Desert Photovoltaic Equipment Inspection Method and System Based on UAV and AI Algorithm

Abstract

The present invention relates to the technical field of equipment inspection, and specifically relates to a method and system for inspecting desert photovoltaic equipment based on drones and AI algorithms. The present invention obtains the local sandstorm density of each pixel point in each inspection image according to the local hue characteristics of each pixel point in each inspection image and the local saturation distribution characteristics of the matching pixel points in different inspection images; obtains the equipment performance of each pixel point in the inspection image according to the position distribution characteristics of the edge pixel points on different edges in the inspection image; obtains multiple blocks of each inspection image based on a preset block side length; obtains the splicing coefficient value corresponding to the preset block side length according to the splicing probability distribution of the pixel points in each block in different training images, and screens out the optimal block side length and the optimal splicing blocks that constitute the best spliced image. The present invention improves the accuracy of equipment inspection by obtaining the best spliced image that more comprehensively represents the equipment state during construction inspection.

Description

Technical Field

[0001] The present invention relates to the technical field of equipment inspection, and specifically relates to a method and system for inspecting desert photovoltaic equipment based on drones and AI algorithms. Background Art

[0002] Desert centralized photovoltaic power stations cover a large area, have a large number of equipment, and are located in harsh environments such as high temperature and sandstorms. Therefore, it is necessary to inspect the construction process of photovoltaic equipment.

[0003] In the prior art, drones are used to take pictures of the inspection area during the construction process of photovoltaic equipment, and edge recognition technology is used to obtain the shape of photovoltaic equipment. However, due to the influence of sandstorms in different desert blocks, the degree of interference of equipment blocks in different images by sandstorms is different. Directly applying edge recognition technology to images results in blurred edges of the recognized facilities and poor recognition effect of photovoltaic equipment. Summary of the Invention

[0004] In order to solve the technical problem of poor recognition effect of photovoltaic equipment without considering the influence of sandstorms, the purpose of the present invention is to provide a method and system for inspecting desert photovoltaic equipment based on drones and AI algorithms. The specific technical solutions adopted are as follows:

[0005] The present invention proposes a method for inspecting desert photovoltaic equipment based on drones and AI algorithms, and the method includes:

[0006] Obtain multiple inspection images of the inspection area of photovoltaic equipment; obtain matching pixel points between different inspection images, and obtain the local sandstorm density of each pixel point in each inspection image according to the local hue characteristics of each pixel point in each inspection image and the local saturation distribution characteristics of the matching pixel points in different inspection images corresponding to it; obtain the equipment representation degree of each pixel point in the inspection image according to the position distribution characteristics of the edge pixels on different edge lines in the inspection image.

[0007] According to the change trend of the equipment representation degree and the local sandstorm density of each pixel point in each inspection image relative to the corresponding matching pixel points in other inspection images, obtain the splicing probability of each pixel point in each inspection image.

[0008] Obtain multiple blocks of each inspection image based on a preset block side length; obtain the splicing coefficient value corresponding to the preset block side length according to the splicing probability distribution of the pixel points in each block in different training images, and screen out the optimal block side length and the optimal splicing blocks that make up the best spliced image.

[0009] Inspect the equipment according to the best spliced image.

[0010] Further, the method for obtaining the matching pixel points includes:

[0011] The matching pixel points between different inspection images after grayscale processing are obtained based on the SIFT matching algorithm.

[0012] Furthermore, the method for obtaining the local wind-sand density includes:

[0013] Obtain the saturation mean value of all pixel points within the neighborhood range of each pixel point on each inspection image in the HSV space as the local saturation; obtain the maximum and minimum values of the local saturation of the matching pixel points in different inspection images, and normalize the local saturation of each pixel point in each inspection image as the relative saturation feature of each pixel point in each inspection image;

[0014] Obtain the degree of fluctuation of the hue of all matching pixel points within the neighborhood window of each pixel point on the inspection image in the HSV space as the local hue feature;

[0015] According to the relative saturation feature and the local hue feature, obtain the local wind-sand density of each pixel point on each inspection image. Both the relative saturation feature and the local hue feature are negatively correlated with the local wind-sand density.

