Method, device and drone for detecting photovoltaic panels

Abstract

The embodiment of the present invention provides a method, device and drone for detecting photovoltaic panels, the method comprising: the ground station of the drone obtains an infrared image taken by an infrared camera carried by the drone, the infrared image includes image information of the photovoltaic panel; the ground station performs image recognition processing on the infrared image to obtain the regional position of the image of the photovoltaic panel in the infrared image; the ground station determines whether the photovoltaic panel has a fault based on the information of the regional position. The method, device and drone provided by the embodiment of the present invention can improve the detection efficiency of photovoltaic panels in the electric field.

Description

Technical Field

[0001] The present application relates to the field of drone application technology, and in particular to a method, device and drone for detecting photovoltaic panels. Background Art

[0002] Photovoltaic panels are devices that convert light energy into electrical energy. When exposed to sunlight, they collect heat and convert light energy into direct current. However, it is precisely because of their long-term exposure to sunlight that they are more prone to wear and tear and damage.

[0003] The existing technology for detecting photovoltaic panels generally includes two methods: manual inspection and inverter monitoring. Among them, manual inspection requires technicians to regularly go to the project site for inspection, which is a large workload and low efficiency. The inverter monitoring method is to use the inverter to monitor the total current or total voltage of the photovoltaic panels in a certain area in real time. When the current or voltage in the area is abnormal, it can only be judged that the photovoltaic panels in the area may have failed, but it is impossible to accurately locate which photovoltaic panel has failed. Therefore, technicians are still required to go to the area for investigation, and there is still a problem of low efficiency. Summary of the invention

[0004] The embodiments of the present invention provide a method, a device and a drone for detecting photovoltaic panels, so as to improve the detection efficiency of photovoltaic panels in an electric field.

[0005] A first aspect of an embodiment of the present invention provides a method for detecting a photovoltaic panel, comprising:

[0006] The ground station of the UAV obtains an infrared image taken by an infrared camera carried by the UAV, wherein the infrared image includes image information of the photovoltaic panel;

[0007] The ground station performs image recognition processing on the infrared image to obtain the regional position of the image of the photovoltaic panel in the infrared image;

[0008] The ground station determines whether the photovoltaic panel has failed based on the information of the regional location.

[0009] A second aspect of an embodiment of the present invention provides a method for detecting a photovoltaic panel, comprising:

[0010] The drone obtains an infrared image taken by an infrared camera carried by the drone, wherein the infrared image includes image information of the photovoltaic panel;

[0011] The drone performs image recognition processing on the infrared image to obtain the regional position of the image of the photovoltaic panel in the infrared image;

[0012] The drone determines whether the photovoltaic panel has failed based on the information of the regional location.

[0013] A third aspect of an embodiment of the present invention provides a ground station, including:

[0014] A communication interface and one or more processors; the one or more processors work individually or in collaboration, and the communication interface is connected to the processors;

[0015] The communication interface is used to: obtain an infrared image taken by an infrared camera carried by the drone, wherein the infrared image includes image information of the photovoltaic panel;

[0016] The processor is used to: perform image recognition processing based on the infrared image to obtain the regional position of the image of the photovoltaic panel in the infrared image;

[0017] The processor is further configured to determine whether a fault occurs to the photovoltaic panel based on the information of the regional location.

[0018] A fourth aspect of an embodiment of the present invention provides a control device, including:

[0019] A communication interface and one or more processors; the one or more processors work individually or in collaboration, and the communication interface is communicatively connected to the processors;

[0020] The communication interface is used to: obtain an infrared image taken by an infrared camera carried by the drone, wherein the infrared image includes image information of the photovoltaic panel;

[0021] The processor is used to: perform image recognition processing based on the infrared image to obtain the regional position of the image of the photovoltaic panel in the infrared image;

[0022] The processor is further configured to determine whether a fault occurs to the photovoltaic panel based on the information of the regional location.

[0023] A fifth aspect of an embodiment of the present invention provides a drone, including:

[0024] body;

[0025] A power system, installed on the fuselage, for providing flight power;

[0026] An infrared camera, mounted on the fuselage, for capturing infrared images;

[0027] A visible light camera, mounted on the body, for capturing visible light images;

[0028] And the control device described in the fourth aspect above.

[0029] The method, device and drone for detecting photovoltaic panels provided by the embodiments of the present invention obtain an infrared image including photovoltaic panel image information obtained by the infrared camera carried by the drone through the ground station of the drone, and perform image recognition processing based on the infrared image to obtain the regional position of the image of the photovoltaic panel in the infrared image, thereby determining whether the photovoltaic panel has a fault based on the information of the regional position. In this way, it is possible to inspect the photovoltaic panels in the electric field through the drone and identify the faulty photovoltaic panels, thus avoiding the waste of human resources caused by manual inspection. Compared with the existing manual inspection and inverter monitoring methods, the drone inspection method has a higher inspection efficiency and can timely and accurately identify faulty photovoltaic panels from the electric field, thereby enhancing the safety of electric field power generation, increasing the power generation of the electric field, and avoiding the losses caused by the accumulation of photovoltaic panel problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 A flow chart of a method for detecting a photovoltaic panel provided by the present invention;

[0031] Figure 2 A schematic diagram of the connection between a ground station and a drone provided in an embodiment of the present invention;

[0032] Figure 3a A schematic diagram of a right-angle template for determining a lower right vertex provided by an embodiment of the present invention;

[0033] Figure 3b A schematic diagram of a right-angle template for determining a lower left vertex provided by an embodiment of the present invention;

[0034] Figure 3c A schematic diagram of a right-angle template for determining an upper right vertex provided by an embodiment of the present invention;

[0035] Figure 3d A schematic diagram of a right-angle template for determining an upper left vertex provided by an embodiment of the present invention;

