Basin unmanned aerial vehicle airfield deployment method and device based on three-dimensional space perception

Abstract

The present application relates to the technical field of geographic information, and particularly relates to a watershed unmanned aerial vehicle airfield deployment method and device based on three-dimensional space perception, computer equipment and a storage medium. Based on the three-dimensional flight path from each candidate facility point of the unmanned aerial vehicle to each monitoring demand point of the unmanned aerial vehicle in the target watershed, the three-dimensional flight path accessibility evaluation index system is constructed for the three-dimensional geographic space constraint in the low-altitude complex environment of the target watershed, the three-dimensional flight path accessibility analysis is carried out, the obtained accessibility index and the unmanned aerial vehicle airfield site selection model are combined, the unmanned aerial vehicle airfield deployment is carried out, the resource allocation is optimized, and the safety and efficiency of the overall flight task are improved.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of geographic information, and in particular to a watershed unmanned aerial vehicle (UAV) airfield deployment method and device based on three-dimensional space perception, a computer device, and a storage medium. BACKGROUND

[0002] With the wide application of UAVs in ecological monitoring, emergency response and other fields, the scientific and reasonable layout of the UAV airfield network has become the key to ensuring its continuous operation capability. Compared with urban and plain areas, the watershed area is mostly located between hills, mountains or basins, with significant terrain undulations and large surface height differences. In addition, the types of artificial auxiliary facilities in the region are diverse and the distribution is complex, such as high-voltage towers, signal towers, etc., and the communication infrastructure is relatively weak, resulting in more constraints and higher uncertainty for UAVs in the flight process.

[0003] However, the current UAV airfield network layout is mainly based on the spatial coverage judgment of monitoring demand, and the accessibility of UAV flight paths under three-dimensional complex spatial constraints has not been considered in the airfield networking layout. This limitation leads to unsatisfactory deployment results, such as coverage blind spots, flight conflicts, and operation risks, making it difficult to effectively meet the flight needs of UAVs in the low-altitude complex environment of the watershed. SUMMARY

[0004] Therefore, the purpose of the present application is to provide a watershed UAV airfield deployment method and device based on three-dimensional space perception, a computer device, and a storage medium. Based on the three-dimensional flight paths constructed from each UAV candidate facility point to each UAV monitoring demand point in the target watershed, a three-dimensional flight path accessibility evaluation index system is constructed for the three-dimensional geographic space constraints in the low-altitude complex environment of the target watershed. The three-dimensional flight path accessibility analysis is carried out, and the obtained accessibility index and UAV airfield site selection model are combined to carry out UAV airfield deployment, so as to optimize resource allocation and improve the safety and efficiency of the overall flight task.

[0005] In a first aspect, the present application provides a watershed UAV airfield deployment method based on three-dimensional space perception, comprising the following steps:

[0006] Obtaining a plurality of field observation stations and a plurality of catchment units in a target watershed, taking each field observation station as a UAV candidate facility point, and taking the geographic center of each catchment unit as a UAV monitoring demand point;

[0007] According to the three-dimensional flight path modeling and sampling point extraction of each UAV candidate facility point and the UAV monitoring demand point, the three-dimensional coordinate data of a plurality of sampling points corresponding to the three-dimensional flight path from each UAV candidate facility point to each UAV monitoring demand point is obtained;

[0008] obtain position attribute data of each sampling point corresponding to the three-dimensional flight path from each candidate facility point of the unmanned aerial vehicle to each monitoring demand point of the unmanned aerial vehicle; input the three-dimensional coordinate data and the position attribute data of the plurality of sampling points corresponding to the three-dimensional flight path from each candidate facility point of the unmanned aerial vehicle to each monitoring demand point of the unmanned aerial vehicle into a preset accessibility index evaluation model for evaluation, to obtain an accessibility index of the three-dimensional flight path from each candidate facility point of the unmanned aerial vehicle to each monitoring demand point of the unmanned aerial vehicle.

[0009] input the accessibility index of the three-dimensional flight path from each candidate facility point of the unmanned aerial vehicle to each monitoring demand point of the unmanned aerial vehicle into a preset unmanned aerial vehicle airport site selection model for target facility point extraction, to obtain a plurality of target facility points, and generate an unmanned aerial vehicle airport deployment scheme.

[0010] In a second aspect, an embodiment of the present application provides a basin unmanned aerial vehicle airport deployment device based on three-dimensional space perception, comprising:

[0011] a point site obtaining module configured to obtain a plurality of field observation stations and a plurality of catchment units in a target basin, take each field observation station as a candidate facility point of an unmanned aerial vehicle, and take a geographic center of each catchment unit as a monitoring demand point of the unmanned aerial vehicle;

[0012] a three-dimensional flight path modeling module configured to model a three-dimensional flight path and extract sampling points according to each candidate facility point of the unmanned aerial vehicle and each monitoring demand point of the unmanned aerial vehicle, to obtain three-dimensional coordinate data of a plurality of sampling points corresponding to the three-dimensional flight path from each candidate facility point of the unmanned aerial vehicle to each monitoring demand point of the unmanned aerial vehicle;

[0013] an accessibility index evaluation module configured to obtain position attribute data of each sampling point corresponding to the three-dimensional flight path from each candidate facility point of the unmanned aerial vehicle to each monitoring demand point of the unmanned aerial vehicle; input the three-dimensional coordinate data and the position attribute data of the plurality of sampling points corresponding to the three-dimensional flight path from each candidate facility point of the unmanned aerial vehicle to each monitoring demand point of the unmanned aerial vehicle into a preset accessibility index evaluation model for evaluation, to obtain an accessibility index of the three-dimensional flight path from each candidate facility point of the unmanned aerial vehicle to each monitoring demand point of the unmanned aerial vehicle.

[0014] an unmanned aerial vehicle airport deployment module configured to input the accessibility index of the three-dimensional flight path from each candidate facility point of the unmanned aerial vehicle to each monitoring demand point of the unmanned aerial vehicle into a preset unmanned aerial vehicle airport site selection model for target facility point extraction, to obtain a plurality of target facility points, and generate an unmanned aerial vehicle airport deployment scheme.

[0015] In a third aspect, an embodiment of the present application provides a computer device, comprising a processor, a memory, and a computer program stored in the memory and executable on the processor; when the computer program is executed by the processor, the steps of the method for deploying a watershed unmanned aerial vehicle airfield based on three-dimensional space perception according to the first aspect are implemented.

[0016] In a fourth aspect, an embodiment of the present application provides a storage medium, which stores a computer program, and when the computer program is executed by a processor, the steps of the method for deploying a watershed unmanned aerial vehicle airfield based on three-dimensional space perception according to the first aspect are implemented.

[0017] In the embodiment of the present application, a method, device, computer device and storage medium for deploying a watershed unmanned aerial vehicle airfield based on three-dimensional space perception are provided. Based on the three-dimensional flight path from the candidate facility point of each unmanned aerial vehicle to the monitoring demand point of each unmanned aerial vehicle in the target watershed, the three-dimensional flight path accessibility evaluation index system is constructed for the three-dimensional geographical space constraint in the low-altitude complex environment of the target watershed, the three-dimensional flight path accessibility analysis is carried out, the obtained accessibility index and the unmanned aerial vehicle airfield site selection model are combined, the unmanned aerial vehicle airfield deployment is carried out, and the safety and efficiency of the overall flight task are improved by optimizing the resource allocation.

[0018] For better understanding and implementation, the present application is described in detail below with reference to the drawings. BRIEF DESCRIPTION OF DRAWINGS

[0019] Figure 1 A flowchart of a method for deploying a watershed unmanned aerial vehicle airfield based on three-dimensional space perception is provided for an embodiment of the present application.

[0020] Figure 2 A flowchart of S1 in the method for deploying a watershed unmanned aerial vehicle airfield based on three-dimensional space perception is provided for an embodiment of the present application.

[0021] Figure 3 A flowchart of S2 in the method for deploying a watershed unmanned aerial vehicle airfield based on three-dimensional space perception is provided for an embodiment of the present application.

[0022] Figure 4 A flowchart of S3 in the method for deploying a watershed unmanned aerial vehicle airfield based on three-dimensional space perception is provided for an embodiment of the present application.

[0023] Figure 5 A flowchart of S32 in the method for deploying a watershed unmanned aerial vehicle airfield based on three-dimensional space perception is provided for an embodiment of the present application.

[0024] Figure 6 A flowchart of S33 in the method for deploying a watershed unmanned aerial vehicle airfield based on three-dimensional space perception is provided for an embodiment of the present application.

[0025] Figure 7 A flowchart of S4 in a method for deploying a watershed UAV airfield based on three-dimensional spatial perception according to an embodiment of the present application is shown in FIG. 4;

[0026] Figure 8 A structural diagram of a device for deploying a watershed UAV airfield based on three-dimensional spatial perception according to an embodiment of the present application is shown in FIG. 5;

[0027] Figure 9 A structural diagram of a computer device according to an embodiment of the present application is shown in FIG. 6. DETAILED DESCRIPTION

[0028] The exemplary embodiments will be described in detail herein with reference to the attached drawings. In the following description, unless otherwise indicated, like numbers in the attached drawings refer to the same or similar elements. The following detailed description includes specific details for the purpose of providing a thorough understanding of the exemplary embodiments. However, it will be apparent to those skilled in the art that the exemplary embodiments can be practiced without these specific details. In some instances, well-known structures and components are not described in detail in order to avoid obscuring the understanding of the exemplary embodiments.

