An efficient photovoltaic power station unmanned aerial vehicle inspection method and system

Abstract

This invention discloses an efficient method for drone inspection of photovoltaic power plants. The drone collects images of the photovoltaic power plant and generates a two-dimensional orthophoto panoramic image. The locations of the components in the two-dimensional orthophoto panoramic image are extracted, and the shooting range is divided. The drone shooting position is generated based on the shooting range and camera information. The drone shooting position is converted into an executable inspection file. This application uses existing target locations, first calculates the GPS matrix of the photovoltaic components, and plans shooting points through the matrix. It plans the minimum number of photos while ensuring complete coverage of all objects. Moreover, the target number and related information in the photos are known at the time of shooting, which improves the efficiency and accuracy of inspection and avoids waste of resources.

Description

Technical Field

[0001] This invention discloses an efficient method and system for drone inspection of photovoltaic power plants, which can be applied to drone inspection of photovoltaic power plants and can also be used for efficient path planning for inspection and photography of fixed target objects. Background Technology

[0002] Existing technologies for drone inspections of photovoltaic power plants result in image redundancy in the collected data, and video data acquisition mode leads to large data volumes and low transmission efficiency.

[0003] Existing technology CN 115480589 A describes a method and system for generating wind turbine inspection routes based on unmanned aerial vehicles (UAVs). This method only requires inputting the geographical information and parameters of the wind turbine to automatically identify the yaw angle and blade angle when the turbine is shut down, and automatically generate inspection routes. This eliminates the need for manual intervention during flight, allowing the UAV to take off from any point and the wind turbine to stop at any angle. However, target data acquisition uses continuous video or image capture, which is time-consuming and wastes hardware resources. Summary of the Invention

[0004] To address the shortcomings of existing technologies, the purpose of this invention is to provide an efficient drone inspection solution for photovoltaic power plants. This solution utilizes existing target locations, plans the minimum number of photos taken while ensuring complete coverage of all objects, and provides the target number and related information in the photos during the shooting process, thereby improving the efficiency and accuracy of inspections and avoiding resource waste.

[0005] Therefore, the ultimate goal of this invention is to develop an efficient drone inspection solution for photovoltaic power plants.

[0006] To achieve the above objectives, the present invention adopts the following technical solution:

[0007] An efficient method for unmanned aerial vehicle (UAV) inspection of photovoltaic power plants includes the following steps:

[0008] S1, the drone collects images of the photovoltaic power station, generates a two-dimensional orthophoto panoramic image, and obtains digital elevation information;

[0009] S2, extract the component positions in the 2D orthophoto panoramic image and divide the shooting range;

[0010] S3 generates the drone's shooting location based on the shooting range and camera information;

[0011] S4 converts the drone's captured locations into executable inspection files and performs the inspection.

[0012] Preferably, step S1 specifically includes the following steps:

[0013] 101) Control the drone group to take photos directly above the photovoltaic power station;

[0014] 102) Based on the collected photos of the area directly above the photovoltaic power station, create a two-dimensional orthophoto panoramic image (tile image) to obtain digital elevation information (3D modeling information).

[0015] Preferably, step S2 specifically includes the following steps:

[0016] 201) Mark the component positions in the 2D orthophoto panoramic image;

[0017] Photovoltaic modules W = (W1, W2, ... W2) in a 2D orthophoto panoramic image were identified and labeled using image vision segmentation and merging algorithms. i …W n ), where n is the number of photovoltaic modules identified, W i Let i represent the i-th photovoltaic module, i = 1, 2, ..., n; obtain the GPS location information of the photovoltaic module to get its latitude and longitude;

[0018] The GPS location information includes GPS information from the four corners of the photovoltaic module, and the area of ​​each photovoltaic module is obtained based on the GPS information from the four corners of the photovoltaic module.

[0019] 202) Map the GPS location information of all photovoltaic modules to the world coordinate system;

[0020] Step 202) specifically includes the following steps:

[0021] The GPS location information (Lng_) of the i-th photovoltaic module i ,Lat_ i Switch to the world coordinate system;

[0022]

[0023]

[0024] In the formula, π refers to the constant 3.1415926; Lng_ i Lat_ represents the longitude of the i-th photovoltaic module. i x represents the dimension of the i-th photovoltaic module; wi Let y represent the x-coordinate of the i-th photovoltaic module in the world coordinate system. wi This represents the ordinate of the i-th photovoltaic module in the world coordinate system;

[0025] Based on x respectively wi and y wi Sort the data in ascending order to form an array X. w and Y w ;

[0026] X w =(x1,x2,…xj …x n (3)

[0027] Y w =(y1,y2,…y j …y n (4)

[0028] j = 1, 2…n; x j Represents the sorted array X w The j-th data in y; j Sorted array Y w The j-th data in array X; will be used as array X w The photovoltaic modules corresponding to the sorting are divided into different rows using a recursive algorithm; the array Y will be used as the basis for this. w The photovoltaic modules are sorted into different columns using a recursive algorithm; a sorting matrix A with row and column numbers is obtained for all photovoltaic modules; the elements in sorting matrix A are represented using the GPS location information of the corresponding photovoltaic modules, and a GPS matrix L corresponding to sorting matrix A is established.

[0029]

[0030] Where Lpq represents the photovoltaic module in the p-th row and q-th column of the GPS matrix L; p = 1, 2, ..., n, q = 1, 2, ..., n;

[0031] Based on the GPS information of the four corner points of the photovoltaic module support, the maximum number of rows and columns of the support required for each photo is set to obtain the maximum width W of the drone shot. Based on the digital elevation information, the height H of the drone shot point is calculated (the height H of the drone shot point is calculated based on the maximum width W of the drone shot and the digital elevation information).

