Photovoltaic panel early warning method, device and equipment based on unmanned aerial vehicle and medium

Abstract

The invention provides a photovoltaic panel early warning method and device based on an unmanned aerial vehicle, equipment and a medium. The method comprises the following steps: extracting vertex image coordinates corresponding to each photovoltaic string in a first photovoltaic string image in a photovoltaic string image sequence; determining a target photovoltaic string based on vertex image coordinates corresponding to each photovoltaic string in the first photovoltaic string image; determining a reference projection area of the target photovoltaic string in the first photovoltaic string image based on the vertex image coordinate of the target photovoltaic string in the first photovoltaic string image; determining a target projection area of the target photovoltaic string in the second photovoltaic string image based on the vertex image coordinate of the target photovoltaic string in the second photovoltaic string image; based on the reference projection area and the target projection area, determining the projection area variation of the target photovoltaic string; and if the projection area variable quantity of the target photovoltaic string meets a preset change condition, generating a photovoltaic panel angle abnormity early warning. Therefore, the power generation efficiency of the photovoltaic panel is improved.

Description

TECHNICAL FIELD

[0001] Embodiments of the present disclosure relate to the technical field of image processing, and in particular, to a method and device for photovoltaic panel early warning based on a UAV, and a medium. BACKGROUND

[0002] Photovoltaic power stations are usually built in slopes or gullies. Due to unstable geology or damage to photovoltaic panel supports, the photovoltaic panels may settle or change in angle, thereby causing the area of the photovoltaic panels receiving sunlight to change and reducing the power generation efficiency of the photovoltaic panels. At the present stage, photovoltaic power stations only discover photovoltaic panel abnormalities after the photovoltaic panels completely collapse.

[0003] However, the existing method is difficult to discover photovoltaic panel abnormalities in a timely manner, thereby reducing the power generation efficiency of the photovoltaic panels. SUMMARY

[0004] Embodiments described herein provide a method and device for photovoltaic panel early warning based on a UAV, which overcomes the above problems.

[0005] In a first aspect, according to the content of the present disclosure, a method for photovoltaic panel early warning based on a UAV is provided, characterized in that it comprises:

[0006] obtaining a time series-based photovoltaic string image sequence captured by a UAV; extracting vertex image coordinates corresponding to each photovoltaic string in a first photovoltaic string image in the photovoltaic string image sequence; and extracting vertex image coordinates corresponding to each photovoltaic string in a second photovoltaic string image in the photovoltaic string image sequence;

[0007] determining a target photovoltaic string based on the vertex image coordinates corresponding to each photovoltaic string in the first photovoltaic string image;

[0008] determining a reference projection area of the target photovoltaic string in the first photovoltaic string image based on the vertex image coordinates of the target photovoltaic string in the first photovoltaic string image, and determining a target projection area of the target photovoltaic string in the second photovoltaic string image based on the vertex image coordinates of the target photovoltaic string in the second photovoltaic string image, the vertex image coordinates of the target photovoltaic string in the second photovoltaic string image being extracted from the vertex image coordinates corresponding to each photovoltaic string in the second photovoltaic string image;

[0009] determining a projection area change amount of the target photovoltaic string based on the reference projection area and the target projection area, and generating a photovoltaic panel angle abnormality early warning if the projection area change amount of the target photovoltaic string meets a preset change condition.

[0010] In a second aspect, according to the present disclosure, a UAV-based photovoltaic panel early warning device is provided, comprising:

[0011] an acquisition and extraction module configured to acquire a time-series-based photovoltaic string image sequence captured by a UAV, extract vertex image coordinates of each photovoltaic string in a first photovoltaic string image in the photovoltaic string image sequence, and extract vertex image coordinates of each photovoltaic string in a second photovoltaic string image in the photovoltaic string image sequence;

[0012] a first determination module configured to determine a target photovoltaic string based on the vertex image coordinates of each photovoltaic string in the first photovoltaic string image;

[0013] a second determination module configured to determine a reference projection area of the target photovoltaic string in the first photovoltaic string image based on the vertex image coordinates of the target photovoltaic string in the first photovoltaic string image, and determine a target projection area of the target photovoltaic string in the second photovoltaic string image based on the vertex image coordinates of the target photovoltaic string in the second photovoltaic string image, the vertex image coordinates of the target photovoltaic string in the second photovoltaic string image being extracted from the vertex image coordinates of each photovoltaic string in the second photovoltaic string image;

[0014] a third determination module configured to determine a projection area change amount of the target photovoltaic string based on the reference projection area and the target projection area, and generate a photovoltaic panel angle abnormality early warning if the projection area change amount of the target photovoltaic string meets a preset change condition.

