Inspection route planning method and device, electronic equipment and storage medium

Abstract

The application provides a method and device for planning an inspection route, electronic equipment and a storage medium. The method comprises the following steps: obtaining a digital orthographic image and a digital elevation model of a target photovoltaic power station area; generating a three-dimensional topographic map of the target photovoltaic power station area according to the digital orthographic image and the digital elevation model; determining a string center position and a string orientation of the photovoltaic string in the three-dimensional topographic map; and planning an inspection route of a camera of a flying machine for the photovoltaic string according to camera parameters of the flying machine and the string center position and the string orientation of the photovoltaic string. The three-dimensional topographic map can be used to more accurately determine the string center position and the string orientation, and then, according to the camera parameters of the flying machine and the string center position and the string orientation of the photovoltaic string, a more accurate inspection route planning result can be obtained, thereby improving the accuracy of the inspection route planning.

Description

Technical Field

[0001] This application relates to the field of photovoltaic drone inspection technology, and more specifically, to an inspection route planning method, device, electronic equipment, and storage medium. Background Technology

[0002] Photovoltaic power plants cover a wide area with diverse terrain. Manual inspections are time-consuming and prone to omissions. In contrast, drone aerial surveying offers advantages such as mobility, efficiency, speed, precision, low operating costs, wide applicability, and short production cycles. Drone aerial surveying is commonly used for inspecting photovoltaic power plants.

[0003] Before using drones to perform aerial surveying tasks, it is necessary to analyze the target area and plan the drone's flight path according to the surveying requirements. Existing inspection flight path planning methods are mainly designed for photovoltaic power plants with relatively flat terrain and neatly arranged photovoltaic strings, which cannot meet the diverse terrain requirements for inspecting photovoltaic power plants and have low accuracy. Summary of the Invention

[0004] In view of this, the purpose of this application is to provide a method, apparatus, electronic device and storage medium for inspection route planning, so as to solve the technical problem of how to improve the accuracy of inspection route planning.

[0005] In a first aspect, embodiments of this application provide an inspection route planning method, which includes:

[0006] Obtain digital orthophoto maps and digital elevation models of the target photovoltaic power station area; wherein, the target photovoltaic power station area includes multiple photovoltaic strings;

[0007] Based on the digital orthophoto map and digital elevation model, a three-dimensional topographic map of the target photovoltaic power station area is generated;

[0008] Determine the center position and orientation of the photovoltaic strings in the three-dimensional topographic map;

[0009] Based on the camera parameters of the drone, as well as the center position and orientation of the photovoltaic string, the drone's inspection route for the photovoltaic string is planned.

[0010] In the above implementation process, a three-dimensional topographic map of the target photovoltaic power station area is generated based on the digital orthophoto map (DOM) and digital elevation model (DEM). Based on the three-dimensional topographic map, the center position and orientation of the photovoltaic strings can be determined more accurately. Then, based on the camera parameters of the drone and the center position and orientation of the photovoltaic strings, a more accurate inspection route planning result can be obtained.

[0011] Optionally, in this embodiment of the application, the step of planning the inspection route of the aerial photography drone for the photovoltaic string based on the camera parameters of the aerial photography drone and the center position and orientation of the photovoltaic string includes: calculating the photo waypoint corresponding to the center position of the string based on the camera parameters of the aerial photography drone and the center position and orientation of the photovoltaic string; and planning the inspection route of the aerial photography drone for the photovoltaic string based on the photo waypoint.

[0012] In the above implementation process, based on the center position and orientation of the cluster determined by the 3D topographic map and the camera parameters of the drone, the photo waypoints corresponding to the center position of the cluster can be calculated more accurately, and the inspection route can be planned based on the photo waypoints, thus improving the accuracy of the inspection route planning.

[0013] Optionally, in this embodiment, the waypoint for taking pictures includes the shooting position, the yaw angle and pitch angle of the drone at the shooting position; the camera parameters include the camera focal length, the sensor size, and the image resolution. The step of calculating the waypoint corresponding to the photovoltaic string based on the drone's camera parameters, the string center position, and the string orientation includes: determining the drone's yaw angle and pitch angle for the waypoint corresponding to the photovoltaic string based on the string orientation; and calculating the shooting position of the waypoint corresponding to the photovoltaic string based on the drone's yaw angle, pitch angle, camera focal length, sensor size, image resolution, and string center position.

[0014] In the above implementation process, based on the string orientation determined by the 3D topographic map, the yaw angle and pitch angle of the drone corresponding to the photography waypoint of the photovoltaic string can be accurately determined; then, based on the drone's yaw angle, pitch angle, camera focal length, sensor size, image resolution, and string center position, the photography position of the photography waypoint corresponding to the photovoltaic string can be accurately calculated; based on the photography position and the drone's yaw angle and pitch angle at that photography position, the photography waypoint corresponding to the string center position can be accurately obtained.