[0016] Furthermore, the method for obtaining the equipment performance includes:

[0017] Perform edge detection on the inspection image after grayscale processing to obtain multiple edge lines corresponding to the inspection image; obtain the angle between the tangent line of each edge pixel point on each edge on each inspection image and the horizontal direction as the tangent angle of each edge pixel point;

[0018] According to the change trend of the tangent angles of all edge pixel points on each edge line, obtain the equipment performance of each edge pixel point;

[0019] For other pixel points except edge pixel points, the corresponding equipment performance is set to the positive integer 1.

[0020] Furthermore, the step of obtaining the equipment performance of each edge pixel point according to the change trend of the tangent angles of all edge pixel points on each edge line includes:

[0021] Construct a tangent angle broken line of all edge pixel points on each edge line in the order of pixel point positions to obtain the extreme value points on the tangent angle broken line; obtain the upper envelope line fitted by all maximum value points and the lower envelope line fitted by all minimum value points, calculate the mean value of the data of all edge pixel points between the upper envelope line and the lower envelope line to form a new tangent angle broken line, and perform a preset number of processes on the tangent angle broken line to obtain a tangent correction angle broken line;

[0022] Obtain the sum of the differences in the tangent correction angles between each edge pixel point and its adjacent edge pixel points on each edge in each inspection image, and use it as the device performance degree of each edge pixel point.

[0023] Further, the method for obtaining the splicing probability includes:

[0024] Obtain the difference in the device performance degree between each pixel point in each inspection image and the matching pixel point in each other inspection image as the device performance difference.

[0025] According to the device performance differences between each pixel point in each inspection image and the matching pixel points in different other inspection images, and the local sandstorm density of the corresponding pixel points in different inspection images, obtain the splicing probability of each pixel point in each inspection image. Both the device performance difference and the local sandstorm density are negatively correlated with the splicing probability.

[0026] Further, the method for obtaining the splicing coefficient value includes:

[0027] Obtain the average value of the splicing probabilities of all pixel points in each block in each inspection image as the splicing probability level corresponding to each block.

[0028] Select the block with the maximum splicing probability level among the blocks at each same position in all inspection images, and use the block at each position in the corresponding inspection image as the splicing block.

[0029] Obtain the cumulative value of the splicing probability levels corresponding to the splicing blocks at all positions, and calculate the product of the cumulative value and the preset block side length as the splicing coefficient value corresponding to the preset block side length.

[0030] Further, the method for obtaining the optimal block side length and the splicing blocks constituting the best spliced image includes:

[0031] Select the preset block side length with the maximum splicing coefficient value among different preset block side lengths, and use the corresponding preset block side length as the optimal block side length; for the optimal block side length, obtain all the splicing blocks corresponding to all positions in different inspection images as the optimal splicing blocks to form the best spliced image.

[0032] Further, the method for obtaining the neighborhood range includes:

[0033] Taking each pixel point as the center, construct a range with an equal width as the neighborhood range of each pixel point.

[0034] The present invention also provides a desert photovoltaic equipment inspection system based on an unmanned aerial vehicle (UAV) and an AI algorithm, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of any one of the desert photovoltaic equipment inspection methods based on a UAV and an AI algorithm are implemented.

[0035] The present invention has the following beneficial effects:

