An unmanned aerial vehicle adaptive control system for image cropping

Abstract

The application discloses a kind of unmanned aerial vehicle adaptive control system for image cropping, comprising: unmanned aerial vehicle camera attitude control module, unmanned aerial vehicle camera attitude control module controls unmanned aerial vehicle camera and the midpoint of measured photovoltaic panel is in relative vertical state;Unmanned aerial vehicle camera attitude control module also controls the flight height and coordinate of unmanned aerial vehicle according to standard vertical relative height;Standard vertical relative height is theoretical value, and is determined according to the actual parameter of measured photovoltaic panel pixel size, known unmanned aerial vehicle camera parameter and measured photovoltaic panel in system setting;Image cropping module, image cropping module carries out image cropping according to the standard vertical relative height of unmanned aerial vehicle camera shooting image, the real-time vertical height of shooting image and the measured photovoltaic panel pixel size in system setting;The application has the beneficial effect that the image difference of different photovoltaic panels obtained is small, and cropping is more convenient.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of unmanned aerial vehicle control and image cropping, in particular to an unmanned aerial vehicle adaptive control system for image cropping. BACKGROUND

[0002] In the unmanned aerial vehicle photovoltaic inspection, due to the differences in the distribution elevation and inclination angle of photovoltaic panels of a photovoltaic power station, when the unmanned aerial vehicle cruises at a fixed height and focuses on high-definition orthographic photography, the size of the photovoltaic panel string in different photos varies due to the change in the relative distance of photography, in order to facilitate AI recognition and positioning labeling in the later stage, the size of the photovoltaic panel string in the photo needs to be unified to further improve the management level.

[0003] At present, the image acquisition and analysis system of most unmanned aerial vehicles usually directly crops and splices the acquired images by using a neural network according to pixel points or residual errors, and the following defects exist, due to the lens angle of photography, the change in the flight height of the unmanned aerial vehicle and the differences in the altitude and inclination angle of the different photovoltaic panels being photographed, when different target images are acquired, there will be certain image pixel differences, which will affect the cropping accuracy, and due to the influence of factors such as storage picture memory and the total amount of images to be photographed, the image clarity should be ensured to be the best in the case of ensuring that the image shooting task is completed as much as possible, so as to facilitate subsequent cropping and labeling. SUMMARY

[0004] The present application aims to solve at least one of the technical problems existing in the prior art, and for this purpose, the present application provides an unmanned aerial vehicle adaptive control system for image cropping, which is used to solve the technical problem of insufficient cropping accuracy caused by the influence of factors such as altitude on pixels in the prior art.

[0005] To achieve the above-mentioned purpose, the present application provides an unmanned aerial vehicle adaptive control system for image cropping, which comprises:

[0006] An unmanned aerial vehicle camera attitude control module, which controls the unmanned aerial vehicle camera and the midpoint of the measured photovoltaic panel to be in a relative vertical state;

[0007] The unmanned aerial vehicle camera attitude control module also controls the flight height and coordinates of the unmanned aerial vehicle according to the standard vertical relative height;

[0008] The standard vertical relative height is a theoretical value, which is determined according to the pixel size of the measured photovoltaic panel, the known parameters of the unmanned aerial vehicle camera and the actual parameters of the measured photovoltaic panel in the system;

[0009] An image cropping module crops the image according to a standard vertical relative height of an image captured by a UAV camera, a real-time vertical height of the captured image, and a pixel size of a measured photovoltaic panel in the system;

[0010] To ensure that the acquired image is a standard image, the camera should be in a relatively vertical state with the midpoint of the photographed plane, rather than a horizontal vertical state, with the photographed plane as the horizontal plane. Secondly, it is also necessary to ensure that the image captured by the camera meets the requirements of the system, so the flight height, i.e., the vertical distance between the camera and the photographed plane, needs to be adjusted.

