A method and apparatus for extracting vegetation information in photovoltaic panel shaded areas

Abstract

This invention discloses a method and apparatus for extracting vegetation information in photovoltaic panel shading areas. The method involves collecting point cloud data and multispectral images of the photovoltaic panel installation area, dividing the point cloud data into multiple grid units, determining the laser point with the maximum elevation value in each grid unit based on the point cloud data, and acquiring the point cloud attribute information of the laser point. The method then extracts the spectral reflectance information of each grid unit from the multispectral image, and superimposes the point cloud attribute information and spectral reflectance information belonging to the same grid unit to obtain total superimposed data. Vegetation information in the photovoltaic panel shading area is then selected from the total superimposed data and corrected based on a reflectance correction coefficient to obtain the target vegetation information. This invention, by fusing point cloud data and multispectral imagery, separates and identifies vegetation information under photovoltaic panel shading. It utilizes rasterization processing and reflectance correction to achieve accurate extraction of vegetation physiological and ecological information in the shaded area.

Description

Technical Field

[0001] This invention relates to the field of mine ecological restoration technology, specifically to a method and apparatus for extracting vegetation information in areas shaded by photovoltaic panels. Background Technology

[0002] In ecological restoration projects in mining areas, the installation of photovoltaic panels has become a common method, achieving the dual goals of photovoltaic power generation and ecological restoration. However, because photovoltaic panels are typically laid out in multiple rows in a regular array, they occupy a large area, and vegetation between and beneath the panels is affected by varying degrees of shading. To achieve accurate monitoring and scientific management of vegetation growth in the restoration area, current methods mainly rely on field surveys or remote sensing technology to periodically obtain physiological and ecological parameters of the vegetation, such as vegetation height, coverage, leaf area index, and various vegetation indices.

[0003] However, the aforementioned mainstream methods all have obvious limitations: field surveys are costly and inefficient, making it difficult to achieve large-scale continuous monitoring; while remote sensing technology based on satellite or drone orthophotos, although it can cover a large area, cannot effectively obtain or accurately identify vegetation information in areas shaded by photovoltaic panels, resulting in incomplete monitoring data and affecting the overall assessment and precise management of ecological restoration effects. Summary of the Invention

[0004] This invention provides a method and apparatus for extracting vegetation information in areas shaded by photovoltaic panels, in order to solve the problem of how to effectively obtain or accurately identify vegetation information over a large area shaded by photovoltaic panels.

[0005] In a first aspect, the present invention provides a method for extracting vegetation information in a photovoltaic panel shading area, the method comprising:

[0006] Point cloud data and multispectral images of the photovoltaic panel installation area are collected, and the point cloud data is divided into multiple grid units. At least one photovoltaic panel is configured in the photovoltaic panel installation area.

[0007] Based on the point cloud data, determine the laser point with the maximum elevation value in each grid cell, and obtain the point cloud attribute information of the laser point;

[0008] The spectral reflectance information of each grid cell is extracted from the multispectral image, and the point cloud attribute information and spectral reflectance information belonging to the same grid cell are superimposed to obtain the total superimposed data.

[0009] Vegetation information of the photovoltaic panel shading area is filtered out from the total superimposed data, and the vegetation information is corrected based on the reflectivity correction coefficient to obtain the target vegetation information. The photovoltaic panel shading area is the area in the photovoltaic panel installation area that is shaded by the photovoltaic panel.

[0010] This invention collects point cloud data and multispectral imagery of the photovoltaic panel installation area, dividing the point cloud data into multiple grid cells. Based on the point cloud data, it identifies the laser point with the highest elevation value in each grid cell and acquires the point cloud attribute information of the laser point. It extracts the spectral reflectance information of each grid cell from the multispectral imagery, and superimposes the point cloud attribute information and spectral reflectance information belonging to the same grid cell to obtain the total superimposed data. From the total superimposed data, it filters out vegetation information in the photovoltaic panel shading area and corrects the vegetation information based on a reflectance correction coefficient to obtain the target vegetation information. This invention, by fusing point cloud data and multispectral imagery, separates and identifies vegetation information under photovoltaic panel shading. It utilizes rasterization processing and reflectance correction to accurately extract the physiological and ecological information of vegetation in the shaded area.

[0011] In one optional implementation, the acquisition of point cloud data and multispectral imagery of the photovoltaic panel installation area includes:

[0012] Obtain the distance of the lidar's emitted pulse and the tilt angle of the gimbal;

[0013] The point cloud data and multispectral images of the photovoltaic panel installation area are collected by a drone, and the flight altitude of the drone during data collection is set according to the distance of the laser radar pulse and the tilt angle of the gimbal:

[0014]

[0015] In the formula, The altitude of the drone; The distance at which the lidar emits pulses; This refers to the tilt angle of the gimbal;

[0016] The process involves obtaining parameters of the photovoltaic panel, including its trailing edge height, underside width, and the width between adjacent panels. The tilt angle of the gimbal is then determined based on these parameters.

[0017]

[0018] In the formula, This refers to the tilt angle of the gimbal; The height of the trailing edge of the photovoltaic panel; The width of the photovoltaic panel is its underside. This refers to the width between two adjacent photovoltaic panels. The tilt angle of the photovoltaic panel is given.

[0019] In one alternative implementation, vegetation information for the photovoltaic panel shading area is filtered from the total overlay data:

[0020] The total superimposed data is input into a pre-trained random forest decision tree model. The random forest decision tree model is then used to remove the first superimposed data of the photovoltaic panel from the total superimposed data to obtain the vegetation information of the photovoltaic panel shading area.

[0021] In one optional implementation, the point cloud attribute information includes the point cloud geometric information of the laser point, the echo intensity, and the laser point reflectivity, and the spectral reflectivity information includes red, green, and blue band spectral reflectivity data.

[0022] The step of using the random forest decision tree model to remove the first superimposed data of the photovoltaic panels from the total superimposed data to obtain the vegetation information of the photovoltaic panel shading area includes:

[0023] Based on the point cloud geometric information, echo intensity, laser point reflectivity, and red, green, and blue band spectral reflectivity characteristics of the total superimposed data, an initial model for identifying the photovoltaic panel is constructed.

