Railway slope inspection planning method and device

Abstract

The invention provides a railway slope inspection planning method and device, and relates to the technical field of measurement and control, and the method comprises the steps: constructing a live-action three-dimensional model of a to-be-inspected railway slope; calculating inspection work data of the unmanned aerial vehicle based on the live-action three-dimensional model; performing first endpoint division on the railway slope to be inspected based on the inspection work data, and constructing unmanned aerial vehicle nest nodes and setting the number of unmanned aerial vehicles based on the divided first endpoints; and performing inspection route planning based on the unmanned aerial vehicle nest and the unmanned aerial vehicle to obtain an inspection scheme of the railway slope to be inspected. According to the invention, by calculating the inspection work data of the unmanned aerial vehicle, arranging the machine nest according to the inspection work data, and performing inspection planning according to the position of the machine nest, the number of the machine nest required to be constructed is reduced, the cost is saved, and the working efficiency of unmanned aerial vehicle inspection is improved.

Description

Technical Field

[0001] The present invention relates to the field of measurement and control technology, and in particular to a railway slope inspection planning method and device. Background Art

[0002] When building railways in mountainous areas, a large number of tunnels and slopes are often required. These engineering structures face challenges from geological activities and climate change, and disasters such as slope landslides seriously endanger the safety of train operations. To ensure the safety of high-speed railways, a slope monitoring system is usually established to regularly check the changes in slope morphology, analyze deformation trends, and identify potential landslide hazards.

[0003] However, existing slope monitoring methods mostly use fixed sensor equipment for continuous monitoring, which has high requirements for the surrounding environment. High-speed railway slopes are generally found in mountainous areas with complex terrain and landforms. The use of fixed cameras and radar monitoring methods is greatly restricted by objective conditions such as terrain and network, making it difficult to set up and maintain fixed monitoring equipment.

[0004] Most of the existing methods of using drones for slope inspection require planning of inspection routes based on the setting of drone nests. However, since it is impossible to determine a good location for building drone nests, a large number of drone nests need to be built, resulting in high consumption costs for drone inspections but low efficiency. Summary of the invention

[0005] The purpose of the present invention is to provide a railway slope inspection planning method and device to improve the above problems. In order to achieve the above purpose, the technical solution adopted by the present invention is as follows:

[0006] In a first aspect, the present application provides a railway slope inspection planning method, comprising:

[0007] Obtaining oblique photogrammetry results of the railway slope to be inspected by the drone, and constructing a real-scene three-dimensional model of the railway slope to be inspected based on the oblique photogrammetry results;

[0008] Calculating the inspection work data of the drone based on the real-scene three-dimensional model, wherein the inspection work data includes the inspection time of the drone on each slope and the inspection time of the drone between two adjacent slopes;

[0009] Based on the inspection work data of the drone, the first endpoint of the railway slope to be inspected is divided, and based on the first endpoint obtained by the division, the drone nest node is constructed and the number of drones is set;

[0010] Inspection routes are planned based on the drone nest nodes and the number of drones to obtain an inspection plan for the railway slope to be inspected.

[0011] In a second aspect, the present application also provides a railway slope inspection planning device, comprising:

[0012] The first processing module is used to obtain the oblique photogrammetry results of the railway slope to be inspected by the UAV;

[0013] A second processing module is used to construct a real-scene three-dimensional model of the railway slope to be inspected based on the oblique photogrammetry results;

[0014] A third processing module is used to calculate the inspection work data of the drone based on the real-scene three-dimensional model, wherein the inspection work data includes the inspection time of the drone on each slope and the inspection time of the drone between two adjacent slopes;

[0015] The fourth processing module is used to divide the railway slope to be inspected into first endpoints based on the inspection work data of the drone, and to construct drone nest nodes and set the number of drones based on the first endpoints obtained by the division;

[0016] The fifth processing module is used to plan the inspection route based on the drone nest node and the number of drones to obtain the inspection plan for the railway slope to be inspected.

[0017] The beneficial effects of the present invention are:

[0018] The present invention calculates the inspection work data of the UAV, arranges the machine nest according to the inspection work data, and then performs inspection planning according to the machine nest position, thereby reducing the number of machine nests required to be constructed, saving costs, and improving the work efficiency of the UAV inspection.