[0011] Further, the UAV camera posture control module comprises the following steps:

[0012] S2-1: The UAV acquires an image plan view of the measured photovoltaic panel;

[0013] S2-2: Four vertices of the measured photovoltaic panel in the image plan view are extracted according to an edge detection algorithm, and the four vertices are defined as targets 1-4, and the corresponding Cartesian coordinates of the targets 1-4 are acquired by the UAV GPS module;

[0014] S2-3: The midpoint coordinates of the measured photovoltaic panel in the image plan view and the inclination angle of the measured photovoltaic panel are acquired according to the Cartesian coordinates (X N ,Y N ,Z N ) of the four targets, and N ∈ (1, 4);

[0015] S2-4: The UAV posture is adjusted according to the midpoint coordinates of the measured photovoltaic panel, the standard vertical relative height, the flight height of the UAV, and the inclination angle of the measured photovoltaic panel.

[0016] Further, the specific method of S2-2 is as follows:

[0017] The image is read and converted into a gray-scale image; the Canny edge detection algorithm is used to detect the edge information of the image, i.e., the approximate outline of the measured photovoltaic panel; the OpenCV contour detection is further used to obtain the rectangular contour of the measured photovoltaic panel in the approximate outline; the pixel coordinates of the four vertices of the rectangular contour of the measured photovoltaic panel are screened and recorded as targets 1-4;

[0018] The pixel coordinates of the targets 1-4 are converted into the Cartesian coordinates (X N ,Y N ,Z N ) of the targets 1-4 in the GPS module of the UAV, which is specifically obtained by inverting the pixel coordinates by the focal length parameter f in the intrinsic matrix of the UAV camera;

[0019] The pixel coordinates can directly obtain the coordinate values of the pixel points in the three-dimensional space, and the pixel coordinates of the four vertices of the rectangular contour of the measured photovoltaic panel are extracted by the contour algorithm and then inverted to obtain the coordinate values of the four vertices of the measured photovoltaic panel in the three-dimensional space.

[0020] Further, the specific method of S2-3 is as follows:

[0021] Determine the midpoint coordinates of the measured photovoltaic panel: according to the average values of the coordinate values of the four targets on the X axis, Y axis and Z axis, respectively, the average values of the coordinate values of the four targets on the X axis, Y axis and Z axis are determined. N ,Y N ,Z N ) respectively;

[0022] Determine the inclination angle of the rectangular plane represented by the measured photovoltaic panel: randomly select any three coordinate values from the Cartesian coordinates (X N ,Y N ,Z N ) of the four targets and the midpoint coordinates of the measured photovoltaic panel to solve the normal vector of the rectangular plane, and then calculate the inclination angle of the rectangular plane according to the angle between the normal vector and the X-Y horizontal plane of the Cartesian coordinate system of the GPS module of the unmanned aerial vehicle, as follows:

[0023] Determine the normal vector of the rectangular plane, and randomly select any three coordinate values from the Cartesian coordinates (X N ,Y N ,Z N ) of the four targets and the midpoint coordinates of the measured photovoltaic panel, and mark them as P1, P2 and P3 respectively;

[0024] Establish vectors and The normal vector of the rectangular plane is the cross product of vectors and ;

[0025] Then calculate the inclination angle according to the normal vector of the rectangular plane and the X-Y horizontal plane normal vector of the Cartesian coordinate system of the GPS module of the unmanned aerial vehicle, as shown in the following formula:

[0026]

[0027] Wherein, n is the normal vector of the rectangular plane;

[0028] k is the X-Y horizontal plane normal vector of the Cartesian coordinate system of the GPS module of the unmanned aerial vehicle.

[0029] Further, the specific method of S2-4 is as follows:

[0030] Obtain the current flight height of the unmanned aerial vehicle by the GPS module of the unmanned aerial vehicle;

[0031] Adjust the flight height, i.e. z f , specifically: 1.5Hsinθ+z M ≥z f ≥1.2Hsinθ+z M ; wherein H is the standard vertical relative height; θ is the measured photovoltaic panel tilt angle; z M is the z coordinate in the measured photovoltaic panel midpoint coordinate;

[0032] The z f after adjusting the flight height is combined with the measured photovoltaic panel midpoint coordinate in step three to solve the distance the UAV needs to translate, specifically:

[0033] The ratio of the x coordinate, y coordinate and z coordinate of the measured photovoltaic panel midpoint in the Cartesian coordinate system is solved;

[0034] According to the above ratio and the z f coordinate of the UAV in the Cartesian coordinate system, the horizontal coordinate (x f , y f ) of the UAV at this height is directly solved, i.e. the horizontal coordinate that should be moved to at this height;

[0035] According to the comparison of the horizontal coordinate of the UAV in the Cartesian coordinate system and the above estimated horizontal coordinate (x f , y f ), the UAV adjusts its flight position;

[0036] According to the measured photovoltaic panel tilt angle, the UAV camera is further adjusted, specifically: the UAV camera adjusts its angle with the UAV as the horizontal plane, ensuring that the angle between the UAV camera and the horizontal plane represented by the UAV is also the measured photovoltaic panel tilt angle;

[0037] There are two purposes for obtaining the measured photovoltaic panel midpoint coordinate: first, according to the measured photovoltaic panel midpoint coordinate, determine the coordinate that the UAV should fly to, because the camera of the UAV needs to be in a relatively vertical state with the measured photovoltaic panel; second, according to the slope of the photovoltaic panel, adjust the slope of the camera to ensure that the shooting angle of the camera is relatively vertical to the plane of the measured photovoltaic panel;

[0038] The standard height is a theoretical value obtained by back-calculation according to the obtained final picture, the actual object to be photographed and various parameters of the camera in an ideal state. However, in actual shooting, the shooting angle is also a theoretical value in the ideal state of shooting only the measured photovoltaic panel, and if there is any deviation of the unmanned aerial vehicle, the full view of the measured photovoltaic panel cannot be shot. Therefore, the operation of increasing the height in the ideal state is needed to expand the shooting angle and range of the camera, but the height cannot be infinitely increased, otherwise the pixel of the measured photovoltaic panel image after final cutting cannot meet the requirements. The height increase is in the range of 0.2-0.5 of the standard height.

[0039] Further, the standard vertical height is obtained by the following steps:

[0040] S6-1: input the pixel size I of the measured photovoltaic panel to be obtained;

[0041] S6-2: input the camera parameters of the unmanned aerial vehicle, including focal length F and camera sensor size D;

[0042] S6-3: input the actual size i of the measured photovoltaic panel;

[0043] S6-4: directly obtain the standard vertical height H=(F*I) / (D*i).

[0044] Further, the specific steps of the image cutting module for cutting the image are as follows:

[0045] S7-1: measure the relative position between the camera of the unmanned aerial vehicle and the measured photovoltaic panel by a direct distance measurement method, that is, the real-time vertical height of the shooting image;

[0046] S7-2: cut the image according to the distance measurement result, the standard vertical relative height and the real-time pixel size of the measured photovoltaic panel. The cutting result is H / Hi x the real-time pixel size of the measured photovoltaic panel, wherein H is the standard vertical height, and Hi is the real-time vertical height of the shooting image. According to this, the four edges of the shooting image are uniformly cut;

[0047] The image pixel shot at the real-time vertical height should be cut according to the input pixel size I of the measured photovoltaic panel to be obtained, that is, the image is cut according to the ratio of the standard vertical relative height to the actual shooting height.

[0048] Further, the direct distance measurement method includes two kinds: one is GPS distance measurement according to the coordinates of the unmanned aerial vehicle after the camera attitude control module controls the flight of the unmanned aerial vehicle and the coordinates of the midpoint of the measured photovoltaic panel; the other is image distance measurement according to the image of the measured photovoltaic panel shot by the camera of the unmanned aerial vehicle and the camera parameters of the unmanned aerial vehicle.

[0049] The beneficial effect of the present application is: ensure that the shooting angle of the unmanned aerial vehicle camera is perpendicular to the plane of the measured photovoltaic panel, and control the unmanned aerial vehicle shooting height to be kept in a relative range, so that the difference between the images of different photovoltaic panels is small, and finally the image is cropped in a way according to the theoretical best pixel acquisition height and the actual shooting height. It is more convenient. BRIEF DESCRIPTION OF DRAWINGS

[0050] In order to more clearly illustrate the technical solutions of the embodiments of the present application and the prior art, the drawings needed in the embodiments and the prior art description will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present application, and those skilled in the art can obtain other drawings according to these drawings without creative labor.