[0029] The terminology used in the present application is for the purpose of describing particular embodiments only and is not intended to be limiting of the present application. As used in the present application and the appended claims, the singular forms "a," "an" and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It will be further understood that the terms "and / or," as used herein, refers to and encompasses any and all possible combinations of one or more of the associated listed items.

[0030] It will be understood that, although the terms first, second, third, etc. can be used herein to describe various information, these terms are not intended to denote a temporal or chronological order. Rather, these terms are used only as labels to identify particular information. For example, a first information could be termed a second information, and, similarly, a second information could be termed a first information without departing from the scope of the present application. As used herein, the term "if' can be interpreted to mean "when" or "upon" or "in response to determining" taking into account the context in which the term is used.

[0031] Reference will now be made to Figure 1 , Figure 1 A flowchart of a method for deploying a watershed UAV airfield based on three-dimensional spatial perception according to an embodiment of the present application is shown in FIG. 3. The method includes the following steps:

[0032] S1 : obtaining a plurality of field observation stations and a plurality of watershed units in a target watershed, taking each of the field observation stations as a candidate facility point for a UAV, and taking a geographic center of each of the watershed units as a monitoring demand point for the UAV.

[0033] The execution subject of the watershed unmanned aerial vehicle airfield deployment method based on three-dimensional space perception is a deployment device of the watershed unmanned aerial vehicle airfield deployment method based on three-dimensional space perception (hereinafter referred to as a deployment device). In an optional embodiment, the deployment device can be a computer device, which can be a server, or a server cluster formed by multiple computer devices.

[0034] In this embodiment, the deployment device obtains a plurality of field observation stations and a plurality of catchment units in a target watershed, takes each field observation station as a candidate facility point of the unmanned aerial vehicle, and takes the geographic center of each catchment unit as a monitoring demand point of the unmanned aerial vehicle, wherein the target watershed is a watershed to be monitored for water ecological environment, and the catchment unit refers to a closed surface area through which surface runoff flows during the process of converging to a common outlet.

[0035] The field observation station is a fixed facility for long-term monitoring of ecological environment elements and system processes, including comprehensive ecological system observation stations, hydrological ecological stations, soil and water conservation stations, atmospheric environment monitoring stations, and water quality monitoring section points, etc. With its perfect infrastructure and convenient transportation conditions, it becomes an ideal choice for unmanned aerial vehicle deployment. Its superior geographical location and existing support facilities not only significantly improve the operation efficiency of the unmanned aerial vehicle, but also effectively reduce the construction cost of the unmanned aerial vehicle deployment. Compared with newly built airfield stations, selecting existing observation stations as candidate facility points has significant cost advantage and implementation feasibility, which can effectively reduce the construction difficulty of the station, shorten the deployment period, and enhance the scene adaptability and running stability of the unmanned aerial vehicle system. Specifically, the deployment device can obtain the field observation stations in the target watershed according to the spatial distribution data of the existing field observation stations in China.

[0036] For the catchment unit, please refer to Figure 2 , Figure 2 The flowchart of S1 in the watershed unmanned aerial vehicle airfield deployment method based on three-dimensional space perception provided by an embodiment of the present application includes steps S11-S12, which are as follows:

[0037] S11: Obtain digital elevation model data of the target watershed.

[0038] In this embodiment, the deployment device obtains digital elevation model data of the target watershed, wherein the digital elevation model (DEM) data is a digital simulation of the topography through limited terrain elevation data, reflecting the natural elevation characteristics of the ground surface, which can be obtained through global DEM products such as SRTM and ASTER GDEM, or provided by the National Basic Geographic Information Center.

[0039] S12: According to the digital elevation model data, the target watershed is divided into catchment units to obtain a plurality of catchment units.

[0040] The watershed terrain is complex, and it is difficult to effectively reflect the hydrological spatial characteristics of the watershed based on the rule grid cell extraction demand point. In order to better fit the hydrological geographical characteristics of the watershed, in this embodiment, the deployment device divides the target watershed into catchment units according to the digital elevation model data to obtain a plurality of catchment units. Specifically, the deployment device can use hydrological analysis software to process and analyze DEM data, divide the target watershed into catchment units, and obtain a plurality of catchment units. After obtaining the catchment unit, the geographical center point of the catchment unit can be extracted, and the geographical center point of the catchment unit is taken as the monitoring demand point of the unmanned aerial vehicle.

[0041] S2: According to the candidate facility point of each unmanned aerial vehicle and the monitoring demand point of the unmanned aerial vehicle, three-dimensional flight path modeling and sampling point extraction are performed to obtain three-dimensional coordinate data of a plurality of sampling points corresponding to the three-dimensional flight path from the candidate facility point of each unmanned aerial vehicle to the monitoring demand point of each unmanned aerial vehicle.

[0042] In this embodiment, the deployment device performs three-dimensional flight path modeling and sampling point extraction according to the candidate facility point of each unmanned aerial vehicle and the monitoring demand point of the unmanned aerial vehicle, and obtains three-dimensional coordinate data of a plurality of sampling points corresponding to the three-dimensional flight path from the candidate facility point of each unmanned aerial vehicle to the monitoring demand point of each unmanned aerial vehicle.

[0043] Please refer to Figure 3 , Figure 3 The flowchart of S2 of the three-dimensional space perception based watershed unmanned aerial vehicle airport deployment method provided by an embodiment of the present application is shown in the figure, which includes steps S21-S24, and the details are as follows:

[0044] S21: Connecting each monitoring demand point of the unmanned aerial vehicle with each candidate facility point of the unmanned aerial vehicle respectively to obtain a three-dimensional flight path from the candidate facility point of each unmanned aerial vehicle to the monitoring demand point of each unmanned aerial vehicle.

[0045] In order to evaluate the three-dimensional flight path accessibility of the unmanned aerial vehicle between the facility point and the demand point, the deployment device connects each monitoring demand point of the unmanned aerial vehicle with each candidate facility point of the unmanned aerial vehicle respectively to construct a three-dimensional flight path straight line segment from the candidate facility point of each unmanned aerial vehicle to the monitoring demand point of each unmanned aerial vehicle as the three-dimensional flight path.

[0046] S22: Obtain three-dimensional coordinate data of each monitoring demand point of the unmanned aerial vehicle and three-dimensional coordinate data of the candidate facility point of the unmanned aerial vehicle; and obtain three-dimensional Euclidean distance of a three-dimensional flight path from each candidate facility point of the unmanned aerial vehicle to each monitoring demand point of the unmanned aerial vehicle according to the three-dimensional coordinate data of each monitoring demand point of the unmanned aerial vehicle, the three-dimensional coordinate data of the candidate facility point of the unmanned aerial vehicle, and a preset three-dimensional Euclidean distance calculation algorithm.

[0047] In the embodiment, the deployment device obtains three-dimensional coordinate data of each monitoring demand point of the unmanned aerial vehicle and the candidate facility point of the unmanned aerial vehicle, wherein the three-dimensional coordinate data includes horizontal coordinate data, vertical coordinate data, and vertical coordinate data.

[0048] Specifically, the deployment device can obtain two-dimensional coordinate data of each monitoring demand point of the unmanned aerial vehicle and the candidate facility point of the unmanned aerial vehicle, the two-dimensional coordinate data including horizontal coordinate data and vertical coordinate data, supplementing the vertical coordinate data by extracting the corresponding ground height value according to the coordinate index of each point in the grid space by using the digital elevation model data, and performing dimension upgrading processing on the two-dimensional coordinate data to obtain three-dimensional coordinate data.

[0049] The deployment device obtains three-dimensional Euclidean distance of a three-dimensional flight path from each candidate facility point of the unmanned aerial vehicle to each monitoring demand point of the unmanned aerial vehicle according to each monitoring demand point of the unmanned aerial vehicle, the three-dimensional coordinate data of the candidate facility point of the unmanned aerial vehicle, and a preset three-dimensional Euclidean distance calculation algorithm, wherein the three-dimensional Euclidean distance calculation algorithm is:

[0050]

[0051] In the formula, D ij is three-dimensional Euclidean distance of a three-dimensional flight path from the candidate facility point of the jth unmanned aerial vehicle to the monitoring demand point of the ith unmanned aerial vehicle, X i ,Y i ,Z i is horizontal coordinate data, vertical coordinate data, and vertical coordinate data of the monitoring demand point of the ith unmanned aerial vehicle, X j ,Y j ,Z j is horizontal coordinate data, vertical coordinate data, and vertical coordinate data of the candidate facility point of the jth unmanned aerial vehicle.