[0032] The steps to construct the GPS matrix L are as follows: the order of columns 1 to n is determined by the size of the horizontal axis, and a recursive algorithm is used to recursively construct Y. w Array, determine if photovoltaic modules are in the same column; by Y w Loop through the array elements from smallest to largest to find supports in the same column. Determine if supports are in the same column by calculating the leftmost and last x-axis coordinate intervals of two adjacent supports. Find the union of the x-axis coordinate intervals of the two supports. If the overlap rate between the union of the x-axis coordinate intervals and the x-axis coordinate intervals of either of the two supports is greater than a certain value (i.e., the ratio of the size of the union to the x-axis coordinate intervals of either of the two supports is greater than a certain value), then the two supports are in the same column. Obtain the n-column sort of the GPS matrix.

[0033] The order of rows 1 to n is determined by the size of the vertical axis, so a recursive algorithm is used to recursively process X. wFor arrays, the criterion for determining whether elements are in the same row is: [X] w The array elements are looped from smallest to largest to find supports in the same row. It is determined whether the supports are in the same row. The Y-axis coordinate intervals of the top and bottom edges of two adjacent supports are calculated. The union of the Y-axis coordinate intervals of the two supports is calculated. If the overlap rate between the union of the Y-axis coordinate intervals and the Y-axis coordinate interval of either of the two supports is greater than a certain value, that is, if the ratio of the size of the union to the Y-axis coordinate interval of either of the two supports (overlap rate) is greater than a certain value, then the two supports are in the same row. The n rows of the GPS matrix are obtained.

[0034] Traverse array Y w The obtained row sorting is used to find the corresponding column in the column sorting through the GPS information of the bracket, and the row and column coordinates of the bracket are determined to determine the corresponding coordinates in the GPS matrix.

[0035] 203) The shooting range is dynamically defined based on the area of ​​the photovoltaic module and the GPS matrix L of the photovoltaic module.

[0036] Preferably, step S3 specifically includes the following steps:

[0037] 301) Determine the GPS coordinates of each shooting point of the UAV based on the component positions in the GPS matrix L;

[0038] 302) Based on the GPS coordinates of the shooting point and the shooting height H, the drone shooting position information is generated. The drone is controlled to adjust the yaw angle, gimbal angle, focal length and drone GPS deviation compensation, so that the drone keeps the altitude as parallel as possible during operation, reduces power consumption and improves inspection efficiency.

[0039] Preferably, step S4 specifically includes the following steps:

[0040] 401) Convert the drone's captured location information into a drone flight path file in kml format; generate kml format text from the waypoint information according to the kml format requirements;

[0041] 402) Import the drone flight path file into the drone remote controller and execute the flight mission.

[0042] A high-efficiency unmanned aerial vehicle (UAV) inspection system for photovoltaic power plants includes a two-dimensional orthophoto panoramic image generation unit, a shooting range division unit, a shooting point confirmation unit, and an inspection execution unit.

[0043] The 2D orthophoto panoramic image generation unit controls a drone to collect images of a photovoltaic power station, generate a 2D orthophoto panoramic image, and obtain digital elevation information;

[0044] The shooting range division unit extracts the component positions from the two-dimensional orthophoto panoramic image and divides the shooting range.

[0045] The shooting point confirmation unit generates the drone's shooting location based on the shooting range and camera information;

[0046] The inspection unit converts the locations captured by the drone into executable inspection files and performs the inspection.

[0047] The working process of the 2D orthophoto panoramic image generation unit includes the following steps:

[0048] 101) Control the drone group to take photos directly above the photovoltaic power station;

[0049] 102) Create a two-dimensional orthophoto panoramic image based on the collected photos taken directly above the photovoltaic power station to obtain digital elevation information.

[0050] The process of dividing the shooting range into units includes the following steps:

[0051] 201) Mark the component positions in the 2D orthophoto panoramic image;

[0052] Photovoltaic modules W = (W1, W2, ... W2) in a 2D orthophoto panoramic image were identified and labeled using image vision segmentation and merging algorithms. i …W n ), where n is the number of photovoltaic modules identified, W i Let i represent the i-th photovoltaic module, i = 1, 2, ..., n; obtain the GPS location information of the photovoltaic module to get its latitude and longitude;

[0053] The GPS location information includes GPS information from the four corners of the photovoltaic module, and the area of ​​each photovoltaic module is obtained based on the GPS information from the four corners of the photovoltaic module.

[0054] 202) Map the GPS location information of all photovoltaic modules to the world coordinate system;

[0055] Step 202) specifically includes the following steps:

[0056] The GPS location information (Lng_) of the i-th photovoltaic module i ,Lat_ i Switch to the world coordinate system;

[0057]

[0058]

[0059] In the formula, π refers to a constant; Lng_ i Lat_ represents the longitude of the i-th photovoltaic module. i x represents the dimension of the i-th photovoltaic module; wi Let y represent the x-coordinate of the i-th photovoltaic module in the world coordinate system.wi This represents the ordinate of the i-th photovoltaic module in the world coordinate system;

[0060] Based on x respectively wi and y wi Sort the data in ascending order to form an array X. w and Y w ;

[0061] X w =(x1,x2,…x j …x n (3)

[0062] Y w =(y1,y2,…y j …y n (4)

[0063] j = 1, 2…n; x j Represents the sorted array X w The j-th data in y; j Sorted array Y w The j-th data in;

[0064] will be array X w The photovoltaic modules corresponding to the sorting are divided into different rows using a recursive algorithm; the array Y will be used as the basis for this. w The photovoltaic modules are sorted into different columns using a recursive algorithm; a sorting matrix A with row and column numbers is obtained for all photovoltaic modules; the elements in sorting matrix A are represented using the GPS location information of the corresponding photovoltaic modules, and a GPS matrix L corresponding to sorting matrix A is established.