[0051] Figure 1 The system schematic diagram of the present application is shown in the figure.

[0052] Figure 2 The shooting angle and cropping schematic diagram of the present application is shown in the figure. DETAILED DESCRIPTION

[0053] In order to make the purpose, technical solutions and advantages of the present application more clear, the present application will be described and explained below in combination with the drawings and embodiments. It should be understood that the specific embodiments described here are only used to explain the present application, and are not used to limit the present application. Based on the embodiments provided by the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0054] Obviously, the drawings in the following description are only some examples or embodiments of the present application, and those skilled in the art can apply the present application to other similar situations without creative labor.

[0055] In addition, it can also be understood that although the efforts made in this development process may be complex and lengthy, some design, manufacture or production changes based on the technical content disclosed in the present application are only conventional technical means for those skilled in the art related to the disclosure of the present application, and should not be understood as insufficient disclosure of the present application.

[0056] If not specifically stated, all embodiments and optional embodiments of the present application can be combined with each other to form new technical solutions.

[0057] Please refer to Figure 1 The system flowchart of the present application includes:

[0058] The unmanned aerial vehicle camera attitude control module controls the unmanned aerial vehicle camera to be in a relative vertical state with the midpoint of the measured photovoltaic panel.

[0059] The unmanned aerial vehicle camera attitude control module also controls the flight height of the unmanned aerial vehicle according to the standard vertical relative height.

[0060] The standard vertical relative height is a theoretical value, and is determined according to the pixel size of the measured photovoltaic panel set in the system, the known parameters of the unmanned aerial vehicle camera, and the actual parameters of the measured photovoltaic panel.

[0061] The image cropping module crops the image according to the standard vertical relative height of the image captured by the unmanned aerial vehicle camera, the real-time vertical height of the captured image, and the pixel size of the measured photovoltaic panel set in the system.

[0062] Specifically,

[0063] To ensure that the shooting angle of the unmanned aerial vehicle camera is in a relative vertical state with the plane of the measured photovoltaic panel, the unmanned aerial vehicle camera attitude control module processes the flight attitude and the camera of the unmanned aerial vehicle as follows:

[0064] The flight attitude part is mainly adjusted according to the coordinate value of the midpoint coordinate of the measured photovoltaic panel in the GPS three-dimensional space. The first step is to directly obtain the image plan view of the measured photovoltaic panel; read the image and convert it into a gray image; detect the edge information of the image, i.e. the approximate outline of the measured photovoltaic panel, by using the Canny edge detection algorithm; further detect the rectangular outline of the measured photovoltaic panel in the approximate outline by using the OpenCV contour detection; and screen the pixel coordinates of the four vertices of the rectangular outline of the measured photovoltaic panel, wherein the pixel coordinates of the four vertices are defined as targets 1-4. The pixel coordinates can be inversely calculated to obtain the corresponding Cartesian coordinates of the targets 1-4 in the GPS module of the unmanned aerial vehicle, i.e. the spatial coordinates of the four vertex coordinates of the measured photovoltaic panel in the GPS geodetic coordinate system, so as to solve the position of the center point of the measured photovoltaic panel in the GPS geodetic coordinate system. The unmanned aerial vehicle only needs to adjust its position in the GPS geodetic coordinate system according to the corresponding GPS adjustment. Figure 2 As shown in FIG. 1, the shooting angle of the unmanned aerial vehicle should be in a relative vertical state with the plane of the measured photovoltaic panel. At this time, the plane of the measured photovoltaic panel should be the horizontal plane. Therefore, to achieve the relative vertical state between the shooting angle of the unmanned aerial vehicle and the plane of the measured photovoltaic panel, the position of the unmanned aerial vehicle should be on the straight line from the origin of the GPS geodetic coordinate system to the midpoint coordinate of the measured photovoltaic panel in the GPS geodetic coordinate system. In addition, the camera angle of the unmanned aerial vehicle camera also needs to be adjusted to capture the midpoint of the measured photovoltaic panel.