[0036] The present invention takes into account the error effects caused by slight shaking of the UAV, obtains the matching pixel points between different inspection images, quantifies the dust interference degree in the inspection environment according to the local hue characteristics of each pixel point in each inspection image and the local saturation distribution characteristics of the matching pixel points in different inspection images; obtains multiple edge lines of each inspection image, and obtains the equipment representation degree of each pixel point in the inspection image according to the position distribution characteristics of the edge pixel points on different edge lines in the inspection image, quantifying the characteristics of each pixel point representing the equipment; furthermore, obtains the splicing probability of each pixel point in each inspection image, which helps to select high-probability pixels to participate in splicing and reduces the influence of low-quality pixels such as blurring and repeated textures; obtains multiple blocks of each inspection image based on a preset block side length, which is convenient for analyzing the sandstorm density and equipment feature distribution in the block; obtains the splicing coefficient value corresponding to the preset block side length according to the splicing probability distribution of the pixel points in each block of different training images, screens out the optimal block side length and the optimal splicing blocks constituting the best spliced image, avoids excessive calculation redundancy caused by too small blocks or loss of details caused by too large blocks, and fuses multiple optimized block images; and inspects the equipment. The present invention improves the accuracy of equipment inspection by obtaining the best spliced image that more comprehensively represents the equipment characteristics during the construction inspection of photovoltaic equipment. Description of the Drawings

[0037] In order to more clearly illustrate the technical solutions and advantages in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for use in the description of the embodiments or the prior art. Obviously, the following drawings are only some embodiments of the present invention. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0038] Figure 1 It is a flowchart of a desert photovoltaic equipment inspection method provided by an embodiment of the present invention based on a UAV and an AI algorithm;

[0039] Figure 2 It is a flowchart of a method for obtaining local sandstorm density provided by an embodiment of the present invention. Detailed Embodiments

[0040] In order to further elaborate on the technical means and effects adopted by the present invention to achieve the intended invention purpose, the following, in conjunction with the accompanying drawings and preferred embodiments, details a method and system for inspecting desert photovoltaic equipment based on drones and AI algorithms according to the present invention, including its specific implementation manners, structures, features, and effects. In the following description, different "one embodiment" or "another embodiment" do not necessarily refer to the same embodiment. In addition, the specific features, structures, or characteristics in one or more embodiments can be combined in any suitable form.

[0041] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by those of ordinary skill in the technical field to which this invention belongs.

[0042] The following specifically describes the specific solution of a method and system for inspecting desert photovoltaic equipment based on drones and AI algorithms provided by the present invention in conjunction with the accompanying drawings.

[0043] Please refer to Figure 1 , which shows a flowchart of a method for inspecting desert photovoltaic equipment based on drones and AI algorithms provided by an embodiment of the present invention, specifically including:

[0044] Step S1: Obtain multiple inspection images of the photovoltaic equipment inspection area.

[0045] In the embodiment of the present invention, in order to eliminate the shaking of the drone caused by environmental wind and the blurring of the collected images, it is necessary to obtain and analyze the original images during the construction process of the photovoltaic equipment; first, during the process of building solar photovoltaic panels in the desert, high-resolution equipment is used to collect images directly above the inspection block. During the collection process, the drone ensures the stability of its own height and position, which is more conducive to analysis. Obtain multiple inspection images of the photovoltaic equipment inspection area.

[0046] It should be noted that in the embodiment of the present invention, one image is collected every 5s, and a total of 12 images within 1 minute are collected for analysis; in other embodiments of the present invention, the acquisition time interval can be specifically set according to specific circumstances, and no limitation and elaboration will be made here.

[0047] Step S2: Obtain the matching pixel points between different inspection images. According to the local hue characteristics of each pixel point in each inspection image and the local saturation distribution characteristics of the matching pixel points in the corresponding different inspection images, obtain the local sandstorm density of each pixel point in each inspection image; obtain multiple edge lines of each inspection image, and according to the position distribution characteristics of the edge pixel points on different edge lines in the inspection image, obtain the equipment representation degree of each pixel point in the inspection image.

[0048] During the construction of photovoltaic equipment, the positions of the pipe piles and brackets for the foundation installation are ensured to be accurate. In order to eliminate the errors caused by the shaking of the drone and obtain the matching pixel points between different inspection images; it should be noted that, in an embodiment of the present invention, the method for obtaining the matching pixel points includes: obtaining the matching pixel points between different inspection images after grayscale processing based on the SIFT matching algorithm. Among them, the inspection images after grayscale processing can eliminate the color channel differences and facilitate the processing of the images; the specific grayscale processing and SIFT matching algorithm are well-known technical means to those skilled in the art and will not be elaborated here.