[0065]

[0066] Where Lpq represents the photovoltaic module in the p-th row and q-th column of the GPS matrix L; p = 1, 2, ..., n, q = 1, 2, ..., n;

[0067] Based on the GPS information of the four corner points of the photovoltaic module support, the maximum number of rows and columns of the support needed to be photographed in each photo is set, the maximum width W of the drone is obtained, and the height H of the drone shooting point is calculated based on the digital elevation information.

[0068] Traverse array Y w The obtained row sorting is used to find the corresponding column in the column sorting through the GPS information of the bracket, and the row and column coordinates of the bracket are determined to determine the corresponding coordinates in the GPS matrix.

[0069] 203) Dynamically define the shooting range based on the area of ​​the photovoltaic module and the GPS matrix L of the photovoltaic module;

[0070] The steps to construct the GPS matrix L are as follows: the order of columns 1 to n is determined by the size of the horizontal axis, and a recursive algorithm is used to recursively construct Y. w Array, determine if photovoltaic modules are in the same column; by Y w Loop through the elements in the array from smallest to largest to find the supports in the same column. Determine if the supports are in the same column. Calculate the X-axis coordinate intervals of the leftmost and last edges of two adjacent supports. Find the union of the X-axis coordinate intervals of the two supports. If the overlap rate between the union of the X-axis coordinate intervals and the X-axis coordinate interval of either support is greater than a certain value, then the two supports are in the same column. Obtain the n-column sort of the GPS matrix.

[0071] The order of rows 1 to n is determined by the size of the vertical axis, so a recursive algorithm is used to recursively process X. w For arrays, the criterion for determining whether elements are in the same row is: [X] w The array elements are looped from smallest to largest to find supports in the same row. It is determined whether the supports are in the same row. The Y-axis coordinate intervals of the top and bottom edges of two adjacent supports are calculated. The union of the Y-axis coordinate intervals of the two supports is calculated. If the overlap rate between the union of the Y-axis coordinate intervals and the Y-axis coordinate interval of either of the two supports is greater than a certain value, then the two supports are in the same row. The n rows of the GPS matrix are obtained.

[0072] The shooting location confirmation unit's working process specifically includes the following steps:

[0073] 301) Determine the GPS coordinates of each shooting point of the UAV based on the component positions in the GPS matrix L;

[0074] 302) Based on the GPS coordinates of the shooting point and the shooting height H, the drone shooting position information is generated, and the drone is controlled to adjust the yaw angle, gimbal angle, focal length and drone GPS deviation compensation to keep the drone at a parallel altitude during operation;

[0075] The specific steps involved in performing the inspection unit's work are as follows:

[0076] 401) Convert the drone's captured location information into a drone flight path file in kml format; generate kml format text from the waypoint information according to the kml format requirements;

[0077] 402) Import the drone flight path file into the drone remote controller and execute the flight mission.

[0078] Compared with the prior art, this application specifically includes the following beneficial effects:

[0079] This application discloses an efficient method and system for unmanned aerial vehicle (UAV) inspection of photovoltaic power plants. Using existing target locations, the system first calculates the GPS matrix of the photovoltaic modules, plans shooting points through the matrix, plans the minimum number of photos while ensuring complete coverage of all objects, and knows the target number and related information in the photos at the time of shooting, thereby improving the efficiency and accuracy of inspection and avoiding waste of resources.

[0080] Before collecting data, this application pre-plans the location and quantity of components in the photos to be collected, reducing redundancy and improving transmission and analysis efficiency. Attached Figure Description

[0081] Figure 1 This is a two-dimensional orthophoto panoramic view of the implementation of this application. Detailed Implementation

[0082] The present invention will be further described below with reference to the accompanying drawings in the embodiments of the present invention.

[0083] It should be noted that the following detailed description is illustrative and intended to provide further explanation of this disclosure. Unless otherwise specified, 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 disclosure pertains. All other embodiments obtained by one of ordinary skill in the art based on the embodiments of this invention without inventive effort are within the scope of protection of this invention.

[0084] An efficient method for unmanned aerial vehicle (UAV) inspection of photovoltaic power plants includes the following steps:

[0085] S1, the drone collects images of the photovoltaic power station and generates a two-dimensional orthophoto panoramic image (e.g., Figure 1 (As shown), obtain digital elevation information;

[0086] S2, extract the component positions in the 2D orthophoto panoramic image and divide the shooting range;

[0087] S3 generates the drone's shooting location based on the shooting range and camera information;

[0088] S4 converts the drone's captured locations into executable inspection files and performs the inspection.

[0089] Step S1 specifically includes the following steps:

[0090] 101) Control the drone group to take photos directly above the photovoltaic power station;

[0091] 102) Based on the collected photos of the area directly above the photovoltaic power station, create a two-dimensional orthophoto panoramic image (tile image) to obtain digital elevation information (3D modeling information).

[0092] Step S2 specifically includes the following steps:

[0093] 201) Mark the component positions in the 2D orthophoto panoramic image;

[0094] Photovoltaic modules W = (W1, W2, ... W2) in a 2D orthophoto panoramic image were identified and labeled using image vision segmentation and merging algorithms. i W n ), where n is the number of photovoltaic modules identified, W i Let i represent the i-th photovoltaic module, i = 1, 2, ..., n; obtain the GPS location information of the photovoltaic module to get its latitude and longitude;

[0095] The GPS location information includes GPS information from the four corners of the photovoltaic module, and the area of ​​each photovoltaic module is obtained based on the GPS information from the four corners of the photovoltaic module.