[0065] The first point: adjust the angle between the camera and the horizontal plane of the UAV to θ, which is the angle corresponding to the tilt angle of the measured photovoltaic panel relative to the horizontal plane of the ground. In this way, the observation angle of the camera is perpendicular to the horizontal plane of the measured photovoltaic panel under ideal conditions when the measured photovoltaic panel is tilted.

[0066] The method for calculating the θ angle is as follows: randomly select any three coordinate values from the Cartesian coordinates (X N ,Y N ,Z N ) of the four targets and the midpoint coordinates of the measured photovoltaic panel to solve the normal vector of the rectangular plane, and then calculate the tilt angle of the rectangular plane according to the angle between the normal vector and the X-Y horizontal plane of the Cartesian coordinate system of the GPS module of the UAV.

[0067] Determine the normal vector of the rectangular plane, and randomly select any three coordinate values from the Cartesian coordinates (X N ,Y N ,Z N ) of the four targets and the midpoint coordinates of the measured photovoltaic panel, and denote them as P1, P2, and P3, respectively.

[0068] Establish vectors and The normal vector of the rectangular plane is the cross product of vectors and .

[0069] Then calculate the tilt angle according to the normal vector of the rectangular plane and the X-Y horizontal plane normal vector of the Cartesian coordinate system of the GPS module of the UAV, as shown in the following formula:

[0070]

[0071] Where n is the normal vector of the rectangular plane.

[0072] k is the X-Y horizontal plane normal vector of the Cartesian coordinate system of the GPS module of the UAV.

[0073] Secondly, ensure the drone can move to a position where the camera can correctly observe the photovoltaic panel under test. Specifically, the drone's position should be on a straight line from the origin of the GPS geodetic coordinate system to the midpoint of the photovoltaic panel. However, due to image pixel requirements, the drone's flight altitude (i.e., shooting distance) needs to be limited. Based on the derived theoretical standard vertical height H, its flight altitude and the horizontal coordinates adjusted accordingly should meet the shooting distance requirements. To ensure a complete view of the photovoltaic panel, it's necessary to raise the drone's height under this ideal condition to expand the camera's field of view and shooting range. However, this elevation cannot be unlimited; otherwise, the final cropped image of the photovoltaic panel will not meet the pixel requirements. Therefore, the elevation should be within 0.2 to 0.5 times the standard height, i.e., the flight altitude should be 1.5Hsinθ+z. M ≥z f ≥1.2Hsinθ+z M Where θ is the tilt angle of the photovoltaic panel being measured, because the midpoint coordinates of the UAV and the photovoltaic panel being measured should be on the same oblique line in the GPS geodetic coordinate system; z M Let z be the z-coordinate of the midpoint of the photovoltaic panel being measured in the GPS geodetic coordinate system. f It should be an altitude that is raised above the midpoint of the measured photovoltaic panel; based on z f For (x) f y f Solve for the ratio between the coordinates of the midpoint of the photovoltaic panel being measured (the solution can be directly referenced here), that is, the position that the UAV should move to in the GPS geodetic coordinate system.

[0074] Furthermore:

[0075] The specific steps for obtaining the standard vertical height H are as follows: Enter the pixel size I of the photovoltaic panel to be measured; enter the drone camera parameters, including: focal length F, camera sensor size D; enter the actual size i of the photovoltaic panel to be measured; directly calculate the standard vertical height as: H = (F*I) / (D*i). The pixel size of the photovoltaic panel to be measured is set according to the drone's memory and task requirements (number of shots), and is set by the user.