[0052] S23: determining, according to the three-dimensional Euclidean distance of the three-dimensional flight path from the candidate facility point of each of the unmanned aerial vehicles to the monitoring demand point of each of the unmanned aerial vehicles and the preset sampling interval, the number of sampling points of the three-dimensional flight path from the candidate facility point of each of the unmanned aerial vehicles to the monitoring demand point of each of the unmanned aerial vehicles; and obtaining, according to the three-dimensional Euclidean distance of the three-dimensional flight path from the candidate facility point of each of the unmanned aerial vehicles to the monitoring demand point of each of the unmanned aerial vehicles, the number of sampling points and a preset relative position calculation algorithm, the relative position of each sampling point of the three-dimensional flight path from the candidate facility point of each of the unmanned aerial vehicles to the monitoring demand point of each of the unmanned aerial vehicles.

[0053] In the embodiment, the deployment device determines, according to the three-dimensional Euclidean distance of the three-dimensional flight path from the candidate facility point of each of the unmanned aerial vehicles to the monitoring demand point of each of the unmanned aerial vehicles and the preset sampling interval, the number of sampling points of the three-dimensional flight path from the candidate facility point of each of the unmanned aerial vehicles to the monitoring demand point of each of the unmanned aerial vehicles, specifically as follows:

[0054]

[0055] In the formula, s is the sampling interval, K ij is the number of sampling points of the three-dimensional flight path from the candidate facility point of the jth unmanned aerial vehicle to the monitoring demand point of the ith unmanned aerial vehicle.

[0056] According to the three-dimensional Euclidean distance of the three-dimensional flight path from the candidate facility point of each of the unmanned aerial vehicles to the monitoring demand point of each of the unmanned aerial vehicles, the number of sampling points and a preset relative position calculation algorithm, the relative position of each sampling point of the three-dimensional flight path from the candidate facility point of each of the unmanned aerial vehicles to the monitoring demand point of each of the unmanned aerial vehicles is obtained, wherein the relative position calculation algorithm is:

[0057]

[0058] In the formula, t ijk is the relative position of the kth sampling point of the three-dimensional flight path from the candidate facility point of the jth unmanned aerial vehicle to the monitoring demand point of the ith unmanned aerial vehicle, k ij is the index of the sampling point of the three-dimensional flight path from the candidate facility point of the jth unmanned aerial vehicle to the monitoring demand point of the ith unmanned aerial vehicle.

[0059] S24: obtaining, according to the three-dimensional coordinate data of the candidate facility point of each of the unmanned aerial vehicles, the relative position of each sampling point of the three-dimensional flight path from the candidate facility point of each of the unmanned aerial vehicles to the monitoring demand point of each of the unmanned aerial vehicles and a preset sampling point three-dimensional coordinate calculation algorithm, the three-dimensional coordinate data of each sampling point of the three-dimensional flight path from the candidate facility point of each of the unmanned aerial vehicles to the monitoring demand point of each of the unmanned aerial vehicles.

[0060] In the embodiment, the deployment device obtains three-dimensional coordinate data of each candidate facility point of each unmanned aerial vehicle, relative positions of each sampling point of a three-dimensional flight path from each candidate facility point of each unmanned aerial vehicle to each monitoring demand point of each unmanned aerial vehicle, and a preset sampling point three-dimensional coordinate calculation algorithm, to obtain three-dimensional coordinate data of each sampling point of a three-dimensional flight path from each candidate facility point of each unmanned aerial vehicle to each monitoring demand point of each unmanned aerial vehicle, so as to realize discretization processing of the three-dimensional flight path, and generate a plurality of sampling points, wherein the three-dimensional coordinate calculation algorithm is:

[0061] L ijk =(X ijk ,Y ijk ,Z ijk )=(X j +t ijk (X i -X j ),Y j +t ijk (Y i -Y j ),Z j +t ijk (Z i -Z j ))

[0062] In the formula, L ijk is three-dimensional coordinate data of the kth sampling point on a three-dimensional flight path from a candidate facility point of the jth unmanned aerial vehicle to a monitoring demand point of the ith unmanned aerial vehicle, X ijk , Y ijk , and Z ijk are respectively horizontal coordinate data, vertical coordinate data, and vertical coordinate data of the kth sampling point on a three-dimensional flight path from a candidate facility point of the jth unmanned aerial vehicle to a monitoring demand point of the ith unmanned aerial vehicle.

[0063] S3: Obtain position attribute data of each sampling point corresponding to a three-dimensional flight path from each candidate facility point of each unmanned aerial vehicle to each monitoring demand point of each unmanned aerial vehicle; input three-dimensional coordinate data and position attribute data of a plurality of sampling points corresponding to a three-dimensional flight path from each candidate facility point of each unmanned aerial vehicle to each monitoring demand point of each unmanned aerial vehicle into a preset reachability index evaluation model for evaluation, to obtain a reachability index of a three-dimensional flight path from each candidate facility point of each unmanned aerial vehicle to each monitoring demand point of each unmanned aerial vehicle.

[0064] In the embodiment, the deployment device obtains position attribute data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each drone to the monitoring demand point of each drone, wherein the position attribute data includes elevation data, building surface model data, and environmental attribute data, and the environmental attribute data includes annual average wind speed value, nearest communication base station distance parameter, and population density value.

[0065] The three-dimensional coordinate data and the position attribute data of the plurality of sampling points corresponding to the three-dimensional flight path from the candidate facility point of each drone to the monitoring demand point of each drone are input into a preset accessibility index evaluation model for evaluation, to obtain an accessibility index of the three-dimensional flight path from the candidate facility point of each drone to the monitoring demand point of each drone.

[0066] The accessibility index evaluation model includes a hard constraint condition and a soft constraint condition, the hard constraint condition is used to indicate the accessibility of the three-dimensional flight path in the physical and regulatory aspects, and the soft constraint condition is used to indicate the accessibility of the three-dimensional flight path in the aspects of environmental flight suitability and public safety. Figure 4 , Figure 4 The flowchart of S3 in the watershed drone airport deployment method based on three-dimensional space perception provided by an embodiment of the present application includes steps S31-S34, and specifically as follows:

[0067] S31: According to the three-dimensional coordinate data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each drone to the monitoring demand point of each drone, the elevation data, the building surface model data, and the hard constraint condition in the accessibility index evaluation model, hard constraint label data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each drone to the monitoring demand point of each drone is obtained.

[0068] In the embodiment, the deployment device obtains position attribute data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each drone to the monitoring demand point of each drone, wherein the position attribute data includes elevation data, building surface model data, and environmental attribute data, and the environmental attribute data includes annual average wind speed value, nearest communication base station distance parameter, and population density value.

[0069] The hard constraints include occlusion constraints, policy constraints and UAV performance constraints, wherein the occlusion constraints include terrain constraints and artificial attachment constraints; the policy constraints include no-fly zone constraints; the UAV performance constraints include UAV vertical height difference constraints and UAV operation radius constraints; the hard constraint label sub-data includes terrain constraint label data, artificial attachment constraint label data, no-fly zone constraint label data, UAV vertical height difference constraint label data and UAV operation radius constraint label data; please refer to Figure 5 , Figure 5 The flowchart of S31 in the watershed UAV airfield deployment method based on three-dimensional space perception provided by an embodiment of the present application is shown in FIG. 6, which includes steps S311-S315, and the details are as follows.

[0070] S311: Obtain terrain constraint label data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each UAV to the monitoring demand point of each UAV according to the elevation data of each sampling point corresponding to the three-dimensional flight path, the elevation threshold of the corresponding sampling point and the terrain constraints.

[0071] The terrain constraints are used to indicate that the three-dimensional flight path cannot pass through the visual occlusion caused by the terrain undulation, and if the occlusion exists, the path is considered to be unreachable.

[0072] In the embodiment, the deployment device obtains terrain constraint label data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each UAV to the monitoring demand point of each UAV according to the elevation data of each sampling point corresponding to the three-dimensional flight path, the elevation threshold of the corresponding sampling point and the terrain constraints, wherein the terrain constraints are as follows:

[0073]

[0074] In the formula, is the terrain constraint label data of the kth sampling point on the three-dimensional flight path from the candidate facility point of the jth UAV to the monitoring demand point of the ith UAV, L ijk is the elevation threshold of the kth sampling point on the three-dimensional flight path from the candidate facility point of the jth UAV to the monitoring demand point of the ith UAV, DEM(X ijk ,Y ijk is the elevation data of the kth sampling point on the three-dimensional flight path from the candidate facility point of the jth UAV to the monitoring demand point of the ith UAV.

[0075] S312: Obtain, according to the building surface model data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each of the unmanned aerial vehicles to the monitoring demand point of each of the unmanned aerial vehicles, the building surface model threshold value of the corresponding sampling point, and the artificial accessory constraint condition, the artificial accessory constraint label data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each of the unmanned aerial vehicles to the monitoring demand point of each of the unmanned aerial vehicles.

[0076] The artificial accessory constraint condition is used to indicate that the three-dimensional flight path cannot pass through the shelter caused by the artificial accessories such as buildings, power towers, communication towers, and the like, and if the shelter exists, the path is considered to be unreachable.