[0015] In a third aspect, a computer device is provided, comprising a memory and a processor, the memory storing a computer program, and the processor implementing the steps of the UAV-based photovoltaic panel early warning method according to any one of the above embodiments when executing the computer program.

[0016] In a fourth aspect, a computer readable storage medium is provided, the computer readable storage medium storing a computer program, and the computer program implementing the steps of the UAV-based photovoltaic panel early warning method according to any one of the above embodiments when executed by a processor.

[0017] The photovoltaic panel early warning method based on the unmanned aerial vehicle provided in the embodiments of the present application comprises the following steps: acquiring a time sequence-based image sequence of photovoltaic strings photographed by the unmanned aerial vehicle; extracting vertex image coordinates corresponding to each photovoltaic string in a first photovoltaic string image in the image sequence of photovoltaic strings; and extracting vertex image coordinates corresponding to each photovoltaic string in a second photovoltaic string image in the image sequence of photovoltaic strings; determining a target photovoltaic string based on the vertex image coordinates corresponding to each photovoltaic string in the first photovoltaic string image; determining a reference projection area of the target photovoltaic string in the first photovoltaic string image based on the vertex image coordinates of the target photovoltaic string in the first photovoltaic string image; determining a target projection area of the target photovoltaic string in the second photovoltaic string image based on the vertex image coordinates of the target photovoltaic string in the second photovoltaic string image, wherein the vertex image coordinates of the target photovoltaic string in the second photovoltaic string image are extracted from the vertex image coordinates corresponding to each photovoltaic string in the second photovoltaic string image; determining a projection area variation of the target photovoltaic string based on the reference projection area and the target projection area; and generating a photovoltaic panel angle abnormality early warning if the projection area variation of the target photovoltaic string meets a preset variation condition. In this way, the area variation of the same photovoltaic string at different time points is used to effectively identify the photovoltaic panel abnormality and generate an abnormality early warning, thereby improving the power generation efficiency of the photovoltaic panel.

[0018] The above description is only a summary of the technical solutions of the embodiments of the present application. In order to more clearly understand the technical means of the embodiments of the present application, the embodiments of the present application can be implemented according to the content of the description, and in order to make the above and other purposes, features and advantages of the embodiments of the present application more obvious and easy to understand, the specific embodiments of the present application are described below. BRIEF DESCRIPTION OF DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings of the embodiments will be briefly described below. It should be noted that the drawings described below only relate to some embodiments of the present disclosure, but not limit the present disclosure, wherein:

[0020] Figure 1 is a flow diagram of a photovoltaic panel early warning method based on an unmanned aerial vehicle provided by the present disclosure.

[0021] Figure 2 is a structural diagram of a target photovoltaic string provided by the present disclosure.

[0022] Figure 3 is a structural diagram of another target photovoltaic string provided by the present disclosure.

[0023] Figure 4 is a structural diagram of a photovoltaic panel early warning device based on an unmanned aerial vehicle provided by the present disclosure.

[0024] Figure 5 is a structural diagram of a computer device provided by the present disclosure.

[0025] It should be noted that the elements in the drawings are schematic and not drawn to scale. DETAILED DESCRIPTION

[0026] In order to make the purpose, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions of the embodiments of the present disclosure will be described clearly and completely below in conjunction with the drawings. Obviously, the described embodiments are part of the embodiments of the present disclosure, rather than all the embodiments. Based on the described embodiments of the present disclosure, all other embodiments obtained by a person of ordinary skill in the art without any inventive effort also belong to the scope of protection of the present disclosure.

[0027] Unless otherwise defined, all terms (including technical and scientific terms) used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this present subject matter belongs. It will be further understood that terms, such as those defined in commonly used dictionaries, should be interpreted as having a meaning that is consistent with their meaning in the context of the specification and relevant art and will not be interpreted in an idealized or overly formal sense unless expressly so defined herein. As used herein, the statement that two or more parts are "connected" or "coupled" together refer to an indirect or direct connection or coupling.

[0028] Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase "in an embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily mutually exclusive of one another. A person of ordinary skill in the art will readily recognize from the disclosure herein, given the total volume of this application that the embodiments described herein can be combined with one another in various ways.