[0024] The initial model is trained until the overall classification score of the initial model is greater than the first threshold, the overall classification score of the photovoltaic panel category is greater than the second threshold, and the overall classification score of the non-photovoltaic panel category is greater than the third threshold, thus obtaining the random forest decision tree model.

[0025] The trained random forest decision tree model identifies the photovoltaic panels in the photovoltaic panel installation area, removes the first superimposed data of the photovoltaic panels, and outputs the vegetation information of the photovoltaic panel shading area.

[0026] In one optional implementation, the step of correcting the vegetation information based on a reflectance correction coefficient to obtain target vegetation information includes:

[0027] The vegetation information in the photovoltaic panel shading area is corrected based on the following formula:

[0028]

[0029] In the formula, For target vegetation information; Vegetation information to be corrected; This is the reflectivity correction factor.

[0030] In one optional embodiment, the reflectivity correction coefficient includes a first reflectivity correction coefficient under the photovoltaic panel, and the method further includes:

[0031] The system obtains a first radiation value of the photovoltaic panel installation area directly exposed to sunlight, a second radiation value of the photovoltaic panel installation area scattered by sunlight, and parameters of the photovoltaic panel. The parameters of the photovoltaic panel include the light transmittance of the photovoltaic panel, the length of the point to be corrected from the vertical point of the trailing edge of the photovoltaic panel, the height of the trailing edge of the photovoltaic panel, the width of the photovoltaic panel at the bottom, and the width between two adjacent photovoltaic panels.

[0032] The first reflectivity correction coefficient is determined based on the first radiation value, the second radiation value, and the parameters of the photovoltaic panel:

[0033]

[0034] In the formula, This is the first reflectivity correction coefficient; The first radiation value under direct sunlight; This is the second value of solar radiation scattered by the sun; The transmittance of the photovoltaic panel is denoted as . The distance from the point to be corrected to the vertical point of the trailing edge of the photovoltaic panel is denoted as ; The height of the trailing edge of the photovoltaic panel; The width of the photovoltaic panel is its underside. This refers to the width between two adjacent photovoltaic panels.

[0035] In an optional embodiment, the reflectivity correction coefficient further includes a second reflectivity correction coefficient between photovoltaic panels, and the method further includes:

[0036] The second reflectivity correction coefficient is determined based on the first radiation value, the second radiation value, and the parameters of the photovoltaic panel:

[0037]

[0038] In the formula, This is the second reflectivity correction coefficient; The first radiation value under direct sunlight; This is the second value of solar radiation scattered by the sun; The transmittance of the photovoltaic panel is denoted as . The distance from the point to be corrected to the vertical point of the trailing edge of the photovoltaic panel is denoted as ; The height of the trailing edge of the photovoltaic panel; The width of the photovoltaic panel is its underside. This refers to the width between two adjacent photovoltaic panels.

[0039] Secondly, the present invention provides a vegetation information extraction device for photovoltaic panel shading areas, the device comprising:

[0040] The data acquisition module is used to acquire point cloud data and multispectral images of the photovoltaic panel installation area, and divide the point cloud data into multiple grid units. At least one photovoltaic panel is configured in the photovoltaic panel installation area.

[0041] The attribute acquisition module is used to determine the laser point with the maximum elevation value in each grid cell based on the point cloud data, and to acquire the point cloud attribute information of the laser point;

[0042] The information overlay module is used to extract the spectral reflectance information of each grid cell from the multispectral image, and overlay the point cloud attribute information and spectral reflectance information belonging to the same grid cell to obtain the total overlay data;

[0043] The information correction module is used to filter out vegetation information of the photovoltaic panel shading area from the total superimposed data, and correct the vegetation information based on the reflectivity correction coefficient to obtain target vegetation information. The photovoltaic panel shading area is the area in the photovoltaic panel installation area that is shaded by the photovoltaic panel.

[0044] Thirdly, the present invention provides an electronic device, comprising: a memory and a processor, wherein the memory and the processor are communicatively connected to each other, the memory stores computer instructions, and the processor executes the computer instructions to perform a method for extracting vegetation information in a photovoltaic panel shading area as described in the first aspect or any corresponding embodiment.

[0045] Fourthly, the present invention provides a computer-readable storage medium storing computer instructions for causing a computer to perform a method for extracting vegetation information in a photovoltaic panel shading area as described in the first aspect or any corresponding embodiment.

[0046] Fifthly, the present invention provides a computer program product, including computer instructions, which are used to cause a computer to execute a method for extracting vegetation information in a photovoltaic panel shading area as described in the first aspect or any corresponding embodiment. Attached Figure Description

[0047] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0048] Figure 1 This is a schematic flowchart of the first method for extracting vegetation information in a photovoltaic panel shaded area according to an embodiment of the present invention.

[0049] Figure 2 This is a schematic diagram of remote sensing data acquisition under a photovoltaic panel for a method of extracting vegetation information in a photovoltaic panel shaded area according to an embodiment of the present invention.

[0050] Figure 3 This is a schematic diagram of a random forest decision tree model for a method of extracting vegetation information in a photovoltaic panel shaded area according to an embodiment of the present invention.

[0051] Figure 4 This is a schematic diagram of the photovoltaic panel shading area range according to a method for extracting vegetation information in a photovoltaic panel shading area according to an embodiment of the present invention.

[0052] Figure 5 This is a scatter plot of the correction value and the true reflectance value of a method for extracting vegetation information in a photovoltaic panel shaded area according to an embodiment of the present invention.

[0053] Figure 6 This is a structural block diagram of a vegetation information extraction device for a photovoltaic panel shaded area according to an embodiment of the present invention;

[0054] Figure 7 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0056] It is understood that before using the technical solutions disclosed in the various embodiments of the present invention, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in the present invention and their authorization should be obtained in accordance with relevant laws and regulations through appropriate means.

[0057] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this invention, "a plurality of" means two or more, unless otherwise explicitly specified.

[0058] In ecological restoration projects in mining areas, the installation of photovoltaic panels has become a common method, achieving the dual goals of photovoltaic power generation and ecological restoration. However, because photovoltaic panels are typically laid out in multiple rows in a regular array, they occupy a large area, and vegetation between and beneath the panels is affected by varying degrees of shading. To achieve accurate monitoring and scientific management of vegetation growth in the restoration area, current methods mainly rely on field surveys or remote sensing technology to periodically obtain physiological and ecological parameters of the vegetation, such as vegetation height, coverage, leaf area index, and various vegetation indices.