[0096] 202) Map the GPS location information of all photovoltaic modules to the world coordinate system;

[0097] Step 202) specifically includes the following steps:

[0098] The GPS location information (Lng_) of the i-th photovoltaic module i ,Lat_ i Switch to the world coordinate system;

[0099]

[0100]

[0101] In the formula, π refers to the constant 3.1415926; Lng_ i Lat_ represents the longitude of the i-th photovoltaic module. i x represents the dimension of the i-th photovoltaic module; wi Let y represent the x-coordinate of the i-th photovoltaic module in the world coordinate system. wi This represents the ordinate of the i-th photovoltaic module in the world coordinate system;

[0102] Based on x respectively wi and y wi Sort the data in ascending order to form an array X. w and Y w ;

[0103] X w =(x1,x2,…x j …x n (3)

[0104] Y w =(y1,y2,…y j …y n (4)

[0105] j = 1, 2…n; x j Represents the sorted array X w The j-th data in y; j Sorted array Y w The j-th data in the array; in this embodiment, the top left corner of the 2D orthophoto panoramic image is the coordinate point (0,0). Given the coordinates of the four corner points of the rectangle of each support frame of the photovoltaic module in the 2D orthophoto panoramic image, sort the data in the 2D coordinate system according to the x-coordinate and y-coordinate of the i-th photovoltaic module; obtain the array X. w and Y w ;

[0106] will be array X w The photovoltaic modules corresponding to the sorting are divided into different rows using a recursive algorithm; the array Y will be used as the basis for this. w The photovoltaic modules are sorted into different columns using a recursive algorithm; a sorting matrix A with row and column numbers is obtained for all photovoltaic modules; the elements in sorting matrix A are represented using the GPS location information of the corresponding photovoltaic modules, and a GPS matrix L corresponding to sorting matrix A is established.

[0107]

[0108] Lpq represents the photovoltaic module in the p-th row and q-th column of the GPS matrix L; p = 1, 2, ..., n, q = 1, 2, ..., n;

[0109] Based on the GPS information of the four corner points of the photovoltaic module support, the maximum number of rows and columns of the support to be photographed in each photo is set (in this embodiment, the drone is set to photograph 3 rows and 2 columns of photovoltaic modules each time). The maximum width W of the drone is obtained. Based on the digital elevation information, the height H of the drone shooting point is calculated (the height H of the drone shooting point is calculated based on the maximum width W of the drone shooting and the digital elevation information).

[0110] The steps to construct the GPS matrix L are as follows: the order of columns 1 to n is determined by the size of the horizontal axis, and a recursive algorithm is used to recursively construct Y. w The array is used to determine if photovoltaic modules belong to the same column; for adjacent photovoltaic modules, the overlap rate along the horizontal axis must be greater than 40%, and so on, until the overlap rate and continuity conditions can no longer be met, and then the array is set to Y. wThe array elements are iterated from smallest to largest to find supports located in the same column. It is determined whether supports are in the same column. The leftmost and rightmost X-axis coordinate intervals of two adjacent supports are calculated, and the union of the X-axis coordinate intervals of the two supports is calculated. If the overlap rate between the union of the X-axis coordinate intervals and the X-axis coordinate interval of either of the two supports is greater than a certain value (i.e., the ratio of the union size to the X-axis coordinate interval of either of the two supports is greater than a certain value (40% in this embodiment), then the two supports are in the same column; the n-column sort of the GPS matrix is ​​obtained.

[0111] The order of rows 1 to n is determined by the size of the vertical axis, so a recursive algorithm is used to recursively process X. w For arrays, the criterion for determining whether elements are in the same row is: [X] w The array elements are looped from smallest to largest to find supports in the same row. It is determined whether the supports are in the same row. The Y-axis coordinate intervals of the top and bottom edges of two adjacent supports are calculated. The union of the Y-axis coordinate intervals of the two supports is calculated. If the overlap rate between the union of the Y-axis coordinate intervals and the Y-axis coordinate interval of either of the two supports is greater than a limit value, that is, the ratio of the size of the union to the Y-axis coordinate interval of either of the two supports (overlap rate) is greater than a limit value (the limit value in this embodiment is 40%), then the two supports are in the same row, and the n-row sort of the GPS matrix is ​​obtained.

[0112] Traverse array Y w The obtained row sorting is used to find the corresponding column in the column sorting through the GPS information of the bracket, and the row and column coordinates of the bracket are determined to determine the corresponding coordinates in the GPS matrix.

[0113] Based on the number of supports captured in each photo, the shooting range (how many rows and columns to shoot; in this embodiment, the value matrix is ​​set to [1:2,3:4] -- taking the 3rd and 4th columns of rows 1-2) is determined, and the GPS information and altitude H of the drone shooting point are obtained.

[0114] 203) The shooting range is dynamically defined based on the area of ​​the photovoltaic module and the GPS matrix L of the photovoltaic module.

[0115] Step S3 specifically includes the following steps:

[0116] 301) Determine the GPS coordinates of each shooting point of the UAV based on the component positions in the GPS matrix L;

[0117] 302) Based on the GPS coordinates of the shooting point and the shooting height H, the drone shooting position information is generated. The drone is controlled to adjust the yaw angle, gimbal angle, focal length and drone GPS deviation compensation, so that the drone keeps the altitude as parallel as possible during operation, reduces power consumption and improves inspection efficiency.

[0118] Step S4 specifically includes the following steps:

[0119] 401) Convert the drone's captured location information into a drone flight path file in kml format; generate kml format text from the waypoint information according to the kml format requirements;

[0120] 402) Import the drone flight path file into the drone remote controller and execute the flight mission.