[0029] The term "and / or", merely used as a description of associated objects, means that there can be three kinds of relations, for example, A and / or B, can represent: there is A, there are A and B, and there is B. In addition, the character " / " in this paper generally represents that the front and rear associated objects are a "or" relationship. Terms such as "first" and "second" are only used to distinguish one component (or part of a component) from another component (or another part of a component).

[0030] In the description of the present application, unless otherwise specified, the meaning of "a plurality of" is two or more (including two), and similarly, "a plurality of groups" means two or more groups (including two groups).

[0031] In order to make the person skilled in the art better understand the present application, the technical solutions in the embodiments of the present application will be described clearly and completely below in conjunction with the drawings.

[0032] Figure 1 is a flowchart of a photovoltaic panel early warning method based on a UAV provided by an embodiment of the present disclosure, as shown in the figure Figure 1 The specific process of the photovoltaic panel early warning method based on a UAV includes the following steps.

[0033] S110, obtain a time series-based image sequence of photovoltaic strings taken by a UAV; extract vertex image coordinates corresponding to each photovoltaic string in a first photovoltaic string image in the image sequence of photovoltaic strings; and extract vertex image coordinates corresponding to each photovoltaic string in a second photovoltaic string image in the image sequence of photovoltaic strings.

[0034] The UAV can be instructed to reach a preset shooting point according to a preset route at different time points and take photos of the photovoltaic strings at a preset angle by sending a photovoltaic string inspection instruction to the UAV. The photovoltaic strings can include a plurality of photovoltaic panels.

[0035] The cloud platform can send multiple photovoltaic string inspection instructions to the UAV. Each photovoltaic string inspection instruction can instruct the UAV to reach the same shooting point according to the same route at a corresponding time point to collect photovoltaic string images. For example, the cloud platform sends a photovoltaic string inspection instruction to the UAV to instruct the UAV to execute the same inspection route at different times and take photos of the photovoltaic strings at the target route point. When taking photos, the gimbal of the UAV is perpendicular to the horizontal and downward, and the gimbal deflection angle is 90°.

[0036] The image sequence of photovoltaic strings includes a first photovoltaic string image taken at a first time and a second photovoltaic string image taken at a second time. The first time is earlier than the second time, and the second time corresponds to any shooting time after the first time. It should be noted that the first time can correspond to the shooting time when the UAV inspects for the first time, and the second time can correspond to the shooting time when the UAV inspects for the second time or subsequent inspections.

[0037] The shape of the photovoltaic string is a quadrilateral, and the corresponding vertex image coordinates of the quadrilateral are the position coordinates of the four vertices of the quadrilateral in the photovoltaic string image.

[0038] In some embodiments, extracting the vertex image coordinates corresponding to each photovoltaic string in the first photovoltaic string image in the image sequence of photovoltaic strings includes:

[0039] The first photovoltaic string image is subjected to contour extraction of the photovoltaic string to obtain the surrounding contour of each photovoltaic string in the first photovoltaic string image; and the vertex image coordinates corresponding to each photovoltaic string in the first photovoltaic string image are determined based on the surrounding contour of each photovoltaic string in the first photovoltaic string image.

[0040] The edge detection algorithm can be used to extract the outline of the photovoltaic string in the first photovoltaic string image to obtain the surrounding outline of each photovoltaic string in the first photovoltaic string image, including: using the Canny edge detection algorithm to process the first photovoltaic string image, such as smoothing the first photovoltaic string image by a Gaussian filter to reduce noise interference; calculating the gradient amplitude and direction of each pixel point in the first photovoltaic string image to determine the possible edge position; refining the edge by the non-maximum suppression technology, and retaining the point with the maximum local gradient as a candidate edge point; using a double-threshold method to screen out the real edge, and obtaining the outline information of each photovoltaic string in the first photovoltaic string image through an edge connection algorithm.

[0041] Therefore, the recognition accuracy of the photovoltaic string outline in the first photovoltaic string image is effectively improved, and reliable basic data is provided for subsequent fault detection and early warning.

[0042] In some embodiments, the vertex image coordinates corresponding to each photovoltaic string in the second photovoltaic string image in the sequence of photovoltaic string images are extracted, including:

[0043] The outline of the photovoltaic string in the second photovoltaic string image is extracted to obtain the surrounding outline of each photovoltaic string in the second photovoltaic string image; and based on the surrounding outline of each photovoltaic string in the second photovoltaic string image, the vertex image coordinates corresponding to each photovoltaic string in the second photovoltaic string image are determined.