[0015] Optionally, in this embodiment of the application, the step of calculating the photographing position of the photographing waypoint corresponding to the photovoltaic string based on the drone's yaw angle, drone's pitch angle, camera focal length, sensor size, image resolution, and string center position includes: based on Calculate the photographing distance D between the photographing position and the center position of the photovoltaic string; calculate the photographing height H corresponding to the photographing position of the photovoltaic string according to H=H0+D*cosβ; according to Calculate the image plane position P corresponding to the image capture location of the photovoltaic string; where, The shooting position is determined based on the shooting height and the shooting plane position. Where f represents the camera focal length, and S... X R represents the width of the image sensor, R0 represents the number of pixels per unit distance, R X The width represents the image resolution, β is equal to the shooting pitch angle, H0 represents the height of the cluster center position, and P0 represents the planar position of the cluster center position. The unit vector representing the position and direction of the image plane. Let α represent the unit vector in the due south direction in the plane. and The angle between the planes, where the plane angle α is positive counterclockwise and its value is equal to the photographing yaw angle.

[0016] In the above implementation process, by calculating the shooting height of the photovoltaic string corresponding to the shooting position and the shooting plane position of the photovoltaic string corresponding to the shooting position, the accurate shooting position point corresponding to the photovoltaic string can be obtained based on the shooting plane position in the "plane corresponding to the shooting height".

[0017] Optionally, in this embodiment of the application, before calculating the photographing waypoint corresponding to the photovoltaic string based on the camera parameters of the drone and the center position and orientation of the photovoltaic string, the method further includes: determining the size of the mapping photosensitive element based on the image resolution; wherein the aspect ratio of the mapping photosensitive element size is consistent with the aspect ratio of the image resolution; the step of calculating the photographing position of the photographing waypoint corresponding to the photovoltaic string based on the drone's yaw angle, drone's pitch angle, camera focal length, photosensitive element size, image resolution, and string center position specifically includes: calculating the photographing position of the photographing waypoint corresponding to the photovoltaic string based on the drone's yaw angle, drone's pitch angle, camera focal length, mapping photosensitive element size, image resolution, and string center position.

[0018] In the above implementation process, in the step of "calculating the shooting position of the shooting point corresponding to the photovoltaic string", it is necessary to "map the imaging position of the string center position in the photosensitive element according to the pixel position of the string center position in the aerial image" in proportion; the size of the mapped photosensitive element is determined by the image resolution in proportion to the image resolution, and the shooting position can be calculated more accurately based on the size of the mapped photosensitive element.

[0019] Optionally, in this embodiment of the application, after planning the inspection route of the drone for the photovoltaic strings based on the camera parameters of the drone and the center position and orientation of the photovoltaic strings, the method further includes: inspecting the photovoltaic strings in the target photovoltaic power station area according to the inspection route to obtain inspection images of the photovoltaic strings; identifying faults in the inspection images to determine faulty inspection images and fault locations in the faulty inspection images; wherein, the faulty inspection images include inspection images with string faults.

[0020] In the aforementioned implementation process, the 3D topographic map allows for a more accurate determination of the photovoltaic string center position and orientation. Furthermore, based on the drone's camera parameters and the center position and orientation of the photovoltaic strings, a more accurate inspection route can be obtained. Inspecting the photovoltaic strings within the target photovoltaic power station area using this route yields higher-precision inspection images, thereby improving the accuracy of fault identification results and obtaining more precise fault locations. Reporting faults based on their locations in the inspection images assists maintenance personnel in fault repair, improving repair efficiency.

[0021] Optionally, in this embodiment of the application, after determining the fault inspection image and the fault location in the inspection image, the method further includes: calculating the three-dimensional fault coordinates of the fault location in the three-dimensional terrain map based on the fault location, the waypoint for obtaining the fault inspection image, and the sensor size and image resolution of the drone; and marking the fault in the three-dimensional terrain map based on the three-dimensional fault coordinates.

[0022] In the above implementation process, by taking the waypoints of the fault inspection images and using the size of the drone's photosensitive element and image resolution, the three-dimensional fault coordinates on the three-dimensional terrain map are calculated. Based on the three-dimensional fault coordinates, maintenance personnel can more intuitively determine the actual fault location, which can better assist maintenance personnel in fault repair and improve fault repair efficiency.

[0023] Optionally, in this embodiment of the application, after calculating the three-dimensional fault coordinates of the fault location in the three-dimensional topographic map, the method further includes: calculating the actual fault geographic coordinates corresponding to the fault location based on the three-dimensional fault coordinates; and reporting the fault based on the three-dimensional topographic map after fault marking and the actual fault geographic coordinates.

[0024] In the above implementation process, the actual geographical coordinates of the fault location are calculated based on the three-dimensional fault coordinates. Maintenance personnel can directly repair the corresponding fault based on the actual geographical coordinates of the fault, which further improves the efficiency of fault repair.