[0049] The suspended particles in the sand and dust will scatter light, resulting in random offsets of the light path, reducing the purity of the color channels, and decreasing the overall saturation of the image; the sand and dust covering makes the originally bright color blocks present a dull effect, and the colors of the sand and dust in a local range are close to the same, with lower hue complexity; therefore, by analyzing the changes in hue and saturation within the local range of the pixel points, it is helpful to understand the influence of sand and dust on the pixel points within the local range of the image; according to the local hue characteristics of each pixel point in each inspection image and the local saturation distribution characteristics of the matching pixel points in different inspection images, the local sand and dust density of each pixel point in each inspection image is obtained.

[0050] Preferably, in an embodiment of the present invention, for the method for obtaining the local sand and dust density, please refer to Figure 2 , which shows a flowchart of a method for obtaining the local sand and dust density. It includes:

[0051] Step S201: Obtain the saturation mean value of all pixel points within the neighborhood range of each pixel point on each inspection image in the HSV space as the local saturation; obtain the maximum and minimum values of the local saturation of the matching pixel points in different inspection images, and normalize the local saturation of each pixel point in each inspection image as the relative saturation feature of each pixel point in each inspection image.

[0052] By calculating the mean value, the saturation of all pixel points within the neighborhood range is analyzed as a whole to quantify the overall saturation level; during the continuous process of sand and dust, the sizes of the sand and dust in different inspection images may be different, showing different saturation situations. Therefore, by analyzing the local saturation of the corresponding matching pixel points in different inspection images, the influence degree of the sand and dust within the range can be reflected. The greater the local saturation, the greater the relative saturation feature, and the greater the influence of the sand and dust.

[0053] It should be noted that the method for normalizing the local saturation of a pixel point based on the maximum and minimum values of local saturation is as follows: Obtain the difference between the maximum and minimum values of local saturation as the saturation range; obtain the difference between the local saturation of each pixel point and the minimum value of local saturation, and calculate the ratio of the difference result to the saturation range, that is, normalize the local saturation of each pixel point. The specific means are well-known technical means to those skilled in the art and will not be elaborated here.

[0054] Step S202: Obtain the degree of fluctuation of the hue in the HSV space of all matching pixel points within the neighborhood window of each pixel point on the inspection image as the local hue feature.

[0055] Dust coverage will cause originally bright color patches to present a dull effect through physical occlusion or light scattering. The more chaotic the hue distribution is, the less affected it is by dust coverage and the more it shows the characteristics of the device.

[0056] It should be noted that in an embodiment of the present invention, the degree of fluctuation is represented by calculating the variance. The larger the variance, the greater the degree of fluctuation; the smaller the variance, the smaller the degree of fluctuation. In other embodiments of the present invention, the degree of fluctuation can also be represented by calculating the range and standard deviation. The specific means are well-known technical means to those skilled in the art and will not be elaborated here.

[0057] Step S203: Obtain the local dust density of each pixel point on each inspection image according to the relative saturation feature and the local hue feature. Both the relative saturation feature and the local hue feature are negatively correlated with the local dust density.

[0058] It should be noted that in the embodiments of the present invention, the larger the relative saturation feature is, the smaller the scattered light affected by sand and dust is, and the smaller the local dust density is, showing a negative correlation. The larger the local hue feature is, the more obvious the hue performance within the divided block of the inspection image is, and the smaller the possibility of being the color covered by sand and dust is, showing a negative correlation.

[0059] In an embodiment of the present invention, the formula for the local dust density is expressed as:

[0060] ;

[0061] Wherein, represents the local dust density of the th pixel point in the th inspection image; represents the variance of the hue in the HSV space of all pixel points within the neighborhood range of the th pixel point in the th inspection image, that is, the local hue feature; represents the th inspection image, and the The relative saturation feature of each pixel point.

[0062] In the formula of local sandstorm density, Adding 0.01 is to avoid the denominator of the formula being 0, making the formula meaningless; the larger the relative saturation feature, the less likely it is to be affected by sandstorms. The larger the local hue feature, the greater the hue change, the more color features are shown, and the less affected by sandstorms. Therefore, the larger the relative saturation feature and the larger the local hue feature, the smaller the local sandstorm density.