[0076] The image cropping module crops the image according to the influence relationship of the size of the photo field of view (i.e. the ratio of the flight height) on the pixels, specifically: the relative position between the unmanned aerial vehicle camera and the measured photovoltaic panel is measured by a direct ranging method, i.e. the real-time vertical height of the photographed image; the image is cropped according to the ranging result, the standard vertical relative height and the real-time pixel size of the measured photovoltaic panel, and the cropping result is H / Hi x the real-time pixel size of the measured photovoltaic panel, wherein H is the standard vertical height, and Hi is the real-time vertical height of the photographed image, and the four edges of the photographed image are uniformly cropped accordingly; wherein the direct ranging method includes two kinds: one is to perform GPS ranging according to the coordinates after the unmanned aerial vehicle camera attitude control module controls the unmanned aerial vehicle to fly and the coordinates of the midpoint of the measured photovoltaic panel; the other is to perform image ranging according to the image of the measured photovoltaic panel photographed by the unmanned aerial vehicle camera and the parameters of the unmanned aerial vehicle camera.

[0077] Therefore, the present application ensures the accuracy of the cropped image by the following operations:

[0078] The camera attitude is adjusted according to the attitude of the measured photovoltaic panel, and the flight height of the unmanned aerial vehicle is adjusted to further adjust the position of the unmanned aerial vehicle for observing the photovoltaic panel, so as to ensure that the shooting angle of the unmanned aerial vehicle is perpendicular to the measured photovoltaic panel.

[0079] The above describes one or more embodiments of the present application in great detail, but the content described is only a specific example of the present application and cannot be considered to limit the application range of the present application. Any other method and change according to the content of the present application shall be within the scope of the patent protection of the present application.

Claims

1. A UAV adaptive control system for image cropping, characterized in that, The application relates to a photovoltaic panel testing system, which comprises the following parts: A UAV camera attitude control module, which controls the relative vertical state between the UAV camera and the midpoint of the measured photovoltaic panel; The UAV camera attitude control module further controls the flight height and coordinates of the UAV according to the standard vertical relative height; The standard vertical relative height is a theoretical value, which is determined according to the pixel size of the measured photovoltaic panel, the known UAV camera parameters and the actual parameters of the measured photovoltaic panel in the system; An image cropping module, which crops the image according to the standard vertical relative height of the image taken by the UAV camera, the real-time vertical height of the taken image and the pixel size of the measured photovoltaic panel set in the system; The UAV camera attitude control module comprises the following steps: S2-1: the UAV obtains the image plane of the measured photovoltaic panel; S2-2: four vertices of the measured photovoltaic panel in the image plane are extracted according to an edge detection algorithm, the four vertices are defined as targets 1-4, and the corresponding Cartesian coordinates of the targets 1-4 are obtained by the UAV GPS module; S2-3: Cartesian coordinates of 4 targets Obtaining the midpoint coordinates of the measured photovoltaic panel and the tilt angle of the measured photovoltaic panel in the image plan view, N ∈ (1, 4); S2-4: the attitude of the UAV is adjusted according to the midpoint coordinates of the measured photovoltaic panel, the standard vertical relative height, the flight height of the UAV and the inclination angle of the measured photovoltaic panel; The specific method of S2-4 is as follows: The current flight height of the UAV is obtained by the UAV GPS module; Adjust the flight height according to the standard vertical relative height and the measured inclination angle of the photovoltaic panel, that is , specifically: ; wherein H is the standard vertical relative height; is the measured inclination angle of the photovoltaic panel; is the z coordinate in the midpoint coordinate of the measured photovoltaic panel; by adjusting the flight height The distance that the UAV needs to translate is solved in combination with the midpoint coordinates of the measured photovoltaic panel in step S2-3, specifically: The ratio of the x coordinate, the y coordinate and the z coordinate of the midpoint of the measured photovoltaic panel in the Cartesian coordinate system is calculated; According to the above ratio and the Cartesian coordinate system of the UAV The coordinate directly obtains the horizontal coordinate of the UAV at this height The horizontal coordinate that should be moved to at this height; According to the comparison between the horizontal coordinates of the contrast unmanned aerial vehicle in the Cartesian coordinate system and the above-mentioned estimated horizontal coordinates of the position, the unmanned aerial vehicle adjusts the flight position of itself; The UAV camera is further adjusted according to the inclination angle of the measured photovoltaic panel, specifically, the angle of the UAV camera is adjusted with the UAV as the horizontal plane, and the included angle between the UAV camera and the horizontal plane represented by the UAV is also ensured to be the inclination angle of the measured photovoltaic panel.