[0025] Secondly, embodiments of this application also provide an inspection route planning device, which includes:

[0026] The data acquisition module is used to acquire digital orthophoto maps and digital elevation models of the target photovoltaic power station area; wherein, the target photovoltaic power station area includes multiple photovoltaic strings;

[0027] A three-dimensional topographic map generation module is used to generate a three-dimensional topographic map of the target photovoltaic power station area based on the digital orthophoto map and the digital elevation model.

[0028] The string determination module is used to determine the string center position and string orientation of the photovoltaic strings in the three-dimensional terrain map;

[0029] The route planning module is used to plan the inspection route of the drone for the photovoltaic string based on the camera parameters of the drone, the center position of the photovoltaic string, and the orientation of the string.

[0030] Thirdly, embodiments of this application also provide an electronic device, including: a memory and a processor, wherein the memory stores a computer program executable by the processor, and when the computer program is executed by the processor, it performs the inspection route planning method as described in the first aspect above.

[0031] Fourthly, embodiments of this application also provide a computer-readable storage medium storing computer program instructions, which, when executed by a processor, perform the inspection route planning method as described in the first aspect above.

[0032] This application provides a method, apparatus, electronic device, and storage medium for planning inspection routes. It acquires digital orthophoto maps and digital elevation models (DEMs) of a target photovoltaic (PV) power station area; generates a three-dimensional topographic map of the area based on these maps; determines the center position and orientation of the PV strings within the target PV power station area; and plans an inspection route for the PV strings based on the camera parameters of a drone and the aforementioned center positions and orientations. The three-dimensional topographic map allows for more accurate determination of the string center positions and orientations, leading to more accurate inspection route planning results and improving the accuracy of the inspection route planning. Attached Figure Description

[0033] To more clearly illustrate the technical solutions of the embodiments of this application, the accompanying drawings used in the embodiments of this application will be briefly introduced below. It should be understood that the following drawings only show some embodiments of this application and should not be regarded as a limitation of the scope. For those skilled in the art, other related drawings can be obtained based on these drawings without creative effort.

[0034] Figure 1 A flowchart illustrating an inspection route planning method provided in this application embodiment;

[0035] Figure 2 A flowchart illustrating a photovoltaic string inspection route planning method is provided for an embodiment of this application.

[0036] Figure 3 A schematic diagram of the vertical position of a drone taking photos, provided in an embodiment of this application;

[0037] Figure 4 This application provides a schematic diagram of the horizontal position of a drone taking photos, as shown in the embodiments of the present application.

[0038] Figure 5 A flowchart illustrating another inspection route planning method provided in this application embodiment;

[0039] Figure 6 A schematic diagram of fault location in a three-dimensional topographic map provided in an embodiment of this application;

[0040] Figure 7 A schematic diagram of the structure of an inspection route planning device provided in this application embodiment;

[0041] Figure 8 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. Detailed Implementation

[0042] The embodiments of the technical solution of this application will now be described in detail with reference to the accompanying drawings. These embodiments are only used to more clearly illustrate the technical solution of this application and are therefore merely examples, and should not be used to limit the scope of protection of this application.

[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to limit this application.

[0044] In the description of the embodiments of this application, technical terms such as "first" and "second" are used only to distinguish different objects and should not be construed as indicating or implying relative importance or implicitly specifying the number, specific order, or primary and secondary relationship of the indicated technical features. In the description of the embodiments of this application, "multiple" means two or more, unless otherwise explicitly defined.

[0045] Please see Figure 1 The illustrated diagram shows a flowchart of an inspection route planning method provided in an embodiment of this application. The inspection route planning method may include the following steps:

[0046] Step 101: Obtain a digital orthophoto map and a digital elevation model of the target photovoltaic power station area; wherein, the target photovoltaic power station area includes multiple photovoltaic strings;

[0047] Step 102: Generate a three-dimensional topographic map of the target photovoltaic power station area based on the digital orthophoto map and digital elevation model;

[0048] Step 103: Determine the center position and orientation of the photovoltaic strings in the three-dimensional topographic map;

[0049] Step 104: Based on the camera parameters of the drone and the center position and orientation of the photovoltaic string, plan the inspection route of the drone for the photovoltaic string.

[0050] In step 101, the Digital Orthophoto Map (DOM) is a set of digital orthophotos generated by digitally differentiating and mosaicking aerial and space photographs, and cropping them according to a certain map area. It is an image that simultaneously possesses map geometric accuracy and image features. A pre-made digital orthophoto map of the target photovoltaic power station area can be directly acquired, or the DOM can be created using a fully digital photogrammetry method, single-image digital differential correction, or orthophoto scanning.

