Detection Method for Photovoltaic Power Station, Detection Device for Photovoltaic Power Station, and Storage Medium

Abstract

The present application discloses a detection method for a photovoltaic power station, a detection device for a photovoltaic power station, and a storage medium. The method includes: acquiring an infrared image, which is obtained by collecting an image of the photovoltaic power station at a preset position, and the infrared image corresponds to the geographical location of the preset position; determining the image position of an abnormal point in the infrared image; determining the geographical location of the abnormal point according to the image position of the abnormal point, the geographical location corresponding to the infrared image, and a pre-established correspondence between the image position and the geographical location; and marking the abnormal point on a map. By the above method, the detection efficiency of the photovoltaic power station can be improved.

Description

Technical Field

[0001] This application relates to the field of image processing, and particularly to a detection method for a photovoltaic power station, a detection device for a photovoltaic power station, and a storage medium. Background Art

[0002] The International Energy Agency (IEA) has conducted research on the demand for international electricity. The IEA's research believes that in the future, non-hydro renewable energy power generation will grow faster than power generation from other fuels. One of the non-hydro renewable energies is solar energy. Therefore, photovoltaic power stations relying on solar power generation have been built on a large scale.

[0003] The particularity of photovoltaic power stations lies in their remote locations, numerous devices, and wide distribution ranges. Detecting the devices of these increasingly large-scale photovoltaic power stations is a difficult problem that urgently needs to be solved. Existing detection methods include manual detection, intelligent robot detection, and so on. However, the efficiency of existing detection methods is not high, resulting in relevant personnel being unable to timely discover abnormal problems and causing adverse consequences. Summary of the Invention

[0004] This application provides a detection method for a photovoltaic power station, a detection device for a photovoltaic power station, and a storage medium, which can solve the problem of low efficiency in the existing detection of photovoltaic power stations.

[0005] To solve the above technical problems, one technical solution adopted by this application is: providing a detection method for a photovoltaic power station. The method includes: acquiring an infrared image, where the infrared image is obtained by collecting an image of the photovoltaic power station at a preset position, and the infrared image corresponds to the geographical location of the preset position; determining the image position of an abnormal point in the infrared image; determining the geographical location of the abnormal point according to the image position of the abnormal point, the geographical location corresponding to the infrared image, and the pre-established correspondence between the image position and the geographical location; and marking the abnormal point on a map.

[0006] To solve the above technical problems, another technical solution adopted by this application is: providing a detection device for a photovoltaic power station, where the detection device for the photovoltaic power station includes a processor and a memory connected to the processor. Among them, the memory stores program instructions; the processor is used to execute the program instructions stored in the memory to implement the above method.

[0007] To solve the above technical problems, yet another technical solution adopted by this application is: providing a storage medium storing program instructions, where the program instructions can implement the above method when executed.

[0008] In the above manner, in the present application, an infrared image of a photovoltaic power station can be obtained, the image position of an abnormal point in the infrared image can be determined, and according to the image position of the abnormal point, the geographical location corresponding to the infrared image, and the pre-established correspondence between the image position and the geographical location, the geographical location of the abnormal point can be determined, and the abnormal point can be marked on a map. Compared with the methods of manual detection and intelligent robot detection, it can more quickly locate the abnormal points of the photovoltaic power station and mark the geographical locations of the abnormal points on the map, facilitating relevant personnel to quickly find the abnormal points. Therefore, the present application can improve the detection efficiency of the photovoltaic power station. BRIEF DESCRIPTION OF THE DRAWINGS

[0009] Figure 1 is a schematic flowchart of the first embodiment of the detection method for a photovoltaic power station in the present application;

[0010] Figure 2 is a schematic diagram of the area to be detected of the photovoltaic power station in the present application;

[0011] Figure 3 is a schematic flowchart of the second embodiment of the detection method for a photovoltaic power station in the present application;

[0012] Figure 4 is a schematic diagram of the target infrared image in the present application;

[0013] Figure 5 is a schematic diagram of the Earth longitude and latitude coordinate system ONE and the image coordinate system O'XY corresponding to the target infrared image;

[0014] Figure 6 is a schematic diagram of the detection result of the infrared image;

[0015] Figure 7 is Figure 1 a specific flowchart of S13 in

[0016] Figure 8 is Figure 1 a specific flowchart of S14 in

[0017] Figure 9 is a schematic diagram of marking severe hot spots in the present application on the map in red;