[0121] A high-efficiency unmanned aerial vehicle (UAV) inspection system for photovoltaic power plants includes a two-dimensional orthophoto panoramic image generation unit, a shooting range division unit, a shooting point confirmation unit, and an inspection execution unit.

[0122] The 2D orthophoto panoramic image generation unit controls a drone to collect images of a photovoltaic power station, generate a 2D orthophoto panoramic image, and obtain digital elevation information;

[0123] The shooting range division unit extracts the component positions from the two-dimensional orthophoto panoramic image and divides the shooting range.

[0124] The shooting point confirmation unit generates the drone's shooting location based on the shooting range and camera information;

[0125] The inspection unit converts the locations captured by the drone into executable inspection files and performs the inspection.

[0126] The working process of the 2D orthophoto panoramic image generation unit includes the following steps:

[0127] 101) Control the drone group to take photos directly above the photovoltaic power station;

[0128] 102) Based on the collected photos taken directly above the photovoltaic power station, a two-dimensional orthophoto panoramic image (tile image) is created to obtain digital elevation information.

[0129] The process of dividing the shooting range into units includes the following steps:

[0130] 201) Mark the component positions in the 2D orthophoto panoramic image;

[0131] Photovoltaic modules W = (W1, W2, ... W2) in a 2D orthophoto panoramic image were identified and labeled using image vision segmentation and merging algorithms. i …W n ), where n is the number of photovoltaic modules identified, W i Let i represent the i-th photovoltaic module, i = 1, 2, ..., n; obtain the GPS location information of the photovoltaic module to get its latitude and longitude;

[0132] The GPS location information includes GPS information from the four corners of the photovoltaic module, and the area of ​​each photovoltaic module is obtained based on the GPS information from the four corners of the photovoltaic module.

[0133] 202) Map the GPS location information of all photovoltaic modules to the world coordinate system;

[0134] Step 202) specifically includes the following steps:

[0135] The GPS location information (Lng_) of the i-th photovoltaic module i ,Lat_ i Switch to the world coordinate system;

[0136]

[0137]

[0138] In the formula, π refers to the constant 3.1415926; Lng_ i Lat_ represents the longitude of the i-th photovoltaic module. i x represents the dimension of the i-th photovoltaic module; wi Let y represent the x-coordinate of the i-th photovoltaic module in the world coordinate system. wi This represents the ordinate of the i-th photovoltaic module in the world coordinate system;

[0139] Based on x respectively wi and y wi Sort the data in ascending order to form an array X. w and Y w ;

[0140] X w =(x1,x2,…x j …x n (3)

[0141] Y w =(y1,y2,…y j …y n (4)

[0142] j = 1, 2…n; x j Represents the sorted array X w The j-th data in y; j Sorted array Y w The j-th data in the array; in this embodiment, the top left corner of the 2D orthophoto panoramic image is the coordinate point (0,0). Given the coordinates of the four corner points of the rectangle of each support frame of the photovoltaic module in the 2D orthophoto panoramic image, sort the data in the 2D coordinate system according to the x-coordinate and y-coordinate of the i-th photovoltaic module; obtain the array X. w and Y w ;

[0143] will be array X w The photovoltaic modules corresponding to the sorting are divided into different rows using a recursive algorithm; the array Y will be used as the basis for this. wThe photovoltaic modules are sorted into different columns using a recursive algorithm; a sorting matrix A with row and column numbers is obtained for all photovoltaic modules; the elements in sorting matrix A are represented using the GPS location information of the corresponding photovoltaic modules, and a GPS matrix L corresponding to sorting matrix A is established.

[0144]

[0145] Where Lpq represents the photovoltaic module in the p-th row and q-th column of the GPS matrix L; p = 1, 2, ..., n, q = 1, 2, ..., n;

[0146] Based on the GPS information of the four corner points of the photovoltaic module support, the maximum number of rows and columns of the support to be photographed in each photo is set, the maximum width W of the drone is obtained, and the height H of the drone shooting point is calculated based on the digital elevation information (the height H of the drone shooting point is calculated based on the maximum width W of the drone shooting and the digital elevation information).

[0147] Traverse array Y w The obtained row sorting is used to find the corresponding column in the column sorting through the GPS information of the bracket, and the row and column coordinates of the bracket are determined to determine the corresponding coordinates in the GPS matrix.

[0148] Based on the number of supports captured in each photo, the shooting range (how many rows and columns to shoot; in this embodiment, the value matrix is ​​set to [1:2,3:4] -- taking the 3rd and 4th columns of rows 1-2) is determined, and the GPS information and altitude H of the drone shooting point are obtained.

[0149] 203) Dynamically define the shooting range based on the area of ​​the photovoltaic module and the GPS matrix L of the photovoltaic module;

[0150] The steps to construct the GPS matrix L are as follows: the order of columns 1 to n is determined by the size of the horizontal axis, and a recursive algorithm is used to recursively construct Y. w The array is used to determine if photovoltaic modules belong to the same column; for adjacent photovoltaic modules, the overlap rate along the horizontal axis must be greater than 40%, and so on, until the overlap rate and continuity conditions can no longer be met, and then the array is set to Y. w The array elements are iterated from smallest to largest to find supports located in the same column. It is determined whether supports are in the same column. The leftmost and rightmost X-axis coordinate intervals of two adjacent supports are calculated, and the union of the X-axis coordinate intervals of the two supports is calculated. If the overlap rate between the union of the X-axis coordinate intervals and the X-axis coordinate interval of either of the two supports is greater than a certain value (i.e., the ratio of the union size to the X-axis coordinate interval of either of the two supports is greater than a certain value (40% in this embodiment), then the two supports are in the same column; the n-column sort of the GPS matrix is ​​obtained.