[0036] Figure 4 for Figure 3a Schematic diagram of the position of the right-angle template in the infrared image;

[0037] Figure 5 A flow chart of a method for detecting a photovoltaic panel provided by an embodiment of the present invention;

[0038] Figure 6a A schematic diagram of a method for marking the regional position of a photovoltaic panel image in an infrared image provided by an embodiment of the present invention;

[0039] Figure 6b A schematic diagram of another method for marking the regional position of a photovoltaic panel image in an infrared image provided by an embodiment of the present invention;

[0040] Figure 7 A schematic diagram of the marking result of the fault point provided by an embodiment of the present invention;

[0041] Figure 8 A flow chart of a method for detecting a photovoltaic panel provided by an embodiment of the present invention;

[0042] Fig. 9 A flow chart of a method for detecting a photovoltaic panel provided by an embodiment of the present invention;

[0043] Fig.10 A schematic diagram of the structure of a ground station provided by an embodiment of the present invention;

[0044] Fig.11 A schematic diagram of the structure of a ground station provided by an embodiment of the present invention;

[0045] Fig.12 A schematic diagram of the structure of a control device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0046] The technical solutions in the embodiments of the present invention will be described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0047] It should be noted that when a component is said to be "fixed to" another component, it can be directly on the other component or there can be a central component. When a component is said to be "connected to" another component, it can be directly connected to the other component or there can be a central component at the same time.

[0048] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used herein in the specification of the present invention are only for the purpose of describing specific embodiments and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0049] Some embodiments of the present invention are described in detail below in conjunction with the accompanying drawings. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0050] The embodiment of the present invention provides a method for detecting a photovoltaic panel. Figure 1 , Figure 1 A flow chart of a method for detecting a photovoltaic panel provided by the present invention, such as Figure 1 As shown, the method in this embodiment includes:

[0051] Step 101: The ground station of the UAV obtains an infrared image taken by an infrared camera carried by the UAV, wherein the infrared image includes image information of the photovoltaic panel.

[0052] In this embodiment, the ground station is a device with computing function and / or processing capability, and the device can specifically be a remote control, a smart phone, a tablet computer, a laptop computer, a watch, a bracelet, etc. and a combination thereof.

[0053] like Figure 2 As shown, the ground station 21 and the drone 22 are connected via an application programming interface (API) 23. Specifically, the ground station 21 and the drone 22 can be connected wirelessly, for example, via at least one of the following methods: wireless fidelity (WIreless-Fidelity, referred to as WI-FI), Bluetooth, software defined radio (SDR) or other custom protocols.

[0054] Optionally, in this embodiment, the UAV can automatically cruise in the electric field according to a predetermined route, or the UAV can be controlled by a ground station to cruise in the electric field.

[0055] In this embodiment, the drone may include the following two configuration modes:

[0056] In one possible configuration, the drone is only equipped with an infrared camera. The drone sends the infrared images it captures to the ground station while cruising. In this configuration, the drone needs to hover at the shooting location for a preset time when photographing the photovoltaic panels. The time length can be set arbitrarily to meet the time required for the ground station to process the image.

[0057] In another possible configuration, the drone is equipped with both a visible light camera and an infrared camera. The drone takes infrared images and visible light images at the same time while cruising, and sends the infrared images and visible light images taken at the same time to the ground station at the same time. At this time, the drone can be set to stay at the shooting location for a preset time length, or it can not stay. Among them, this embodiment assumes that the infrared image and the visible light image taken at the same time overlap.

[0058] Step 102: The ground station performs image recognition processing on the infrared image to obtain the regional position of the image of the photovoltaic panel in the infrared image.

[0059] In this embodiment, the method for the ground station to perform image recognition processing on the infrared image includes the following:

[0060] In one possible method, based on the characteristic that the surface temperature of the photovoltaic panel is higher than the ambient temperature, the ground station is configured to determine the edge position of the image of the photovoltaic panel in the infrared image according to the temperature distribution presented in the infrared image. For example, when there is a dividing line in the infrared image and the temperature difference on both sides thereof is higher than a preset threshold, the edge position is determined to be an edge position of the image of the photovoltaic panel in the infrared image. Furthermore, the ground station determines the regional position of the image of the photovoltaic panel in the infrared image according to the edge position of the image of the photovoltaic panel in the infrared image. The preset threshold involved above can be set as needed and is not specifically limited in this embodiment.

[0061] Optionally, in this embodiment, the method for determining the regional position of the image of the photovoltaic panel in the infrared image according to the edge position of the image of the photovoltaic panel in the infrared image includes the following:

[0062] In one possible method, the ground station configures the geometric parameters of the figure enclosed by the edge positions determined above with the pre-stored geometric parameters of the image of the photovoltaic panel in the infrared image, and if the absolute value of the difference between the two is within a preset range, the regional position of the figure enclosed by the edge positions is determined to be the regional position of the image of the photovoltaic panel in the infrared image. The above-mentioned geometric parameters include aspect ratio and / or area.

[0063] In another possible method, based on a preset right-angle template, the positions of the four vertices of the image of the photovoltaic panel are searched around the above edge position, and then the area surrounded by the positions of the four vertices is determined as the regional position of the image of the photovoltaic panel in the infrared image. Among them, the above preset right-angle template can be one or more. When the preset right-angle template is one, the method for determining the regional position of the image of the photovoltaic panel in the infrared image is similar to the prior art and will not be repeated here.