[0051] Among them, the Digital Elevation Model (DEM) is a digital simulation of the ground terrain (i.e., a digital representation of the terrain surface morphology) achieved through limited terrain elevation data. It is a physical ground model that represents the ground elevation in the form of an ordered numerical array. A pre-built DEM model of the target photovoltaic power station area can be directly obtained, or the data source for building the DEM model of the target photovoltaic power station area can be obtained through methods such as photogrammetry, ground surveying, digitization of existing topographic maps, or extraction from existing DEM libraries. Then, the DEM model of the target photovoltaic power station area can be built based on the obtained data source.

[0052] In step 102, development tools such as Unity3D or Unreal Engine (e.g., Unreal Engine 4) can be used to generate a 3D topographic map of the target photovoltaic power station area based on the aforementioned digital orthophoto map and digital elevation model. Specifically, the geographic coordinates corresponding to the color data contained in the aforementioned digital orthophoto map and the geographic coordinates corresponding to the ground elevation data contained in the aforementioned digital elevation model can be converted into 3D spatial coordinates in the development tools such as Unity3D or Unreal Engine. Based on the 3D spatial coordinates corresponding to each color data contained in the aforementioned digital orthophoto map and the 3D spatial coordinates corresponding to each ground elevation data contained in the aforementioned digital elevation model, a 3D topographic map of the target photovoltaic power station area can be generated in the development tools such as Unity3D or Unreal Engine. Alternatively, multiple first reference points are identified in the digital elevation model, and their geographic coordinates are obtained. These geographic coordinates are then converted into first three-dimensional spatial coordinates in development tools such as Unity3D or Unreal Engine. Multiple second reference points are identified in the digital orthophoto map, and their geographic coordinates are obtained. These geographic coordinates are then converted into second three-dimensional spatial coordinates in development tools such as Unity3D or Unreal Engine. Based on the first three-dimensional spatial coordinates, the digital elevation data contained in the digital elevation model is converted into development tools such as Unity3D or Unreal Engine. Similarly, based on the second three-dimensional spatial coordinates, the color data contained in the digital orthophoto map is converted into development tools such as Unity3D or Unreal Engine. This allows for the fusion of the digital elevation model and the digital orthophoto map within Unity3D or Unreal Engine, generating a three-dimensional topographic map of the target photovoltaic power station area.

[0053] In step 103, the 3D coordinates of the center point and edge points of each photovoltaic string can be determined by identifying the 3D topographic map. The string center position is determined based on the center point coordinates, and the string orientation is determined based on the edge point coordinates. Alternatively, manual annotation can be used to annotate the existing 3D topographic model training map. The photovoltaic string recognition model to be trained is then trained based on the manually annotated string center positions and orientations. The model parameters of the photovoltaic string recognition model to be trained are adjusted based on the recognition results of the 3D topographic model training map to obtain a "trained photovoltaic string recognition model" that meets the preset recognition accuracy. The "trained photovoltaic string recognition model" is then used to identify the "3D topographic map of the target photovoltaic power station area" to obtain the string center positions and orientations of the photovoltaic strings in the aforementioned 3D topographic map.

[0054] In step 104, the aerial photography drone refers to a machine used to inspect the photovoltaic strings in the target photovoltaic power station area according to a planned inspection route, such as an aerial photography drone. Based on the camera parameters of the aerial photography drone and the center position of the photovoltaic strings, the shooting point where the center of the strings is located in the center of the shooting frame can be determined. According to the orientation of the strings, the shooting point parallel to the surface of the photovoltaic string panels can be determined, thus obtaining a more accurate and clear shooting image and improving the accuracy of the inspection route planning.

[0055] Therefore, the inspection route planning method provided in this application generates a three-dimensional topographic map of the target photovoltaic power station area through digital orthophoto maps and digital elevation models. Based on the three-dimensional topographic map, the center position and orientation of the photovoltaic strings can be determined more accurately. Then, based on the camera parameters of the drone and the center position and orientation of the photovoltaic strings, a more accurate inspection route planning result can be obtained, thus improving the accuracy of the inspection route planning.

[0056] Please refer to Figure 2 , Figure 2 This is a flowchart illustrating a photovoltaic string inspection route planning method provided in an embodiment of this application.

[0057] In some optional embodiments, step 104, planning the inspection route of the photovoltaic string by the drone based on the camera parameters of the drone and the center position and orientation of the photovoltaic string, may include: step 1041, calculating the photo waypoint corresponding to the center position of the photovoltaic string based on the camera parameters of the drone and the center position and orientation of the photovoltaic string; step 1042, planning the inspection route of the drone for the photovoltaic string based on the photo waypoint.

[0058] Based on the camera parameters of the drone and the center position of the photovoltaic (PV) string, a waypoint can be determined where the string center is located in the center of the captured image. According to the string orientation, a waypoint parallel to the PV string's panel surface can be determined. The planned inspection route for the PV string can include some or all of the calculated waypoints. Specifically, if each waypoint only captures one PV string, the planned inspection route must include all calculated waypoints; if each waypoint corresponds to multiple PV strings, the planned inspection route can include only some or all of the calculated waypoints.