[0151] The order of rows 1 to n is determined by the size of the vertical axis, so a recursive algorithm is used to recursively process X. w For arrays, the criterion for determining whether elements are in the same row is: [X] w The array elements are looped from smallest to largest to find supports in the same row. It is determined whether the supports are in the same row. The Y-axis coordinate intervals of the top and bottom edges of two adjacent supports are calculated. The union of the Y-axis coordinate intervals of the two supports is calculated. If the overlap rate between the union of the Y-axis coordinate intervals and the Y-axis coordinate interval of either of the two supports is greater than a limit value, that is, the ratio of the size of the union to the Y-axis coordinate interval of either of the two supports (overlap rate) is greater than a limit value (the limit value in this embodiment is 40%), then the two supports are in the same row, and the n-row sort of the GPS matrix is ​​obtained.

[0152] The shooting location confirmation unit's working process specifically includes the following steps:

[0153] 301) Determine the GPS coordinates of each shooting point of the UAV based on the component positions in the GPS matrix L;

[0154] 302) Based on the GPS coordinates of the shooting point and the shooting height H, the drone shooting position information is generated, and the drone is controlled to adjust the yaw angle, gimbal angle, focal length and drone GPS deviation compensation, so that the drone keeps the altitude as parallel as possible during operation, reduces power consumption and improves inspection efficiency.

[0155] The specific steps involved in performing the inspection unit's work are as follows:

[0156] 401) Convert the drone's captured location information into a drone flight path file in kml format; generate kml format text from the waypoint information according to the kml format requirements;

[0157] 402) Import the drone flight path file into the drone remote controller and execute the flight mission.

[0158] The above are merely preferred embodiments of this disclosure and are not intended to limit this disclosure. Various modifications and variations can be made to this disclosure by those skilled in the art. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of this disclosure should be included within the scope of protection of this disclosure.

[0159] While the specific embodiments of this disclosure have been described above in conjunction with the accompanying drawings, this is not intended to limit the scope of protection of this disclosure. Those skilled in the art should understand that various modifications or variations that can be made by those skilled in the art without creative effort based on the technical solutions of this disclosure are still within the scope of protection of this disclosure.

[0160] The technical solution of the present invention has been described above with reference to the preferred embodiments shown in the accompanying drawings. However, it will be readily understood by those skilled in the art that the scope of protection of the present invention is obviously not limited to these specific embodiments. Without departing from the principles of the present invention, those skilled in the art can make equivalent changes or substitutions to the relevant technical features, and the technical solutions after such changes or substitutions will all fall within the scope of protection of the present invention.

[0161] Numerous specific details are set forth in the specification provided herein. However, it will be understood that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures, and techniques have not been shown in detail so as not to obscure the understanding of this specification.

[0162] Similarly, it should be understood that, in order to streamline this disclosure and aid in understanding one or more of the various aspects of the invention, in the above description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof. However, this method of disclosure should not be interpreted as reflecting an intention that the claimed invention requires more features than expressly recited in each claim. Rather, as reflected in the claims, inventive aspects lie in fewer than all features of a single foregoing disclosed embodiment. Therefore, the claims following the detailed description are hereby expressly incorporated into that detailed description, wherein each claim itself is a separate embodiment of the invention.

[0163] Those skilled in the art will understand that the modules, units, or groups of devices in the examples disclosed herein can be arranged in the device as described in this embodiment, or alternatively, can be located in one or more devices different from the device in this example. The modules in the foregoing examples can be combined into a single module or, in addition, can be divided into multiple sub-modules.

[0164] Those skilled in the art will understand that modules in the device of the embodiments can be adaptively changed and placed in one or more devices different from that embodiment. Modules, units, or groups in the embodiments can be combined into a single module, unit, or group, and further, they can be divided into multiple sub-modules, sub-units, or sub-groups. Except where at least some of such features and / or processes or units are mutually exclusive, any combination can be used to combine all features disclosed in this specification (including the accompanying claims, abstract, and drawings) and all processes or units of any method or device so disclosed. Unless expressly stated otherwise, each feature disclosed in this specification (including the accompanying claims, abstract, and drawings) may be replaced by an alternative feature that serves the same, equivalent, or similar purpose.

[0165] Furthermore, those skilled in the art will understand that although some embodiments described herein include certain features but not others included in other embodiments, combinations of features from different embodiments are intended to be within the scope of the invention and form different embodiments. For example, in the following claims, any of the claimed embodiments can be used in any combination.

[0166] Furthermore, some of the embodiments described herein are methods or combinations of method elements that can be implemented by a processor of a computer system or by other means of performing the functions. Therefore, a processor having the necessary instructions for implementing the methods or method elements forms means for implementing the methods or method elements. Furthermore, the elements described herein in the apparatus embodiments are examples of means for implementing the functions performed by elements for the purposes of carrying out the invention.

[0167] The various techniques described herein can be implemented in combination with hardware or software, or a combination thereof. Thus, the methods and apparatus of the present invention, or certain aspects or portions thereof, can take the form of program code (i.e., instructions) embedded in a tangible medium, such as a floppy disk, CD-ROM, hard disk, or any other machine-readable storage medium, wherein when the program is loaded into and executed by a machine such as a computer, the machine becomes an apparatus for practicing the present invention.

[0168] When the program code is executed on a programmable computer, the computing device generally includes a processor, a processor-readable storage medium (including volatile and non-volatile memory and / or storage elements), at least one input device, and at least one output device. The memory is configured to store program code; the processor is configured to execute the method of the present invention according to instructions in the program code stored in the memory.

