assist in completing the tracking and inspection.

[0043] It should be noted that the grid-based management of the regulatory area is necessary for the deployment of inspection drones. The regulatory area can be divided into several grid-based inspection zones based on the inspection capabilities of the drones. One or more inspection drones can be deployed in each inspection zone.

[0044] like Figure 3 As shown, the monitored area can be divided into several rectangles, each serving as an inspection zone. At least one inspection drone is configured for each inspection zone. The drones in each zone are responsible for daily inspections of that zone and can be deployed to other zones for tracking inspections when necessary. The inspection drones are permanently stationed within their respective inspection zones and can be recharged via hangars located within those zones. Figure 3 The black dots in each inspection area represent the configured inspection drones.

[0045] In some other preferred embodiments, if the monitored area is small, all inspection drones can be fixed at a single integrated base station, where all drones can recharge and conduct daily inspections of the associated areas according to the inspection plan.

[0046] The implementation process of this invention, which extends the tracking region based on the circumcircle of the target region, is as follows: D01: Obtain the circumcircle of the target region; The circumcircle contains the target area. If the abnormal state of the target area expands outward, it is very likely to extend beyond the circumcircle in a short time. If the target area or its circumcircle is still used as the tracking area, it is very likely that the tracking will be meaningless.

[0047] D02: Expand the circumcircle according to the preset radius expansion value to obtain the tracking area.

[0048] The radius expansion value is set based on anomaly type and historical tracking experience, and can also be set as a radius expansion ratio. This radius expansion value extends the radius of the circumcircle, resulting in a larger circular area, which is then used as the tracking area. The area between the tracking area and the circumcircle serves as a buffer zone to ensure the reliability of tracking inspections. For example, when tracking personnel involved in illegal logging, the time interval between the last inspection and the current inspection can be calculated, along with the real-time movement distance per unit time. Combining these two measurements, the total movement distance can be calculated. If the total movement distance is greater than the circumcircle radius, the difference between the total movement distance and the circumcircle radius is used as the preset radius expansion value; if the total movement distance is not greater than the circumcircle radius, the radius expansion value takes the default value, such as 3km.

[0049] like Figure 4As shown, the elliptical region is the target region. First, the circumcircle of the target region is obtained, and then the tracking region is obtained by expanding the circumcircle using a preset radius expansion value. Figure 4 The outermost circular area. Assuming the anomaly type in the target area is illegal logging, and those responsible for the illegal logging may have fled, the outermost circle is expanded according to a preset radius expansion value, such as 3km. Figure 4 The difference between the radius of the circumcircle and the radius of the tracking area is 3 km.

[0050] The number of target drones should not be too few, as this will prevent the tracking area from being covered; nor should it be too many, as this will result in a waste of resources. This invention determines the required number of drones based on the maximum tracking field of view of the inspection drone, and the implementation process is as follows: E01: Retrieve the maximum tracking field of view of the inspection drone; where maximum tracking field of view refers to the maximum range of ground targets that the inspection drone can identify. Maximum tracking field of view (MRL) refers to the maximum field of view of an inspection drone at a flight altitude that allows it to identify ground targets. The MRL may vary depending on the type of anomaly. For example, for fire tracking, the MRL only needs to be able to identify the burned area, while for illegal logging, the MRL needs to ensure that relevant personnel can be identified.

[0051] E02: Calculate the demand for drones in the tracking area by taking the coverage of the tracking area boundary as the target and combining the maximum tracking field of view.

[0052] To cover the tracking area, multiple inspection drones are needed, but too many drones would waste resources and increase the difficulty of image processing. This invention uses the maximum tracking field of view of the inspection drone as a reference to determine the number of inspection drones needed to cover the boundary of the tracking area, which is the drone requirement.

[0053] like Figure 5 As shown, the circular area represents the expanded tracking area. Assuming the maximum tracking field of view of the inspection drone exactly covers 1 / 4 of the tracking area's boundary (arc-shaped boundary), at least 4 inspection drones are needed to cover the tracking area, thus the required number of drones is 4.