[0063] It should be noted that in an embodiment of the present invention, the neighborhood range is a range with an equal-width scale centered on each pixel point, where the size can be set to 5×5; in other embodiments of the present invention, the size of the neighborhood range can be specifically set according to specific circumstances, which will not be limited and elaborated here.

[0064] Due to the influence of sandstorms, the degree of interference of the divided blocks shown in different images by sandstorms is different, the contrast of their edges decreases, and there are depressions at the edges, resulting in blurred edges of the recognition device. By analyzing the position distribution of edge pixel points, the device performance of the pixel points is reflected. According to the position distribution characteristics of edge pixel points on different edge lines in the inspection image, the device performance of each pixel point in the inspection image is obtained.

[0065] Preferably, in an embodiment of the present invention, the method for obtaining the device performance includes:

[0066] Performing edge detection on the grayscale processed inspection image to obtain multiple edge lines corresponding to the inspection image; obtaining the angle between the tangent line of each edge pixel point on each edge of each inspection image and the horizontal direction as the tangent angle of each edge pixel point;

[0067] According to the change trend of the tangent angles of all edge pixel points on each edge line, the device performance of each edge pixel point is obtained;

[0068] Preferably, in an embodiment of the present invention, according to the change trend of the tangent angles of all edge pixel points on each edge line, obtaining the device performance of each edge pixel point includes:

[0069] Constructing a tangent angle broken line of all edge pixel points on each edge line in the order of the positions of the pixel points to obtain the extreme points on the tangent angle broken line; obtaining the upper envelope line fitted by all maximum points and the lower envelope line fitted by all minimum points, calculating the mean value of the data of all edge pixel points between the upper envelope line and the lower envelope line to form a new tangent angle broken line, and performing a preset number of processes on the tangent angle broken line to obtain a tangent correction angle broken line;

[0070] Obtain the sum of the differences in the tangent correction angles between each edge pixel point and its adjacent edge pixel points on each edge in each inspection image, and use it as the device performance degree of each edge pixel point.

[0071] It should be noted that, in an embodiment of the present invention, for the tangent angle of each tangent pixel point, in order to perform a filtering operation on each pixel point to eliminate the influence of wind and sand, the fitting method is obtained by using cubic sample interpolation. In other embodiments of the present invention, existing fitting methods such as polynomial fitting can also be used. The specific means are well-known technical means to those skilled in the art and will not be elaborated here.

[0072] It should be noted that, in the embodiments of the present invention, the preset number of times of processing can be specifically set according to specific situations. In an embodiment of the present invention, it is set to 3, and no further limitation and elaboration will be made here.

[0073] For other pixel points except the edge pixel points, the corresponding device performance degree is set to the positive integer 1.

[0074] Step S3: According to the device performance degree and the change trend of the local wind and sand density of each pixel point in each inspection image relative to the corresponding matching pixel points in other inspection images, obtain the splicing probability of each pixel point in each inspection image.

[0075] There are differences in the feature representation capabilities of photovoltaic devices in different images. The position change range of each pixel point in the images taken by the drone itself is relatively small. By analyzing the device performance degree and the change trend of the local wind and sand density of each pixel point in each inspection image relative to the corresponding matching pixel points in other inspection images, the pixel points that are more valuable for reflecting the device characteristics are reflected; according to the device performance degree and the change trend of the local wind and sand density of each pixel point in each inspection image relative to the corresponding matching pixel points in other inspection images, obtain the splicing probability of each pixel point in each inspection image.

[0076] Preferably, in an embodiment of the present invention, the method for obtaining the splicing probability includes:

[0077] Obtain the difference in the device performance degree between each pixel point in each inspection image and the matching pixel points in each other inspection image, as the device performance difference;

[0078] According to the device performance difference between each pixel point in each inspection image and the matching pixel points in different other inspection images, and the local wind and sand density of the corresponding pixel points in different inspection images, obtain the splicing probability of each pixel point in each inspection image. Both the device performance difference and the local wind and sand density are negatively correlated with the splicing probability.