[0018] Figure 10 is a schematic diagram of marking ordinary hot spots in the present application on the map in blue;

[0019] Figure 11 is for relevant personnel in the present application to search for Figure 9 severe hot spots in

[0020] Figure 12 is for relevant personnel in the present application to search for Figure 10Schematic diagram of the process of ordinary hot spots;

[0021] Figure 13 It is a schematic diagram of the distribution of the geographical location 1 of the relevant personnel of the present application and the geographical location of ordinary hot spots;

[0022] Figure 14 It is a schematic diagram of the distribution of the geographical location 1 of the relevant personnel of the present application and the geographical location of severe hot spots;

[0023] Figure 15 It is Figure 1 Another specific process schematic diagram of S14 in;

[0024] Figure 16 It is a schematic diagram of the present application for annotating infrared images on a map;

[0025] Figure 17 It is a schematic diagram of the infrared image of a mountain photovoltaic power station and the annotation of abnormal points in the corresponding visible image;

[0026] Figure 18 It is a schematic diagram of the infrared image of a flat photovoltaic power station and the annotation of abnormal points in the corresponding visible image;

[0027] Figure 19 It is a schematic diagram of the infrared image of a water surface photovoltaic power station and the annotation of abnormal points in the corresponding visible image;

[0028] Figure 20 It is a schematic diagram of the structure of an embodiment of the detection device of the photovoltaic power station of the present application;

[0029] Figure 21 It is a schematic diagram of the structure of an embodiment of the storage medium of the present application. Detailed implementation manners

[0030] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.

[0031] The terms "first", "second", and "third" in the present application are only used for descriptive purposes, and cannot be understood as indicating or implying relative importance or implicitly specifying the quantity of the indicated technical features. Thus, the features defined with "first", "second", and "third" may explicitly or implicitly include at least one of the features. In the description of the present application, the meaning of "a plurality" is at least two, such as two, three, etc., unless otherwise specifically defined.

[0032] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present application. The appearance of the phrase in various locations in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments without conflict.

[0033] Figure 1 1 is a flow chart of the first embodiment of the detection method of the photovoltaic power station of the present application. It should be noted that if there are substantially the same results, this embodiment is not based on Figure 1 The process sequence shown is limited. Figure 1 As shown, this embodiment may include:

[0034] S11: Acquire an infrared image.

[0035] The infrared image is obtained by collecting images of the photovoltaic power station at a preset position, and the infrared image corresponds to the geographical location of the preset position.

[0036] The preset position may be a pre-specified position in the area to be detected of the photovoltaic power station. The area to be detected of the photovoltaic power station may be the entire area of ​​the photovoltaic power station or a partial area of ​​the photovoltaic power station. The area to be detected of the photovoltaic power station may include multiple preset positions, and image acquisition may be performed above each preset position to obtain a corresponding infrared image. The sum of the field of view of the infrared image obtained at each preset position can cover the area to be detected of the photovoltaic power station. The geographical location may be represented by longitude and latitude coordinates.

[0037] Combination Figure 2 Give an example. Figure 2 The schematic diagram of the detection area of ​​the photovoltaic power station is as follows: the geographical locations of the four corners (upper left corner, upper right corner, lower left corner and lower right corner) of the detection area can be collected first. Figure 2 The 1 in represents the geographical location of the corner point of the area to be detected. Multiple routes are planned based on these four geographical locations, and multiple waypoints are set on each route. Figure 2 2 represents the waypoint, and 3 represents the field of view of the infrared image taken at the waypoint. Use a drone equipped with an infrared camera to fly over the area to be inspected according to the planned route. During the flight, image acquisition is performed for each waypoint to obtain the corresponding infrared image. Figure 2 The 4 in the figure represents the flight direction of the drone. The arrow in the upper left corner indicates the direction in which the drone starts to fly. The drone flies in the direction indicated by the arrow until it ends at the lower right corner. After the flight, all infrared images of the area to be detected are collected.

[0038] S12: Determine the image position of the abnormal point in the infrared image.

[0039] The abnormal point in the infrared image may be a pixel point where an abnormality occurs in the infrared image. The abnormality referred to in this application includes, but is not limited to, aging, cracking problems caused by manufacturing processes, and hot spot phenomena. The hot spot phenomenon is used as an example for explanation below. In the case where the abnormality is a hot spot phenomenon, the abnormal point may be referred to as a hot spot.