[0064] However, in the case where there are multiple preset right-angle templates, this embodiment preferably uses four different right-angle templates to respectively determine the positions of the four vertices of the image of the photovoltaic panel in the infrared image. Specifically, Figure 3a A schematic diagram of a right-angle template for determining a lower right vertex provided by an embodiment of the present invention, Figure 3b A schematic diagram of a right-angle template for determining a lower left vertex provided by an embodiment of the present invention, Figure 3c A schematic diagram of a right-angle template for determining the upper right vertex provided by an embodiment of the present invention, Figure 3d A schematic diagram of a right-angle template for determining an upper left vertex provided by an embodiment of the present invention, Figure 4 for Figure 3a The schematic diagram of the position of the right-angle template in the infrared image is shown. Figure 4 The dotted line in the figure is the boundary position of the influence of the photovoltaic panel in the infrared image, such as Figure 4As shown in the figure, if the length of the overlapping area between the right-angle template and the dotted line in the figure is greater than the first preset length, and the length of the non-overlapping area is less than the second preset length, then it is determined that the location of point G may be the lower right vertex of the image of the photovoltaic panel on the infrared image. Similarly, the right-angle template is used to traverse the entire infrared image to find the possible locations of all lower right vertices. Similarly, through Figure 3b , Figure 3c , Figure 3d The right-angle template shown finds all possible locations of the other three vertices of the photovoltaic panel image on the infrared image. It should be noted here that the vertices determined according to the right-angle template may be right-angle points or not, and the four vertices of the photovoltaic panel image in the infrared image should be right-angle points, so the vertices determined above may be the vertices of the photovoltaic panel image on the infrared image or not.

[0065] Furthermore, the ground station performs cluster analysis on the positions of the vertices obtained above to obtain the positions of all actually existing right-angle points. Taking the upper right vertex as an example, the ground station performs cluster analysis on all positions of the upper right vertex that may exist and are within a preset range to obtain the position of the actually existing upper right right-angle point. At this time, the positions of the upper right right right-angle points obtained may be multiple. By analogy, the positions of all actually existing right-angle points in the infrared image can be obtained.

[0066] Furthermore, after obtaining the positions of all the right-angle points, the ground station determines the positions of the four vertices of the image of the photovoltaic panel from all the positions where the right-angle points actually exist based on the optimal path algorithm.

[0067] Specifically, the optimal path algorithm involved in this embodiment can be based on a preset reference right-angle template, first estimate the geometric parameters (including aspect ratio and / or area) of the region where the photovoltaic panel image is located on the infrared image, and further, determine one position as the reference position from all the positions where the right-angle points actually exist, and traverse the positions where the other right-angle points actually exist. If there are three positions and the reference position, the geometric parameters of the quadrilateral formed by the geometric parameters match the geometric parameters obtained by the aforementioned estimation based on the reference right-angle template, then determine the three positions and the reference position as the positions of the four vertices of the photovoltaic panel image. By analogy, the positions of the four vertices of all photovoltaic panel images in the infrared image can be determined.

[0068] In another method of performing image recognition processing on infrared images, the drone sends the infrared image and visible light image taken at the same time to the ground station. The ground station compares the visible light image and the infrared image. Since the two are overlapping, the regional position of the photovoltaic panel image in the infrared image can be determined based on the regional position of the photovoltaic panel image in the visible light image.

[0069] Step 103: The ground station determines whether a fault occurs in the photovoltaic panel based on the information of the regional position of the photovoltaic panel in the infrared image.

[0070] In actual scenarios, infrared images can reflect the temperature distribution. When the temperature of at least one sub-area in the regional position of the photovoltaic panel image in the infrared image is significantly higher than the temperature of other areas, it means that a hot spot has occurred in the photovoltaic panel or other faults have occurred that cause the temperature of the local area of ​​the photovoltaic panel to be too high.

[0071] After determining that the photovoltaic panel has failed, if the drone adopts the strategy of hovering at the shooting position for a preset length of time, then the ground station can map the relative position of the fault position on the infrared image to the position of the faulty photovoltaic panel relative to the drone in the actual scene, thereby controlling the drone to fly directly above the faulty photovoltaic panel, and obtaining the positioning information of the drone when it is directly above the faulty photovoltaic panel, thereby obtaining the actual position of the photovoltaic panel on site based on the positioning information. Alternatively, when the drone adopts the solution of simultaneously carrying an infrared camera and a visible light camera, since the visible light image and the infrared image obtained at the same time overlap, the ground station can match the visible light image taken at the same time as the infrared image with the pre-stored on-site power station map to determine the actual position of the photovoltaic panel on site, or the ground station controls the drone to fly directly above the faulty photovoltaic panel based on the visible light image taken at the same time as the infrared image containing the image of the faulty photovoltaic panel, and determines the actual position of the photovoltaic panel on site based on the positioning information of the drone at this time, wherein the above-mentioned actual position includes the geographical location (such as longitude and latitude) or / and the number of the photovoltaic panel.

[0072] Optionally, after determining the actual location of the faulty photovoltaic panel, the ground station outputs a maintenance reminder message, which includes the actual location of the faulty photovoltaic panel. Specifically, the maintenance reminder message can be output in voice, text or any other possible form.

[0073] In this embodiment, the ground station of the drone obtains an infrared image including the image information of the photovoltaic panel taken by the infrared camera carried by the drone, and performs image recognition processing based on the infrared image to obtain the regional position of the image of the photovoltaic panel in the infrared image, thereby determining whether the photovoltaic panel has a fault based on the information of the regional position. In this way, the drone can inspect the photovoltaic panels in the electric field and identify the faulty photovoltaic panels, avoiding the waste of human resources caused by manual inspection. Compared with the existing manual inspection and inverter monitoring methods, the drone inspection method has a higher inspection efficiency and can timely and accurately identify the faulty photovoltaic panels from the electric field, thereby enhancing the safety of electric field power generation, increasing the power generation of the electric field, and avoiding the losses caused by the accumulation of photovoltaic panel problems.