[0044] The edge detection algorithm can be used to extract the outline of the photovoltaic string in the second photovoltaic string image to obtain the surrounding outline of each photovoltaic string in the second photovoltaic string image, including: using the Canny edge detection algorithm to process the second photovoltaic string image, such as smoothing the second photovoltaic string image by a Gaussian filter to reduce noise interference; calculating the gradient amplitude and direction of each pixel point in the second photovoltaic string image to determine the possible edge position; refining the edge by the non-maximum suppression technology, and retaining the point with the maximum local gradient as a candidate edge point; using a double-threshold method to screen out the real edge, and obtaining the outline information of each photovoltaic string in the second photovoltaic string image through an edge connection algorithm.

[0045] Therefore, the recognition accuracy of the photovoltaic string outline in the second photovoltaic string image is effectively improved, and reliable basic data is provided for subsequent fault detection and early warning.

[0046] In some embodiments, the method further comprises: performing Gaussian filtering on the first photovoltaic string image to denoise the first photovoltaic string image; and performing grayscale processing on the first photovoltaic string image; performing Gaussian filtering on the second photovoltaic string image to denoise the second photovoltaic string image; and performing grayscale processing on the second photovoltaic string image. In this way, by performing grayscale processing on the first photovoltaic string image and the second photovoltaic string image respectively, the data dimension can be reduced, the calculation complexity can be simplified, the key brightness information can be retained, the feature expressiveness of the image can be enhanced, the noise interference in the image can be effectively reduced, and the quality of the photovoltaic string image can be improved.

[0047] In S120, the target photovoltaic string is determined based on the vertex image coordinates of each photovoltaic string in the first photovoltaic string image.

[0048] In this way, the target photovoltaic string can be determined by selecting the photovoltaic string closest to the image center of the first photovoltaic string image.

[0049] In some embodiments, the target photovoltaic string is determined based on the vertex image coordinates of each photovoltaic string in the first photovoltaic string image, including:

[0050] In this way, the target photovoltaic string can be determined by calculating the contour center coordinates of each photovoltaic string in the first photovoltaic string image based on the vertex image coordinates of each photovoltaic string in the first photovoltaic string image, calculating the image distance between the contour center coordinates of each photovoltaic string in the first photovoltaic string image and the image center coordinates of the first photovoltaic string image, and determining the photovoltaic string corresponding to the smallest image distance as the target photovoltaic string.

[0051] In this way, the contour center coordinates of each photovoltaic string can be obtained by calculating the average value of the vertex image coordinates of each photovoltaic string. Specifically, the contour center coordinates of each photovoltaic string can be obtained by summing and averaging the horizontal and vertical coordinates of all vertices of each photovoltaic string.

[0052] In this way, by regarding the photovoltaic string closest to the image center of the photovoltaic string image as the photovoltaic string replacing the photovoltaic string in the first photovoltaic string image, the key region of the first photovoltaic string image can be quickly focused on, the calculation complexity can be effectively reduced, and the selection efficiency of the target photovoltaic string can be improved.

[0053] In S130, the reference projection area of the target photovoltaic string in the first photovoltaic string image is determined based on the vertex image coordinates of the target photovoltaic string in the first photovoltaic string image, and the target projection area of the target photovoltaic string in the second photovoltaic string image is determined based on the vertex image coordinates of the target photovoltaic string in the second photovoltaic string image.

[0054] The vertex image coordinates of the target photovoltaic string in the second photovoltaic string image are extracted from the vertex image coordinates corresponding to each photovoltaic string in the second photovoltaic string image. By analyzing the distribution characteristics of each photovoltaic string in the second photovoltaic string image, the vertex image coordinates of the target photovoltaic string can be accurately extracted from the vertex image coordinates corresponding to each photovoltaic string in the second photovoltaic string image. The reference projection area of the target photovoltaic string in the first photovoltaic string image is the projection area of the target photovoltaic string in the vertical horizontal direction at the first time; and the target projection area of the target photovoltaic string in the second photovoltaic string image is the projection area of the target photovoltaic string in the vertical horizontal direction at the second time.

[0055] As shown in Figure 2 , the vertex image coordinates of the target photovoltaic string in the first photovoltaic string image are (x 01 , y 01 ), (x 02 , y 02 ), (x 03 , y 03 ), and (x 04 , y 04 ), respectively. The reference projection area S0 of the target photovoltaic string in the first photovoltaic string image is (x 02 -x 01 )(y 04 -y 01 )(x 04 -x 01 )(y 02 -y 01 ) / 2. As shown in Figure 3 , the vertex image coordinates of the target photovoltaic string in the second photovoltaic string image are (x n1 , y n1 ), (x n2 , y n2 ), (x n3 , y n3 ), and (x n4 , y n4 ), respectively. The target projection area S n of the target photovoltaic string in the second photovoltaic string image is (x n2 -x n1 )(y n4 -y n1 )(x n4 -x n1 )(y n2 -y n1 ) / 2.