[0019] Other features and advantages of the present invention will be set forth in the following description, and in part will become apparent from the description, or may be understood by practicing embodiments of the present invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0020] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings required for use in the embodiments are briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present invention and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0021] Figure 1 It is a schematic diagram of a flow chart of a railway slope inspection planning method described in an embodiment of the present invention;

[0022] Figure 2 It is a schematic diagram of the structure of a railway slope inspection planning device described in an embodiment of the present invention;

[0023] Figure 3is a schematic diagram of an initial three-dimensional model described in an embodiment of the present invention;

[0024] Figure 4 This is a schematic diagram of the location of the drone nest node described in an embodiment of the present invention;

[0025] Figure 5 Schematic diagram of the relative positions of the slope node, the non-slope road section and the drone nest node described in the embodiment of the present invention;

[0026] Figure 6 Schematic diagram of the transfer of the UAV between machine nests described in an embodiment of the present invention.

[0027] Markings in the figure: 901, first processing module; 902, second processing module; 903, third processing module; 904, fourth processing module; 905, fifth processing module; 9011, first processing unit; 9012, second processing unit; 9013, third processing unit; 9014, fourth processing unit; 9015, fifth processing unit; 9021, sixth processing unit; 9022, seventh processing unit; 9031, eighth processing unit; 9032, ninth processing unit; 90121, third processing submodule; 90122, fourth processing submodule; 90123, fifth processing submodule; 90124, sixth processing submodule; 90141, first processing submodule; 90142, second processing submodule. DETAILED DESCRIPTION

[0028] In order to make the purpose, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, rather than all of the embodiments. The components of the embodiments of the present invention generally described and shown in the drawings here can be arranged and designed in various different configurations. Therefore, the following detailed description of the embodiments of the present invention provided in the drawings is not intended to limit the scope of the claimed invention, but merely represents selected embodiments of the present invention. Based on the embodiments in the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0029] It should be noted that similar reference numerals and letters represent similar items in the following drawings, so once an item is defined in one drawing, it does not need to be further defined and explained in the subsequent drawings. At the same time, in the description of the present invention, the terms "first", "second", etc. are only used to distinguish the description and cannot be understood as indicating or implying relative importance.

[0030] Embodiment 1:

[0031] This embodiment provides a railway slope inspection planning method.

[0032] See also Figure 1 , the figure shows that the method includes step S1, step S2, step S3, and step S4.

[0033] S1, obtaining oblique photogrammetry results of a railway slope to be inspected by a drone, and constructing a real-life three-dimensional model of the railway slope to be inspected based on the oblique photogrammetry results.

[0034] Specifically, step S1 includes:

[0035] S11, obtaining first information, wherein the first information includes satellite image data of the railway slope to be inspected, terrain data around the railway, and railway planning vector data, and constructing an initial three-dimensional model based on the first information to obtain an initial three-dimensional model of the railway slope to be inspected;

[0036] Specifically, step S11 includes:

[0037] S111, constructing a scene three-dimensional model based on the terrain data around the railway, wherein the scene three-dimensional model is a three-dimensional model including two-dimensional plane data and vertical height data of the railway slope to be inspected, wherein the terrain data around the railway is acquired through satellite remote sensing such as stereo image pairs and SAR, and a scene three-dimensional model representing the terrain is constructed through the terrain data around the railway, and the scene three-dimensional model is 2.5D and includes two-dimensional plane data and vertical height data of the terrain around the railway;

[0038] S112, spatially registering the satellite image data of the railway slope to be inspected and the railway planning vector data to obtain the railway area information to be inspected, wherein GIS software is used to read the spatial coordinates of the raster image and the vector data, and superimpose and display them to achieve preliminary registration; then manually or automatically marking the same-name points, using the geographic registration tool provided by the GIS software, to achieve accurate registration of the two data, and obtain the railway area in the image;

[0039] S113, target recognition is performed on the railway area information to be inspected based on the YOLOv8-seg model, and pixel classification is performed on the railway area information to be inspected after target recognition through the YOLOv8-seg model to obtain the railway slope area information to be inspected, wherein a target recognition network based on the YOLOv8-seg model is used to extract regions with landslide triangular faces, slope attachments, exposed rock and soil, etc. from the image; and then pixel classification is performed on the recognition result of the previous step through a semantic segmentation network based on YOLOv8-seg to obtain a pixel-level region on the image in the railway area in the image, that is, the railway slope image region to be inspected;

[0040] S114, superimposing the scene three-dimensional model and the railway slope area information to be inspected to obtain the initial three-dimensional model, wherein the scene three-dimensional model representing the terrain is superimposed with the railway slope image to be inspected to obtain the initial three-dimensional model of the railway and the surrounding scene, wherein the scene three-dimensional model and the railway slope image to be inspected are superimposed according to the spatial position, and the scene three-dimensional model is divided into two types: inspection target area and non-target area through the pixel-level image area obtained in S23. One method is to traverse the pixels of each inspection target in the satellite image, and mark the triangular faces containing pixel points in each horizontal space of the three-dimensional model. Finally, all the marked triangular faces are the target inspection areas. The significance of this step is to obtain the slope area required for inspection area division.