[0169] By way of example, and not limitation, computer-readable media include computer storage media and communication media. Computer storage media stores information such as computer-readable instructions, data structures, program modules, or other data. Communication media generally embodies computer-readable instructions, data structures, program modules, or other data in the form of modulated data signals such as carrier waves or other transmission mechanisms, and includes any information delivery medium. Any combination of the above is also included within the scope of computer-readable media.

[0170] As used herein, unless otherwise specified, the use of ordinal numbers such as “first,” “second,” “third,” etc., to describe ordinary objects merely indicates different instances of similar objects and is not intended to imply that the objects being described must have a given order in time, space, ordering, or any other manner.

[0171] Although the invention has been described with reference to a limited number of embodiments, those skilled in the art will understand from the foregoing description that other embodiments are conceivable within the scope of the invention described herein. Furthermore, it should be noted that the language used in this specification has been chosen primarily for readability and instructional purposes, and not for the purpose of interpreting or limiting the subject matter of the invention. Therefore, many modifications and variations will be apparent to those skilled in the art without departing from the scope and spirit of the appended claims. The disclosure of the invention is illustrative and not restrictive, and the scope of the invention is defined by the appended claims.

Claims

1. A highly efficient method for unmanned aerial vehicle (UAV) inspection of photovoltaic power plants, characterized in that, Includes the following steps: S1, the drone collects images of the photovoltaic power station, generates a two-dimensional orthophoto panoramic image, and obtains digital elevation information; S2, extract the component positions in the 2D orthophoto panoramic image and divide the shooting range; S3 generates the drone's shooting location based on the shooting range and camera information; S4 converts the drone's captured locations into an executable inspection file and performs the inspection. Step S2 specifically includes the following steps: 201) Mark the positions of components in the 2D orthophoto panoramic image; Photovoltaic modules in a 2D orthophoto panoramic image were identified and labeled using image vision segmentation and merging algorithms. , It is the number of photovoltaic modules identified. Indicates the first One photovoltaic module Obtain the GPS location information of the photovoltaic modules to get their latitude and longitude. The GPS location information includes GPS information from the four corners of the photovoltaic module, and the area of ​​each photovoltaic module is obtained based on the GPS information from the four corners of the photovoltaic module. 202) Map the GPS location information of all photovoltaic modules to the world coordinate system; Step 202) specifically includes the following steps: The first GPS location information of each photovoltaic module Switch to world coordinate system; （1）； （2）； In the formula It refers to a constant; Indicates the first The longitude of each photovoltaic module Indicates the first The latitude of each photovoltaic module; Represents the world coordinate system. The horizontal axis of each photovoltaic module Represents the world coordinate system. The vertical axis of each photovoltaic module; Based on respectively and Sort the arrays in ascending order. and ; （3）； （4）； ; Represents the sorted array The first in One data point; Sorted array The first in One data point; will be in array The photovoltaic modules corresponding to the sorting are divided into different rows using a recursive algorithm; the array will be used as the sorting method. The photovoltaic modules are sorted into different columns using a recursive algorithm; a sorting matrix A with row and column numbers is obtained for all photovoltaic modules; the elements in sorting matrix A are represented using the GPS location information of the corresponding photovoltaic modules, and a GPS matrix corresponding to sorting matrix A is constructed. : （4）； in, Representing the GPS matrix The first in Line number A series of photovoltaic modules; , ; Based on the GPS information of the four corner points of the photovoltaic module support, the maximum number of rows and columns of the support needed to be photographed in each photo is set, the maximum width W of the drone is obtained, and the height H of the drone shooting point is calculated based on the digital elevation information. Traversing the array The obtained row sorting is used to find the corresponding column in the column sorting using the GPS information of the bracket, thereby determining the row and column coordinates of the bracket and the corresponding coordinates in the GPS matrix; 203) The shooting range is dynamically defined based on the area of ​​the photovoltaic module and the GPS matrix L of the photovoltaic module.

2. The efficient unmanned aerial vehicle (UAV) inspection method for photovoltaic power plants according to claim 1, characterized in that, Step S1 specifically includes the following steps: 101) Control the drone group to take photos directly above the photovoltaic power station; 102) Create a two-dimensional orthophoto panoramic image based on the collected photos taken directly above the photovoltaic power station to obtain digital elevation information.

3. The efficient unmanned aerial vehicle (UAV) inspection method for photovoltaic power plants according to claim 1, characterized in that, Establish GPS matrix Specifically, it includes the following steps: using a recursive algorithm recursively. Array, determine if photovoltaic modules are in the same column; The array elements are iterated from smallest to largest to find supports located in the same column. To determine if supports are in the same column, the leftmost and rightmost x-axis coordinate intervals of two adjacent supports are calculated. The union of these x-axis coordinate intervals is then calculated. If the overlap between the union of these intervals and the x-axis coordinate interval of either support is greater than a certain value, then the two supports are in the same column. The GPS matrix is ​​then obtained. Column sorting; Use a recursive algorithm to recursively process For arrays, the criterion for determining whether elements are in the same row is: The array elements are iterated from smallest to largest to find supports in the same row. For each support in a row, the Y-axis coordinates of the top and bottom edges of adjacent supports are calculated. The union of these Y-axis coordinates is then calculated. If the overlap between the union of these Y-axis coordinates and the Y-axis coordinates of either support is greater than a certain value, then the two supports are in the same row, and the GPS matrix is ​​obtained. Sort by row.

4. The efficient unmanned aerial vehicle (UAV) inspection method for photovoltaic power plants according to claim 1, characterized in that, Step S3 specifically includes the following steps: 301) Based on the GPS matrix The location of the components determines the GPS coordinates of each shooting point of the drone; 302) Based on the GPS coordinates of the shooting point and the shooting height H, the drone shooting position information is generated, and the drone is controlled to adjust the yaw angle, gimbal angle, focal length and drone GPS deviation compensation to keep the drone at a parallel altitude during operation.