[0056] S140, determine a projection area change quantity of the target photovoltaic string based on the reference projection area and the target projection area; if the projection area change quantity of the target photovoltaic string meets a preset change condition, generate an angle abnormality early warning of the photovoltaic panel.

[0057] The projection area change quantity of the target photovoltaic string is a change quantity in a process from the reference projection area corresponding to the first moment to the target projection area corresponding to the second moment, that is, an area difference between the target projection area and the reference projection area.

[0058] The preset change condition can include a threshold range of the projection area change quantity or a specific change mode. When the projection area change quantity of the target photovoltaic string exceeds the set threshold or presents a change trend inconsistent with the normal situation, it is determined that the preset change condition is met. The angle abnormality early warning can be generated in a manner such as visual interface prompt, sound alarm, or sending a notification message to a specified terminal, so as to help the operation and maintenance personnel quickly locate the potential problem area and take timely measures to avoid energy loss or equipment damage caused by the angle abnormality of the photovoltaic panel.

[0059] In some embodiments, determining the projection area change quantity of the target photovoltaic string based on the reference projection area and the target projection area includes: calculating an area difference between the target projection area and the reference projection area; and determining the area difference between the target projection area and the reference projection area as the projection area change quantity of the target photovoltaic string. Thus, through the projection area change quantity, the morphological change of the target photovoltaic string in different time periods can be effectively reflected, and the angle change of the photovoltaic panel in different time periods can be effectively quantified.

[0060] In some embodiments, the method further includes:

[0061] obtaining a preset warning threshold and a photovoltaic panel area threshold; if the projection area change quantity of the target photovoltaic string is between the preset warning threshold and the photovoltaic panel area threshold, determining that the projection area change quantity of the target photovoltaic string meets the preset change condition; if the projection area change quantity of the target photovoltaic string is not between the preset warning threshold and the photovoltaic panel area threshold, determining that the projection area change quantity of the target photovoltaic string does not meet the preset change condition.

[0062] The photovoltaic panel area threshold can be used to describe the actual area of the target photovoltaic panel or the actual area of the target photovoltaic string. When it is determined that the projection area change quantity of the target photovoltaic string meets the preset change condition, it is determined that the angle of the target photovoltaic panel changes at the second moment; when it is determined that the projection area change quantity of the target photovoltaic string does not meet the preset change condition, it is determined that the angle of the target photovoltaic panel does not change at the second moment.

[0063] In this embodiment, a photovoltaic string image sequence photographed by a UAV based on a time sequence is acquired; vertex image coordinates corresponding to each photovoltaic string in a first photovoltaic string image in the photovoltaic string image sequence are extracted; vertex image coordinates corresponding to each photovoltaic string in a second photovoltaic string image in the photovoltaic string image sequence are extracted; a target photovoltaic string is determined based on the vertex image coordinates corresponding to each photovoltaic string in the first photovoltaic string image; a reference projection area of the target photovoltaic string in the first photovoltaic string image is determined based on the vertex image coordinates of the target photovoltaic string in the first photovoltaic string image; a target projection area of the target photovoltaic string in the second photovoltaic string image is determined based on the vertex image coordinates of the target photovoltaic string in the second photovoltaic string image, the vertex image coordinates of the target photovoltaic string in the second photovoltaic string image being extracted from the vertex image coordinates corresponding to each photovoltaic string in the second photovoltaic string image; a projection area variation of the target photovoltaic string is determined based on the reference projection area and the target projection area; and a photovoltaic panel angle abnormality early warning is generated if the projection area variation of the target photovoltaic string meets a preset variation condition. In this way, the area variation of the same photovoltaic string at different time points is used to effectively identify the photovoltaic panel abnormality and generate an abnormality early warning, thereby improving the photovoltaic panel power generation efficiency.

[0064] Figure 4 A structure schematic diagram of a photovoltaic panel early warning device based on a UAV is provided in this embodiment. The photovoltaic panel early warning device based on a UAV can include:

[0065] The acquisition and extraction module 410 is configured to acquire a photovoltaic string image sequence photographed by a UAV based on a time sequence; extract vertex image coordinates corresponding to each photovoltaic string in a first photovoltaic string image in the photovoltaic string image sequence; and extract vertex image coordinates corresponding to each photovoltaic string in a second photovoltaic string image in the photovoltaic string image sequence.