[0041] S12, calculating inspection work data corresponding to the initial three-dimensional model based on the initial three-dimensional model of the railway slope to be inspected;

[0042] Specifically, step S12 includes:

[0043] S121, such as Figure 3 As shown, after obtaining the area, shape, length, width, slope and cross section of the slope from the initial three-dimensional model of the railway and the surrounding scene, the workload of the drone inspection is preliminarily estimated. In this embodiment, the workload of the drone inspection is considered by calculating the inspection time of the drone on each slope and the inspection time of the drone between two adjacent slopes;

[0044] S122, a rectangle is used to fit the slope area. The triangle is the slope shape. The length of the circumscribed fitting rectangle parallel to the railway is l, and the width perpendicular to the railway is s. Since the shooting is perpendicular to the slope surface, when the camera parameters, image resolution, and vertical distance from the ground are fixed, it can be considered that the number of flights required in the horizontal direction is proportional to the length of the slope, that is, one flight is performed every n meters in the direction perpendicular to the railway. Then, the calculation formula for the workload required for the flight in the horizontal direction, that is, the direction parallel to the railway, is:

[0045]

[0046] Among them, w1 is the workload required for the drone to fly in the horizontal direction, l is the length of the circumscribed fitting rectangle corresponding to the slope parallel to the railway, s is the width of the circumscribed fitting rectangle corresponding to the slope perpendicular to the railway, α is the reciprocal of the maximum flight speed of the drone in the horizontal direction, and p is the slope of the slope. The idea of ​​this formula is time = distance / speed, and the calculated w1 is time;

[0047] S123, it is also necessary to calculate the workload required for the drone to fly in the vertical direction, that is, in the direction perpendicular to the railway. The calculation formula is:

[0048] w2=β·p·2s(p 2 +1) -2

[0049] Among them, w2 is the workload required for the UAV to fly in the vertical direction, β is the inverse of the maximum flight speed of the UAV in the vertical direction, p is the slope of the slope, s is the width of the circumscribed fitting rectangle corresponding to the slope perpendicular to the railway. Since there is a height difference in the slope, the height difference is calculated separately through this formula to obtain the workload w2 of the UAV in the vertical direction;

[0050] S124, through the calculation of step S311 and step S312, the total workload of the UAV on a single slope is finally obtained, and the calculation formula is:

[0051]

[0052] Among them, W n is the total workload of the UAV on a single slope, w1 is the workload required by the UAV in the horizontal direction, w2 is the workload required by the UAV in the vertical direction, n is the distance of each flight in the direction perpendicular to the railway, α is the reciprocal of the maximum flight speed of the UAV in the horizontal direction, β is the reciprocal of the maximum flight speed of the UAV in the vertical direction, p is the slope of the slope, and s is the width of the circumscribed fitting rectangle corresponding to the slope perpendicular to the railway;

[0053] S125, calculate the workload w of the UAV flying on the non-slope section between adjacent slopes k , the calculation formula is:

[0054] w k =α·k

[0055] Among them, k is the distance between two adjacent slopes, that is, the length of the slope-free section.

[0056] S13, dividing the railway slope to be inspected into second endpoints based on the inspection work data corresponding to the initial three-dimensional model, and constructing drone nest nodes and setting the number of drones based on the second endpoints obtained by the division;

[0057] Specifically, step S13 includes:

[0058] S131, such as Figure 4 As shown in FIG. 1 , for the workload obtained in step S3, a railway is represented as an alternation of a slope-free railway section and a slope, where w ki is the workload required for the UAV to fly on the i-th slope-free section, w niis the total workload required for the UAV to fly at the i-th slope node. P1, P2 and P3 represent three adjacent UAV nest nodes. All the workloads required can be expressed in a workload list [w k1 ,w n1 ,w k2 ,w n2 ,w k3 ,w n3 ,……]express;

[0059] S132, for a specific type of drone, the working capacity of the drone is considered by the maximum time it can fly, and 20% is reserved to deal with unexpected events, and the remaining part is considered as the effective working capacity of the drone; taking DJI Latitude 300 RTK as an example, in P mode, the maximum horizontal flight speed is 17m / s, the maximum ascent speed is 4m / s, and the maximum flight time is 55min. Its total working capacity is the maximum flight time of 3300 seconds, and the effective working capacity is M=3300*0.8=2640s; for the work calculation in the inspection, let α=1 / 17 (horizontal speed), β=1 / 4 (vertical speed), each operation content can be converted into corresponding time, and the longer the distance, the more time, and the greater the slope, the more time.