[0040] Image algorithms (target segmentation algorithms, target detection algorithms, etc.) can be used to detect infrared images and obtain detection results. Compared with traditional detection algorithms, image algorithms have the characteristics of strong robustness, high accuracy, and strong adaptability (can detect photovoltaic power stations in mountains, water surfaces, flat land, and roofs).

[0041] In a specific implementation, the detection result may include the image position of the abnormal point in the infrared image.

[0042] In another specific embodiment, in the case of multiple categories of abnormalities, the detection result may include the image location (bounding boxes) of the abnormal point, as well as the probability of the abnormal point belonging to each category. For example, the abnormality includes three categories: aging, splinter, and hot spot. The detection result includes the location of the abnormal point, as well as the probability that the abnormal point belongs to aging, the probability that the abnormal point belongs to splinter, and the probability that the abnormal point belongs to hot spot. The category to which the abnormal point belongs can be determined based on the probability that the abnormal point belongs to each category. For example, if the probability that the abnormal point belongs to a hot spot is greater than a threshold value of 0.5, it can be determined that the abnormal point belongs to a hot spot.

[0043] In another specific embodiment, the abnormality can be divided into multiple levels according to the severity of the abnormality, and the detection result can include the image position of the abnormal point and the probability of the abnormal point belonging to each level of abnormality. For example, hot spots are divided into two levels: severe and ordinary. The detection result includes the probability that the abnormal point belongs to a severe hot spot and the probability of an ordinary hot spot. According to the probability that the abnormal point belongs to each level of abnormality, it is determined whether it belongs to which level of abnormality.

[0044] S13: Determine the geographical location of the abnormal point according to the image location of the abnormal point, the geographical location corresponding to the infrared image, and the pre-established correspondence between the image location and the geographical location.

[0045] The image position involved in the present application may be a pixel coordinate in the image. For a method of obtaining the pre-established correspondence between the image position and the geographical location, please refer to the following embodiments.

[0046] S14: Mark the abnormal points on the map.

[0047] After marking the abnormal points on the map, relevant personnel can find the abnormal points according to the marks to perform subsequent maintenance work.

[0048] In this application, an infrared image of a photovoltaic power station can be obtained, the image position of the abnormal point in the infrared image can be determined, and according to the image position of the abnormal point, the geographical location corresponding to the infrared image, and the pre-established correspondence between the image position and the geographical location, the geographical location of the abnormal point can be determined, and the abnormal point can be marked on the map. Compared with the methods of manual detection and intelligent robot detection, it can locate the abnormal points of the photovoltaic power station more quickly and mark the geographical location of the abnormal points on the map, which is convenient for relevant personnel to quickly find the abnormal points. Therefore, through the implementation of this embodiment, the detection efficiency of the photovoltaic power station can be improved.

[0049] Figure 3 It is a schematic flowchart of the second embodiment of the detection method of the photovoltaic power station in this application. It should be noted that if there are substantially the same results, this embodiment is not limited to Figure 3 the process sequence shown. As Figure 3 shown, on the basis of the above-mentioned first embodiment, this embodiment may further include:

[0050] S21: Collect the target infrared image of the target area.

[0051] The target area includes at least two reference objects, and the target infrared image includes at least two reference points corresponding to the at least two reference objects respectively.

[0052] The target area can be an artificially selected area in the photovoltaic power station that includes reference objects.

[0053] In a specific implementation manner, the at least two reference objects may include a first reference object and a second reference object, and the at least two reference points may include a first reference point corresponding to the first reference object and a second reference point corresponding to the second reference object.

[0054] In another specific implementation manner, the at least two reference objects may include a first reference object, a second reference object, and a third reference object, and the at least two reference points may include a first reference point corresponding to the first reference object, a second reference point corresponding to the second reference object, and a third reference point corresponding to the third reference object. The line connecting the first reference point and the second reference point is parallel to the longitude direction, and the line connecting the second reference point and the third reference point is parallel to the latitude direction. Combining Figure 4 and Figure 5 for an example.

[0055] The head of the drone faces due east (E), and the target infrared image of the target area is collected. Figure 4It is a schematic diagram of the target infrared image. The target area includes the first reference object A, the second reference object B, and the third reference object C.