[0059] The process involves generating a planned route based on photo waypoints and pre-defined route planning rules. These rules include the number of photovoltaic (PV) strings corresponding to each photo waypoint, the horizontal spacing between PV strings, and the vertical spacing between PV strings. Maintenance personnel can also adjust the photo waypoint selection rules according to actual needs. For example, when inspecting the first horizontal or vertical row of PV strings separately, the inspection route can be planned solely based on the photo waypoints corresponding to those strings; alternatively, for a target inspection area, at least three points can be selected around the target inspection area to form a convex polygon, and a planned route for the target inspection area can be generated according to the pre-defined route planning rules.

[0060] In some optional embodiments, the aforementioned waypoints include the shooting location, the drone's yaw angle and pitch angle at the shooting location; the aforementioned camera parameters include the camera focal length, sensor size, and image resolution; step 1042, calculating the waypoints corresponding to the photovoltaic string based on the drone's camera parameters and the string center position and string orientation, may include: step 10421, determining the drone's yaw angle and pitch angle of the waypoints corresponding to the photovoltaic string based on the string orientation; step 10422, calculating the shooting location of the waypoints corresponding to the photovoltaic string based on the drone's yaw angle, pitch angle, camera focal length, sensor size, image resolution, and string center position.

[0061] Specifically, the yaw and pitch angles of the drone are determined based on the orientation of the photovoltaic string, ensuring the captured image is parallel to the surface of the photovoltaic string panel. In other words, the drone's frustum axis is perpendicular to the photovoltaic string panel surface. The drone's camera parameters refer to the parameters of the camera within the drone, and the drone's frustum axis refers to the axis of the camera's frustum within the drone.

[0062] In some optional embodiments, before step 1042, calculating the photo waypoint corresponding to the photovoltaic string based on the camera parameters of the drone and the center position and orientation of the photovoltaic string, the inspection route planning method may further include: determining the size of the mapping photosensitive element based on the image resolution; wherein the aspect ratio of the mapping photosensitive element size is consistent with the aspect ratio of the image resolution; step 10422, calculating the photo position of the photo waypoint corresponding to the photovoltaic string based on the drone's yaw angle, drone's pitch angle, camera focal length, photosensitive element size, image resolution, and string center position, may specifically include: calculating the photo position of the photo waypoint corresponding to the photovoltaic string based on the drone's yaw angle, drone's pitch angle, camera focal length, mapping photosensitive element size, image resolution, and string center position.

[0063] If the aspect ratio of the photosensitive element is smaller than the aspect ratio of the image resolution, it can be based on Calculate the height of the image sensor. R X R represents the width of the image resolution. y S indicates the high resolution of the image. X S represents the width of the photosensitive element. y This indicates the height of the image sensor. If the aspect ratio of the image sensor is greater than the aspect ratio of the image resolution, it can be based on... Calculate the width of the photosensitive element.

[0064] Please refer to Figure 3 , Figure 3 This is a schematic diagram illustrating the vertical position of a drone taking photos, as provided in an embodiment of this application. Please refer to... Figure 4 , Figure 4 This is a schematic diagram of the horizontal position of a drone taking pictures, provided as an embodiment of this application.

[0065] In some optional embodiments, step 10422 above, calculating the photographing position of the photographing waypoint corresponding to the photovoltaic string based on the drone's yaw angle, drone pitch angle, camera focal length, sensor size, image resolution, and string center position, may include: based on Calculate the photographing distance D between the photographing position and the center position of the photovoltaic string; calculate the photographing height H corresponding to the photographing position of the photovoltaic string according to H=H0+D*cosβ; according to Calculate the image plane position P corresponding to the image capture location of the photovoltaic string; where, The shooting position is determined based on the shooting height and the shooting plane position. Where f represents the camera focal length, and S... X R represents the width of the image sensor, R0 represents the number of pixels per unit distance, R XThe width represents the image resolution, β is equal to the shooting pitch angle, H0 represents the height of the cluster center position, and P0 represents the planar position of the cluster center position. The unit vector representing the position and direction of the image plane. Let α represent the unit vector in the due south direction in the plane. and The angle between the planes, where the plane angle α is positive counterclockwise and its value is equal to the photographing yaw angle.

[0066] Please refer to Figure 5 , Figure 5 This is a flowchart illustrating another inspection route planning method provided in an embodiment of this application.

[0067] In some optional embodiments, after step 104, where the drone plans an inspection route for the photovoltaic string based on the camera parameters of the drone and the center position and orientation of the photovoltaic string, the inspection route planning method may further include:

[0068] Step 105: Inspect the photovoltaic strings in the target photovoltaic power station area according to the inspection route to obtain the inspection images of the photovoltaic strings;

[0069] Step 106: Perform fault identification on the inspection images to determine the faulty inspection images and the fault locations in the faulty inspection images; wherein, the faulty inspection images include inspection images with string faults.