[0066] The first determination module 420 is configured to determine a target photovoltaic string based on the vertex image coordinates corresponding to each photovoltaic string in the first photovoltaic string image.

[0067] The second determination module 430 is configured to determine a reference projection area of the target photovoltaic string in the first photovoltaic string image based on the vertex image coordinates of the target photovoltaic string in the first photovoltaic string image; and determine a target projection area of the target photovoltaic string in the second photovoltaic string image based on the vertex image coordinates of the target photovoltaic string in the second photovoltaic string image, the vertex image coordinates of the target photovoltaic string in the second photovoltaic string image being extracted from the vertex image coordinates corresponding to each photovoltaic string in the second photovoltaic string image.

[0068] The third determining module 440 is configured to determine a projection area variation of the target photovoltaic string based on the reference projection area and the target projection area; and generate a photovoltaic panel angle abnormality early warning if the projection area variation of the target photovoltaic string meets a preset variation condition.

[0069] In this embodiment, the acquisition and extraction module 410 is specifically configured to:

[0070] The contour extraction of the photovoltaic string is performed on the first photovoltaic string image to obtain the surrounding contour of each photovoltaic string in the first photovoltaic string image; and the vertex image coordinates corresponding to each photovoltaic string in the first photovoltaic string image are determined based on the surrounding contour of each photovoltaic string in the first photovoltaic string image.

[0071] In this embodiment, the acquisition and extraction module 410 is specifically configured to:

[0072] The contour extraction of the photovoltaic string is performed on the second photovoltaic string image to obtain the surrounding contour of each photovoltaic string in the second photovoltaic string image; and the vertex image coordinates corresponding to each photovoltaic string in the second photovoltaic string image are determined based on the surrounding contour of each photovoltaic string in the second photovoltaic string image.

[0073] In this embodiment, the first determining module 420 is specifically configured to:

[0074] The contour center coordinates of each photovoltaic string in the first photovoltaic string image are determined based on the vertex image coordinates corresponding to each photovoltaic string in the first photovoltaic string image; the image distance between the contour center coordinates of each photovoltaic string in the first photovoltaic string image and the image center coordinates of the first photovoltaic string image is calculated; and the photovoltaic string corresponding to the minimum image distance is determined as the target photovoltaic string.

[0075] In this embodiment, the third determining module 440 is specifically configured to:

[0076] The area difference between the target projection area and the reference projection area is calculated; and the area difference between the target projection area and the reference projection area is determined as the projection area variation of the target photovoltaic string.

[0077] In this embodiment, the first processing module is further included.

[0078] The first processing module is configured to acquire a preset alarm threshold and a photovoltaic panel area threshold; determine that the projection area variation of the target photovoltaic string meets the preset variation condition if the projection area variation of the target photovoltaic string is between the preset alarm threshold and the photovoltaic panel area threshold; and determine that the projection area variation of the target photovoltaic string does not meet the preset variation condition if the projection area variation of the target photovoltaic string is not between the preset alarm threshold and the photovoltaic panel area threshold.

[0079] In the embodiment, the second processing module is further included.

[0080] The second processing module is configured to perform Gaussian filtering on the first photovoltaic string image to denoise the first photovoltaic string image, perform grayscale processing on the first photovoltaic string image, perform Gaussian filtering on the second photovoltaic string image to denoise the second photovoltaic string image, and perform grayscale processing on the second photovoltaic string image.

[0081] The UAV-based photovoltaic panel early warning device provided by the present disclosure can execute the method embodiments, and the specific implementation principles and technical effects can be referred to the method embodiments, which will not be described here again.

[0082] The present application also provides a computer device. For details, please refer to Figure 5 , Figure 5 The present application also provides a computer device. For details, please refer to

[0083] The computer device includes a memory 510 and a processor 520 which are connected to each other through a system bus. It should be noted that only the computer device with the memory 510 and the processor 520 is shown in the figure, but it should be understood that it is not required to implement all the shown components, and more or less components can be alternatively implemented. Among them, those skilled in the art can understand that the computer device herein is a device capable of automatically performing numerical calculation and / or information processing according to pre-set or stored instructions, and its hardware includes but is not limited to microprocessors, application specific integrated circuits (ASICs), field programmable gate arrays (FPGAs), digital signal processors (DSPs), embedded devices, etc.