[0059] However, the aforementioned mainstream methods all have obvious limitations: field surveys are costly and inefficient, making it difficult to achieve large-scale continuous monitoring; while remote sensing technology based on satellite or drone orthophotos, although it can cover a large area, cannot effectively obtain or accurately identify vegetation information in areas shaded by photovoltaic panels, resulting in incomplete monitoring data and affecting the overall assessment and precise management of ecological restoration effects.

[0060] Based on this, the present invention provides an embodiment of a method for extracting vegetation information in a photovoltaic panel shaded area. It should be noted that the steps shown in the flowchart in the accompanying drawings can be executed in a computer system such as a set of computer-executable instructions. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be executed in a different order than that shown here.

[0061] This embodiment provides a method for extracting vegetation information in areas shaded by photovoltaic panels. Figure 1 This is a flowchart of a method for extracting vegetation information in a photovoltaic panel shading area according to an embodiment of the present invention, such as... Figure 1 As shown, the process includes the following steps:

[0062] Step S101: Collect point cloud data and multispectral images of the photovoltaic panel installation area, divide the point cloud data into multiple grid units, and configure at least one photovoltaic panel in the photovoltaic panel installation area.

[0063] Step S102: Determine the laser point with the maximum elevation value in each grid cell based on the point cloud data, and obtain the point cloud attribute information of the laser point.

[0064] Step S103: Extract the spectral reflectance information of each grid cell from the multispectral image, and superimpose the point cloud attribute information and spectral reflectance information belonging to the same grid cell to obtain the total superimposed data.

[0065] Step S104: Filter out vegetation information in the photovoltaic panel shading area from the total superimposed data, and correct the vegetation information based on the reflectance correction coefficient to obtain the target vegetation information. The photovoltaic panel shading area is the area in the photovoltaic panel installation area that is shaded by the photovoltaic panel.

[0066] This embodiment provides a method for extracting vegetation information in photovoltaic panel shading areas. It involves collecting point cloud data and multispectral imagery of the photovoltaic panel installation area, dividing the point cloud data into multiple grid cells, determining the laser point with the maximum elevation value in each grid cell based on the point cloud data, and acquiring the point cloud attribute information of the laser point. The spectral reflectance information of each grid cell is extracted from the multispectral imagery, and the point cloud attribute information and spectral reflectance information belonging to the same grid cell are superimposed to obtain total superimposed data. Vegetation information in the photovoltaic panel shading area is then selected from the total superimposed data and corrected based on a reflectance correction coefficient to obtain the target vegetation information. This embodiment, by fusing point cloud data and multispectral imagery, separates and identifies vegetation information under photovoltaic panel shading. It utilizes rasterization processing and reflectance correction to achieve accurate extraction of vegetation physiological and ecological information in the shaded area.

[0067] Step S101: Collect point cloud data and multispectral images of the photovoltaic panel installation area, divide the point cloud data into multiple grid units, and configure at least one photovoltaic panel in the photovoltaic panel installation area.

[0068] Point cloud data refers to a massive set of discrete points acquired through 3D sensing devices such as LiDAR, representing the spatial 3D coordinates and additional attribute information of an object's surface. In one embodiment, point cloud data can be high-density 3D coordinate point data containing all ground features such as the ground, vegetation, and photovoltaic panels, obtained by scanning the photovoltaic panel installation area with airborne or vehicle-mounted LiDAR. Each point typically contains attributes such as location information and reflection intensity.

[0069] Multispectral imagery refers to image data acquired by devices equipped with multiple sensors of specific wavelengths, which simultaneously record the reflected or radiated energy of ground objects in different electromagnetic spectrum bands. In one embodiment, multispectral imagery can utilize sensors mounted on drones or high-resolution satellites to simultaneously acquire spectral information in several bands, such as blue, green, red, and near-infrared, of the photovoltaic panel installation area, thereby generating images that can reflect the physiological state of vegetation (such as chlorophyll content and moisture status).

[0070] A grid cell refers to a set of grid units of uniform shape and size that are regularly divided into continuous geographic spaces to facilitate spatial analysis and information management. In one embodiment, the area covered by point cloud data is divided into grids according to a set spatial resolution (e.g., 0.1 m x 0.1 m), and each grid is called a grid cell, which is used for subsequent data statistics and fusion operations.

[0071] like Figure 2 As shown, based on the photovoltaic power station design data, an on-site survey and measurement were conducted in the photovoltaic panel installation area to obtain photovoltaic panel installation parameters, including but not limited to:

[0072] Photovoltaic panel leading edge height Height of the trailing edge of the photovoltaic panel Solar panel tilt angle (The tilt angle of a photovoltaic panel refers to the angle between the upper surface of the photovoltaic panel and the vertical plane, i.e., an acute angle), and the width under the panel. Width between boards ("Between panels" refers to two adjacent photovoltaic panels), photovoltaic panel transmittance coefficient.

[0073] Simultaneous measurement of the first radiation value under direct sunlight The second radiation value scattered by the sun Simultaneous measurement refers to the simultaneous measurement of direct solar radiation and diffuse solar radiation values ​​on the ground during UAV aerial surveys.

[0074] To ensure that the point cloud data and multispectral imagery collected by the drone completely cover the vegetation in the photovoltaic panel installation area, the drone's flight altitude and gimbal tilt angle are set using the following formula:

[0075]

[0076] Among them, the tilt angle of the gimbal The following conditions must be met:

[0077]

[0078] In the above formula:

[0079] This refers to the flight altitude of the drone. The distance at which the lidar emits pulses; This refers to the tilt angle of the gimbal, which is the angle between the gimbal and the horizontal plane. This refers to the height of the trailing edge of the photovoltaic panel. This refers to the underside width of the photovoltaic panel. This refers to the width between two adjacent photovoltaic panels. The tilt angle of the photovoltaic panel is the angle between the upper surface of the photovoltaic panel and the vertical plane.

[0080] in," "This is the minimum tilt angle of the gimbal, which is the angle between the line connecting the bottom of the front edge of the photovoltaic panel and the height of the rear panel and the ground."