[0060] S133, such as Figure 4 As shown, for a drone nest node P2, the drones starting to work from the nest node P2 include two working modes: to the drone nest node P1 on the left and to the drone nest node P3 on the right. Therefore, it is necessary to ensure that the workload required for the work in both directions is less than the effective working capacity M. According to the workload list in step S41 and the effective working capacity of the drone in step S42, the workload list [w k1 ,w n1 ,w k2 ,w n2 ,w k3 ,w n3 ,……] is divided into multiple paragraphs whose total workload is less than the effective work capacity M. For example, if the workload list is [12, 43, 53, 24, 73, 21, 4, 56……], assuming that the effective work capacity is M=80, then the division result is: [|12, 43|53, 24|73|21, 4|56……], ensuring that the workload in each paragraph is less than M, and the greedy algorithm can be used for division;

[0061] S134, set up drones and nests at the end of each section, and add two nests and a redundant drone at the beginning and end of the line, divide the area according to the workload, and make preliminary nest and drone node layout. This is a simplified method, the purpose is to leave margin for node adjustment after subsequent refined modeling, and in fact, the nest node can be arranged between nodes, that is, W k It can be decomposed and solved by dynamic programming method.

[0062] S14, performing track planning of an oblique photogrammetry route based on the drone nest nodes and the number of drones to obtain an oblique photogrammetry route, performing oblique photogrammetry on the railway slope to be inspected according to the oblique photogrammetry route, and constructing the real-scene three-dimensional model based on the oblique photogrammetry result;

[0063] Specifically, step S14 includes:

[0064] like Figure 4 As shown, Figure 4 Only the routes of the drone nest nodes P1, P2 and P3 are shown in the figure. After the establishment is completed, the oblique photogrammetry route of the drone is generated based on the drone nest nodes P1, P2 and P3. The drone performs oblique photogrammetry on the railway slope to be inspected according to the oblique photogrammetry route to obtain the oblique photogrammetry result. The nest and drone arranged in step S13 are used for track planning to obtain the oblique photogrammetry route, wherein the entire inspection scene is obliquely photogrammed according to the oblique photogrammetry route to construct a refined real-life three-dimensional model of the entire railway slope inspection scene. Most of the existing methods for slope inspection using drones require manual oblique photography along the railway first, and then Then, a real-life 3D model is constructed based on the results of the oblique photography, and trajectory planning and machine nest layout are performed based on the real-life 3D model, thereby completing the automatic inspection of the UAV on the slope. However, manual oblique photography along the railway line involves a large amount of field work and is too costly. In this embodiment, an initial 3D model is first established for the initial layout of the machine nest, so that the UAV can perform oblique photography of the railway line without manual intervention, thereby constructing a real-life 3D model, and then adjusting the machine nest position through the real-life 3D model, thereby realizing automatic inspection of the UAV. The layout of the UAV machine nest and the trajectory planning of the UAV are realized through a two-stage modeling method, which greatly reduces the field workload, reduces the overall workload, and saves costs.

[0065] S2, calculating the inspection work data of the drone based on the real-life three-dimensional model, the inspection work data including the inspection time of the drone on each slope and the inspection time of the drone between two adjacent slopes. In this embodiment, the calculation of the inspection work data of the drone corresponding to the initial three-dimensional model has been described in detail in step S12, and the method for calculating the inspection work data of the drone using the real-life three-dimensional model is the same as step S12;

[0066] S3, based on the inspection work data of the drone, the first endpoint of the railway slope to be inspected is divided, and based on the first endpoint obtained by the division, the drone nest node is constructed and the number of drones is set. In this embodiment, step S13 has preliminarily planned the position of the drone nest node, so after the real-life 3D model is established, it is only necessary to adjust the position of the drone nest node, re-divide the first endpoint based on the real-life 3D model, and adjust the number and position of the drone nest node based on the second endpoint obtained after the re-division, and reset the preset number of drones;