[0079] In an embodiment of the present invention, the formula for the splicing probability is expressed as:

[0080] ;

[0081] Among them, represents the splicing probability of the th pixel point in the th inspection image; represents the device performance of the th pixel point in the th inspection image; represents the local sandstorm density of the th pixel point in the th inspection image; represents the device performance of the corresponding matching pixel point of the th pixel point in the th inspection image; represents the local sandstorm density of the corresponding matching pixel point of the th pixel point in the th inspection image; represents the number of other inspection images; represents the normalization function.

[0082] In the formula of the splicing probability, adding 0.01 is to avoid the denominator of the formula being 0 and the formula being meaningless; the smaller the local sandstorm density, the less affected by the sandstorm, and the higher the reference value; represents the difference in device performance between the th pixel point in the th inspection image and the corresponding matching pixel point of the th pixel point in the th inspection image, that is, the device performance difference. The smaller the device performance difference, the closer the performance at the corresponding pixel point position, the more able to represent the actual image features, and the greater the splicing probability.

[0083] Step S4: Obtain multiple blocks of each inspection image based on the preset block side length; according to the splicing probability distribution of the pixel points in each block of different training images, obtain the splicing coefficient value corresponding to the preset block side length, and screen out the optimal block side length and the optimal splicing blocks that make up the best spliced image.

[0084] To avoid the problems of splitting and sharpening in the splicing result caused by using a single pixel point for splicing, local blocks are analyzed, and multiple blocks of each inspection image are obtained based on a preset block side length. It should be noted that in an embodiment of the present invention, due to the analysis of the preset block side length, the preset block is square. The common divisors of the length and width of the image are obtained, and the same values are selected in ascending order to obtain multiple preset block side lengths, and the image is divided. Among them, in order to ensure the analysis of a sufficient amount of data, the minimum preset block side length is 3. That is, if the length is 40, the common divisors are 1, 2, 4, 5, 10, 20, 40, and the width is 20, the common divisors are 1, 2, 4, 5, 10, 20, then the preset block side lengths are 4, 5, 10, 20. In other embodiments of the present invention, the size of the preset block side length can be specifically set according to specific circumstances, and no limitation and elaboration will be made here.

[0085] Preferably, in an embodiment of the present invention, the method for obtaining the splicing coefficient value includes:

[0086] Obtain the average splicing probability of all pixel points in each block of each inspection image as the splicing probability level corresponding to each block;

[0087] Select the block with the maximum splicing probability level among the blocks at each same position in all inspection images, and use the block at each position of the corresponding inspection image as the splicing block;

[0088] Obtain the accumulated value of the splicing probability levels corresponding to the splicing blocks at all positions, and calculate the product of the accumulated value and the preset block side length as the splicing coefficient value corresponding to the preset block side length.

[0089] In an embodiment of the present invention, the formula for the splicing coefficient value is expressed as:

[0090] ;

[0091] Wherein, represents the preset block side length of the splicing coefficient value; represents the preset block side length; represents the maximum splicing probability in the blocks at the th same position in all inspection images; represents that the preset block side length is the number of blocks on the inspection image;

[0092] In the formula of the splicing coefficient value, represents the accumulated value of the maximum splicing probabilities in the blocks at each same position in all inspection images when the preset block side length is . The greater the maximum splicing probability corresponding to the block at each position, the more accurate the performance characteristics, and the greater the splicing coefficient value.

[0093] The larger the splicing coefficient value under each preset block side length, the more device features are exhibited in the spliced image under the preset block side length, which is more conducive to subsequent inspection of the device. Therefore, the larger the splicing coefficient value, the more necessary it is to perform division and splicing under the corresponding block side length to screen out the optimal block side length.