[0084] The computer device can be a desktop computer, a notebook computer, a palm computer, a cloud server and other computing devices. The computer device can interact with the user through a keyboard, a mouse, a remote controller, a touchpad or a voice control device.

[0085] The memory 510 includes at least one type of readable storage medium, including nonvolatile memory or volatile memory, for example, flash memory, a hard disk, a multimedia card, a card-type memory (e.g., SD or DX memory, etc.), random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM), electrically erasable programmable read-only memory (EEPROM), programmable read-only memory (PROM), a magnetic memory, a magnetic disk, an optical disk, etc. The RAM can include static RAM or dynamic RAM. In some embodiments, the memory 510 can be an internal memory unit of the computer device, for example, a hard disk or a memory of the computer device. In other embodiments, the memory 510 can also be an external storage device of the computer device, for example, a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, or a flash card, etc. equipped on the computer device. Of course, the memory 510 can include both an internal memory unit and an external storage device of the computer device. In this embodiment, the memory 510 is generally used to store an operating system and various application software installed on the computer device, for example, program codes of the above-described method, etc. In addition, the memory 510 can also be used to temporarily store various data that has been output or will be output.

[0086] The processor 520 is generally used to perform the overall operation of the computer device. In this embodiment, the memory 510 is used to store program codes or instructions, which include computer operation instructions, and the processor 520 is used to execute the program codes or instructions stored in the memory 510 or process data, for example, run the program codes of the above-described method.

[0087] In this article, the bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Architecture (EISA) bus, etc. The bus system can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one thick line is shown in the figure, but it does not mean that there is only one bus or only one type of bus.

[0088] Another embodiment of the present application also provides a computer readable medium, which can be a computer readable signal medium or a computer readable medium. The processor in the computer reads the computer readable program code stored in the computer readable medium, so that the processor can perform the function actions specified in each step or combination of steps in the above method; generate the device implementing the function actions specified in each block or combination of blocks in the block diagram.

[0089] The computer readable medium includes but is not limited to electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device or apparatus, or any appropriate combination of the foregoing, for storing program codes or instructions, which include computer operation instructions, and processors for executing the program codes or instructions of the above method stored in the memory.

[0090] The definition of the memory and the processor can refer to the description of the foregoing computer device embodiment, which will not be repeated here.

[0091] In several embodiments provided in the present application, it should be understood that the disclosed system, device and method can be implemented in other ways. For example, the device embodiment described above is only schematic, for example, the division of modules or units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be indirect coupling or communication connection through some interface, device or unit, which can be electrical, mechanical or other forms.

[0092] The function units or modules in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of software function unit.

[0093] If the integrated unit is implemented in the form of a software function unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or say the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a number of instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to execute all or part of the steps of the methods in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various media that can store program codes.

[0094] In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The application can be implemented by means of both hardware and software, and any combination thereof. In the device claim enumerating several means, several of these means can be embodied by one and the same item of hardware. The mere fact that certain measures are recited in mutually different claims does not indicate that a combination of these measures cannot be used to advantage. The use of relative terms such as "first", "second" and "third", etc. does not connote any prioritization, but such terms are used to distinguish a certain feature from another feature with the same name. The steps of the methods described in the above embodiments should not be understood as necessarily limited in their sequence, except when this is explicitly specified.

[0095] The above embodiments are only used to illustrate the technical solutions of the present application, rather than limit them; even though the present application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that: it can still modify the technical solutions recorded in the foregoing embodiments, or make equivalent replacement for part of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A method for early warning of photovoltaic panels based on drones, characterized by, The method comprises: acquiring a time series-based photovoltaic string image sequence taken by a UAV; extracting vertex image coordinates corresponding to each photovoltaic string in a first photovoltaic string image in the photovoltaic string image sequence; and extracting vertex image coordinates corresponding to each photovoltaic string in a second photovoltaic string image in the photovoltaic string image sequence; determining a target photovoltaic string based on the vertex image coordinates corresponding to each photovoltaic string in the first photovoltaic string image; determining a reference projection area of the target photovoltaic string in the first photovoltaic string image based on the vertex image coordinates of the target photovoltaic string in the first photovoltaic string image, and determining a target projection area of the target photovoltaic string in the second photovoltaic string image based on the vertex image coordinates of the target photovoltaic string in the second photovoltaic string image, the vertex image coordinates of the target photovoltaic string in the second photovoltaic string image being extracted from the vertex image coordinates corresponding to each photovoltaic string in the second photovoltaic string image; determining a projection area variation of the target photovoltaic string based on the reference projection area and the target projection area, and generating a photovoltaic panel angle abnormality early warning if the projection area variation of the target photovoltaic string meets a preset variation condition.