[0067] Specifically, step S3 includes:

[0068] S31, performing trajectory planning based on the refined real-scene 3D model, recalculating the workload corresponding to the flight segment obtained in step S5, and determining whether the recalculated workload exceeds the working capacity of the drone; the change in the length of the route only affects the calculation of the workload, and does not affect the calculation of the working capacity M of the drone;

[0069] S32: If there is a route that exceeds the working capacity of the drone, i.e., an unqualified route, the flight segment needs to be adjusted, i.e., the position of the drone nest node needs to be readjusted;

[0070] Specifically, step S32 includes:

[0071] S321, firstly, the transfer path between the slope nodes or the flight mode of the drone can be adjusted. For example, when the path is automatically generated, in order to simplify the algorithm logic, a rectangle is used as the inspection object, but in practice it is mostly a semi-ellipse. Redundant routes can be adjusted to reduce the workload required for the nodes;

[0072] The automatic transfer between slope nodes is generated in a two-dimensional order. The actual scene is three-dimensional, and there is a large height difference between the slope nodes and the adjacent slope nodes. Since the vertical flight of UAV consumes much more energy than the horizontal flight, changing the order may reduce the overall workload required;

[0073] There are many flight models for drones, and the sensors and algorithms used are different. For example, whether IMU or RTK is used will also affect the flight speed.

[0074] S322, if the adjacent routes have high redundancy, adjust the position of the nest, and redistribute the work content of the unqualified routes and their adjacent routes according to the adjusted position of the nest, so that each route is qualified. For example: if the workload between the nest node A and the nest node B adjacent to the nest node A exceeds the effective working capacity of the UAV, and the workload between the nest node B and the nest node C adjacent to the nest node B is redundant, that is, the workload is more than the effective working capacity. At this time, if the redundant workload is greater than the excess workload, the position of the nest node B can be moved, and the route can be adjusted accordingly, so that the workload between the nest nodes A and B, and the workload between the nest nodes B and C are all lower than the effective working capacity of the UAV.

[0075] S323, if in step S622, the redundant workload is less than the excess workload, then a new machine nest node D is added between the machine nest node A and the machine nest node B, and the positions of the machine nest node B and the machine nest node D are moved, so that the workload between the machine nest nodes is less than the effective working capacity of the drone, and then the route is replanned based on the adjusted machine nest nodes.

[0076] S4, performing inspection route planning based on the drone nest node and the drone to obtain an inspection plan for the railway slope to be inspected;

[0077] Specifically, step S4 includes:

[0078] After the position of the drone nest is adjusted, the drone nest node, slope node and slope-free road section between them are as follows: Figure 5 As shown in the figure, there are m slope nodes and m non-slope sections corresponding to the m slope nodes, w ki is the workload required for the UAV to fly on the i-th slope-free section, w ni is the total workload required for the UAV to fly at the i-th slope node, 1≤i≤m; there are q UAV nest nodes in total, P i is the i-th drone nest node, 1≤i≤q, and one of the first and last nests is an empty nest without a drone;

[0079] Only consider the transfer of drones between nests, such as Figure 6 As shown, Figure 6In the figure, "yes" and "no" respectively indicate that there is a drone in the machine nest or no drone; "no>yes" means that there is no drone in the machine nest at the beginning of this inspection task, and there is a drone after the completion. The drone inspection process is carried out alternately according to the two transfer methods in the figure; the drone inspection task is planned according to the transfer of drones between machine nests. This embodiment adopts alternating operation of multiple machine nests, which avoids the consumption of drones needing to return to the starting point after operation. Compared with the mode in which one machine nest is responsible for an area, it effectively improves the inspection operation capability of drones while reducing the number of machine nests required and reducing cost consumption.

[0080] Embodiment 2:

[0081] like Figure 2 As shown, this embodiment provides a railway slope inspection planning device, which includes a first processing module 901, a second processing module 902, a third processing module 903, a fourth processing module 904 and a fifth processing module 905, wherein specifically:

[0082] The first processing module is used to obtain the oblique photogrammetry results of the railway slope to be inspected by the UAV;

[0083] A second processing module is used to construct a real-scene three-dimensional model of the railway slope to be inspected based on the oblique photogrammetry results;

[0084] A third processing module is used to calculate the inspection work data of the drone based on the real-scene three-dimensional model, wherein the inspection work data includes the inspection time of the drone on each slope and the inspection time of the drone between two adjacent slopes;

[0085] A fourth processing module is used to divide the railway slope to be inspected into first endpoints based on the inspection work data of the drone, and to construct a drone nest node based on the first endpoints obtained by the division and set a preset number of drones;

[0086] The fifth processing module is used to plan the inspection route based on the drone nest node and the drone to obtain the inspection plan for the railway slope to be inspected.