[0056] Figure 5 It is a schematic diagram of the Earth longitude-latitude coordinate system ONE and the image coordinate system O'XY corresponding to the target infrared image. Among them, O is the origin of the Earth longitude-latitude coordinate system, N is the north latitude (0° to 90°), S is the south latitude (0° to -90°), E is the east longitude (0° to 180°), and W is the west longitude (0° to -180°). X is the horizontal axis of the image (0 ≤ X ≤ +∞), and Y is the vertical axis of the image (0 ≤ Y ≤ +∞). O' is the origin of the upper left corner of the image coordinate system, X is the horizontal axis of the image (0 ≤ X ≤ +∞), and Y is the vertical axis of the image (0 ≤ Y ≤ +∞). a, b, and c are the first reference point, the second reference point, and the third reference point on the target infrared image respectively.

[0057] Put O'XY under ONE to form a local coordinate system, where the horizontal axis X of the image is parallel to the longitude direction, and the vertical axis Y of the image is parallel to the latitude direction. The line connecting a and b is parallel to the horizontal axis X of the image, and the horizontal axis X of the image is parallel to the east longitude direction E. Therefore, the line connecting a and b is parallel to the longitude direction (east longitude E), and the line connecting b and c is parallel to the latitude direction (south latitude N).

[0058] S22: Obtain the geographical locations of at least two reference objects, and obtain the image positions of at least two reference points.

[0059] Taking at least two reference objects including the first reference object, the second reference object, and the third reference object, and at least two reference points including the first reference point, the second reference point, and the third reference point as examples for illustration.

[0060] Devices with geographical location acquisition functions can be used to obtain the geographical locations of the first reference object A, the second reference object B, and the third reference object C respectively. For example, A(gax1, gy1), B(gx2, gy2), and C(gx3, gy3) are obtained.

[0061] The image positions of the first reference point a, the second reference point b, and the third reference point c in the target infrared image can be obtained respectively. For example, a(px1, py1), b(px2, py2), and c(px3, py3) are obtained.

[0062] S23: Determine the correspondence between the image position and the geographical location according to the geographical locations of at least two reference objects and the image positions of at least two reference points.

[0063] The correspondence between the image position and the geographical location can be the equivalent value of the longitude direction and the latitude direction corresponding to one pixel unit, the equivalent value of the geographical distance corresponding to one pixel unit, and so on.

[0064] In a specific embodiment, if at least two reference objects include a first reference object, a second reference object, and a third reference object, and at least two reference points include a first reference point, a second reference point, and a third reference point, the equivalent values corresponding to the longitude direction and the latitude direction of a pixel unit can be determined according to the geographical positions of the second reference object and the third reference object, and the image positions of the second reference point and the third reference point.

[0065] In this way, the equivalent values ug (ugx, ugy) corresponding to the longitude direction and the latitude direction of a pixel unit can be calculated using the following formula:

[0066]

[0067]

[0068] where (gx 1 , gy 1 ) is the geographical position (longitude coordinate, latitude coordinate) of the first reference object, (gx 2 , gy 2 ) is the geographical position of the second reference object, (gx 3 , gy 3 ) is the geographical position of the third reference object, (px 1 , py 1 ) is the image position (abscissa, ordinate) of the first reference point, (px 2 , py 2 ) is the image position of the second reference point, (px 3 , py 3 ) is the image position of the third reference point.

[0069] In another specific embodiment, if at least two reference objects include a first reference object, a second reference object, and a third reference object, and at least two reference points include a first reference point, a second reference point, and a third reference point, the equivalent value corresponding to the geographical distance of a pixel unit can be determined according to the image positions of the first reference point and the second reference point, and the geographical distance between the first reference object and the second reference object.

[0070] In this way, the equivalent value pd (pdx, pdy) corresponding to the geographical distance of a pixel unit can be calculated using the following formula:

[0071]

[0072]

[0073] Among them, xd is the geographical distance between the second reference object and the third reference object, and yd is the geographical distance between the first reference object and the second reference object. The geographical distance is the actual distance on the geography / the distance between geographical locations.

[0074] In addition, based on the second embodiment above, S13 may further include: determining the geographical location of the abnormal point according to the image position of the abnormal point, the geographical location corresponding to the infrared image, and the equivalent values of the longitude direction and the latitude direction corresponding to one pixel unit in the infrared image.

[0075] The geographical location corresponding to the infrared image may be the geographical location where the infrared camera is located when the infrared image is taken, that is, the geographical location of the preset position corresponding to the infrared image, that is, the geographical location of the center point of the infrared image.