[0054] After identifying the tracking area and its corresponding drone demand, select several target drones from a pool of inspection drones. The process is as follows: F01: The inspection drone closest to the boundary of the tracking area is used as the reference drone; the intersection of the line connecting the reference drone and the boundary of the tracking area is used as the reference point; The intersection of the line connecting the reference UAV and the boundary of the tracking area refers to the intersection of the line connecting the reference UAV and the center line of the tracking area with the boundary of the tracking area.

[0055] F02: Based on the reference point and the maximum tracking field of view, several reference points are sequentially determined on the boundary of the tracking area; the number of reference points is consistent with the demand for drones; After determining the baseline drone and reference point, other reference points are determined along the tracking area boundary clockwise or counterclockwise according to the drone demand, thus obtaining all reference points on the tracking area boundary.

[0056] F03: Match the nearest inspection drone to each reference point in turn; mark the inspection drones matched with several reference points as target drones, and associate the target drones with the reference points.

[0057] Similarly, the nearest inspection drone can be matched to each reference point along the boundary of the tracking area in a clockwise or counterclockwise direction. Each reference point is matched with one inspection drone, and a relationship is established between them. The inspection drone associated with each reference point is the target drone in the tracking area.

[0058] like Figure 5 As shown, inspection drone D1 is the inspection drone closest to the boundary of the tracking area. It is also the inspection drone deployed in the same tracking area as the target area. Using inspection drone D1 as the reference drone, and the intersection of the line connecting it to the boundary of the tracking area as the reference point, three other reference points are determined based on the drone demand in the tracking area. Each reference point equally divides the tracking area boundary. Inspection drones are matched to the other reference points based on proximity to the reference point, resulting in inspection drones D2, D3, and D4, for a total of four target drones.

[0059] It is important to note that when matching several target drones to a tracking area, inspection drones can be selected not only from outside the tracking area but also from inside the tracking area. For example... Figure 5 If the inspection drone D1' is located inside the tracking area and is closest to the boundary of the tracking area, the inspection drone D1' can be used as the reference drone.

[0060] When planning tracking routes for target drones, each target drone includes two route segments: one segment from the target drone to a reference point, and the other segment from the reference point to the center of the tracking area. The implementation process for planning tracking routes for target drones in this invention is as follows: G01: Retrieve the target drone and its associated reference points; use the center of the tracking area as the tracking endpoint; G02: Plan route segment one between the real-time location of the target UAV and the reference point, and plan route segment two between the reference point and the tracking endpoint; combine route segment one and route segment two to generate the tracking route.

[0061] like Figure 6 As shown, the line connecting the target UAV to the boundary of the tracking area is route segment one, which is the route taken by the target UAV from its location to the tracking area; the line connecting the reference point and the center of the tracking area is route segment two, and the target UAV will be tracked and inspected along route segment two after reaching the reference point.

[0062] After planning a tracking route for the target drone, tracking can be achieved by having the target drone patrol along the tracking route. However, since the tracking area is circular, if multiple target drones continuously track to the center of the circle with their maximum tracking field of view, there will be significant overlap in the field of view. This not only compromises the reliability of the tracking results but also prevents the acquisition of more accurate tracking data. This invention adjusts the tracking altitude in real time while the target drone is patrolling along route segment two. The implementation process is as follows: H01: Determine the boundary of the tracking area covered by the maximum tracking field of view of the target UAV, and determine the tracking target area by the boundary of the tracking area and the center of the tracking area; wherein, the tracking target area is a fan-shaped area; H02: Adjust the tracking altitude of the target drone according to the target area to ensure that the target drone's field of vision always covers the target area.