[0087] The first processing module includes a first processing unit 9011, a second processing unit 9012, a third processing unit 9013, a fourth processing unit 9014 and a fifth processing unit 9015:

[0088] A first processing unit is used to obtain first information, wherein the first information includes satellite image data of the railway slope to be inspected, terrain data around the railway, and railway planning vector data;

[0089] A second processing unit is used to construct an initial three-dimensional model based on the first information to obtain an initial three-dimensional model of the railway slope to be inspected;

[0090] A third processing unit is used to calculate the inspection work data corresponding to the initial three-dimensional model based on the initial three-dimensional model of the railway slope to be inspected;

[0091] A fourth processing unit is used to divide the railway slope to be inspected into second endpoints based on the inspection work data corresponding to the initial three-dimensional model, and to construct a drone nest node and set a preset number of drones based on the second endpoints obtained by the division;

[0092] The fifth processing unit is used to perform trajectory planning of the oblique photogrammetry route based on the drone nest nodes and the number of drones, obtain the oblique photogrammetry route, perform oblique photogrammetry on the railway slope to be inspected according to the oblique photogrammetry route, and construct the real-scene three-dimensional model based on the result of the oblique photogrammetry.

[0093] The second processing module includes a sixth processing unit 9021 and a seventh processing unit 9022:

[0094] a sixth processing unit, configured to calculate the inspection time of the drone at each slope based on the maximum flight speed of the drone and second information of the real-scene three-dimensional model, wherein the maximum flight speed of the drone includes the maximum flight speed of the drone in the horizontal direction and the maximum flight speed in the vertical direction, and the second information includes the shape, area, length, width, slope, and cross-section of each slope in the real-scene three-dimensional model;

[0095] The seventh processing unit is used to calculate the inspection time of the UAV between two adjacent slopes based on the maximum flight speed of the UAV in the horizontal direction.

[0096] The fourth processing unit includes a first processing submodule 90141 and a second processing submodule 90142:

[0097] A first processing submodule is used to obtain the inspection work data of the UAV corresponding to the initial three-dimensional model and the maximum single flight time of the UAV;

[0098] The second processing submodule is used to divide the railway slope to be inspected into multiple first sections based on the maximum single flight time of the UAV and the inspection work data of the UAV corresponding to the initial three-dimensional model, and obtain the second endpoint, wherein the first section consists of the slope of the railway slope to be inspected and the slope-free section between the adjacent slopes, the first time corresponding to the first section does not exceed the maximum single flight time of the UAV, the first time is the sum of the inspection time of the slope corresponding to the first section and the inspection time of the UAV between two adjacent slopes, and the endpoint of each first section is the second endpoint.

[0099] The third processing module includes an eighth processing unit 9031 and a ninth processing unit 9032:

[0100] an eighth processing unit, configured to calculate inspection work data corresponding to the real-scene three-dimensional model based on the third information of the real-scene three-dimensional model, and obtain a second time corresponding to the first section, wherein the second time is the sum of the inspection time of the slope corresponding to the first section calculated according to the real-scene three-dimensional model and the inspection time of the drone between two adjacent slopes, wherein the third information includes the shape, area, length, width, slope, cross section of each slope in the real-scene three-dimensional model, and the distance between adjacent slopes;

[0101] The ninth processing unit is used to re-divide the second endpoint based on the second time, wherein, if the second time corresponding to the first paragraph exceeds the maximum single flight time of the drone, the second endpoint is moved or added until the second time corresponding to each of the first paragraphs is lower than the maximum single flight time of the drone, thereby obtaining the first endpoint.

[0102] The second processing unit includes a third processing submodule 90121, a fourth processing submodule 90122, a fifth processing submodule 90123 and a sixth processing submodule 90124:

[0103] A third processing submodule is used to construct a scene three-dimensional model based on the terrain data around the railway, wherein the scene three-dimensional model is a three-dimensional model including two-dimensional plane data and vertical height data of the railway slope to be inspected;

[0104] The fourth processing submodule is used to spatially register the satellite image data of the railway slope to be inspected with the railway planning vector data to obtain the railway area information to be inspected;

[0105] The fifth processing submodule is used to perform target recognition on the railway area information to be inspected based on the YOLOv8-seg model, and perform pixel classification on the railway area information to be inspected after target recognition through the YOLOv8-seg model to obtain the railway slope area information to be inspected;

[0106] The sixth processing submodule is used to superimpose the scene three-dimensional model and the railway slope area information to be inspected to obtain the initial three-dimensional model.