[0076] The geographical location (gx, gy) of the abnormal point can be calculated using the following formula:

[0077]

[0078] Among them, (cgx, cgy) is the geographical location corresponding to the infrared image, (ugx, ugy) are the equivalent values of the longitude direction and the latitude direction corresponding to one pixel unit in the infrared image, (cpx, cpy) is the image position of the center point of the infrared image, and (px, py) is the image position of the abnormal point.

[0079] Illustratively, the calculated geographical location (αgx, αgy) of the ordinary hot spot is:

[0080]

[0081] The geographical location (βgx, βgy) of the severe hot spot is:

[0082]

[0083] Among them, (αpx, αpy) is the image position of the ordinary hot spot, and (βpx, βpy) is the image position of the severe hot spot.

[0084] Figure 6 It is a schematic diagram of the detection result of the infrared image, where 5 is the image position of the ordinary hot spot, 6 is the image position of the severe hot spot, and 7 represents the image position of the center point of the infrared image.

[0085] With reference to Figure 7 , in another specific implementation, S13 may include the following sub-steps:

[0086] S131: Determine the geographical distance increment of the abnormal point according to the image position of the abnormal point and the equivalent value of the geographical distance corresponding to one pixel unit in the infrared image.

[0087] The geographical distance increment (dx, dy) of the abnormal point can be calculated using the following formula:

[0088]

[0089] Among them, (cpx, cpy) is the image position of the center point of the mid-infrared image, (px, py) is the image position of the abnormal point, and (pdx, pdy) is the equivalent value of the geographical distance corresponding to one pixel unit in the infrared image.

[0090] S132: Determine the geographical position increments of the abnormal point in the longitude direction and the latitude direction according to the geographical distance increment and the equivalent values of the geographical distance corresponding to the longitude direction and the latitude direction.

[0091] The geographical position increments (zx, zy) of the abnormal point in the longitude direction and the latitude direction can be calculated using the following formula:

[0092]

[0093] (dgx, dgy) are the equivalent values of the geographical distance corresponding to the longitude direction and the latitude direction. Among them, the equivalent values of the geographical distance corresponding to the longitude direction and the latitude direction can be determined according to the geographical positions of the first reference object and the second reference object, and the geographical distance between the first reference object and the second reference object.

[0094] Among them, the equivalent values of the geographical distance corresponding to the longitude direction and the latitude direction (dgx, dgy) can be calculated using the following formula:

[0095]

[0096] S133: Determine the geographical position of the abnormal point according to the geographical position increment and the geographical position corresponding to the infrared image.

[0097] The geographical position of the abnormal point can be calculated using the following formula:

[0098]

[0099] Among them, (cpx, cpy) is the image position of the center point of the mid-infrared image.

[0100] With reference to Figure 8 , in a specific embodiment, if the abnormal point is a hot spot and the detection result of the infrared image mentioned above includes the hot spot level, then S14 may include the following sub-steps:

[0101] S141: Determine the hot spot level.

[0102] S142: Mark the hot spots on the map using corresponding display methods according to the hot spot levels.

[0103] It can be understood that different display methods can be set for different hot spot levels. Mark the hot spots on the map using corresponding display methods according to the hot spot levels, which is convenient for relevant personnel to clarify the hot spot levels based on the marks, and then determine the priority order of inspection and maintenance.

[0104] For example, the display method for a severe hot spot level is red, and the display method for an ordinary hot spot level is blue. Thus, mark the severe hot spots as red and the ordinary hot spots as blue on the map. Among them, for an infrared image, for the schematic diagram of marking the severe hot spots as red on the map, please refer to Figure 9 , Figure 9 where 8 in Figure 10 is the mark for the severe hot spots; for the schematic diagram of marking the ordinary hot spots as blue on the map, please refer to Figure 10 where 9 in

[0105] Continue to refer to Figure 11 and Figure 12 , when relevant personnel want to find the severe hot spots in Figure 9 / Figure 10 the ordinary hot spots in

[0106] they can use a device with a geographical location acquisition function to collect the current geographical location 1 where they are located, move a certain geographical distance, and then re-collect the current geographical location 2 where they are located, and so on, until they reach the geographical location of the severe hot spots / ordinary hot spots. Figure 13 The figure shows the distribution map of the geographical location 1 of relevant personnel and the geographical location of ordinary hot spots, Figure 14 and the figure shows the distribution map of the geographical location 1 of relevant personnel and the geographical location of severe hot spots.