[0074] The embodiment of the present invention provides a method for detecting a photovoltaic panel. Figure 5 , Figure 5 A flow chart of a method for detecting a photovoltaic panel provided by an embodiment of the present invention, such as Figure 5 As shown, in Figure 1 Based on the illustrated embodiment, the method comprises:

[0075] Step 201: The ground station of the UAV obtains an infrared image taken by an infrared camera carried by the UAV, wherein the infrared image includes image information of the photovoltaic panel.

[0076] Step 202: The ground station performs image recognition processing on the infrared image to obtain the regional position of the image of the photovoltaic panel in the infrared image.

[0077] Step 203: The ground station displays the infrared image.

[0078] Step 204: The ground station marks the location of the photovoltaic panel image in the infrared image.

[0079] Optionally, in this embodiment, the method of marking the regional position of the image of the photovoltaic panel in the infrared image includes the following:

[0080] based on Figure 1 In the embodiment, the location of the region of the image of the photovoltaic panel in the infrared image is actually determined by the locations of the four vertices of the image of the photovoltaic panel in the infrared image. Figure 6a As shown in FIG. 1 , in a possible marking method, the positions of the four vertices of the image of the photovoltaic panel are directly marked in the displayed infrared image. Then, the area between the four vertices is the area position of the image of the photovoltaic panel in the infrared image. Figure 6b As shown, another possible identification method is to connect two adjacent vertices of the four vertices of the photovoltaic panel image on the basis of the above-mentioned marking method to form a boundary line of the photovoltaic panel image, so that the area enclosed by the boundary line is the regional position of the photovoltaic panel image in the infrared image.

[0081] Step 205 : The ground station determines whether the photovoltaic panel has failed based on the information of the regional position of the photovoltaic panel in the infrared image, and if so, executes step 206 .

[0082] Step 206: The ground station marks the fault point location of the photovoltaic panel in the infrared image.

[0083] For example, Figure 7 A schematic diagram of the marking result of the fault point provided by the embodiment of the present invention is shown as follows: Figure 7As shown, the position of the fault point on the photovoltaic panel can be marked on the infrared image by any graphic. Optionally, the actual position information of the photovoltaic panel can be marked on the infrared image while marking the fault point, such as global positioning GPS information and / or photovoltaic panel number information, etc. Of course, this is only an example and not the only limitation of the present invention.

[0084] In this embodiment, the ground station displays an infrared image and marks the affected area of ​​the photovoltaic panel on the infrared image. If the photovoltaic panel fails, the fault location of the photovoltaic panel is marked on the infrared image. This can intuitively reflect the fault condition and location of the photovoltaic panel, thereby improving the user experience.

[0085] The embodiment of the present invention provides a method for detecting a photovoltaic panel. Figure 8 ,like Figure 8 As shown, the method comprises the following steps:

[0086] Step 301: The drone obtains an infrared image taken by its onboard infrared camera, wherein the infrared image includes image information of the photovoltaic panel.

[0087] Step 302: The drone performs image recognition processing on the infrared image to obtain the regional position of the image of the photovoltaic panel in the infrared image.

[0088] Optionally, in this embodiment, the method for the drone to perform image recognition processing on the infrared image and obtain the regional position of the image of the photovoltaic panel in the infrared image includes: determining the edge position of the image of the photovoltaic panel in the infrared image according to the temperature distribution presented in the infrared image; determining the regional position of the image of the photovoltaic panel in the infrared image according to the edge position of the image of the photovoltaic panel in the infrared image. Among them, the method for determining the regional position of the image of the photovoltaic panel in the infrared image according to the edge position of the image of the photovoltaic panel in the infrared image includes: searching for the positions of the four vertices of the image around the edge position based on a preset right-angle template; and determining the regional position of the image of the photovoltaic panel in the infrared image based on the positions of the four vertices. Among them, the method of searching for the positions of the four vertices of the image around the edge position based on a preset right-angle template specifically includes: traversing the infrared image with four right-angle templates respectively to detect all possible positions of right-angle points around the edge position, and the four right-angle templates are used to detect the possible positions of the four different vertices of the image respectively; performing cluster analysis on all possible positions of right-angle points to obtain the positions of all actual right-angle points; based on the optimal path algorithm, determining the positions of the four vertices of the image from all the positions of actual right-angle points. Among them, before determining the positions of the four vertices of the image from all the positions of actual right-angle points based on the optimal path algorithm, it includes: estimating the area range of the image on the infrared image based on a preset reference right-angle template, and calculating and obtaining the geometric parameters of the area range, and the geometric parameters include the aspect ratio and / or the area. The optimal path algorithm is based on determining the positions of the four vertices of the image from all the positions of the actual right-angle points, including: determining a position as a reference position from all the positions of the actual right-angle points, and traversing the positions of the remaining actual right-angle points; if there are three positions and the reference position, the geometric parameters of the quadrilateral formed by the quadrilateral match the geometric parameters of the area range, then determining the three positions and the reference position as the positions of the four vertices of the image.

[0089] Step 303: The drone determines whether a photovoltaic panel has failed based on the regional location information.

[0090] Optionally, if a photovoltaic panel fails, the method of this embodiment also includes: the drone obtains a visible light image taken by a visible light camera carried by the drone, and the visible light image overlaps with the infrared image; the infrared image is matched with the visible light image, and the position of the failed photovoltaic panel is determined on the visible light image; the visible light image is matched with a pre-stored on-site power station map to determine the actual position of the photovoltaic panel on site, or based on the visible light image, the drone flies above the photovoltaic panel and determines the actual position of the photovoltaic panel on site based on the positioning information of the current position; the actual position includes the geographic location and / or number.

[0091] Optionally, after determining the actual location of the photovoltaic panel on site, the method provided in this embodiment further includes: the drone sends a maintenance reminder message to the ground station, wherein the maintenance reminder message includes the actual location of the photovoltaic panel.