[0094] Preferably, in an embodiment of the present invention, the method for obtaining the optimal block side length and the splicing blocks constituting the best spliced image includes:

[0095] Select the one with the largest splicing coefficient value among different preset block side lengths, and use the corresponding preset block side length as the optimal block side length; for the optimal block side length, obtain the splicing blocks corresponding to all positions in different inspection images as the optimal splicing blocks to form the best spliced image.

[0096] Step S5: Inspect the device according to the best spliced image.

[0097] The best spliced image can provide a high-precision and distortion-free device inspection image, which helps to more intuitively display the device status.

[0098] It should be noted that in another embodiment of the present invention, inspecting the device through the obtained best spliced image includes: performing Gaussian filtering on the best spliced image, inputting the processed best spliced image into a neural network model for training, judging the abnormal degree of device construction in the image by manual scoring of the image, and dividing it between [0, 1]; inputting different inspection areas of the photovoltaic device into the trained neural network model for analysis. When the abnormal degree is greater than the preset abnormal threshold, a reminder is sent to the staff in the construction site by the drone, and reminder data is sent to the staff at the control terminal; when the abnormal degree is less than or equal to the preset abnormal threshold, the drone moves horizontally to the next area to be inspected, and at the same time, the relevant images collected are retained at the control terminal. Among them, the preset abnormal threshold is set to 0.3. In other embodiments of the present invention, the size of the preset abnormal threshold can be specifically set according to specific situations and will not be limited and elaborated here.

[0099] In summary, the present invention obtains the local sandstorm density of each pixel in each inspection image based on the local hue feature of each pixel in each inspection image and the local saturation distribution feature of the matching pixels in different inspection images; obtains the equipment performance of each pixel in the inspection image based on the position distribution feature of the edge pixels on different edge lines in the inspection image; obtains multiple blocks of each inspection image based on a preset block side length; obtains the splicing coefficient value corresponding to the preset block side length according to the splicing probability distribution of the pixels in each block in different training images, and screens out the optimal block side length and the optimal splicing blocks constituting the best spliced image. The present invention improves the accuracy of equipment inspection by obtaining the best spliced image that more comprehensively represents the equipment state during construction inspection.

[0100] The present invention also proposes a desert photovoltaic equipment inspection system based on a drone and an AI algorithm, including a memory, a processor, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of any one of the desert photovoltaic equipment inspection methods based on a drone and an AI algorithm are implemented.

[0101] It should be noted that: the above sequence of the embodiments of the present invention is only for description and does not represent the superiority or inferiority of the embodiments. The processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0102] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other. The key point of each embodiment is to illustrate the differences from other embodiments.

Claims

1. A method for inspecting desert photovoltaic equipment based on drones and AI algorithms, characterized in that, The method includes: Obtaining multiple inspection images of the inspection area of the photovoltaic device; obtaining matching pixel points between different inspection images, and obtaining the local sandstorm density of each pixel point in each inspection image according to the local hue feature of each pixel point in each inspection image and the local saturation distribution feature of the matching pixel points in different inspection images; obtaining the device performance degree of each pixel point in the inspection image according to the position distribution feature of the edge pixel points on different edge lines in the inspection image; Obtaining the splicing probability of each pixel point in each inspection image according to the change trend of the device performance degree and the local sandstorm density of each pixel point relative to the corresponding matching pixel points in other inspection images; Obtaining multiple blocks of each inspection image based on the preset block side length; obtaining the splicing coefficient value corresponding to the preset block side length according to the splicing probability distribution of the pixel points in each block in different training images, and screening out the optimal block side length and the optimal splicing blocks that constitute the best spliced image; Inspecting the device according to the best spliced image; The method for obtaining the local sandstorm density includes: Obtaining the saturation mean value of all pixel points in the neighborhood range of each pixel point on each inspection image in the HSV space as the local saturation; obtaining the maximum and minimum values of the local saturation of the matching pixel points in different inspection images, and normalizing the local saturation of each pixel point in each inspection image as the relative saturation feature of each pixel point in each inspection image; Obtaining the fluctuation degree of the hue of all matching pixel points in the neighborhood window of each pixel point on the inspection image in the HSV space as the local hue feature; Obtaining the local sandstorm density of each pixel point on each inspection image according to the relative saturation feature and the local hue feature, and both the relative saturation feature and the local hue feature are negatively correlated with the local sandstorm density.