[0081] In one embodiment, the drone is equipped with a multispectral camera to acquire multispectral images of the photovoltaic panel installation area, and a lidar to acquire point cloud data of the photovoltaic panel installation area. Specifically, the steps include:

[0082] Obtain the distance of the lidar emitted pulse and the gimbal tilt angle; collect point cloud data and multispectral images of the photovoltaic panel installation area using a drone, and set the drone's flight altitude for data collection based on the lidar emitted pulse distance and gimbal tilt angle:

[0083]

[0084] In the formula, This refers to the flight altitude of the drone; The distance at which the lidar emits pulses; The tilt angle of the gimbal is determined by acquiring the parameters of the photovoltaic panel, including its trailing edge height, underside width, and the distance between adjacent panels.

[0085]

[0086] In the formula, This refers to the tilt angle of the gimbal; This refers to the height of the trailing edge of the photovoltaic panel; This refers to the underside width of the photovoltaic panel. This refers to the width between two adjacent photovoltaic panels. The tilt angle of the photovoltaic panel.

[0087] For step S102, the laser point with the maximum elevation value in each grid cell is determined based on the point cloud data, and the point cloud attribute information of the laser point is obtained.

[0088] After rasterizing and partitioning the point cloud data, the laser point with the highest elevation value in each raster cell is determined based on the point cloud data, and the point cloud attribute information of that laser point is obtained. In one embodiment, the elevation values ​​of all laser points within each raster cell are first traversed and compared to select the single laser point with the highest elevation value in that cell. Subsequently, the point cloud attribute information of the highest point is extracted, including but not limited to the laser point's three-dimensional spatial coordinates, reflection intensity, and echo number, among other core attributes.

[0089] Point cloud attribute information refers to the quantitative data that characterizes the physical or geometric features of each laser point in a laser point cloud, in addition to its three-dimensional spatial coordinates. In one embodiment, point cloud attribute information may include the reflection intensity of each laser point (reflecting the strength of the ground surface's ability to reflect laser light), the number of echoes (the number of echoes generated by the interaction between the laser pulse and the ground object), and the height value derived from point cloud processing (usually referring to the elevation relative to a certain reference surface), etc.

[0090] This embodiment filters and extracts the laser point with the highest elevation within each grid cell to initially identify and lock the top surface information of the corresponding grid cell. Since photovoltaic panels typically constitute the highest cover layer within an artificial area, this embodiment can effectively separate the photovoltaic panel point cloud from the vegetation point cloud below it, thereby pre-distinguishing the vertical distribution layers of different land features at the data structure level. This lays the data foundation for accurately distinguishing the reflection signal of the photovoltaic panel itself from the spectral information of the shaded vegetation.

[0091] For step S103, the spectral reflectance information of each grid cell is extracted from the multispectral image, and the point cloud attribute information and spectral reflectance information belonging to the same grid cell are superimposed to obtain the total superimposed data.

[0092] like Figure 3 As shown, multispectral imagery and point cloud data are fused to output total overlay data, giving the point cloud data rich spectral information. Specifically, the point cloud data is divided into several grid cells, and the laser point with the highest elevation value in each grid cell is retained. The point cloud geometric information, echo intensity, and laser point reflectivity of the laser point are obtained as the point cloud attribute information of the grid cell. Simultaneously, the red, green, and blue band spectral reflectivity information of the grid cells at the corresponding spatial locations is extracted from the multispectral imagery. The spectral reflectivity information of the grid cells at the same location is overlaid with the point cloud attribute information to output total overlay data.

[0093] Spectral reflectance information refers to the ability of a ground surface to reflect solar electromagnetic waves of different wavelengths. In one embodiment, spectral reflectance information refers to the red, green, and blue band spectral reflectance data extracted from a registered multispectral image.

[0094] Specifically, new attribute fields for red, green, and blue reflectance are created in the LAS file format of the point cloud data. The raster cells of the point cloud are traversed, and the center point coordinates of each raster cell are used as an index. This index is then used to extract the red, green, and blue band spectral reflectance information of the corresponding raster cell in the multispectral image. This spectral reflectance information is then written into the newly created attribute fields in the LAS file, achieving the overlay of multispectral reflectance with existing geometric information, echo intensity, laser point reflectance, and other point cloud attribute information.

[0095] This embodiment achieves effective fusion of point cloud data and multispectral information by creating red, green, and blue reflectance attribute fields in the LAS file and extracting spectral reflectance information for corresponding coordinates from multispectral imagery. It not only preserves the original geometric information, echo intensity, and laser point reflectance attributes of the point cloud but also introduces multispectral reflectance data, thereby enriching the attribute information of the point cloud and enabling it to more accurately reflect the spectral characteristics of ground features.

[0096] For step S104, vegetation information of the photovoltaic panel shading area is filtered out from the total superimposed data, and the vegetation information is corrected based on the reflectance correction coefficient to obtain the target vegetation information. The photovoltaic panel shading area is the area in the photovoltaic panel installation area that is shaded by the photovoltaic panel.

[0097] After obtaining the total superimposed data that integrates point cloud attributes and spectral reflectance, vegetation information in the photovoltaic panel shading area is filtered out from the total superimposed data.

[0098] Vegetation information in photovoltaic (PV) panel shading areas refers to the ecological data of plants within a PV power generation array whose direct solar radiation is significantly reduced due to the physical shading and projection effects of the overhead PV panels. Specifically, the vegetation information for PV panel shading areas consists of data records separated from the total overlay data based on spatial relationships and preliminary classification results, corresponding to the shaded areas. This information includes the location of the shaded vegetation, multispectral reflectance obtained from limited and diffused light, and the corresponding point cloud structure attributes. The specific steps include:

[0099] Vegetation information of the photovoltaic panel shading area is extracted from the total superimposed data: The total superimposed data is input into a pre-trained random forest decision tree model, and the first superimposed data of the photovoltaic panel is removed from the total superimposed data to obtain the vegetation information of the photovoltaic panel shading area.

[0100] In one embodiment, a stratified sampling method is used to divide the dataset into training samples (70%) and test samples (30%). The training samples are selected to train the random forest decision tree model, and the test samples are used to verify the accuracy of the random forest decision tree model.