[0077] In this embodiment, the deployment device obtains, according to the building surface model data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each of the unmanned aerial vehicles to the monitoring demand point of each of the unmanned aerial vehicles, the building surface model threshold value of the corresponding sampling point, and the artificial accessory constraint condition, the artificial accessory constraint label data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each of the unmanned aerial vehicles to the monitoring demand point of each of the unmanned aerial vehicles, wherein the artificial accessory constraint condition is:

[0078]

[0079] In the formula, is the artificial accessory constraint label data of the kth sampling point on the three-dimensional flight path from the candidate facility point of the jth unmanned aerial vehicle to the monitoring demand point of the ith unmanned aerial vehicle, I ijk is the building surface model threshold value of the kth sampling point on the three-dimensional flight path from the candidate facility point of the jth unmanned aerial vehicle to the monitoring demand point of the ith unmanned aerial vehicle, DSM(X ijk ,Y ijk is the building surface model data of the kth sampling point on the three-dimensional flight path from the candidate facility point of the jth unmanned aerial vehicle to the monitoring demand point of the ith unmanned aerial vehicle.

[0080] S313: Obtain, according to the horizontal coordinate data and the vertical coordinate data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each of the unmanned aerial vehicles to the monitoring demand point of each of the unmanned aerial vehicles, all two-dimensional coordinate sets in the preset no-fly zone, and the no-fly zone constraint condition, the no-fly zone constraint label data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each of the unmanned aerial vehicles to the monitoring demand point of each of the unmanned aerial vehicles.

[0081] The no-fly zone constraint condition is used to indicate that the three-dimensional flight path cannot pass through the no-fly zone legally or administratively, including the airport periphery, the military control zone, and the like, and once it passes through, it is considered to be unreachable.

[0082] In the embodiment, the deployment device obtains the flight-restricted area constraint label data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each unmanned aerial vehicle to the monitoring demand point of each unmanned aerial vehicle according to the horizontal coordinate data and the vertical coordinate data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each unmanned aerial vehicle to the monitoring demand point of each unmanned aerial vehicle, all two-dimensional coordinate sets in the flight-restricted area, and the flight-restricted area constraint condition, wherein the flight-restricted area constraint condition is:

[0083]

[0084] In the formula, is the flight-restricted area constraint label data of the kth sampling point on the three-dimensional flight path from the candidate facility point of the jth unmanned aerial vehicle to the monitoring demand point of the ith unmanned aerial vehicle, Z no-fly is all two-dimensional coordinate sets in the flight-restricted area, X ijk ,Y ijk is the horizontal coordinate data and the vertical coordinate data of the kth sampling point on the three-dimensional flight path from the candidate facility point of the jth unmanned aerial vehicle to the monitoring demand point of the ith unmanned aerial vehicle.

[0085] S314: Obtain the three-dimensional coordinate data of the candidate facility point of each unmanned aerial vehicle, and obtain the unmanned aerial vehicle vertical height difference constraint label data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each unmanned aerial vehicle to the monitoring demand point of each unmanned aerial vehicle according to the vertical coordinate data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each unmanned aerial vehicle to the monitoring demand point of each unmanned aerial vehicle, the vertical coordinate data of the candidate facility point of each unmanned aerial vehicle, and the unmanned aerial vehicle vertical height difference constraint condition.

[0086] The unmanned aerial vehicle vertical height difference constraint condition is used to indicate that the vertical height difference between the sampling point and the facility point on the three-dimensional flight path should not exceed the maximum vertical flight height of the unmanned aerial vehicle, and if it exceeds, it is considered as unreachable.

[0087] In the embodiment, the deployment device obtains the three-dimensional coordinate data of the candidate facility point of each unmanned aerial vehicle, and obtains the unmanned aerial vehicle vertical height difference constraint label data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each unmanned aerial vehicle to the monitoring demand point of each unmanned aerial vehicle according to the vertical coordinate data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each unmanned aerial vehicle to the monitoring demand point of each unmanned aerial vehicle, the vertical coordinate data of the candidate facility point of each unmanned aerial vehicle, and the unmanned aerial vehicle vertical height difference constraint condition, wherein the unmanned aerial vehicle vertical height difference constraint condition is:

[0088]

[0089] In the formula, Z is vertical height difference constraint label data of the UAV for the kth sampling point on the three-dimensional flight path from the candidate facility point of the jth UAV to the monitoring demand point of the ith UAV, j Z is vertical coordinate data of the candidate facility point of the jth UAV, ijk H is the maximum flight height of the UAV, and Z is vertical coordinate data of the kth sampling point on the three-dimensional flight path from the candidate facility point of the jth UAV to the monitoring demand point of the ith UAV.

[0090] S315: Obtain UAV operation radius constraint label data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each UAV to the monitoring demand point of each UAV according to the vertical coordinate data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each UAV to the monitoring demand point of each UAV, the horizontal coordinate data and the vertical coordinate data of the candidate facility point of each UAV, and the UAV operation radius constraint condition.

[0091] The UAV operation radius constraint condition is used to indicate that the horizontal distance between the sampling point and the facility point on the three-dimensional flight path should not exceed the UAV operation radius, and the path is unreachable beyond the range.

[0092] In this embodiment, the deployment device obtains the UAV operation radius constraint label data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each UAV to the monitoring demand point of each UAV according to the vertical coordinate data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each UAV to the monitoring demand point of each UAV, the horizontal coordinate data and the vertical coordinate data of the candidate facility point of each UAV, and the UAV operation radius constraint condition, wherein the UAV operation radius constraint condition is:

[0093]

[0094] In the formula, X is the UAV operation radius constraint label data of the kth sampling point on the three-dimensional flight path from the candidate facility point of the jth UAV to the monitoring demand point of the ith UAV, Z is vertical coordinate data of the kth sampling point on the three-dimensional flight path from the candidate facility point of the jth UAV to the monitoring demand point of the ith UAV. j ,Y j R is the maximum operation radius of the UAV, and the horizontal coordinate data and the vertical coordinate data of the candidate facility point of the jth UAV are obtained.

[0095] S32: Obtain soft constraint label data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each UAV to the monitoring demand point of each UAV according to the environmental attribute data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each UAV to the monitoring demand point of each UAV and the soft constraint condition in the accessibility index evaluation model.

[0096] In this embodiment, the deployment device obtains soft constraint label data for each sampling point corresponding to the three-dimensional flight path from each candidate facility point of each UAV to the monitoring requirement point of each UAV, based on the environmental attribute data of each sampling point corresponding to the three-dimensional flight path from each candidate facility point of each UAV to the monitoring requirement point of each UAV and the soft constraint conditions in the accessibility index evaluation model. The soft constraint conditions are used to indicate the accessibility of the three-dimensional flight path in terms of environmental flight suitability and public safety.

[0097] The soft constraints include environmental flight suitability constraints and public safety constraints. The environmental flight suitability constraints include wind speed constraints and communication level constraints; the public safety constraints include population density constraints. The soft constraint tag sub-data includes wind speed constraint tag data, communication level constraint tag data, and population density constraint tag data. Please refer to [link to relevant documentation]. Figure 6 , Figure 6 The flowchart of step S32 in the method for deploying unmanned aerial vehicles (UAVs) in a watershed based on three-dimensional spatial perception, provided in an embodiment of this application, includes steps S321 to S323, as follows:

[0098] S321: Determine the minimum and maximum annual average wind speeds based on the annual average wind speeds of the sampling points; obtain the wind speed constraint label data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point to the monitoring requirement point of each UAV based on the minimum and maximum annual average wind speeds, the annual average wind speeds of each sampling point corresponding to the three-dimensional flight path from the candidate facility point to the monitoring requirement point of each UAV, and the wind speed constraint conditions.

[0099] The wind speed constraint condition is used to indicate that the lower the wind speed, the more suitable it is for human-machine non-flight and the stronger the accessibility.

[0100] In this embodiment, the deployment device determines the minimum and maximum annual average wind speeds based on the annual average wind speed values ​​of the sampling points. Based on the minimum and maximum annual average wind speeds, the annual average wind speed values ​​of each sampling point corresponding to the three-dimensional flight path from each candidate facility point of the UAV to the monitoring requirement point of each UAV, and the wind speed constraint conditions, it obtains wind speed constraint label data for each sampling point corresponding to the three-dimensional flight path from each candidate facility point of the UAV to the monitoring requirement point of each UAV. The wind speed constraint conditions are:

[0101]

[0102] In the formula, The wind speed constraint label data of the kth sampling point on the three-dimensional flight path from the candidate facility point of the jth unmanned aerial vehicle to the monitoring demand point of the ith unmanned aerial vehicle is v ijk The annual average wind speed value of the kth sampling point on the three-dimensional flight path from the candidate facility point of the jth unmanned aerial vehicle to the monitoring demand point of the ith unmanned aerial vehicle is v min The minimum value of the annual average wind speed is v max The maximum value of the annual average wind speed is v

[0103] S322: Obtain the communication level constraint data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each unmanned aerial vehicle to the monitoring demand point of each unmanned aerial vehicle according to the nearest communication base station distance parameter of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each unmanned aerial vehicle to the monitoring demand point of each unmanned aerial vehicle and the communication level constraint condition.