[0070] The inspection images can include thermal infrared images and visible light images of the photovoltaic (PV) strings. Fault identification can be performed on these images based on the daily inspection and maintenance requirements of the PV power plant. Specifically, the images can identify faults such as whether there is damage to the PV string panel surface, whether there are obstructions on the PV string panel surface, the cleanliness of the PV string panel surface, and whether the PV string panel temperature is normal.

[0071] In some optional embodiments, after determining the fault inspection image and the fault location in the fault inspection image as described above, the inspection route planning method may further include: step 107, calculating the three-dimensional fault coordinates of the fault location in the three-dimensional topographic map based on the fault location, the waypoints of the fault inspection image, and the sensor size and image resolution of the drone; step 108, marking the fault in the three-dimensional topographic map based on the three-dimensional fault coordinates.

[0072] Please refer to Figure 6 , Figure 6This is a schematic diagram of fault location in a three-dimensional topographic map provided in an embodiment of this application.

[0073] If we take the lower left corner of the photosensitive element as the origin of the coordinate system, we can... The photosensitive fault location Y(x0, y0) within the photosensitive element is calculated; where S(x, y) is the photosensitive element size, R(x, y) is the image resolution, and R(x0, y0) are the coordinates of the fault location in the fault inspection image. If the center point of the photosensitive element is taken as the origin, then according to... The photosensitive fault location S(x0, y0) in the photosensitive element is calculated.

[0074] The waypoints for capturing fault inspection images include the drone's yaw and pitch angles. The direction of the view frustum axis when capturing the fault inspection image is determined based on these angles. Calculate the angle θ between the connection between the fault location and its photographic waypoint, relative to the direction of the view frustum axis. This is the location of the photosensitive fault calculated with the center point of the photosensitive element as the origin of the coordinate system. It is determined based on the included angle θ and the location of the fault within the photosensitive element. Determine the three-dimensional coordinates of the fault location on the three-dimensional topographic map.

[0075] In some optional embodiments, after calculating the three-dimensional fault coordinates of the fault location in the three-dimensional topographic map, the inspection route planning method may further include: calculating the actual fault geographic coordinates corresponding to the fault location based on the three-dimensional fault coordinates; and reporting the fault based on the three-dimensional topographic map after fault marking and the actual fault geographic coordinates.

[0076] Specifically, the actual fault geographic coordinates can be determined based on the correspondence between the 3D coordinates in the 3D topographic map and the actual geographic coordinates. The actual fault geographic coordinates include the latitude and longitude coordinates of the fault location.

[0077] Please refer to Figure 7 , Figure 7 A schematic diagram of an inspection route planning device is provided. The inspection route planning device includes:

[0078] The data acquisition module 201 is used to acquire digital orthophoto maps and digital elevation models of the target photovoltaic power station area; wherein, the target photovoltaic power station area includes multiple photovoltaic strings;

[0079] The three-dimensional topographic map generation module 202 is used to generate a three-dimensional topographic map of the target photovoltaic power station area based on the digital orthophoto map and the digital elevation model.

[0080] The string determination module 203 is used to determine the string center position and string orientation of the photovoltaic string in the three-dimensional terrain map;

[0081] The route planning module 204 is used to plan the inspection route of the drone for the photovoltaic string based on the camera parameters of the drone and the center position and orientation of the photovoltaic string.

[0082] In some optional embodiments, the route planning module 204 may include: a photo waypoint calculation module, used to calculate the photo waypoint corresponding to the center position of the photovoltaic string based on the camera parameters of the drone and the center position and orientation of the photovoltaic string; and a waypoint planning route module, used to plan the inspection route of the drone for the photovoltaic string based on the photo waypoint.

[0083] In some optional embodiments, the aforementioned waypoints may include the shooting location, the drone's yaw angle and pitch angle at the shooting location; the aforementioned camera parameters may include the camera focal length, sensor size, and image resolution. The aforementioned waypoint calculation module may include: an angle determination module, used to determine the drone's yaw angle and pitch angle for the waypoints corresponding to the photovoltaic strings based on the string orientation; and a position determination module, used to calculate the shooting location of the waypoints corresponding to the photovoltaic strings based on the drone's yaw angle, pitch angle, camera focal length, sensor size, image resolution, and string center position.

[0084] In some optional embodiments, the inspection route planning device may further include: a mapping size determination module, used to determine the size of the mapping photosensitive element based on the image resolution; wherein the aspect ratio of the mapping photosensitive element size is consistent with the aspect ratio of the image resolution; the aforementioned position determination module may specifically be used to: calculate the photographing position of the photographing waypoint corresponding to the photovoltaic string based on the drone's yaw angle, drone's pitch angle, camera focal length, mapping photosensitive element size, image resolution, and string center position.