[0101] The random forest decision tree model can be trained through the following steps:

[0102] a. In the original dataset, use the Bootstrap method to randomly select K new samples with replacement from the original dataset, and use the new samples to construct K classification trees;

[0103] b. Assuming there are n features, select the Mtry feature at each node of each classification tree, where the Mtry feature < n. Calculate the Gini impurity of each Mtry feature and select the feature with the strongest classification ability for node splitting based on the index value.

[0104] c. Directly generate multiple classification trees to form a random forest decision tree model, classify the new data, and obtain the final output through weighted voting of the classification results;

[0105] The weights are determined based on the classification error of the out-of-bag (OOB) data for each classification tree (the smaller the error, the higher the weight).

[0106] Point cloud attribute information includes the point cloud geometry of the laser points, echo intensity, and laser point reflectivity. Spectral reflectivity information includes red, green, and blue band spectral reflectivity data. Specifically, new data is classified in the following way:

[0107]

[0108] In the formula, To identify the combined classification results; For the first The output of the classification tree; For the first The weight of each tree; For the discriminant function, if equals category , The value is 1 if it is 1, otherwise it is 0. Label all possible categories; This represents the number of trees in the random forest.

[0109] In the random forest decision tree model, the number of decision trees, Ntree, and the number of node feature selections, Mtry, are set. Ntree is set to 500, and Mtry is set to 2. The expression for the random forest decision tree model is:

[0110]

[0111] In the formula, Point cloud categories estimated based on a random forest decision tree model; It is the random forest algorithm; Point cloud planar features; Point cloud reflectance; The value represents the point cloud echo intensity.

[0112] The dataset is also used to evaluate the accuracy of the random forest decision tree model. During training, model accuracy is assessed using accuracy, precision, recall, and F1 score (i.e., overall evaluation score). Accuracy is... Accuracy Recall rate F1 score The expression is:

[0113]

[0114]

[0115]

[0116]

[0117] In the formula, This represents the total number of samples. This indicates that both the true class and the classification result of the sample are 0. The number of samples. The classification result of the sample is However, the actual category is not... The number of samples; The true class of the sample is However, the classification result is not... The number of samples.

[0118] The classification accuracy of the random forest decision tree model is evaluated using the aforementioned accuracy evaluation metrics. For example, when the overall classification accuracy is greater than 90%, and the F1 scores for photovoltaic panels and non-photovoltaic panels are greater than or equal to 93% and 92% respectively, the model is considered to have completed training.

[0119] The trained random forest decision tree model is used to classify solar panels and non-solar panels. The first overlay data of the solar panel-shaded areas is removed, and the vegetation information of the solar panel-shaded areas is output. Specifically, the steps are as follows:

[0120] Based on the point cloud geometric information, echo intensity, laser point reflectivity, and spectral reflectivity features of the red, green, and blue bands of the total superimposed data, an initial model for identifying photovoltaic panels is constructed. The initial model is trained until the overall classification score of the initial model is greater than the first threshold, the overall classification score of the photovoltaic panel category is greater than the second threshold, and the overall classification score of the non-photovoltaic panel category is greater than the third threshold, thus obtaining a random forest decision tree model. Based on the trained random forest decision tree model, photovoltaic panels in the photovoltaic panel installation area are identified, and the first superimposed data of the photovoltaic panels is removed, outputting the vegetation information of the photovoltaic panel shading area.

[0121] Next, the selected vegetation information is corrected based on a reflectance correction coefficient. Because the shading caused by photovoltaic panels results in systematic differences in the light conditions (such as light intensity and spectral composition) received by the vegetation beneath them compared to conditions under full sunlight, directly measured reflectance cannot accurately reflect the physiological state of the vegetation, such as chlorophyll content and biomass. Therefore, a reflectance correction coefficient is needed to compensate for the spectral distortion caused by shading, ultimately outputting target vegetation information that more accurately reflects the physiological and ecological characteristics of the vegetation itself.

[0122] The reflectance correction factor can refer to the scaling factor or functional relationship used to correct the observed reflectance to the reference value under standard lighting conditions in order to compensate for the distortion of the spectral measurement values ​​of ground objects caused by non-ideal lighting conditions (such as shading).

[0123] Vegetation information is corrected based on reflectivity correction coefficients to obtain target vegetation information. Specifically, the vegetation information in the photovoltaic panel shading area is corrected based on the following formula:

[0124]

[0125] In the formula, For target vegetation information; Vegetation information to be corrected; This is the reflectivity correction factor.

[0126] The reflectivity correction coefficient includes a first reflectivity correction coefficient under the photovoltaic panel and a second reflectivity correction coefficient between photovoltaic panels. Specifically, it involves obtaining the first radiation value of the solar-directed photovoltaic panel installation area, the second radiation value of the solar-scattered photovoltaic panel installation area, and the parameters of the photovoltaic panels. The photovoltaic panel parameters include the light transmittance of the photovoltaic panel, the length of the point to be corrected from the vertical point of the trailing edge of the photovoltaic panel, the height of the trailing edge of the photovoltaic panel, the width under the photovoltaic panel, and the width between two adjacent photovoltaic panels. The first reflectivity correction coefficient is determined based on the first radiation value, the second radiation value, and the parameters of the photovoltaic panels.

[0127]

[0128] In the formula, This is the first reflectivity correction factor; The first radiation value under direct sunlight; This is the second value of solar radiation scattered by the sun; The transmittance of the photovoltaic panel; such as Figure 4 As shown, The distance from the point to be corrected to the vertical point of the trailing edge of the photovoltaic panel; This refers to the height of the trailing edge of the photovoltaic panel; This refers to the underside width of the photovoltaic panel. This refers to the width between two adjacent photovoltaic panels.

[0129] The second reflectivity correction coefficient is determined based on the first radiation value, the second radiation value, and the parameters of the photovoltaic panel:

[0130]

[0131] In the formula, This is the second reflectivity correction factor; The first radiation value under direct sunlight; This is the second value of solar radiation scattered by the sun; The transmittance of the photovoltaic panel; The distance from the point to be corrected to the vertical point of the trailing edge of the photovoltaic panel; This refers to the height of the trailing edge of the photovoltaic panel; This refers to the underside width of the photovoltaic panel. This refers to the width between two adjacent photovoltaic panels.

[0132] like Figure 5 As shown, a scatter plot of the corrected value and the true reflectance value is presented. The plot contains two types of data points: the corrected value represents the vegetation spectral reflectance value after being processed by the reflectance correction coefficient, and the unobstructed value represents the true reflectance value (or reference true value) of the same vegetation under ideal unobstructed conditions.