[0104] The communication level constraint condition is used to construct a buffer zone according to the spatial distribution of communication base stations. The closer to the base station, the better the communication guarantee and the stronger the accessibility.

[0105] In this embodiment, the deployment device obtains the communication level constraint data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each unmanned aerial vehicle to the monitoring demand point of each unmanned aerial vehicle according to the nearest communication base station distance parameter of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each unmanned aerial vehicle to the monitoring demand point of each unmanned aerial vehicle and the communication level constraint condition, wherein the communication level constraint condition is:

[0106]

[0107] In the formula, The communication level constraint label data of the kth sampling point on the three-dimensional flight path from the candidate facility point of the jth unmanned aerial vehicle to the monitoring demand point of the ith unmanned aerial vehicle is d ijk The nearest communication base station distance parameter of the kth sampling point on the three-dimensional flight path from the candidate facility point of the jth unmanned aerial vehicle to the monitoring demand point of the ith unmanned aerial vehicle is L1, L2, L3, and L4, which are the first, second, third, and fourth coverage distances of the communication base stations distributed in a step-by-step increasing manner.

[0108] S323: Determine the minimum value of the population density and the maximum value of the population density according to the population density value of the sampling point; and obtain the population density constraint data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each unmanned aerial vehicle to the monitoring demand point of each unmanned aerial vehicle according to the population density data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each unmanned aerial vehicle to the monitoring demand point of each unmanned aerial vehicle and the population density constraint condition.

[0109] The population density constraint is used to represent that the lower the population density, the smaller the potential impact on public safety, and the stronger the accessibility.

[0110] In the embodiment, the deployment device determines a minimum population density value and a maximum population density value according to the population density values of the sampling points; obtains population density constraint data of each sampling point corresponding to the three-dimensional flight path of the candidate facility point of each unmanned aerial vehicle to the monitoring demand point of each unmanned aerial vehicle according to the population density data of each sampling point corresponding to the three-dimensional flight path of the candidate facility point of each unmanned aerial vehicle to the monitoring demand point of each unmanned aerial vehicle and the population density constraint, wherein the unmanned aerial vehicle operation radius constraint is:

[0111]

[0112] In the formula, POP is the population density constraint data, POP ijk is the population density value of the kth sampling point on the three-dimensional flight path from the candidate facility point of the jth unmanned aerial vehicle to the monitoring demand point of the ith unmanned aerial vehicle, POP min is the minimum population density value, POP max is the maximum population density value.

[0113] S33: Obtain the local accessibility index of each sampling point corresponding to the three-dimensional flight path of the candidate facility point of each unmanned aerial vehicle to the monitoring demand point of each unmanned aerial vehicle according to the hard constraint label data, the soft constraint label data of each sampling point corresponding to the three-dimensional flight path of the candidate facility point of each unmanned aerial vehicle to the monitoring demand point of each unmanned aerial vehicle, and a preset local accessibility index calculation algorithm.

[0114] In the embodiment, the deployment device obtains the local accessibility index of each sampling point corresponding to the three-dimensional flight path of the candidate facility point of each unmanned aerial vehicle to the monitoring demand point of each unmanned aerial vehicle according to the hard constraint label data, the soft constraint label data of each sampling point corresponding to the three-dimensional flight path of the candidate facility point of each unmanned aerial vehicle to the monitoring demand point of each unmanned aerial vehicle, and a preset local accessibility index calculation algorithm, wherein the local accessibility index calculation algorithm is:

[0115]

[0116] In the formula, α ijk is the local accessibility index of the kth sampling point on the three-dimensional flight path from the candidate facility point of the jth unmanned aerial vehicle to the monitoring demand point of the ith unmanned aerial vehicle, the u-th hard constraint label sub-data in the hard constraint label data of the k-th sampling point on the three-dimensional flight path from the candidate facility point of the j-th UAV to the monitoring demand point of the i-th UAV, U being the number of hard constraint label sub-data, the w-th soft constraint label sub-data in the soft constraint label data of the k-th sampling point on the three-dimensional flight path from the candidate facility point of the j-th UAV to the monitoring demand point of the i-th UAV, W being the number of soft constraint label sub-data.

[0117] S34: obtaining the reachability index of the three-dimensional flight path from the candidate facility point of each of the UAVs to the monitoring demand point of each of the UAVs according to the hard constraint label data of each of the sampling points corresponding to the three-dimensional flight path from the candidate facility point of each of the UAVs to the monitoring demand point of each of the UAVs, the local reachability index, and a preset three-dimensional flight path comprehensive reachability index calculation algorithm.

[0118] In this embodiment, the deployment device obtains the reachability index of the three-dimensional flight path from the candidate facility point of each of the UAVs to the monitoring demand point of each of the UAVs according to the hard constraint label data of each of the sampling points corresponding to the three-dimensional flight path from the candidate facility point of each of the UAVs to the monitoring demand point of each of the UAVs, the local reachability index, and a preset three-dimensional flight path comprehensive reachability index calculation algorithm, wherein the three-dimensional flight path comprehensive reachability index calculation algorithm is:

[0119]

[0120] wherein, α ij the reachability index of the three-dimensional flight path from the candidate facility point of the j-th UAV to the monitoring demand point of the i-th UAV, K being the number of sampling points corresponding to the three-dimensional flight path, the hard constraint label data of the k-th sampling point on the three-dimensional flight path from the candidate facility point of the j-th UAV to the monitoring demand point of the i-th UAV.

[0121] S4: inputting the reachability index of the three-dimensional flight path from the candidate facility point of each of the UAVs to the monitoring demand point of each of the UAVs into a preset UAV airfield site selection model to extract target facility points, obtaining a plurality of target facility points, and generating a UAV airfield deployment scheme.

[0122] In this embodiment, the deployment device inputs the reachability index of the three-dimensional flight path from the candidate facility point of each of the UAVs to the monitoring demand point of each of the UAVs into a preset UAV airfield site selection model to extract target facility points, obtains a plurality of target facility points, and generates a UAV airfield deployment scheme.

[0123] Based on the constructed 3D flight paths from candidate facility points of each UAV to the monitoring demand points of each UAV in the target watershed, and considering the 3D geospatial constraints in the complex low-altitude environment of the target watershed, a 3D flight path accessibility evaluation index system is constructed. 3D flight path accessibility analysis is carried out, and combined with the obtained accessibility index and UAV airport site selection model, UAV airport deployment is carried out to optimize resource allocation and improve the overall safety and efficiency of flight missions. This reflects the organic integration of 3D spatial perception, 3D flight path accessibility, and UAV airport deployment strategies, which can enhance the reliability and adaptability of UAV operations in complex watershed environments.

[0124] The UAV airport site selection model includes a three-dimensional flight path accessibility index maximization objective function, a constraint on the number of target facility points, and a constraint on the selection of candidate facility points; please refer to Figure 7 , Figure 7 The flowchart of step S4 in the method for deploying UAVs in a watershed based on three-dimensional spatial perception according to an embodiment of this application is shown below, including step S41:

[0125] S41: Based on the accessibility index of the three-dimensional flight path from each candidate facility point of the UAV to the monitoring requirement point of each UAV, the objective function for maximizing the accessibility index of the three-dimensional flight path, the constraint on the number of target facility points, and the constraint on the selection of candidate facility points, with the objective of maximizing the accessibility index of all three-dimensional flight paths, target facility points are extracted from the candidate facility points of the UAV to obtain a number of target facility points.

[0126] The objective function for maximizing the three-dimensional flight path reachability index is:

[0127]

[0128] z i =max{α ij ·x j},or

[0129] In the formula, z i Let x be the maximum reachability index of the 3D flight path corresponding to the monitoring requirement point of the i-th UAV. It represents the reachability index value of the 3D flight path with the highest reachability index among all candidate facility points of the selected deployed j-th UAV for the monitoring requirement point of the i-th UAV. N is the number of monitoring requirement points of UAVs. j Let M be the selection variable for the candidate facility point of the j-th UAV, indicating whether the candidate facility point of the j-th UAV is selected as the target facility point, and M is the number of candidate facility points of the UAV.

[0130] The target facility point quantity constraint condition is:

[0131]

[0132] In the formula, P is the number of target facility points;

[0133] The candidate facility point selection constraint condition is:

[0134]

[0135] In the formula, y ij is the service variable of the candidate facility point of the jth unmanned aerial vehicle to the monitoring demand point of the ith unmanned aerial vehicle, indicating whether the candidate facility point of the jth unmanned aerial vehicle serves the monitoring demand point of the ith unmanned aerial vehicle.