[0107] Refer to Figure 15 , in another specific embodiment, S14 may include the following sub-steps:

[0108] S143: Determine the image positions of the fiducial points in the infrared image.

[0109] The fiducial points may include at least two pixel points in the infrared image, and the image positions of the fiducial points can jointly reflect the size and the field of view of the infrared image. For example, the fiducial points may be the points at the lower left corner and the upper right corner of the infrared image. Or, the fiducial points may be the points at the upper left corner and the lower right corner of the infrared image. Or, the fiducial points may be the points at the upper left corner, the lower right corner, the lower left corner, and the upper right corner of the infrared image. In the following description of this application, only the fiducial points at the lower left corner and the upper right corner of the infrared image are used for illustration.

[0110] S144: Determine the geographical locations of the fiducial points according to the image positions of the fiducial points, the geographical location corresponding to the infrared image, the equivalent values in the longitude direction and the latitude direction corresponding to one pixel unit in the infrared image, and the image position of the center point of the infrared image.

[0111] The geographical locations of the fiducial points can be determined according to the image positions of the fiducial points, the geographical location corresponding to the infrared image, the equivalent values in the longitude direction and the latitude direction corresponding to one pixel unit in the infrared image, and the image position of the center point of the infrared image.

[0112] The following formula can be used to calculate the geographical locations of the fiducial points:

[0113]

[0114] Where, (lgx, bgy) is the geographical location corresponding to the lower left corner of the infrared image, (rgx, tgy) is the geographical location corresponding to the upper right corner of the infrared image, (cgx, cgy) is the geographical location corresponding to the infrared image, (ugx, ugy) is the equivalent value in the longitude direction and the latitude direction corresponding to one pixel unit in the infrared image, and (cpx, cpy) is the image position of the center point of the mid-infrared image.

[0115] S145: Mark the infrared image on the map according to the corresponding relationship between the image positions and the geographical locations of the fiducial points.

[0116] For example, when there are n infrared images corresponding to the area to be detected, some or all of the infrared images can be marked on the map according to the geographical locations lbgi (lgxi, bgyi) of the lower left corners and the geographical locations rtgi (rgxi, tgyi) of the upper right corners of the n infrared images. For the schematic diagram of marking an infrared image on the map, please refer to Figure 16 .

[0117] The marking method in S143 - S145 can be, but is not limited to, applicable to the abnormal points of the photovoltaic power stations in remote mountainous areas. It can be understood that since the terrain within the field of view of the infrared image cannot be specified in remote areas, marking the infrared image on the map by means of pasting can enable relevant personnel to find the abnormal points more intuitively and vividly.

[0118] In other embodiments, in order to enable relevant personnel to more intuitively view the on-site scenario of abnormal points, visible images of the area to be detected in the photovoltaic power station can also be obtained, so that the obtained visible images are associated with the infrared images one by one. Thus, the field of view of the infrared image and the abnormal points therein can be marked / drawn in the corresponding visible image, and the abnormal points in the infrared image can be marked in the corresponding visible image. For an example of marking the field of view of the infrared image and the abnormal points in the infrared image in the corresponding visible image, please refer to Figures 17 - 19 . Among them, Figure 17 is a schematic diagram of the infrared image of the mountain photovoltaic power station and the abnormal points marked in the corresponding visible image, Figure 18 is a schematic diagram of the infrared image of the flat-ground photovoltaic power station and the abnormal points marked in the corresponding visible image, Figure 19 is a schematic diagram of the infrared image of the water-surface photovoltaic power station and the abnormal points marked in the corresponding visible image. Figures 17 - 19 In , 7 represents the field of view of the infrared image in the visible image, and 8 represents the abnormal points in the infrared image.

[0119] Figure 20 is a schematic structural diagram of an embodiment of the detection device of the photovoltaic power station of the present application. As Figure 20 shown, the detection device of the photovoltaic power station includes a processor 31 and a memory 32 coupled to the processor 31.

[0120] Among them, the memory 32 stores program instructions for implementing the method of any of the above embodiments; the processor 31 is configured to execute the program instructions stored in the memory 32 to implement the steps of the above method embodiments. Among them, the processor 31 may also be referred to as a CPU (Central Processing Unit, central processing unit). The processor 31 may be an integrated circuit chip with signal processing capabilities. The processor 31 may also be a general-purpose processor, a digital signal processor (DSP), an application-specific integrated circuit (ASIC), a field-programmable gate array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The general-purpose processor may be a microprocessor or the processor 31 may also be any conventional processor, etc.