[0133] As shown in the figure, the scatter points of the corrected values ​​and the unshaded values ​​exhibit a high degree of convergence and are concentrated along a near 1:1 reference line. This indicates that after processing with the reflectance correction coefficient, the vegetation reflectance values, which were originally distorted due to photovoltaic panel shading, have been effectively corrected, and their values ​​have been restored to a level close to the true unshaded state. This result intuitively verifies that by systematically compensating and restoring the spectral reflectance of shaded vegetation, the problem of inaccurate vegetation information acquisition caused by photovoltaic panel shading has been successfully solved, providing a reliable data foundation for the accurate inversion of vegetation ecological parameters in areas under photovoltaic panels.

[0134] This embodiment also provides a vegetation information extraction device for photovoltaic panel shading areas. This device is used to implement the above embodiments and preferred embodiments, and details already described will not be repeated. As used below, the term "module" can refer to a combination of software and / or hardware that performs a predetermined function. Although the devices described in the following embodiments are preferably implemented in software, hardware implementation, or a combination of software and hardware, is also possible and contemplated.

[0135] This embodiment provides a device for extracting vegetation information in areas shaded by photovoltaic panels, such as... Figure 6 As shown, it includes:

[0136] The data acquisition module 601 is used to acquire point cloud data and multispectral images of the photovoltaic panel installation area, and divide the point cloud data into multiple grid units. At least one photovoltaic panel is configured in the photovoltaic panel installation area.

[0137] The attribute acquisition module 602 is used to determine the laser point with the maximum elevation value in each grid cell based on the point cloud data, and to acquire the point cloud attribute information of the laser point.

[0138] The information overlay module 603 is used to extract the spectral reflectance information of each grid cell from the multispectral image, and overlay the point cloud attribute information and spectral reflectance information belonging to the same grid cell to obtain the total overlay data.

[0139] The information correction module 604 is used to filter out vegetation information in the photovoltaic panel shading area from the total superimposed data, and correct the vegetation information based on the reflectance correction coefficient to obtain the target vegetation information. The photovoltaic panel shading area is the area in the photovoltaic panel installation area that is shaded by the photovoltaic panel.

[0140] In some optional implementations, the data acquisition module 601 is specifically used to acquire the distance of the lidar emitted pulse and the gimbal tilt angle; to acquire point cloud data and multispectral images of the photovoltaic panel installation area via a drone, and to set the drone's flight altitude during acquisition based on the distance of the lidar emitted pulse and the gimbal tilt angle.

[0141]

[0142] In the formula, This refers to the flight altitude of the drone; The distance at which the lidar emits pulses; This refers to the tilt angle of the gimbal;

[0143] This involves acquiring the parameters of the photovoltaic panel, including its trailing edge height, underside width, and the distance between adjacent panels. The tilt angle of the gimbal is then determined based on these parameters.

[0144]

[0145] In the formula, This refers to the tilt angle of the gimbal; This refers to the height of the trailing edge of the photovoltaic panel; This refers to the underside width of the photovoltaic panel. This refers to the width between two adjacent photovoltaic panels. The tilt angle of the photovoltaic panel.

[0146] In some optional implementations, the information correction module 604 is specifically used to input the total superimposed data into a pre-trained random forest decision tree model, and use the random forest decision tree model to remove the first superimposed data of the photovoltaic panel from the total superimposed data to obtain the vegetation information of the photovoltaic panel shading area.

[0147] In some optional implementations, the point cloud attribute information includes the point cloud geometric information, echo intensity, and laser point reflectivity of the laser points, and the spectral reflectivity information includes red, green, and blue band spectral reflectivity data; the information correction module 604 is specifically used to construct an initial model for identifying photovoltaic panels based on the point cloud geometric information, echo intensity, laser point reflectivity, and red, green, and blue band spectral reflectivity features of the total superimposed data; the initial model is trained until the overall classification comprehensive evaluation score of the initial model is greater than a first threshold, the comprehensive evaluation score of the photovoltaic panel category is greater than a second threshold, and the comprehensive evaluation score of the non-photovoltaic panel category is greater than a third threshold, thus obtaining a random forest decision tree model; the photovoltaic panels in the photovoltaic panel installation area are identified based on the trained random forest decision tree model, and the first superimposed data of the photovoltaic panels is removed, outputting the vegetation information of the photovoltaic panel shading area.

[0148] In some optional implementations, the information correction module 604 is specifically used to correct the vegetation information of the photovoltaic panel shading area based on the following formula:

[0149]

[0150] In the formula, For target vegetation information; Vegetation information to be corrected; This is the reflectivity correction factor.

[0151] In some optional implementations, the information correction module 604 is specifically used to acquire a first radiation value of the solar direct photovoltaic panel installation area, a second radiation value of the solar diffuse photovoltaic panel installation area, and parameters of the photovoltaic panel; the parameters of the photovoltaic panel include the light transmittance of the photovoltaic panel, the length of the point to be corrected from the vertical point of the trailing edge of the photovoltaic panel, the height of the trailing edge of the photovoltaic panel, the width of the photovoltaic panel under the panel, and the width between two adjacent photovoltaic panels; and a first reflectivity correction coefficient is determined based on the first radiation value, the second radiation value, and the parameters of the photovoltaic panel.

[0152]

[0153] In the formula, This is the first reflectivity correction factor; The first radiation value under direct sunlight; This is the second value of solar radiation scattered by the sun; The transmittance of the photovoltaic panel; The distance from the point to be corrected to the vertical point of the trailing edge of the photovoltaic panel; This refers to the height of the trailing edge of the photovoltaic panel; This refers to the underside width of the photovoltaic panel. This refers to the width between two adjacent photovoltaic panels.

[0154] In some optional implementations, the information correction module 604 is specifically used to determine a second reflectivity correction coefficient based on the first radiation value, the second radiation value, and the parameters of the photovoltaic panel:

[0155]

[0156] In the formula, This is the second reflectivity correction factor; The first radiation value under direct sunlight; This is the second value of solar radiation scattered by the sun; The transmittance of the photovoltaic panel; The distance from the point to be corrected to the vertical point of the trailing edge of the photovoltaic panel; This refers to the height of the trailing edge of the photovoltaic panel; This refers to the underside width of the photovoltaic panel. This refers to the width between two adjacent photovoltaic panels.