[0107] It should be noted that, regarding the device in the above embodiment, the specific manner in which each module performs the operation has been described in detail in the embodiment of the method, and will not be elaborated here.

[0108] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

[0109] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. A railway slope inspection planning method, characterized in that: include: Obtaining oblique photogrammetry results of the railway slope to be inspected by the drone, and constructing a real-scene three-dimensional model of the railway slope to be inspected based on the oblique photogrammetry results; Calculating the inspection work data of the drone based on the real-scene three-dimensional model, wherein the inspection work data includes the inspection time of the drone on each slope and the inspection time of the drone between two adjacent slopes; Based on the inspection work data of the drone, the first endpoint of the railway slope to be inspected is divided, and based on the first endpoint obtained by the division, the drone nest node is constructed and the number of drones is set; Inspection routes are planned based on the drone nest nodes and the number of drones to obtain an inspection plan for the railway slope to be inspected.

2. A railway slope inspection planning method according to claim 1, characterized in that The method of constructing a real-life three-dimensional model of the railway slope to be inspected based on the oblique photogrammetry results includes: Acquire first information, wherein the first information includes satellite image data of the railway slope to be inspected, terrain data around the railway, and railway planning vector data; constructing an initial three-dimensional model based on the first information to obtain an initial three-dimensional model of the railway slope to be inspected; Calculating inspection work data corresponding to the initial three-dimensional model based on the initial three-dimensional model of the railway slope to be inspected; Based on the inspection work data of the drone corresponding to the initial three-dimensional model, the railway slope to be inspected is divided into second endpoints, and based on the second endpoints obtained by the division, drone nest nodes are constructed and the number of drones is set; The track planning of the oblique photogrammetry route is performed based on the drone nest nodes and the number of drones to obtain the oblique photogrammetry route, and the oblique photogrammetry is performed on the railway slope to be inspected according to the oblique photogrammetry route, and the real-scene three-dimensional model is constructed based on the oblique photogrammetry result.

3. A railway slope inspection planning method according to claim 1, characterized in that ,The calculation of the inspection work data of the drone based on the real-scene three-dimensional model includes: Calculate the inspection time of the drone on each slope based on the maximum flight speed of the drone and the second information of the real-scene three-dimensional model, wherein the maximum flight speed of the drone includes the maximum flight speed of the drone in the horizontal direction and the maximum flight speed in the vertical direction, and the second information includes the shape, area, length, width, slope and cross-section of each slope in the real-scene three-dimensional model; The inspection time of the UAV between two adjacent slopes is calculated based on the maximum flight speed of the UAV in the horizontal direction.

4. A railway slope inspection planning method according to claim 2, characterized in that The second endpoint division of the railway slope to be inspected based on the inspection work data of the drone corresponding to the initial three-dimensional model includes: Obtaining inspection work data of the UAV corresponding to the initial three-dimensional model and the maximum single flight time of the UAV; Based on the maximum single flight time of the UAV and the inspection work data of the UAV corresponding to the initial three-dimensional model, the railway slope to be inspected is divided into multiple first sections to obtain the second endpoint, wherein the first section consists of the slope of the railway slope to be inspected and the slope-free section between the adjacent slopes, the first time corresponding to the first section does not exceed the maximum single flight time of the UAV, the first time is the sum of the inspection time of the slope corresponding to the first section and the inspection time of the UAV between two adjacent slopes, and the endpoint of each first section is the second endpoint.

5. A railway slope inspection planning method according to claim 4, characterized in that The inspection work data based on the UAV performs the first endpoint division on the railway slope to be inspected, including: Calculate the inspection work data corresponding to the real-scene three-dimensional model based on the third information of the real-scene three-dimensional model to obtain the second time corresponding to the first section, where the second time is the sum of the inspection time of the slope corresponding to the first section calculated according to the real-scene three-dimensional model and the inspection time of the drone between two adjacent slopes, and the third information includes the shape, area, length, width, slope, cross-section of each slope in the real-scene three-dimensional model and the distance between adjacent slopes; The second endpoint is re-divided based on the second time, wherein, if the second time corresponding to the first paragraph exceeds the maximum single flight time of the drone, the second endpoint is moved or added until the second time corresponding to each first paragraph is lower than the maximum single flight time of the drone, thereby obtaining the first endpoint.