2. The unmanned aerial vehicle adaptive control system for image cropping of claim 1, wherein, The specific method of S2-2 is as follows: The image is read and converted into a gray image; the Canny edge detection algorithm is adopted to detect the edge information of the image, that is, the approximate outline of the measured photovoltaic panel; the rectangular outline of the measured photovoltaic panel in the approximate outline is further detected by using the OpenCV contour detection; the pixel coordinates of the four vertices of the rectangular outline of the measured photovoltaic panel are screened and recorded as targets 1-4; According to the pixel coordinates of the targets 1~4, the pixel coordinates are converted into the Cartesian coordinates of the targets 1~4 in the GPS module of the unmanned aerial vehicle , and the pixel coordinates are specifically inversely obtained by the focal length parameter f in the intrinsic matrix of the unmanned aerial vehicle camera.

3. The unmanned aerial vehicle adaptive control system for image cropping of claim 1, wherein, The specific method of S2-3 is as follows: determining the midpoint coordinates of the measured photovoltaic panel: according to the cartesian coordinates of the four targets the average value of the coordinate values on the X-axis, Y-axis, and Z-axis, respectively, is determined; Determine the tilt angle of the rectangular plane represented by the measured photovoltaic panel: randomly select the Cartesian coordinates of four targets And any three coordinate values in the midpoint coordinates of the measured photovoltaic panel to solve the normal vector of the rectangular plane, and according to the angle between the normal vector and the X-Y horizontal plane of the Cartesian coordinate system of the unmanned aerial vehicle with GPS module, the tilt angle of the rectangular plane is calculated, as follows: Determining the normal vector of the rectangular plane from the Cartesian coordinates of the 4 targets and the three arbitrarily selected coordinate values from the midpoint coordinates of the measured photovoltaic panel are denoted as ; establishing a vector and The normal vector of the rectangular plane is the cross product of the vectors and ; The inclination angle is calculated according to the normal vector of the rectangular plane and the X-axis-Y-axis horizontal plane normal vector of the Cartesian coordinate system of the GPS module of the UAV, and the specific formula is as shown in the following formula: ； Wherein, n is the normal vector of the rectangular plane; K is the X-axis-Y-axis horizontal plane normal vector of the Cartesian coordinate system of the GPS module of the UAV.

4. The unmanned aerial vehicle adaptive control system for image cropping of claim 1, wherein, The specific steps for obtaining the standard vertical height are as follows: S6-1: the pixel size I of the measured photovoltaic panel to be obtained is inputted; S6-2: the parameters of the UAV camera are inputted, including the focal length F and the camera sensor size D; S6-3: the actual size i of the measured photovoltaic panel is inputted; S6-4: the standard vertical height is directly calculated as H= (F*I) / (D*i).

5. The unmanned aerial vehicle adaptive control system for image cropping of claim 1, wherein, The specific steps for the image cropping module to crop the image are as follows: S7-1: the relative position between the UAV camera and the measured photovoltaic panel is measured by a direct ranging method, that is, the real-time vertical height of the taken image. S7-2: According to the ranging result, the standard vertical relative height and the real-time measured photovoltaic panel pixel size, the image is cropped, and the cropping result is H / Hi x the real-time measured photovoltaic panel pixel size, wherein H is the standard vertical height, and Hi is the real-time vertical height of the photographed image, according to which the four edges of the photographed image are uniformly cropped.

6. The UAV adaptive control system for image cropping of claim 5, wherein, The direct ranging method includes two kinds: One is to control the coordinates of the unmanned aerial vehicle after the unmanned aerial vehicle camera attitude control module controls the flight and the coordinates of the measured photovoltaic panel midpoint to perform GPS ranging; Another is to perform image ranging according to the measured photovoltaic panel image photographed by the unmanned aerial vehicle camera and the unmanned aerial vehicle camera parameters.

Images