[0157] The vegetation information extraction device for photovoltaic panel shading areas provided in this embodiment of the invention can execute the vegetation information extraction method for photovoltaic panel shading areas provided in any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the method. Further functional descriptions of the above modules and units are the same as those in the corresponding embodiments described above, and will not be repeated here.

[0158] Figure 7 This is a schematic diagram of the structure of an electronic device provided in an embodiment of the present invention.

[0159] The following is a detailed reference. Figure 7 This diagram illustrates a suitable structural schematic for implementing an electronic device according to embodiments of the present invention. The electronic device may include a processor (e.g., a central processing unit, graphics processor, etc.) 701, which can perform various appropriate actions and processes based on a program stored in read-only memory (ROM) 702 or a program loaded from memory 708 into random access memory (RAM) 703. The RAM 703 also stores various programs and data required for the operation of the electronic device. The processor 701, ROM 702, and RAM 703 are interconnected via a bus 704. An input / output (I / O) interface 705 is also connected to the bus 704.

[0160] Typically, the following devices can be connected to I / O interface 705: input devices 706 including, for example, touchscreens, touchpads, keyboards, mice, cameras, microphones, accelerometers, gyroscopes, etc.; output devices 707 including, for example, liquid crystal displays (LCDs), speakers, vibrators, etc.; memory devices 708 including, for example, magnetic tapes, hard disks, etc.; and communication devices 709. Communication device 709 allows electronic devices to exchange data via wireless or wired communication with other devices. Although Figure 7Electronic devices with various devices are shown, but it should be understood that it is not required to implement or have all of the devices shown, and more or fewer devices may be implemented or have instead.

[0161] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via a communication device 709, or installed from a memory 708, or installed from a ROM 702. When the computer program is executed by the processor 701, it performs the functions defined in the method for extracting vegetation information in a photovoltaic panel shading area according to embodiments of the present invention.

[0162] Figure 7 The electronic device shown is merely an example and should not be construed as limiting the functionality and scope of use of the embodiments of the present invention.

[0163] This invention also provides a computer-readable storage medium. The methods described above according to embodiments of the invention can be implemented in hardware or firmware, or implemented as computer code that can be recorded on a storage medium, or implemented as computer code downloaded via a network and originally stored on a remote storage medium or a non-transitory machine-readable storage medium and then stored on a local storage medium. Thus, the methods described herein can be processed by software stored on a storage medium using a general-purpose computer, a dedicated processor, or programmable or dedicated hardware. The storage medium can be a magnetic disk, optical disk, read-only memory, random access memory, flash memory, hard disk, or solid-state drive, etc.; further, the storage medium can also include combinations of the above types of memory. It is understood that computers, processors, microprocessor controllers, or programmable hardware include storage components capable of storing or receiving software or computer code. When the software or computer code is accessed and executed by the computer, processor, or hardware, it implements the method for extracting vegetation information in a photovoltaic panel shading area shown in the above embodiments.

[0164] A portion of this invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide the methods and / or technical solutions according to the invention through the operation of the computer. Those skilled in the art will understand that the forms in which computer program instructions exist in a computer-readable medium include, but are not limited to, source files, executable files, installation package files, etc. Correspondingly, the ways in which computer program instructions are executed by a computer include, but are not limited to: the computer directly executing the instructions, or the computer compiling the instructions and then executing the corresponding compiled program, or the computer reading and executing the instructions, or the computer reading and installing the instructions and then executing the corresponding installed program. Here, the computer-readable medium can be any available computer-readable storage medium or communication medium accessible to a computer.

[0165] Although embodiments of the invention have been described in conjunction with the accompanying drawings, those skilled in the art can make various modifications and variations without departing from the spirit and scope of the invention, and such modifications and variations all fall within the scope defined by the appended claims.

Claims

1. A method for extracting vegetation information of a shading area of a photovoltaic panel, characterized in that, The method includes: Point cloud data and multispectral images of the photovoltaic panel installation area are collected, and the point cloud data is divided into multiple grid units. At least one photovoltaic panel is configured in the photovoltaic panel installation area. Based on the point cloud data, determine the laser point with the maximum elevation value in each grid cell, and obtain the point cloud attribute information of the laser point; The spectral reflectance information of each grid cell is extracted from the multispectral image, and the point cloud attribute information and spectral reflectance information belonging to the same grid cell are superimposed to obtain the total superimposed data. Vegetation information of the photovoltaic panel shaded area is filtered out from the total superimposed data, and the vegetation information is corrected based on the reflectivity correction coefficient to obtain the target vegetation information. The photovoltaic panel shaded area is the area in the photovoltaic panel installation area that is shaded by the photovoltaic panel. The vegetation information in the photovoltaic panel shading area is corrected based on the following formula: In the formula, is target vegetation information; is vegetation information to be corrected; is a reflectance correction coefficient, the reflectance correction coefficient including a first reflectance correction coefficient under a photovoltaic panel and a second reflectance correction coefficient between photovoltaic panels ; the method further includes: The system obtains a first radiation value of the photovoltaic panel installation area directly exposed to sunlight, a second radiation value of the photovoltaic panel installation area scattered by sunlight, and parameters of the photovoltaic panel. The parameters of the photovoltaic panel include the light transmittance of the photovoltaic panel, the length of the point to be corrected from the vertical point of the trailing edge of the photovoltaic panel, the height of the trailing edge of the photovoltaic panel, the width of the photovoltaic panel at the bottom, and the width between two adjacent photovoltaic panels. The first reflectivity correction coefficient is determined based on the first radiation value, the second radiation value, and the parameters of the photovoltaic panel: wherein, is the first reflectance correction coefficient; is a first radiation value of the direct sun; is a second radiation value of the diffuse sun; is a light transmission coefficient of the photovoltaic panel; is a length of the point to be corrected from the back edge foot point of the photovoltaic panel; is a back edge height of the photovoltaic panel; is a panel under width of the photovoltaic panel; is a panel-to-panel width of two adjacent photovoltaic panels. The second reflectivity correction coefficient is determined based on the first radiation value, the second radiation value, and the parameters of the photovoltaic panel: In the formula, This is the second reflectivity correction coefficient; The first radiation value under direct sunlight; This is the second value of solar radiation scattered by the sun; The transmittance of the photovoltaic panel is denoted as . The distance from the point to be corrected to the vertical point of the trailing edge of the photovoltaic panel is denoted as ; The height of the trailing edge of the photovoltaic panel; The width of the photovoltaic panel is its underside. This refers to the width between two adjacent photovoltaic panels.