[0085] In some optional embodiments, the above-mentioned position determination module can be specifically used to: based on Calculate the photographing distance D between the photographing position and the center position of the photovoltaic string; calculate the photographing height H corresponding to the photographing position of the photovoltaic string according to H=H0+D*cosβ; according to Calculate the image plane position P corresponding to the image capture location of the photovoltaic string; where, The shooting position is determined based on the shooting height and the shooting plane position. Where f represents the camera focal length, and S... XR represents the width of the image sensor, R0 represents the number of pixels per unit distance, R X The width represents the image resolution, β is equal to the shooting pitch angle, H0 represents the height of the cluster center position, and P0 represents the planar position of the cluster center position. The unit vector representing the position and direction of the image plane. Let α represent the unit vector in the due south direction in the plane. and The angle between the planes, where the plane angle α is positive counterclockwise and its value is equal to the photographing yaw angle.

[0086] In some optional embodiments, the inspection route planning device may further include: an inspection image acquisition module, used to inspect the photovoltaic strings in the target photovoltaic power station area according to the inspection route, and obtain inspection images of the photovoltaic strings; and a fault identification module, used to identify faults in the inspection images, determine faulty inspection images in the inspection images and the fault locations in the faulty inspection images; wherein, the faulty inspection images include inspection images with string faults.

[0087] In some optional embodiments, the inspection route planning device may further include: a three-dimensional fault coordinate calculation module, used to calculate the three-dimensional fault coordinates of the fault location on the three-dimensional topographic map based on the fault location, the waypoints for acquiring the fault inspection image, and the size and image resolution of the photosensitive element of the drone; and a fault marking module, used to mark the fault on the three-dimensional topographic map based on the three-dimensional fault coordinates.

[0088] In some optional embodiments, the inspection route planning device may further include: a geographic coordinate calculation module, used to calculate the actual geographic coordinates of the fault location based on the three-dimensional fault coordinates; and a fault reporting module, used to report the fault based on the three-dimensional topographic map after the fault is marked and the actual geographic coordinates of the fault.

[0089] It should be understood that this device corresponds to the above-described inspection route planning method embodiment and is capable of performing the various steps involved in the above method embodiment. The specific functions of this device can be found in the description above, and detailed descriptions are omitted here to avoid repetition. The device includes at least one software functional module that can be stored in memory or embedded in the device's operating system (OS) in the form of software or firmware.

[0090] Please refer to Figure 8 , Figure 8This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application. The electronic device 300 provided in this application includes a processor 301 and a memory 302. These components are interconnected and communicate with each other via a communication bus 303 and / or other forms of connection mechanisms (not shown). The memory 302 stores a computer program executable by the processor 301. When the computer program is executed by the processor 301, it performs the above-described inspection route planning method.

[0091] This application embodiment also provides a computer-readable storage medium storing computer program instructions, which are executed by processor 301 to perform the above-mentioned inspection route planning method.

[0092] The storage medium can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as Static Random Access Memory (SRAM), Electrically Erasable Programmable Read-Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Red-Only Memory (PROM), Read-Only Memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0093] It should be understood that the disclosed apparatus and methods can also be implemented in other ways, given the several embodiments provided in this application. The apparatus embodiments described above are merely illustrative. For example, the flowcharts and block diagrams in the accompanying drawings illustrate the architecture, functionality, and operation of possible implementations of apparatus, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram may represent a module, segment, or portion of code, which contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than those marked in the drawings. For example, two consecutive blocks may actually be executed substantially in parallel, or they may sometimes be executed in reverse order, depending on the functions involved. It should also be noted that each block in a block diagram and / or flowchart, and combinations of blocks in block diagrams and / or flowcharts, can be implemented using a dedicated hardware-based system that performs the specified function or action, or using a combination of dedicated hardware and computer instructions.

[0094] In addition, the functional modules in the various embodiments of this application can be integrated together to form an independent part, or each module can exist independently, or two or more modules can be integrated to form an independent part.

[0095] The above description is only an optional implementation of the embodiments of this application, but the protection scope of the embodiments of this application is not limited thereto. Any changes or substitutions that can be easily conceived by those skilled in the art within the technical scope disclosed in the embodiments of this application should be covered within the protection scope of the embodiments of this application.