6. A railway slope inspection planning device, characterized in that: include: The first processing module is used to obtain the oblique photogrammetry results of the railway slope to be inspected by the UAV; A second processing module is used to construct a real-scene three-dimensional model of the railway slope to be inspected based on the oblique photogrammetry results; A third processing module is used to calculate the inspection work data of the drone based on the real-scene three-dimensional model, wherein the inspection work data includes the inspection time of the drone on each slope and the inspection time of the drone between two adjacent slopes; The fourth processing module is used to divide the railway slope to be inspected into first endpoints based on the inspection work data of the drone, and to construct drone nest nodes and set the number of drones based on the first endpoints obtained by the division; The fifth processing module is used to plan the inspection route based on the drone nest node and the number of drones to obtain the inspection plan for the railway slope to be inspected.

7. A railway slope inspection planning device according to claim 6, characterized in that: The first processing module comprises: A first processing unit is used to obtain first information, wherein the first information includes satellite image data of the railway slope to be inspected, terrain data around the railway, and railway planning vector data; A second processing unit is used to construct an initial three-dimensional model based on the first information to obtain an initial three-dimensional model of the railway slope to be inspected; A third processing unit is used to calculate the inspection work data corresponding to the initial three-dimensional model based on the initial three-dimensional model of the railway slope to be inspected; A fourth processing unit is used to divide the railway slope to be inspected into second endpoints based on the inspection work data corresponding to the initial three-dimensional model, and to construct a drone nest node and set the number of drones based on the second endpoints obtained by the division; The fifth processing unit is used to perform trajectory planning of the oblique photogrammetry route based on the drone nest nodes and the number of drones, obtain the oblique photogrammetry route, perform oblique photogrammetry on the railway slope to be inspected according to the oblique photogrammetry route, and construct the real-scene three-dimensional model based on the result of the oblique photogrammetry.

8. A railway slope inspection planning device according to claim 6, characterized in that: The second processing module comprises: a sixth processing unit, configured to calculate the inspection time of the drone at each slope based on the maximum flight speed of the drone and second information of the real-scene three-dimensional model, wherein the maximum flight speed of the drone includes the maximum flight speed of the drone in the horizontal direction and the maximum flight speed in the vertical direction, and the second information includes the shape, area, length, width, slope, and cross-section of each slope in the real-scene three-dimensional model; The seventh processing unit is used to calculate the inspection time of the UAV between two adjacent slopes based on the maximum flight speed of the UAV in the horizontal direction.

9. A railway slope inspection planning device according to claim 7, characterized in that: The fourth processing unit comprises: A first processing submodule is used to obtain the inspection work data of the UAV corresponding to the initial three-dimensional model and the maximum single flight time of the UAV; The second processing submodule is used to divide the railway slope to be inspected into multiple first sections based on the maximum single flight time of the UAV and the inspection work data of the UAV corresponding to the initial three-dimensional model, and obtain the second endpoint, wherein the first section consists of the slope of the railway slope to be inspected and the slope-free section between the adjacent slopes, the first time corresponding to the first section does not exceed the maximum single flight time of the UAV, the first time is the sum of the inspection time of the slope corresponding to the first section and the inspection time of the UAV between two adjacent slopes, and the endpoint of each first section is the second endpoint.

10. A railway slope inspection planning device according to claim 9, characterized in that: The third processing module comprises: an eighth processing unit, configured to calculate inspection work data corresponding to the real-scene three-dimensional model based on the third information of the real-scene three-dimensional model, and obtain a second time corresponding to the first section, wherein the second time is the sum of the inspection time of the slope corresponding to the first section calculated according to the real-scene three-dimensional model and the inspection time of the drone between two adjacent slopes, wherein the third information includes the shape, area, length, width, slope, cross section of each slope in the real-scene three-dimensional model, and the distance between adjacent slopes; The ninth processing unit is used to re-divide the second endpoint based on the second time, wherein, if the second time corresponding to the first paragraph exceeds the maximum single flight time of the drone, the second endpoint is moved or added until the second time corresponding to each of the first paragraphs is lower than the maximum single flight time of the drone, thereby obtaining the first endpoint.

Images