2. The method according to claim 1, characterized in that, The acquisition of point cloud data and multispectral images of the photovoltaic panel installation area includes: Obtain the distance of the lidar's emitted pulse and the tilt angle of the gimbal; The point cloud data and multispectral images of the photovoltaic panel installation area are collected by a drone, and the flight altitude of the drone during data collection is set according to the distance of the laser radar pulse and the tilt angle of the gimbal: In the formula, The altitude of the drone; The distance at which the lidar emits pulses; This refers to the tilt angle of the gimbal; The process involves obtaining parameters of the photovoltaic panel, including its trailing edge height, underside width, and the width between adjacent panels. The tilt angle of the gimbal is then determined based on these parameters. In the formula, This refers to the tilt angle of the gimbal; The height of the trailing edge of the photovoltaic panel; The width of the photovoltaic panel is its underside. This refers to the width between two adjacent photovoltaic panels. The tilt angle of the photovoltaic panel is given.

3. The method according to claim 1, characterized in that, Vegetation information in the photovoltaic panel shading area was filtered out from the total superimposed data: The total superimposed data is input into a pre-trained random forest decision tree model. The random forest decision tree model is then used to remove the first superimposed data of the photovoltaic panel from the total superimposed data to obtain the vegetation information of the photovoltaic panel shading area.

4. The method according to claim 3, characterized in that, The point cloud attribute information includes the point cloud geometric information of the laser point, echo intensity, and laser point reflectivity; the spectral reflectivity information includes red, green, and blue band spectral reflectivity data. The step of using the random forest decision tree model to remove the first superimposed data of the photovoltaic panels from the total superimposed data to obtain the vegetation information of the photovoltaic panel shading area includes: Based on the point cloud geometric information, echo intensity, laser point reflectivity, and red, green, and blue band spectral reflectivity characteristics of the total superimposed data, an initial model for identifying the photovoltaic panel is constructed. The initial model is trained until the overall classification score of the initial model is greater than the first threshold, the overall classification score of the photovoltaic panel category is greater than the second threshold, and the overall classification score of the non-photovoltaic panel category is greater than the third threshold, thus obtaining the random forest decision tree model. The trained random forest decision tree model identifies the photovoltaic panels in the photovoltaic panel installation area, removes the first superimposed data of the photovoltaic panels, and outputs the vegetation information of the photovoltaic panel shading area.

5. A device for extracting vegetation information in a photovoltaic panel shading area, characterized in that, The device includes: The data acquisition module is used to acquire point cloud data and multispectral images of the photovoltaic panel installation area, and divide the point cloud data into multiple grid units. At least one photovoltaic panel is configured in the photovoltaic panel installation area. The attribute acquisition module is used to determine the laser point with the maximum elevation value in each grid cell based on the point cloud data, and to acquire the point cloud attribute information of the laser point; The information overlay module is used to extract the spectral reflectance information of each grid cell from the multispectral image, and overlay the point cloud attribute information and spectral reflectance information belonging to the same grid cell to obtain the total overlay data; The information correction module is used to filter out vegetation information of the photovoltaic panel shading area from the total superimposed data, and correct the vegetation information based on the reflectance correction coefficient to obtain the target vegetation information. The photovoltaic panel shading area is the area in the photovoltaic panel installation area that is shaded by the photovoltaic panel. The information correction module is specifically used to correct the vegetation information in the photovoltaic panel shading area based on the following formula: In the formula, For target vegetation information; Vegetation information to be corrected; This is a reflectivity correction factor, which includes a first reflectivity correction factor under the photovoltaic panel. The second reflectivity correction factor between the photovoltaic panel and the photovoltaic panel ; The information correction module is specifically used to acquire a first radiation value of the photovoltaic panel installation area directly exposed to sunlight, a second radiation value of the photovoltaic panel installation area scattered by sunlight, and parameters of the photovoltaic panel; the parameters of the photovoltaic panel include the light transmittance coefficient of the photovoltaic panel, the length of the point to be corrected from the vertical point of the trailing edge of the photovoltaic panel, the height of the trailing edge of the photovoltaic panel, the width of the bottom of the photovoltaic panel, and the width between two adjacent photovoltaic panels; and to determine the first reflectivity correction coefficient based on the first radiation value, the second radiation value, and the parameters of the photovoltaic panel. In the formula, This is the first reflectivity correction coefficient; The first radiation value under direct sunlight; This is the second value of solar radiation scattered by the sun; The transmittance of the photovoltaic panel is denoted as . The distance from the point to be corrected to the vertical point of the trailing edge of the photovoltaic panel is denoted as ; The height of the trailing edge of the photovoltaic panel; The width of the photovoltaic panel is its underside. This refers to the width between two adjacent photovoltaic panels. The information correction module is specifically used to determine the second reflectivity correction coefficient based on the first radiation value, the second radiation value, and the parameters of the photovoltaic panel: In the formula, This is the second reflectivity correction coefficient; The first radiation value under direct sunlight; This is the second value of solar radiation scattered by the sun; The transmittance of the photovoltaic panel is denoted as . The distance from the point to be corrected to the vertical point of the trailing edge of the photovoltaic panel is denoted as ; The height of the trailing edge of the photovoltaic panel; The width of the photovoltaic panel is its underside. This refers to the width between two adjacent photovoltaic panels.

6. An electronic device, characterized in that, include: The system includes a memory and a processor, which are interconnected. The memory stores computer instructions, and the processor executes the computer instructions to perform a method for extracting vegetation information in a photovoltaic panel shading area as described in any one of claims 1 to 4.

7. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing the computer to execute a method for extracting vegetation information in a photovoltaic panel shading area according to any one of claims 1 to 4.

8. A computer program product, characterized in that, The method includes computer instructions for causing a computer to execute a method for extracting vegetation information in a photovoltaic panel shading area according to any one of claims 1 to 4.

Images