Claims

1. A method for planning inspection routes, characterized in that, The method includes: Obtain digital orthophoto maps and digital elevation models of the target photovoltaic power station area; wherein, the target photovoltaic power station area includes multiple photovoltaic strings; Based on the digital orthophoto map and digital elevation model, a three-dimensional topographic map of the target photovoltaic power station area is generated; Determine the center position and orientation of the photovoltaic strings in the three-dimensional topographic map; Based on the camera parameters of the drone, the center position and orientation of the photovoltaic string, calculate the photo waypoint corresponding to the center position of the string; The drone will plan its inspection route for the photovoltaic strings based on the photographed waypoints. The photography waypoints include the photography location, the drone's yaw angle and pitch angle at the photography location; the camera parameters include the camera focal length, sensor size and image resolution. The step of calculating the photography waypoints corresponding to the photovoltaic string based on the camera parameters of the drone, the center position of the photovoltaic string, and the string orientation includes: Based on the orientation of the photovoltaic string, determine the yaw angle and pitch angle of the drone for the corresponding photography waypoint; according to Calculate the shooting distance between the shooting position and the center position of the string. ; according to Calculate the image height of the image at the image location corresponding to the photovoltaic string. ; according to Calculate the image plane position corresponding to the image capture location of the photovoltaic string. ;in, ; The shooting position is determined based on the shooting height and the shooting plane position; Where f represents the focal length of the camera, S X R represents the width of the image sensor, R0 represents the number of pixels per unit distance, R X The width represents the image resolution, β is equal to the shooting pitch angle, H0 represents the height of the cluster center position, and P0 represents the planar position of the cluster center position. The unit vector representing the position and direction of the image plane. Let α represent the unit vector in the due south direction in the plane. and The angle between the planes, where the plane angle α is positive counterclockwise and its value is equal to the photographing yaw angle.

2. The method according to claim 1, characterized in that, After planning the inspection route of the drone for the photovoltaic string based on the camera parameters of the drone and the center position and orientation of the photovoltaic string, the method further includes: The photovoltaic strings in the target photovoltaic power station area are inspected according to the inspection route to obtain inspection images of the photovoltaic strings; Fault identification is performed on the inspection images to determine the faulty inspection images and the fault locations in the faulty inspection images; wherein, the faulty inspection images include inspection images with string faults.

3. The method according to claim 2, characterized in that, After determining the faulty inspection image and the fault location in the faulty inspection image, the method further includes: Based on the fault location, the waypoints for acquiring the fault inspection image, and the size and image resolution of the drone's photosensitive element, calculate the three-dimensional fault coordinates of the fault location on the three-dimensional terrain map; The fault is marked on the three-dimensional terrain map based on the three-dimensional fault coordinates.

4. The method according to claim 3, characterized in that, After calculating the three-dimensional fault coordinates of the fault location in the three-dimensional topographic map, the method further includes: Calculate the actual geographical coordinates of the fault location based on the three-dimensional fault coordinates; The fault is reported based on the three-dimensional topographic map after the fault is marked and the actual geographical coordinates of the fault.

5. A patrol route planning device, characterized in that, The device includes: The data acquisition module is used to acquire digital orthophoto maps and digital elevation models of the target photovoltaic power station area; wherein, the target photovoltaic power station area includes multiple photovoltaic strings; A three-dimensional topographic map generation module is used to generate a three-dimensional topographic map of the target photovoltaic power station area based on the digital orthophoto map and the digital elevation model. The string determination module is used to determine the string center position and string orientation of the photovoltaic strings in the three-dimensional terrain map; The route planning module is used to plan the inspection route of the drone for the photovoltaic string based on the camera parameters of the drone and the center position and orientation of the photovoltaic string. Specifically, the route planning module is used for: Based on the camera parameters of the drone, the center position and orientation of the photovoltaic string, calculate the photo waypoint corresponding to the center position of the string; The drone's inspection route for the photovoltaic strings is planned based on the photographing waypoints; wherein, the photographing waypoints include the photographing location, the drone's yaw angle and pitch angle at the photographing location; the camera parameters include the camera focal length, sensor size and image resolution; The step of calculating the photography waypoints corresponding to the photovoltaic string based on the camera parameters of the drone, the center position of the photovoltaic string, and the string orientation includes: Based on the orientation of the photovoltaic string, determine the yaw angle and pitch angle of the drone for the corresponding photography waypoint; according to Calculate the shooting distance between the shooting position and the center position of the string. ; according to Calculate the image height of the image at the image location corresponding to the photovoltaic string. ; according to Calculate the image plane position corresponding to the image capture location of the photovoltaic string. ;in, ; The shooting position is determined based on the shooting height and the shooting plane position; Where f represents the focal length of the camera, S X R represents the width of the image sensor, R0 represents the number of pixels per unit distance, R X The width represents the image resolution, β is equal to the shooting pitch angle, H0 represents the height of the cluster center position, and P0 represents the planar position of the cluster center position. The unit vector representing the position and direction of the image plane. Let α represent the unit vector in the due south direction in the plane. and The angle between the planes, where the plane angle α is positive counterclockwise and its value is equal to the photographing yaw angle.

6. An electronic device, characterized in that, The electronic device includes: Memory; processor; The memory stores a computer program executable by the processor, which, when executed by the processor, performs the method described in any one of claims 1-4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer program instructions that, when executed by a processor, perform the method described in any one of claims 1-4.

Images