5. The efficient unmanned aerial vehicle (UAV) inspection method for photovoltaic power plants according to claim 1, characterized in that, Step S4 specifically includes the following steps: 401) Convert the drone's captured location information into a drone flight path file in kml format; generate kml format text from the waypoint information according to the kml format requirements; 402) Import the drone flight path file into the drone remote controller and execute the flight mission.

6. A high-efficiency unmanned aerial vehicle (UAV) inspection system for photovoltaic power plants, characterized in that: It includes a 2D orthophoto panoramic image generation unit, a shooting range division unit, a shooting point confirmation unit, and an execution inspection unit; The 2D orthophoto panoramic image generation unit controls a drone to collect images of a photovoltaic power station, generate a 2D orthophoto panoramic image, and obtain digital elevation information; The shooting range division unit extracts the component positions from the two-dimensional orthophoto panoramic image and divides the shooting range. The shooting point confirmation unit generates the drone's shooting location based on the shooting range and camera information; The inspection unit converts the locations captured by the drone into executable inspection files and performs the inspection. The process of dividing the shooting range into units includes the following steps: 201) Mark the positions of components in the 2D orthophoto panoramic image; Photovoltaic modules in a 2D orthophoto panoramic image were identified and labeled using image vision segmentation and merging algorithms. , It is the number of photovoltaic modules identified. Indicates the first One photovoltaic module Obtain the GPS location information of the photovoltaic modules to get their latitude and longitude. The GPS location information includes GPS information from the four corners of the photovoltaic module, and the area of ​​each photovoltaic module is obtained based on the GPS information from the four corners of the photovoltaic module. 202) Map the GPS location information of all photovoltaic modules to the world coordinate system; Step 202) specifically includes the following steps: The first GPS location information of each photovoltaic module Switch to world coordinate system; （1）； （2）； In the formula It refers to a constant; Indicates the first The longitude of each photovoltaic module Indicates the first The latitude of each photovoltaic module; Represents the world coordinate system. The horizontal axis of each photovoltaic module Represents the world coordinate system. The vertical axis of each photovoltaic module; Based on respectively and Sort the arrays in ascending order. and ; （3）； （4）； ; Represents the sorted array The first in One data point; Sorted array The first in One data point; will be in array The photovoltaic modules corresponding to the sorting are divided into different rows using a recursive algorithm; the array will be used as the sorting method. The photovoltaic modules are sorted into different columns using a recursive algorithm; a sorting matrix A with row and column numbers is obtained for all photovoltaic modules; the elements in sorting matrix A are represented using the GPS location information of the corresponding photovoltaic modules, and a GPS matrix corresponding to sorting matrix A is constructed. : （4）； in, Representing the GPS matrix The first in Line number A series of photovoltaic modules; , ; Based on the GPS information of the four corner points of the photovoltaic module support, the maximum number of rows and columns of the support needed to be photographed in each photo is set, the maximum width W of the drone is obtained, and the height H of the drone shooting point is calculated based on the digital elevation information. Traversing the array The obtained row sorting is used to find the corresponding column in the column sorting using the GPS information of the bracket, thereby determining the row and column coordinates of the bracket and the corresponding coordinates in the GPS matrix; 203) Dynamically define the shooting range based on the area of ​​the photovoltaic module and the GPS matrix L of the photovoltaic module; Establish GPS matrix Specifically, it includes the following steps: using a recursive algorithm recursively. Array, determine if photovoltaic modules are in the same column; The array elements are iterated from smallest to largest to find supports located in the same column. To determine if supports are in the same column, the leftmost and rightmost x-axis coordinate intervals of two adjacent supports are calculated. The union of these x-axis coordinate intervals is then calculated. If the overlap between the union of these intervals and the x-axis coordinate interval of either support is greater than a certain value, then the two supports are in the same column. The GPS matrix is ​​then obtained. Column sorting; Use a recursive algorithm to recursively process For arrays, the criterion for determining whether elements are in the same row is: The array elements are iterated from smallest to largest to find supports in the same row. For each support in a row, the Y-axis coordinates of the top and bottom edges of adjacent supports are calculated. The union of these Y-axis coordinates is then calculated. If the overlap between the union of these Y-axis coordinates and the Y-axis coordinates of either support is greater than a certain value, then the two supports are in the same row, and the GPS matrix is ​​obtained. Sort by row.

7. A high-efficiency photovoltaic power station drone inspection system according to claim 6, characterized in that, The working process of the 2D orthophoto panoramic image generation unit includes the following steps: 101) Control the drone group to take photos directly above the photovoltaic power station; 102) Create a two-dimensional orthophoto panoramic image based on the collected photos taken directly above the photovoltaic power station to obtain digital elevation information.

8. The high-efficiency photovoltaic power station drone inspection system according to claim 6, characterized in that, The shooting location confirmation unit's working process specifically includes the following steps: 301) Based on the GPS matrix The location of the components determines the GPS coordinates of each shooting point of the drone; 302) Based on the GPS coordinates of the shooting point and the shooting height H, the drone shooting position information is generated, and the drone is controlled to adjust the yaw angle, gimbal angle, focal length and drone GPS deviation compensation to keep the drone at a parallel altitude during operation; The specific steps involved in performing the inspection unit's work are as follows: 401) Convert the drone's captured location information into a drone flight path file in kml format; generate kml format text from the waypoint information according to the kml format requirements; 402) Import the drone flight path file into the drone remote controller and execute the flight mission.

Images