[0136] In the embodiment, the deployment device extracts target facility points from the candidate facility points of the unmanned aerial vehicles according to the reachability indexes of the three-dimensional flight paths of the candidate facility points of the unmanned aerial vehicles to the monitoring demand points of the unmanned aerial vehicles, the three-dimensional flight path reachability index maximization target function, the target facility point quantity constraint condition, and the candidate facility point selection constraint condition, so as to maximize the reachability indexes of all the three-dimensional flight paths. The hard constraint indexes such as terrain shielding, building shielding, restricted flight area, and unmanned aerial vehicle performance constraint, and the soft constraint indexes such as wind speed condition, communication coverage, and population density distribution are comprehensively considered, the "three-dimensional flight path reachability" is introduced as an important basis for judging the unmanned aerial port deployment stage, and the purpose is to screen out high-risk or high-coverage cost candidate facility point-monitoring demand point combinations in advance, so as to optimize resource allocation and improve the safety and efficiency of the whole flight task.

[0137] Please refer to Figure 8 , Figure 8 The structure diagram of the watershed unmanned aerial port deployment device based on three-dimensional space perception provided by an embodiment of the present application is shown in FIG. 8. The device can realize all or part of the three-dimensional space perception based watershed unmanned aerial port deployment device through software, hardware, or a combination of both. The device 8 includes:

[0138] A point site obtaining module 81 is configured to obtain a plurality of field observation stations and a plurality of catchment units in a target watershed, take each field observation station as a candidate facility point of an unmanned aerial vehicle, and take the geographic center of each catchment unit as a monitoring demand point of the unmanned aerial vehicle.

[0139] a three-dimensional flight path modeling module 82, configured to perform three-dimensional flight path modeling and sample point extraction according to the candidate facility points of each of the UAVs and the monitoring demand points of the UAVs, to obtain three-dimensional coordinate data of a plurality of sample points corresponding to the three-dimensional flight paths from the candidate facility points of each of the UAVs to the monitoring demand points of each of the UAVs;

[0140] an accessibility index evaluation module 83, configured to obtain position attribute data of the sample points corresponding to the three-dimensional flight paths from the candidate facility points of each of the UAVs to the monitoring demand points of each of the UAVs; and input the three-dimensional coordinate data and the position attribute data of the plurality of sample points corresponding to the three-dimensional flight paths from the candidate facility points of each of the UAVs to the monitoring demand points of each of the UAVs into a preset accessibility index evaluation model to perform evaluation, to obtain accessibility indexes of the three-dimensional flight paths from the candidate facility points of each of the UAVs to the monitoring demand points of each of the UAVs;

[0141] a UAV air hub deployment module 84, configured to input the accessibility indexes of the three-dimensional flight paths from the candidate facility points of each of the UAVs to the monitoring demand points of each of the UAVs into a preset UAV air hub site selection model to perform target facility point extraction, to obtain a plurality of target facility points, and to generate a UAV air hub deployment scheme.

[0142] In the embodiment of the present application, the point position obtaining module obtains a plurality of field observation stations and a plurality of catchment units in a target basin, takes each of the field observation stations as a candidate facility point of a UAV, and takes a geographic center of each of the catchment units as a monitoring demand point of the UAV; the three-dimensional flight path modeling module performs three-dimensional flight path modeling and sampling point extraction according to the candidate facility points of each of the UAVs and the monitoring demand points of the UAVs, and obtains three-dimensional coordinate data of a plurality of sampling points corresponding to a three-dimensional flight path from each of the candidate facility points of the UAVs to each of the monitoring demand points of the UAVs; the accessibility index evaluation module obtains position attribute data of each of the sampling points corresponding to the three-dimensional flight path from each of the candidate facility points of the UAVs to each of the monitoring demand points of the UAVs; the three-dimensional coordinate data and the position attribute data of the plurality of sampling points corresponding to the three-dimensional flight path from each of the candidate facility points of the UAVs to each of the monitoring demand points of the UAVs are input into a preset accessibility index evaluation model for evaluation, and an accessibility index of the three-dimensional flight path from each of the candidate facility points of the UAVs to each of the monitoring demand points of the UAVs is obtained; the UAV airfield deployment module inputs the accessibility index of the three-dimensional flight path from each of the candidate facility points of the UAVs to each of the monitoring demand points of the UAVs into a preset UAV airfield site selection model for target facility point extraction, obtains a plurality of target facility points, and generates a UAV airfield deployment scheme. Based on the three-dimensional flight paths from each of the candidate facility points of the UAVs to each of the monitoring demand points of the UAVs constructed in the target basin, the three-dimensional flight path accessibility evaluation index system is constructed for the three-dimensional geographic space constraints in the low-altitude complex environment of the target basin, the three-dimensional flight path accessibility analysis is carried out, the accessibility index obtained and the UAV airfield site selection model are combined, the UAV airfield deployment is carried out, the resource allocation is optimized, and the safety and efficiency of the overall flight task are improved.

[0143] Please refer to Figure 9 , Figure 9 The structural schematic diagram of the computer device provided in an embodiment of the present application, the computer device 8 comprises a processor 91, a memory 92, and a computer program 93 stored in the memory 92 and executable on the processor 91; the computer device can store a plurality of instructions, the instructions are suitable for being loaded and executed by the processor 91 to execute the method steps of the embodiments shown in Figures 1 to 7 , and the specific execution process can refer to the specific description of the embodiments shown in Figures 1 to 7 , which will not be described here.

[0144] The processor 91 can include one or more processing cores. The processor 91 connects various parts within the server by running or executing instructions, programs, code sets or instruction sets stored in the memory 92, and calling data in the memory 92, to perform various functions and process data of the drainage area unmanned aerial vehicle airfield deployment device 8 based on three-dimensional space perception. Optionally, the processor 91 can be implemented in at least one of a hardware form of a digital signal processing (Digital Signal Processing, DSP), a field-programmable gate array (Field-Programmable Gate Array, FPGA), and a programmable logic array (Programble Logic Array, PLA). The processor 91 can be integrated with one or a combination of a central processing unit 91 (Central Processing Unit, CPU), a graphics processing unit 91 (Graphics Processing Unit, GPU), and a modem. Among them, the CPU is mainly used to process operating systems, user interfaces, and application programs; the GPU is used to render and draw the content displayed on the touch display screen; and the modem is used to process wireless communication. It can be understood that the above-mentioned modem can also not be integrated into the processor 91, but can be realized by a separate chip.

[0145] The memory 92 can include a random access memory 92 (Random Access Memory, RAM) and a read-only memory 92 (Read-Only Memory). Optionally, the memory 92 includes a non-transitory computer-readable storage medium. The memory 92 can be used to store instructions, programs, codes, code sets or instruction sets. The memory 92 can include a program storage area and a data storage area, wherein the program storage area can store instructions for implementing an operating system, instructions for at least one function (such as touch instructions, etc.), instructions for implementing the above-mentioned various method embodiments, etc.; the data storage area can store data involved in the above-mentioned various method embodiments, etc. The memory 92 can also be at least one storage device located away from the aforementioned processor 91.

[0146] The embodiments of the present application also provide a storage medium, which can store a plurality of instructions. The instructions are suitable for being loaded and executed by a processor to perform the method steps of the embodiments shown in the above Figures 1 to 7 The specific execution process can refer to the specific description of the embodiments shown in the above Figures 1 to 7 The specific execution process can refer to the specific description of the embodiments shown in the above

[0147] Those skilled in the art can clearly understand that, for the convenience and brevity of description, only the above-mentioned division of each functional unit and module is exemplified, and in actual application, the above-mentioned functions can be completed by different functional units and modules according to needs, that is, the internal structure of the device is divided into different functional units or modules to complete all or part of the functions described above. Each functional unit and module in the embodiment can be integrated in one processing unit, or each unit can be physically present separately, or two or more units can be integrated in one unit. The above-mentioned integrated unit can be realized in the form of hardware or software. In addition, the specific name of each functional unit and module is only for the convenience of mutual distinction, and does not limit the protection scope of the present application. The specific working process of the unit and module in the above system can be referred to the corresponding process in the foregoing method embodiment, which will not be described here.

[0148] In the above embodiments, the description of each embodiment has its own emphasis, and the parts not described or recorded in detail in a certain embodiment can be referred to the related description of other embodiments.

[0149] Those of ordinary skill in the art can realize that the units and algorithm steps of each example described in combination with the embodiments disclosed herein can be realized in electronic hardware or a combination of computer software and electronic hardware. Whether the functions are executed in hardware or software depends on the specific application and design constraints of the algorithm. Professional technicians can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of the present application.

[0150] In the embodiments provided by the present application, it should be understood that the disclosed apparatus / terminal device and method can be implemented in other ways. For example, the above-mentioned apparatus / terminal device embodiments are only schematic. The division of the modules or units is only a logical function division, and there can be another division manner in actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed mutual coupling or direct coupling or communication connection can be indirect coupling or communication connection through some interface, device or unit, and can be electrical, mechanical or other forms.

[0151] The units described as separate components can or can not be physically separated, and the components shown as units can or can not be physical units, that is, they can be located in one place, or can be distributed on multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the embodiment.

[0152] In addition, each function unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically separately, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software function unit.