2. The method of claim 1, wherein, The extraction of the vertex image coordinates corresponding to each photovoltaic string in the first photovoltaic string image in the photovoltaic string image sequence comprises: performing photovoltaic string contour extraction on the first photovoltaic string image to obtain an enclosing contour of each photovoltaic string in the first photovoltaic string image; determining the vertex image coordinates corresponding to each photovoltaic string in the first photovoltaic string image based on the enclosing contour of each photovoltaic string in the first photovoltaic string image.

3. The method of claim 2, wherein, The extraction of the vertex image coordinates corresponding to each photovoltaic string in the second photovoltaic string image in the photovoltaic string image sequence comprises: performing photovoltaic string contour extraction on the second photovoltaic string image to obtain an enclosing contour of each photovoltaic string in the second photovoltaic string image; determining the vertex image coordinates corresponding to each photovoltaic string in the second photovoltaic string image based on the enclosing contour of each photovoltaic string in the second photovoltaic string image.

4. The method of claim 1, wherein, The determination of the target photovoltaic string based on the vertex image coordinates corresponding to each photovoltaic string in the first photovoltaic string image comprises: determining contour center coordinates of each photovoltaic string in the first photovoltaic string image based on the vertex image coordinates corresponding to each photovoltaic string in the first photovoltaic string image; calculating image distances between the contour center coordinates of each photovoltaic string in the first photovoltaic string image and an image center coordinate of the first photovoltaic string image, and determining a photovoltaic string corresponding to a minimum image distance as the target photovoltaic string.

5. The method of claim 1, wherein, The determination of the projection area variation of the target photovoltaic string based on the reference projection area and the target projection area comprises: calculating an area difference between the target projection area and the reference projection area, and determining the area difference between the target projection area and the reference projection area as the projection area variation of the target photovoltaic string.

6. The method of claim 1, wherein, The method further comprises: acquiring a preset warning threshold and a photovoltaic panel area threshold; If the projection area change amount of the target photovoltaic string is between the preset warning threshold and the photovoltaic panel area threshold, it is determined that the projection area change amount of the target photovoltaic string meets a preset change condition. If the projection area change amount of the target photovoltaic string is not between the preset warning threshold and the photovoltaic panel area threshold, it is determined that the projection area change amount of the target photovoltaic string does not meet a preset change condition.

7. The method of claim 3, wherein, Further comprising: performing Gaussian filtering on the first photovoltaic string image to denoise the first photovoltaic string image; and performing grayscale processing on the first photovoltaic string image; performing Gaussian filtering on the second photovoltaic string image to denoise the second photovoltaic string image; and performing grayscale processing on the second photovoltaic string image.

8. A drone-based photovoltaic panel early warning device, characterized in that, Comprising: an acquisition and extraction module configured to acquire a photovoltaic string image sequence captured by a UAV based on a time sequence; extract the vertex image coordinates corresponding to each photovoltaic string in the first photovoltaic string image in the photovoltaic string image sequence; and extract the vertex image coordinates corresponding to each photovoltaic string in the second photovoltaic string image in the photovoltaic string image sequence; a first determination module configured to determine a target photovoltaic string based on the vertex image coordinates corresponding to each photovoltaic string in the first photovoltaic string image; a second determination module configured to determine a reference projection area of the target photovoltaic string in the first photovoltaic string image based on the vertex image coordinates of the target photovoltaic string in the first photovoltaic string image; and determine a target projection area of the target photovoltaic string in the second photovoltaic string image based on the vertex image coordinates of the target photovoltaic string in the second photovoltaic string image, the vertex image coordinates of the target photovoltaic string in the second photovoltaic string image being extracted from the vertex image coordinates corresponding to each photovoltaic string in the second photovoltaic string image; a third determination module configured to determine a projection area change amount of the target photovoltaic string based on the reference projection area and the target projection area; and generate a photovoltaic panel angle abnormality warning if the projection area change amount of the target photovoltaic string meets a preset change condition.

9. A computer device, comprising: A memory and a processor, the memory storing a computer program, and the processor executing the computer program to implement the UAV-based photovoltaic panel warning method of any one of claims 1-7.

10. A computer-readable storage medium having stored thereon a computer program, characterized in that, The computer program is executed by the processor to implement the UAV-based photovoltaic panel warning method of any one of claims 1-7.

Images