2. The inspection method of desert photovoltaic equipment based on drones and AI algorithms according to claim 1, characterized in that The method for obtaining the matching pixel points includes: Obtaining the matching pixel points between different inspection images after grayscale processing based on the SIFT matching algorithm.

3. The inspection method of desert photovoltaic equipment based on drones and AI algorithms according to claim 1, characterized in that, The method for obtaining the device performance degree includes: Performing edge detection on the inspection image after grayscale processing to obtain multiple edge lines corresponding to the inspection image; obtaining the angle between the tangent of each edge pixel point on each edge on each inspection image and the horizontal direction as the tangent angle of each edge pixel point; Obtaining the device performance degree of each edge pixel point according to the change trend of the tangent angles of all edge pixel points on each edge line; For other pixel points except the edge pixel points, the corresponding device performance degree is set to the positive integer 1.

4. The inspection method of desert photovoltaic equipment based on drones and AI algorithms according to claim 3, characterized in that, The obtaining the device performance degree of each edge pixel point according to the change trend of the tangent angles of all edge pixel points on each edge line includes: Construct a broken line of the tangent angles of all edge pixels on each edge line in the order of the pixel positions, and obtain the extreme points on the broken line of the tangent angles; obtain the upper envelope line fitted by all the maximum points and the lower envelope line fitted by all the minimum points, calculate the mean value of the data of all edge pixels between the upper envelope line and the lower envelope line, form a new broken line of the tangent angles, and perform a preset number of processes on the broken line of the tangent angles to obtain a corrected broken line of the tangent angles. Obtain the sum of the differences in the corrected tangent angles between each edge pixel and its adjacent edge pixels on each edge in each inspection image, and use it as the device performance degree of each edge pixel.

5. The inspection method of desert photovoltaic equipment based on drones and AI algorithms according to claim 1, wherein The method for obtaining the splicing probability includes: Obtain the difference in the device performance degree between each pixel in each inspection image and the matching pixel in each other inspection image, as the device performance difference. According to the device performance differences between each pixel in each inspection image and the matching pixels in different other inspection images, and the local sandstorm density of the corresponding pixels in different inspection images, obtain the splicing probability of each pixel in each inspection image. Both the device performance difference and the local sandstorm density are negatively correlated with the splicing probability.

6. The inspection method of desert photovoltaic equipment based on drones and AI algorithms according to claim 1, characterized in that, The method for obtaining the splicing coefficient value includes: Obtain the mean value of the splicing probabilities of all pixels in each block in each inspection image, as the splicing probability level corresponding to each block. Select the block with the maximum splicing probability level among the blocks at each same position in all inspection images, and use the block at each position in the corresponding inspection image as the splicing block. Obtain the cumulative value of the splicing probability levels corresponding to the splicing blocks at all positions, and calculate the product of the cumulative value and the preset block side length, as the splicing coefficient value corresponding to the preset block side length.

7. A method for inspecting desert photovoltaic equipment based on drones and AI algorithms according to claim 6, characterized in that, The method for obtaining the optimal block side length and the splicing blocks constituting the best spliced image includes: Select the preset block side length with the maximum splicing coefficient value among different preset block side lengths, and use the corresponding preset block side length as the optimal block side length; for the optimal block side length, obtain the splicing blocks corresponding to all positions in different inspection images, as the optimal splicing blocks, and form the best spliced image.

8. A method for inspecting desert photovoltaic equipment based on drones and AI algorithms according to claim 1, characterized in that, The method for obtaining the neighborhood range includes: With each pixel as the center, construct a range with an equal width as the neighborhood range of each pixel.

9. A desert photovoltaic equipment inspection system based on drones and AI algorithms, the system comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the steps of the method for inspecting desert photovoltaic devices based on an unmanned aerial vehicle and an AI algorithm according to any one of claims 1 to 8.

Images