[0092] The method provided in this embodiment, its execution mode and beneficial effects are similar to Figure 1 The embodiments are similar and will not be described again here.

[0093] The embodiment of the present invention provides a method for detecting a photovoltaic panel. Fig. 9 ,like Fig. 9 As shown, in Figure 8 Based on the embodiment, the method comprises the following steps:

[0094] Step 401: The drone obtains an infrared image taken by an infrared camera carried by the drone, wherein the infrared image includes image information of the photovoltaic panel;

[0095] Step 402: The drone performs image recognition processing on the infrared image to obtain the regional position of the image of the photovoltaic panel in the infrared image;

[0096] Step 403: The UAV determines whether a photovoltaic panel has failed based on information about the regional position of the photovoltaic panel in the infrared image.

[0097] Step 404: The drone marks the area location of the image of the photovoltaic panel in the infrared image.

[0098] Optionally, a possible method is that a drone marks the vertex position of the image of the photovoltaic panel in the infrared image.

[0099] Another possible way is that the drone connects the vertex positions of the image of the photovoltaic panel in the infrared image to form a boundary line of the image.

[0100] Step 405: The drone sends the infrared image of the area where the image of the photovoltaic panel is marked to the ground station.

[0101] Optionally, when the drone detects that a photovoltaic panel has a fault, the drone marks the location of the fault point of the photovoltaic panel in the infrared image, and sends the infrared image including the location of the fault point and the regional location of the image of the photovoltaic panel to the ground station.

[0102] The method provided in this embodiment, its execution mode and beneficial effects are similar to Figure 5 The embodiments are similar and will not be described again here.

[0103] An embodiment of the present invention provides a ground station, which may be the ground station described in the above embodiment. Fig.10 A schematic diagram of the structure of a ground station provided by an embodiment of the present invention is shown in FIG. Fig.10 As shown, the ground station 10 includes: a communication interface 11 and one or more processors 12; the one or more processors work alone or in collaboration, and the communication interface 11 and the processor 12 are connected; the communication interface 11 is used to obtain an infrared image taken by an infrared camera carried by a drone, wherein the infrared image includes image information of a photovoltaic panel; the processor 12 is used to perform image recognition processing based on the infrared image to obtain the regional position of the image of the photovoltaic panel in the infrared image; the processor 12 is also used to determine whether the photovoltaic panel has a fault based on the information of the regional position.

[0104] Optionally, the processor 12 is configured to:

[0105] Determining the edge position of the image of the photovoltaic panel in the infrared image according to the temperature distribution presented in the infrared image;

[0106] The regional position of the image of the photovoltaic panel in the infrared image is determined according to the edge position of the image of the photovoltaic panel in the infrared image.

[0107] Optionally, the processor 12 is configured to:

[0108] Based on a preset right-angle template, searching for positions of four vertices of the image around the edge position;

[0109] Based on the positions of the four vertices, the regional position of the image of the photovoltaic panel in the infrared image is determined.

[0110] Optionally, the processor 12 is configured to:

[0111] Traversing the infrared image with four right-angle templates respectively to detect all possible right-angle points around the edge position, wherein the four right-angle templates are respectively used to detect possible positions of four different vertices of the image;

[0112] Perform cluster analysis on all possible locations of right angles to obtain all locations where right angles actually exist;

[0113] Based on the optimal path algorithm, the positions of the four vertices of the image are determined from the positions of all actually existing right-angle points.

[0114] Optionally, the processor 12 is further configured to:

[0115] Before determining the positions of the four vertices of the image from the positions of all actually existing right-angle points based on the optimal path algorithm, the area range of the image on the infrared image is estimated based on a preset reference right-angle template, and the geometric parameters of the area range are calculated, wherein the geometric parameters include the aspect ratio and / or the area.

[0116] Optionally, the processor 12 is configured to:

[0117] Determine a position from all positions where right-angle points actually exist as a reference position, and traverse the remaining positions where right-angle points actually exist;

[0118] If there are three positions and the reference position whose geometric parameters of a quadrilateral match the geometric parameters of the region, the three positions and the reference position are determined to be the positions of the four vertices of the image.

[0119] Optionally, the communication interface 11 is further used to obtain a visible light image captured by a visible light camera carried by the drone, wherein the visible light image overlaps with the infrared image;

[0120] The processor 12 is further configured to:

[0121] Matching the infrared image with the visible light image, and determining the location of the failed photovoltaic panel on the visible light image;

[0122] Matching the visible light image with a pre-stored on-site power station map to determine the actual location of the photovoltaic panel on site, or

[0123] Based on the visible light image, the drone is controlled to fly above the photovoltaic panel, and the actual position of the photovoltaic panel at the site is determined according to the positioning information of the drone;

[0124] The actual location includes a geographical location and / or a number.

[0125] Optionally, the communication interface 11 is further used to: output a maintenance reminder message, wherein the maintenance reminder message includes the actual position of the photovoltaic panel.

[0126] The ground station provided in this embodiment can perform Figure 1 The technical solutions of the embodiments, their execution methods and beneficial effects are similar and will not be described in detail here.

[0127] An embodiment of the present invention provides a ground station, which may be the ground station described in the above embodiment. Fig.11 A schematic diagram of the structure of a ground station provided by an embodiment of the present invention is shown in FIG. Fig.11 As shown, in Fig.10 Based on the embodiment, the ground station 10 further includes: a display component 13, the display component 13 is coupled to the processor 12; the display component 13 is used to: display the infrared image; the display component 13 is used to: mark the regional position of the image of the photovoltaic panel in the infrared image.

[0128] Optionally, the display component 13 is used to mark the vertex position of the image of the photovoltaic panel in the infrared image.