[0063] like Figure 7 As shown, after target UAV D1 reaches the reference point by tracking and inspecting along route segment one with its maximum tracking field of view, target UAV D1 can start tracking towards the center of the tracking area along route two with its maximum tracking field of view. However, if tracking and inspection continues with the maximum tracking field of view, the final tracking and inspection areas of adjacent target UAVs will have a large overlap. Therefore, the tracking target area of ​​target UAV D1 is determined by the boundary of the tracking area and the center of the tracking area, i.e. Figure 7 In the medium gray fan-shaped area, the target drone D1 can complete the tracking inspection based on the target area. During the tracking inspection, the tracking altitude can be adjusted to ensure that the tracking field of view covers the target area. It can also obtain more reliable inspection data at a lower tracking altitude.

[0064] A second aspect of the present invention provides an integrated air-ground-land intelligent monitoring system for forest and grassland resources, including a central processing module and several inspection drones; Central processing module: used to identify target areas from the monitored area using image recognition technology; wherein the target area is an abnormal area that needs to be tracked and inspected; used to match several target drones with the target area as the target for tracking and inspection; to plan tracking routes for several target drones with the target area as the encirclement target; and to control several target drones to track and inspect the target area according to the tracking route, while sending the tracking information to the inspection personnel.

[0065] The central processing module communicates with several inspection drones and also with a remote sensing satellite platform to acquire remote sensing images. The central processing module is also connected to the smart terminals of inspection personnel, allowing them to access inspection data in real time.

[0066] It should be understood that the descriptions of technical features, technical solutions, beneficial effects, or similar language in this application do not imply that all features and advantages can be achieved in any single embodiment. Rather, it is understood that the description of a feature or beneficial effect means that a specific technical feature, technical solution, or beneficial effect is included in at least one embodiment. Therefore, the descriptions of technical features, technical solutions, or beneficial effects in this specification do not necessarily refer to the same embodiment. Furthermore, the technical features, technical solutions, and beneficial effects described in this embodiment can be combined in any suitable manner. Those skilled in the art will understand that embodiments can be implemented without one or more specific technical features, technical solutions, or beneficial effects of a particular embodiment. In other embodiments, additional technical features and beneficial effects may be identified in specific embodiments that do not embody all embodiments.

[0067] In the above embodiments, implementation can be achieved entirely or partially through software, hardware, firmware, or any other combination thereof. When implemented using a software program, it can be implemented entirely or partially in the form of a computer program product. This computer program product includes one or more computer instructions. When the computer program instructions are loaded and executed on a computer, all or part of the processes or functions described in the embodiments of this application are generated. The computer can be a general-purpose computer, a special-purpose computer, a computer network, or other programmable device. The computer instructions can be stored in a computer-readable storage medium or transmitted from one computer-readable storage medium to another. For example, computer instructions can be transmitted from one website, computer, server, or data center to another website, computer, server, or data center via wired (e.g., coaxial cable, fiber optic, digital subscriber line (DSL)) or wireless (e.g., infrared, wireless, microwave, etc.) means. The computer-readable storage medium can be any available medium accessible to a computer or a data storage device containing one or more servers, data centers, etc., that can be integrated with the medium. The available media can be magnetic media (e.g., floppy disks, hard disks, magnetic tapes), optical media (e.g., DVDs), or semiconductor media (e.g., solid-state disks (SSDs)).

[0068] The above embodiments are only used to illustrate the technical methods of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical methods of the present invention without departing from the spirit and scope of the technical methods of the present invention.

Claims

1. A method for intelligent monitoring of forest and grassland resources integrating air, land, and space, characterized in that, include: The target area is identified from the monitored area using image recognition technology; the target area is an abnormal area that needs to be tracked and inspected. The system aims to match several target drones with the goal of tracking and inspecting the target area; and to plan tracking routes for the target drones by encircling the target area. Control several target drones to track and inspect the target area according to the tracking route, and send the tracking information to the inspection personnel at the same time.

2. The integrated air-ground-space intelligent monitoring method for forest and grassland resources according to claim 1, characterized in that, The target area is identified from the regulatory area using image recognition technology, including: Based on the analysis of image data, several abnormal areas and their abnormality types were identified within the monitored area; the image data was acquired through remote sensing satellites or inspection drones. Determine whether the anomaly type of the abnormal region belongs to the preset tracking type; if yes, mark the abnormal region as the target region; otherwise, do not mark the abnormal region.