[0153] The integrated module / unit, if realized in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, all or part of the processes in the above-mentioned embodiment methods can also be completed by a computer program instructing related hardware, and the computer program can be stored in a computer readable storage medium. The computer program, when executed by a processor, can implement the steps of each method embodiment. The computer program includes computer program code, which can be in the form of source code, object code, an executable file, or some intermediate form.

[0154] The present application is not limited to the above-described embodiments, and various modifications or changes can be made to the present application without departing from the spirit and scope of the present application. Therefore, it is intended that the present application encompass all such modifications and changes and fall within the scope of the appended claims and their equivalents.

Claims

1. A method for deploying a watershed UAV airfield based on three-dimensional spatial perception, characterized in that, The method comprises the following steps: obtaining a plurality of field observation stations and a plurality of catchment units in a target basin, taking each of the field observation stations as a candidate facility point of a UAV, and taking a geographic center of each of the catchment units as a monitoring demand point of the UAV; performing three-dimensional flight path modeling and sampling point extraction according to the candidate facility point of each of the UAVs and the monitoring demand point of the UAV to obtain three-dimensional coordinate data of a plurality of sampling points corresponding to a three-dimensional flight path from the candidate facility point of each of the UAVs to the monitoring demand point of each of the UAVs; obtaining position attribute data of each of the sampling points corresponding to the three-dimensional flight path from the candidate facility point of each of the UAVs to the monitoring demand point of each of the UAVs, wherein the position attribute data comprises elevation data, building surface model data and environmental attribute data; inputting the three-dimensional coordinate data and the position attribute data of the plurality of sampling points corresponding to the three-dimensional flight path from the candidate facility point of each of the UAVs to the monitoring demand point of each of the UAVs into a preset reachability index evaluation model, obtaining hard constraint label data of each of the sampling points corresponding to the three-dimensional flight path from the candidate facility point of each of the UAVs to the monitoring demand point of each of the UAVs according to the three-dimensional coordinate data, the elevation data, the building surface model data of each of the sampling points and a hard constraint condition in the reachability index evaluation model, and the hard constraint condition is used to indicate the reachability of the three-dimensional flight path in the physical and regulatory levels; obtaining soft constraint label data of each of the sampling points corresponding to the three-dimensional flight path from the candidate facility point of each of the UAVs to the monitoring demand point of each of the UAVs according to the environmental attribute data of each of the sampling points and a soft constraint condition in the reachability index evaluation model, and the soft constraint condition is used to indicate the reachability of the three-dimensional flight path in the environmental flight and public safety aspects; obtaining a local reachability index of each of the sampling points corresponding to the three-dimensional flight path from the candidate facility point of each of the UAVs to the monitoring demand point of each of the UAVs according to the hard constraint label data, the soft constraint label data of each of the sampling points and a preset local reachability index calculation algorithm, and the local reachability index calculation algorithm is: In the formula, For the first j The candidate facility points for the drones to the first i The third drone's three-dimensional flight path to the monitoring requirement point k Local accessibility index of each sampling point For the first j The candidate facility points for the drones to the first i The third drone's three-dimensional flight path to the monitoring requirement point k In the hard constraint label data of the sampling point, the first u A hard-constraint labeled subdata, U The number of hard-constrained labeled sub-data. For the first j The candidate facility points for the drones to the first i The third drone's three-dimensional flight path to the monitoring requirement point k In the soft constraint label data of the sampling point, the first w A soft constraint label sub-data, W This represents the number of soft constraint labels; obtaining a reachability index of the three-dimensional flight path from the candidate facility point of each of the UAVs to the monitoring demand point of each of the UAVs according to the hard constraint label data, the local reachability index of each of the sampling points and a preset three-dimensional flight path comprehensive reachability index calculation algorithm, and the three-dimensional flight path comprehensive reachability index calculation algorithm is: In the formula, For the first j The candidate facility points for the drones to the first i The accessibility index of the three-dimensional flight path of a drone for monitoring the required points. K This represents the number of sampling points corresponding to the three-dimensional flight path. For the first j The candidate facility points for the drones to the first i The third drone's three-dimensional flight path to the monitoring requirement point k Hard-constraint label data for each sampling point; The reachability indexes of the three-dimensional flight paths from each candidate facility point of the unmanned aerial vehicle to each monitoring demand point of the unmanned aerial vehicle are input into a preset unmanned aerial vehicle airport site selection model, and the reachability indexes of the three-dimensional flight paths from each candidate facility point of the unmanned aerial vehicle to each monitoring demand point of the unmanned aerial vehicle, a three-dimensional flight path reachability index maximization objective function of the unmanned aerial vehicle airport site selection model, a target facility point quantity constraint condition and a candidate facility point selection constraint condition are used to maximize the reachability indexes of all the three-dimensional flight paths, so as to extract target facility points from the candidate facility points of the unmanned aerial vehicle, obtain a plurality of target facility points, and generate an unmanned aerial vehicle airport deployment scheme.

2. The method of claim 1, wherein, The three-dimensional flight path modeling and sampling point extraction are performed according to the candidate facility points of each unmanned aerial vehicle and the monitoring demand points of the unmanned aerial vehicle, and three-dimensional coordinate data of a plurality of sampling points corresponding to the three-dimensional flight paths from each candidate facility point of the unmanned aerial vehicle to each monitoring demand point of the unmanned aerial vehicle are obtained, including the following steps: The candidate facility points of each unmanned aerial vehicle are linearly connected with the monitoring demand points of each unmanned aerial vehicle respectively, and three-dimensional flight paths from each candidate facility point of the unmanned aerial vehicle to each monitoring demand point of the unmanned aerial vehicle are obtained. Three-dimensional coordinate data of each monitoring demand point of the unmanned aerial vehicle and three-dimensional coordinate data of each candidate facility point of the unmanned aerial vehicle are obtained, and three-dimensional Euclidean distances of the three-dimensional flight paths from each candidate facility point of the unmanned aerial vehicle to each monitoring demand point of the unmanned aerial vehicle are obtained according to the three-dimensional coordinate data of each monitoring demand point of the unmanned aerial vehicle, the three-dimensional coordinate data of each candidate facility point of the unmanned aerial vehicle and a preset three-dimensional Euclidean distance calculation algorithm, wherein the three-dimensional coordinate data includes horizontal coordinate data, vertical coordinate data and vertical coordinate data. The number of sampling points of the three-dimensional flight paths from each candidate facility point of the unmanned aerial vehicle to each monitoring demand point of the unmanned aerial vehicle is determined according to the three-dimensional Euclidean distances of the three-dimensional flight paths from each candidate facility point of the unmanned aerial vehicle to each monitoring demand point of the unmanned aerial vehicle and a preset sampling interval, and the relative positions of each sampling point of the three-dimensional flight paths from each candidate facility point of the unmanned aerial vehicle to each monitoring demand point of the unmanned aerial vehicle are obtained according to the three-dimensional Euclidean distances of the three-dimensional flight paths from each candidate facility point of the unmanned aerial vehicle to each monitoring demand point of the unmanned aerial vehicle, the number of sampling points and a preset relative position calculation algorithm. The three-dimensional coordinate data of each sampling point of the three-dimensional flight paths from each candidate facility point of the unmanned aerial vehicle to each monitoring demand point of the unmanned aerial vehicle are obtained according to the three-dimensional coordinate data of each candidate facility point of the unmanned aerial vehicle, the relative positions of each sampling point of the three-dimensional flight paths from each candidate facility point of the unmanned aerial vehicle to each monitoring demand point of the unmanned aerial vehicle and a preset sampling point three-dimensional coordinate calculation algorithm.

3. The three-dimensional space-aware based watershed drone airfield deployment method of claim 1, wherein: The hard constraints include occlusion constraints, policy constraints and UAV performance constraints, wherein the occlusion constraints include terrain constraints and artificial attachment constraints; the policy constraints include no-fly zone constraints; and the UAV performance constraints include UAV vertical height difference constraints and UAV operation radius constraints. The hard constraint label sub-data includes terrain constraint label data, artificial attachment constraint label data, no-fly zone constraint label data, UAV vertical height difference constraint label data and UAV operation radius constraint label data. The hard constraint label data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each UAV to the monitoring demand point of each UAV is obtained according to the three-dimensional coordinate data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each UAV to the monitoring demand point of each UAV, the elevation data of each sampling point, the building surface model data of each sampling point, the hard constraint conditions in the accessibility index evaluation model, and comprises the following steps: The terrain constraint label data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each UAV to the monitoring demand point of each UAV is obtained according to the elevation data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each UAV to the monitoring demand point of each UAV, the elevation threshold of the corresponding sampling point and the terrain constraints. The artificial attachment constraint label data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each UAV to the monitoring demand point of each UAV is obtained according to the building surface model data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each UAV to the monitoring demand point of each UAV, the building surface model threshold of the corresponding sampling point and the artificial attachment constraints. The no-fly zone constraint label data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each UAV to the monitoring demand point of each UAV is obtained according to the horizontal coordinate data and the vertical coordinate data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each UAV to the monitoring demand point of each UAV, all two-dimensional coordinate sets in the preset no-fly zone and the no-fly zone constraints. The UAV vertical height difference constraint label data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each UAV to the monitoring demand point of each UAV is obtained according to the vertical coordinate data of each sampling point corresponding to the three-dimensional flight path from the candidate facility point of each UAV to the monitoring demand point of each UAV, the vertical coordinate data of the candidate facility point of each UAV and the UAV vertical height difference constraints. According to the vertical coordinate data of each sampling point corresponding to the three-dimensional flight path from each candidate facility point of the unmanned aerial vehicle to the monitoring demand point of the unmanned aerial vehicle, the horizontal coordinate data and the longitudinal coordinate data of each candidate facility point of the unmanned aerial vehicle, and the unmanned aerial vehicle operation radius constraint condition, the unmanned aerial vehicle operation radius constraint label data of each sampling point corresponding to the three-dimensional flight path from each candidate facility point of the unmanned aerial vehicle to the monitoring demand point of the unmanned aerial vehicle is obtained.