[0129] Optionally, the display component 13 is used to connect the vertex positions of the image of the photovoltaic panel in the infrared image to form a boundary line of the image.

[0130] Optionally, the display component 13 is used to: when a failure occurs in the photovoltaic panel, mark the fault point position of the photovoltaic panel in the infrared image.

[0131] The ground station provided in this embodiment can perform Figure 5 The technical solutions of the embodiments, their execution methods and beneficial effects are similar and will not be described in detail here.

[0132] The embodiment of the present invention provides a control device. Fig.12 , Fig.12 A schematic diagram of the structure of a control device provided in an embodiment of the present invention, such as Fig.12 As shown, the control device 20 includes: a communication interface 21 and one or more processors 22; the one or more processors work alone or in collaboration, and the communication interface 21 and the processor 22 are communicatively connected; the communication interface 21 is used to obtain an infrared image taken by an infrared camera carried by the drone, wherein the infrared image includes image information of the photovoltaic panel; the processor 22 is used to perform image recognition processing based on the infrared image to obtain the regional position of the image of the photovoltaic panel in the infrared image; the processor 22 is also used to determine whether the photovoltaic panel has a fault based on the information of the regional position.

[0133] Optionally, the processor 22 is configured to:

[0134] Determining the edge position of the image of the photovoltaic panel in the infrared image according to the temperature distribution presented in the infrared image;

[0135] The regional position of the image of the photovoltaic panel in the infrared image is determined according to the edge position of the image of the photovoltaic panel in the infrared image.

[0136] Optionally, the processor 22 is configured to:

[0137] Based on a preset right-angle template, searching for positions of four vertices of the image around the edge position;

[0138] Based on the positions of the four vertices, the regional position of the image of the photovoltaic panel in the infrared image is determined.

[0139] Optionally, the processor 22 is configured to:

[0140] Traversing the infrared image with four right-angle templates respectively to detect all possible right-angle points around the edge position, wherein the four right-angle templates are respectively used to detect possible positions of four different vertices of the image;

[0141] Perform cluster analysis on all possible locations of right angles to obtain all locations where right angles actually exist;

[0142] Based on the optimal path algorithm, the positions of the four vertices of the image are determined from the positions of all actually existing right-angle points.

[0143] Optionally, the processor 22 is used to estimate the area range of the image on the infrared image based on a preset reference rectangular template, and calculate geometric parameters of the area range, where the geometric parameters include aspect ratio and / or area.

[0144] Optionally, the processor 22 is configured to:

[0145] Determine a position from all positions where right-angle points actually exist as a reference position, and traverse the remaining positions where right-angle points actually exist;

[0146] If there are three positions and the reference position whose geometric parameters of a quadrilateral match the geometric parameters of the region, the three positions and the reference position are determined to be the positions of the four vertices of the image.

[0147] Optionally, the communication interface 21 is further used to: obtain a visible light image captured by a visible light camera carried by the drone, wherein the visible light image overlaps with the infrared image;

[0148] The processor 22 is further configured to:

[0149] Matching the infrared image with the visible light image, and determining the location of the failed photovoltaic panel on the visible light image;

[0150] Matching the visible light image with a pre-stored on-site power station map to determine the actual location of the photovoltaic panel on site, or

[0151] Based on the visible light image, fly above the photovoltaic panel, and determine the actual position of the photovoltaic panel on site based on the positioning information of the current position;

[0152] The actual location includes a geographical location and / or a number.

[0153] Optionally, the communication interface 21 is further used to send a maintenance reminder message to a ground station, wherein the maintenance reminder message includes the actual position of the photovoltaic panel.

[0154] This embodiment can be used to perform Figure 8 The technical solutions of the embodiments, their execution methods and beneficial effects are similar and will not be described in detail here.

[0155] The embodiment of the present invention provides a control device. Fig.12 Based on the embodiment, the processor 22 is used to: mark the regional position of the image of the photovoltaic panel in the infrared image; the communication interface 21 is used to: send the infrared image with the regional position of the image of the photovoltaic panel marked to the ground station. The processor 22 is used to: mark the vertex position of the image of the photovoltaic panel in the infrared image. The processor 22 is used to: connect the vertex positions of the image of the photovoltaic panel in the infrared image to form the boundary line of the image. The processor 22 is used to: when the photovoltaic panel fails, mark the fault point position of the photovoltaic panel in the infrared image.

[0156] This embodiment can be used to perform Fig. 9 The technical solutions of the embodiments, their execution methods and beneficial effects are similar and will not be described in detail here.

[0157] An embodiment of the present invention provides a drone, which includes a fuselage, a power system installed on the fuselage for providing flight power, an infrared camera installed on the fuselage for capturing infrared images, a visible light camera installed on the fuselage for capturing visible light images, and a control device as described in the above embodiment.

[0158] Among them, the execution method and beneficial effects of the control device of the drone provided in this embodiment are the same as those of the control device involved in the above embodiments, and will not be repeated here.

[0159] In the several embodiments provided by the present invention, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic. For example, the division of the units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0160] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0161] In addition, each functional unit in each embodiment of the present invention may be integrated into one processing unit, or each unit may exist physically separately, or two or more units may be integrated into one unit. The above-mentioned integrated unit may be implemented in the form of hardware or in the form of hardware plus software functional units.

[0162] The above-mentioned integrated unit implemented in the form of a software functional unit can be stored in a computer-readable storage medium. The above-mentioned software functional unit is stored in a storage medium, including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor to perform some steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM), random access memory (RAM), disk or optical disk and other media that can store program codes.

[0163] Those skilled in the art can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example for illustration. In actual applications, the above-mentioned functions can be assigned to different functional modules as needed, that is, the internal structure of the device is divided into different functional modules to complete all or part of the functions described above. The specific working process of the device described above can refer to the corresponding process in the aforementioned method embodiment, and will not be repeated here.