3. The integrated air-ground-space intelligent monitoring method for forest and grassland resources according to claim 1, characterized in that, The objective is to match several target drones, including: The tracking area is expanded based on the circumcircle of the target area; the number of drones required for the tracking area is calculated based on the maximum tracking field of view of the inspection drone; the inspection drones are set up in the gridded monitoring area; A number of inspection drones within the monitored area that meet the requirements are selected; among them, meeting the requirements includes both machine status and mission status meeting the requirements. With the encirclement and tracking area as the target, a number of target drones are selected from a number of inspection drones based on the demand for drones.

4. The integrated air-ground-space intelligent monitoring method for forest and grassland resources according to claim 3, characterized in that, Several inspection drones will be deployed in the regulated area, including: The regulatory area is divided into grids to obtain several inspection areas; Several inspection areas are equipped with inspection drones, and the inspection drones are set up in the inspection areas; the inspection drones are used to carry out routine inspections of the inspection areas.

5. The integrated air-ground-space intelligent monitoring method for forest and grassland resources according to claim 3, characterized in that, The tracking region is obtained by expanding the circumcircle of the target region, including: Obtain the circumcircle of the target region; The tracking area is obtained by expanding the outer circle according to the preset radius expansion value.

6. The integrated air-ground-space intelligent monitoring method for forest and grassland resources according to claim 3, characterized in that, The required number of drones for the tracking area is calculated based on the maximum tracking field of view of the inspection drone, including: Retrieve the maximum tracking field of view of the inspection drone; where maximum tracking field of view refers to the maximum range of ground targets that the inspection drone can identify. With the goal of covering the boundary of the tracking area, the demand for drones in the tracking area is calculated by combining the maximum tracking field of view.

7. The integrated air-ground-space intelligent monitoring method for forest and grassland resources according to claim 3, characterized in that, Based on the demand for drones, several target drones were identified from a pool of inspection drones, including: The inspection drone closest to the boundary of the tracking area is used as the reference drone; the intersection of the line connecting the reference drone and the boundary of the tracking area is used as the reference point. Based on the reference points and the maximum tracking field of view, several reference points are sequentially determined on the boundary of the tracking area; the number of reference points is consistent with the number of drones required. The nearest inspection drone is matched to each reference point in turn; the inspection drones matched to several reference points are marked as target drones, and the target drones are associated with the reference points.

8. The integrated air-ground-space intelligent monitoring method for forest and grassland resources according to claim 7, characterized in that, Planning tracking routes for several target drones, including: Retrieve the target drone and its associated reference points; use the center of the tracking area as the tracking endpoint; Plan route segment one between the real-time location of the target UAV and the reference point, and plan route segment two between the reference point and the tracking endpoint; then combine route segment one and route segment two to generate the tracking route.

9. The integrated air-ground-space intelligent monitoring method for forest and grassland resources according to claim 8, characterized in that, When the target drone is tracking and inspecting along route segment two, the tracking altitude is adjusted in real time, including: Determine the boundary of the tracking area covered by the maximum tracking field of view of the target UAV, and use the boundary of the tracking area and the center of the tracking area to determine the tracking target area; wherein, the tracking target area is a fan-shaped area; Adjust the tracking altitude of the target drone according to the target area to ensure that the target drone's field of vision always covers the target area.

10. An integrated air-ground intelligent monitoring system for forest and grassland resources, used to execute the integrated air-ground intelligent monitoring method for forest and grassland resources as described in any one of claims 1 to 9, characterized in that, Includes a central processing module and several inspection drones; Central processing module: used to identify target areas from the monitored area using image recognition technology; where the target area is an abnormal area that needs to be tracked and inspected; Used for matching several target drones with the goal of tracking and inspecting a target area; planning tracking routes for several target drones with the target area as an encirclement target; and... This is used to control several target drones to track and inspect target areas according to the tracking route, while sending tracking information to inspection personnel.

Images