4. The method of claim 3, wherein: The soft constraint condition includes an environment suitable for flying constraint and a public safety constraint, wherein the environment suitable for flying constraint includes a wind speed constraint condition and a communication level constraint condition; the public safety constraint includes a population density constraint condition; The soft constraint label sub-data includes wind speed constraint condition label data, communication level constraint condition label data, and population density constraint condition label data; and the environment attribute data includes an annual average wind speed value, a nearest communication base station distance parameter, and a population density value; The soft constraint label data of each sampling point corresponding to the three-dimensional flight path from each candidate facility point of the unmanned aerial vehicle to the monitoring demand point of the unmanned aerial vehicle is obtained according to the environment attribute data of each sampling point corresponding to the three-dimensional flight path from each candidate facility point of the unmanned aerial vehicle to the monitoring demand point of the unmanned aerial vehicle and the soft constraint condition in the accessibility index evaluation model, and includes the following steps: According to the annual average wind speed value of the sampling point, the minimum value and the maximum value of the annual average wind speed are determined; and according to the minimum value and the maximum value of the annual average wind speed, the annual average wind speed value of each sampling point corresponding to the three-dimensional flight path from each candidate facility point of the unmanned aerial vehicle to the monitoring demand point of the unmanned aerial vehicle, and the wind speed constraint condition, the wind speed constraint label data of each sampling point corresponding to the three-dimensional flight path from each candidate facility point of the unmanned aerial vehicle to the monitoring demand point of the unmanned aerial vehicle is obtained; According to the nearest communication base station distance parameter of each sampling point corresponding to the three-dimensional flight path from each candidate facility point of the unmanned aerial vehicle to the monitoring demand point of the unmanned aerial vehicle and the communication level constraint condition, the communication level constraint data of each sampling point corresponding to the three-dimensional flight path from each candidate facility point of the unmanned aerial vehicle to the monitoring demand point of the unmanned aerial vehicle is obtained; According to the population density value of the sampling point, the minimum value and the maximum value of the population density are determined; and according to the population density data of each sampling point corresponding to the three-dimensional flight path from each candidate facility point of the unmanned aerial vehicle to the monitoring demand point of the unmanned aerial vehicle and the population density constraint condition, the population density constraint data of each sampling point corresponding to the three-dimensional flight path from each candidate facility point of the unmanned aerial vehicle to the monitoring demand point of the unmanned aerial vehicle is obtained.

5. The three-dimensional space-aware based watershed drone airfield deployment method of claim 1, wherein, The obtaining of the several field observation stations and the catchment units in the target watershed includes the following steps: Obtaining digital elevation model data of the target watershed; According to the digital elevation model data, the target watershed is divided into catchment units, and several catchment units are obtained.

6. A three-dimensional space perception based watershed UAV airfield deployment apparatus, characterized by, It includes: The point obtaining module is configured to obtain a plurality of field observation stations and a plurality of catchment units in a target basin, take each of the field observation stations as a candidate facility point of a UAV, and take a geographic center of each of the catchment units as a monitoring demand point of the UAV; The three-dimensional flight path modeling module is configured to model a three-dimensional flight path and extract a sampling point according to the candidate facility point of each of the UAVs and the monitoring demand point of the UAV, and obtain three-dimensional coordinate data of a plurality of sampling points corresponding to the three-dimensional flight path from the candidate facility point of each of the UAVs to the monitoring demand point of each of the UAVs; The reachability index evaluation module is configured to obtain position attribute data of each of the sampling points corresponding to the three-dimensional flight path from the candidate facility point of each of the UAVs to the monitoring demand point of each of the UAVs, wherein the position attribute data includes elevation data, building surface model data, and environmental attribute data; The three-dimensional coordinate data and the position attribute data of the plurality of sampling points corresponding to the three-dimensional flight path from the candidate facility point of each of the UAVs to the monitoring demand point of each of the UAVs are input into a preset reachability index evaluation model, three-dimensional coordinate data, elevation data, building surface model data, and a hard constraint condition in the reachability index evaluation model are used to obtain hard constraint label data of each of the sampling points corresponding to the three-dimensional flight path from the candidate facility point of each of the UAVs to the monitoring demand point of each of the UAVs; the hard constraint condition is used to indicate the reachability of the three-dimensional flight path in the physical and regulatory levels; The environmental attribute data of each of the sampling points corresponding to the three-dimensional flight path from the candidate facility point of each of the UAVs to the monitoring demand point of each of the UAVs and a soft constraint condition in the reachability index evaluation model are used to obtain soft constraint label data of each of the sampling points corresponding to the three-dimensional flight path from the candidate facility point of each of the UAVs to the monitoring demand point of each of the UAVs; the soft constraint condition is used to indicate the reachability of the three-dimensional flight path in the environmental flight and public safety aspects; The hard constraint label data, the soft constraint label data, and a preset local reachability index calculation algorithm of each of the sampling points corresponding to the three-dimensional flight path from the candidate facility point of each of the UAVs to the monitoring demand point of each of the UAVs are used to obtain a local reachability index of each of the sampling points, wherein the local reachability index calculation algorithm is: In the formula, For the first j The candidate facility points for the drones to the first i The third drone's three-dimensional flight path to the monitoring requirement point k Local accessibility index of each sampling point For the first j The candidate facility points for the drones to the first i The third drone's three-dimensional flight path to the monitoring requirement point k In the hard constraint label data of the sampling point, the first u A hard-constraint labeled subdata, U The number of hard-constrained labeled sub-data. For the first j The candidate facility points for the drones to the first i The third drone's three-dimensional flight path to the monitoring requirement point k In the soft constraint label data of the sampling point, the first w A soft constraint label subdata, W This represents the number of soft constraint labels; The hard constraint label data, the local reachability index, and a preset three-dimensional flight path comprehensive reachability index calculation algorithm of each of the sampling points corresponding to the three-dimensional flight path from the candidate facility point of each of the UAVs to the monitoring demand point of each of the UAVs are used to obtain a reachability index of the three-dimensional flight path from the candidate facility point of each of the UAVs to the monitoring demand point of each of the UAVs, wherein the three-dimensional flight path comprehensive reachability index calculation algorithm is: In the formula, is the number of candidate facility points of the first j unmanned aerial vehicle, i is the accessibility index of the three-dimensional flight path from the candidate facility point of the first K unmanned aerial vehicle to the monitoring demand point of the first unmanned aerial vehicle, j is the number of sampling points corresponding to the three-dimensional flight path, i is the hard constraint label data of the first k sampling point on the three-dimensional flight path from the candidate facility point of the first unmanned aerial vehicle to the monitoring demand point of the first unmanned aerial vehicle. The unmanned aerial vehicle airport deployment module is configured to input the accessibility indexes of the three-dimensional flight paths from the candidate facility points of the unmanned aerial vehicles to the monitoring demand points of the unmanned aerial vehicles into a preset unmanned aerial vehicle airport site selection model, and to extract target facility points from the candidate facility points of the unmanned aerial vehicles according to the accessibility indexes of the three-dimensional flight paths from the candidate facility points of the unmanned aerial vehicles to the monitoring demand points of the unmanned aerial vehicles, a three-dimensional flight path accessibility index maximization objective function of the unmanned aerial vehicle airport site selection model, a target facility point quantity constraint condition, and a candidate facility point selection constraint condition, so as to maximize the accessibility indexes of all the three-dimensional flight paths, to obtain a plurality of target facility points, and to generate an unmanned aerial vehicle airport deployment scheme.

7. A computer device, comprising: The method comprises the following steps: The storage medium stores a computer program, and the computer program is executed by the processor to implement the steps of the method for deploying an unmanned aerial vehicle airport in a drainage basin based on three-dimensional space perception according to any one of claims 1 to 5.

8. A storage medium characterized by: The storage medium stores a computer program, and the computer program is executed by the processor to implement the steps of the method for deploying an unmanned aerial vehicle airport in a drainage basin based on three-dimensional space perception according to any one of claims 1 to 5.

Images