[0164] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for detecting a photovoltaic panel, characterized in that: include: The ground station of the UAV obtains an infrared image taken by an infrared camera carried by the UAV, wherein the infrared image includes image information of the photovoltaic panel; The ground station performs image recognition processing on the infrared image to obtain the regional position of the image of the photovoltaic panel in the infrared image; The ground station determines whether the photovoltaic panel has failed based on the information of the regional location; When the photovoltaic panel fails, the method further comprises: Acquire a visible light image captured by a visible light camera carried by the drone; Matching the infrared image with the visible light image, and determining the location of the failed photovoltaic panel on the visible light image; The visible light image is matched with a pre-stored on-site power station map to determine the actual position of the photovoltaic panel on site, or, based on the visible light image, the drone is controlled to fly above the photovoltaic panel, and the actual position of the photovoltaic panel on site is determined according to the positioning information of the drone.

2. The method according to claim 1, characterized in that: After the ground station performs image recognition processing on the infrared image to obtain the regional position of the image of the photovoltaic panel in the infrared image, the method further includes: The ground station displays the infrared image; The ground station marks the regional position of the image of the photovoltaic panel in the infrared image.

3. The method according to claim 2, characterized in that The ground station marks the regional position of the image of the photovoltaic panel in the infrared image, including: The ground station marks the vertex position of the image of the photovoltaic panel in the infrared image.

4. The method according to claim 2, characterized in that The ground station marks the regional position of the image of the photovoltaic panel in the infrared image, including: The ground station connects the vertex positions of the images of the photovoltaic panels in the infrared image to form a boundary line of the image.

5. The method according to claim 1, characterized in that: The method further comprises: When the photovoltaic panel fails, the ground station marks the location of the failure point of the photovoltaic panel in the infrared image.

6. The method according to claim 1, characterized in that The ground station performs image recognition processing on the infrared image to obtain the regional position of the image of the photovoltaic panel in the infrared image, including: The ground station determines the edge position of the image of the photovoltaic panel in the infrared image according to the temperature distribution presented in the infrared image; The ground station determines the regional position of the image of the photovoltaic panel in the infrared image according to the edge position of the image of the photovoltaic panel in the infrared image.

7. The method according to claim 6, characterized in that The ground station determines the regional position of the image of the photovoltaic panel in the infrared image according to the edge position of the image of the photovoltaic panel in the infrared image, including: Based on a preset right-angle template, searching for positions of four vertices of the image around the edge position; Based on the positions of the four vertices, the regional position of the image of the photovoltaic panel in the infrared image is determined.

8. The method according to claim 7, characterized in that The step of searching for the positions of four vertices of the image around the edge position based on a preset right-angle template includes: Traversing the infrared image with four right-angle templates respectively to detect all possible right-angle points around the edge position, wherein the four right-angle templates are respectively used to detect possible positions of four different vertices of the image; Perform cluster analysis on all possible locations of right angles to obtain all locations where right angles actually exist; Based on the optimal path algorithm, the positions of the four vertices of the image are determined from the positions of all actually existing right-angle points.

9. The method according to claim 8, characterized in that Before determining the positions of the four vertices of the image from the positions of all actually existing right-angle points based on the optimal path algorithm, the method includes: Based on a preset reference rectangular template, the area range of the image on the infrared image is estimated, and geometric parameters of the area range are calculated and obtained, wherein the geometric parameters include aspect ratio and / or area.

10. The method according to claim 9, characterized in that The method of determining the positions of the four vertices of the image from the positions of all actually existing right-angle points based on the optimal path algorithm includes: Determine a position from all the positions where the right-angle points actually exist as the reference position, and traverse the remaining positions where the right-angle points actually exist; When the geometric parameters of a quadrilateral formed by three positions and the reference position match the geometric parameters of the area range, the three positions and the reference position are determined to be the positions of the four vertices of the image.

11. The method according to any one of claims 1 to 10, characterized in that The actual location includes a geographical location and / or a number.

12. The method according to claim 11, characterized in that After determining the actual location of the photovoltaic panel at the site, the method further includes: A maintenance reminder message is output, wherein the maintenance reminder message includes the actual position of the photovoltaic panel.

13. The method according to any one of claims 1 to 10, characterized in that The ground station determines whether the photovoltaic panel fails according to the information of the regional location, including: If, according to the image of the photovoltaic panel in the infrared image, there is at least one sub-region whose temperature is obviously higher than that of other regions in the regional position, it is determined that the photovoltaic panel has failed.

14. A method for detecting a photovoltaic panel, characterized in that: include: The drone obtains an infrared image taken by an infrared camera carried by the drone, wherein the infrared image includes image information of the photovoltaic panel; The drone performs image recognition processing on the infrared image to obtain the regional position of the image of the photovoltaic panel in the infrared image; The drone determines whether the photovoltaic panel has failed based on the information of the regional location; When the photovoltaic panel fails, the method further comprises: The drone matches the infrared image with a visible light image captured by a visible light camera carried by the drone, and determines the location of the failed photovoltaic panel on the visible light image; The drone matches the visible light image with a pre-stored on-site power station map to determine the actual location of the photovoltaic panel on site, or, The drone flies above the photovoltaic panel based on the visible light image, and determines the actual position of the photovoltaic panel on site based on the positioning information of the current position.

15. The method according to claim 14, characterized in that After the drone performs image recognition processing on the infrared image to obtain the regional position of the image of the photovoltaic panel in the infrared image, the method further includes: The drone marks the regional location of the image of the photovoltaic panel in the infrared image; The drone sends an infrared image of the area where the image of the photovoltaic panel is marked to the ground station.

16. The method according to claim 15, characterized in that The drone marks the regional position of the image of the photovoltaic panel in the infrared image, including: The drone marks the vertex position of the image of the photovoltaic panel in the infrared image.

17. The method according to claim 15, characterized in that The drone marks the regional position of the image of the photovoltaic panel in the infrared image, including: The drone connects the vertex positions of the images of the photovoltaic panels in the infrared image to form a boundary line of the image.

18. The method according to claim 14, characterized in that The method further comprises: When the photovoltaic panel fails, the drone marks the location of the failure point of the photovoltaic panel in the infrared image.

19. The method according to claim 14, characterized in that The drone performs image recognition processing on the infrared image to obtain the regional position of the image of the photovoltaic panel in the infrared image, including: The drone determines the edge position of the image of the photovoltaic panel in the infrared image according to the temperature distribution presented in the infrared image; The drone determines the regional position of the image of the photovoltaic panel in the infrared image according to the edge position of the image of the photovoltaic panel in the infrared image.

20. The method according to claim 19, characterized in that The drone determines the regional position of the image of the photovoltaic panel in the infrared image according to the edge position of the image of the photovoltaic panel in the infrared image, including: The drone searches for positions of four vertices of the image around the edge position based on a preset right-angle template; The drone determines the regional position of the image of the photovoltaic panel in the infrared image based on the positions of the four vertices.

21. The method according to claim 20, characterized in that The drone searches for the positions of four vertices of the image around the edge position based on a preset right-angle template, including: The drone traverses the infrared image with four right-angle templates respectively to detect all possible right-angle points around the edge position, and the four right-angle templates are used to detect possible positions of four different vertices of the image respectively; The drone performs cluster analysis on all possible locations of right angles to obtain all locations of actual right angles; The drone determines the positions of the four vertices of the image from the positions of all actually existing right-angle points based on an optimal path algorithm.

22. The method according to claim 21, characterized in that Before the drone determines the positions of the four vertices of the image from all the positions of the actually existing right-angle points based on the optimal path algorithm, the method includes: The drone estimates the area range of the image on the infrared image based on a preset reference right-angle template, and calculates and obtains geometric parameters of the area range, wherein the geometric parameters include aspect ratio and / or area.

23. The method according to claim 22, characterized in that The drone determines the positions of the four vertices of the image from all the positions of the actually existing right-angle points based on the optimal path algorithm, including: The drone determines a position from all positions where right-angle points actually exist as a reference position, and traverses the remaining positions where right-angle points actually exist; When the geometric parameters of a quadrilateral formed by three positions and the reference position match the geometric parameters of the area range, the three positions and the reference position are determined to be the positions of the four vertices of the image.

24. The method according to any one of claims 14 to 23, characterized in that The actual location includes a geographical location and / or a number.

25. The method according to claim 24, characterized in that After determining the actual location of the photovoltaic panel at the site, the method further includes: The UAV sends a maintenance reminder message to the ground station, and the maintenance reminder message includes the actual position of the photovoltaic panel.

26. The method according to any one of claims 14 to 23, characterized in that The drone determines whether the photovoltaic panel has failed according to the information of the regional location, including: If, according to the image of the photovoltaic panel in the infrared image, there is at least one sub-region whose temperature is obviously higher than that of other regions in the regional position, it is determined that the photovoltaic panel has failed.

27. A ground station, characterized in that: include: A communication interface and one or more processors; the one or more processors work individually or in collaboration, and the communication interface is connected to the processors; The communication interface is used to: obtain an infrared image taken by an infrared camera carried by the drone, wherein the infrared image includes image information of the photovoltaic panel; The processor is used to: perform image recognition processing based on the infrared image to obtain the regional position of the image of the photovoltaic panel in the infrared image; The processor is also used to: determine whether the photovoltaic panel has a fault according to the information of the regional location; When the photovoltaic panel fails, obtaining a visible light image captured by a visible light camera carried by the drone; Matching the infrared image with the visible light image, and determining the location of the failed photovoltaic panel on the visible light image; Matching the visible light image with a pre-stored on-site power station map to determine the actual location of the photovoltaic panel on site, or, Based on the visible light image, the drone is controlled to fly above the photovoltaic panel, and the actual position of the photovoltaic panel on site is determined according to the positioning information of the drone.

28. The ground station according to claim 27, characterized in that The ground station also includes a display component coupled to the processor; The display component is used to: display the infrared image; The display component is used to mark the regional position of the image of the photovoltaic panel in the infrared image.

29. A control device, characterized in that: include: A communication interface and one or more processors; the one or more processors work individually or in collaboration, and the communication interface is communicatively connected to the processors; The communication interface is used to: obtain an infrared image taken by an infrared camera carried by the drone, wherein the infrared image includes image information of the photovoltaic panel; The communication interface is also used to: obtain a visible light image captured by a visible light camera carried by the drone; The processor is used to: perform image recognition processing on the infrared image to obtain the regional position of the image of the photovoltaic panel in the infrared image; The processor is also used to: determine whether the photovoltaic panel has a fault according to the information of the regional location; When the photovoltaic panel fails, matching the infrared image with the visible light image, and determining the position of the failed photovoltaic panel on the visible light image; Matching the visible light image with a pre-stored on-site power station map to determine the actual location of the photovoltaic panel on site, or, Based on the visible light image, the drone is controlled to fly above the photovoltaic panel, and the actual position of the photovoltaic panel on site is determined according to the positioning information of the current position of the drone.

30. A drone, characterized in that: include: body; A power system, installed on the fuselage, for providing flight power; An infrared camera, mounted on the fuselage, for capturing infrared images; A visible light camera, mounted on the body, for capturing visible light images; And a control device as claimed in claim 29.

Images