[0121] Figure 21 is a schematic structural diagram of an embodiment of the computer-readable storage medium of the present application. As Figure 21As shown in the figure, the computer-readable storage medium 40 of the embodiment of the present application stores program instructions 41, and when the program instructions 41 are executed, the methods provided in the above embodiments of the present application are implemented. Among them, the program instructions 41 can form a program file and be stored in the above computer-readable storage medium 40 in the form of a software product, so that a computer device (which can be a personal computer, a server, or a network device, etc.) or a processor can execute all or part of the steps of the methods in various embodiments of the present application. The aforementioned computer-readable storage medium 40 includes: various media that can store program codes, such as USB flash drives, mobile hard disks, read-only memories (ROMs), random access memories (RAMs), magnetic disks, or optical discs, or terminal devices such as computers, servers, mobile phones, and tablets.

[0122] In several embodiments provided by the present application, it should be understood that the disclosed systems, devices, and methods can be implemented in other ways. For example, the device embodiments described above are merely illustrative. For example, the division of units is only a logical function division. In actual implementation, there may be other division methods. For example, 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 displayed or discussed couplings or direct couplings or communication connections to each other can be through some interfaces, and the indirect couplings or communication connections of devices or units can be in electrical, mechanical, or other forms.

[0123] In addition, each functional unit in various embodiments of the present application can be integrated in a processing unit, or each unit can exist physically alone, or two or more units can be integrated in one unit. The above integrated unit can be implemented in the form of hardware or in the form of a software functional unit. The above are only the embodiments of the present application and do not limit the patent scope of the present application. Any equivalent structure or equivalent process transformation made by using the specification and drawings of the present application, or directly or indirectly applied to other related technical fields, is equally included in the patent protection scope of the present application.

Claims

1. A detection method for a photovoltaic power station, characterized in that, an infrared image is obtained, and the infrared image is obtained by collecting an image of the photovoltaic power station at a preset position, and the infrared image corresponds to the geographical location of the preset position; determine the image position of the abnormal point in the infrared image; determine the geographical location of the abnormal point according to the image position of the abnormal point, the geographical location corresponding to the infrared image, and the pre-established correspondence between the image position and the geographical location; mark the abnormal point on the map; wherein, the marking the abnormal point on the map includes: determine the image positions of the fiducial points in the infrared image, and the fiducial points are the points at the lower left corner and the upper right corner of the infrared image; determine the geographical locations of the fiducial points according to the image positions of the fiducial points, the geographical location corresponding to the infrared image, the equivalent values of one pixel unit in the longitude direction and the latitude direction in the infrared image, and the image position of the center point of the infrared image; annotate the infrared image on the map according to the correspondence between the image positions and the geographical locations of the fiducial points; wherein, the determining the geographical locations of the fiducial points according to the image positions of the fiducial points, the geographical location corresponding to the infrared image, the equivalent values of one pixel unit in the longitude direction and the latitude direction in the infrared image, and the image position of the center point of the infrared image includes: calculate the geographical locations of the fiducial points by using the following formula: wherein, (lgx, bgy) is the geographical location corresponding to the lower left corner of the infrared image, (rgx, tgy) is the geographical location corresponding to the upper right corner of the infrared image, (cgx, cgy) is the geographical location corresponding to the infrared image, (ugx, ugy) is the equivalent values of one pixel unit in the longitude direction and the latitude direction in the infrared image, and (cpx, cpy) is the image position of the center point of the infrared image.

2. The method according to claim 1, characterized in that, the method further includes: collect a target infrared image of a target area, the target area includes at least two reference objects, and the target infrared image includes at least two reference points respectively corresponding to the at least two reference objects; obtain the geographical locations of the at least two reference objects, and obtain the image positions of the at least two reference points; determine the correspondence between the image position and the geographical location according to the geographical locations of the at least two reference objects and the image positions of the at least two reference points.

3. The method according to claim 2, characterized in that, the at least two reference objects include a first reference object, a second reference object and a third reference object, the at least two reference points include a first reference point corresponding to the first reference object, a second reference point corresponding to the second reference object, and a third reference point corresponding to the third reference object, and the line connecting the first reference point and the second reference point is parallel to the longitude direction, and the line connecting the second reference point and the third reference point is parallel to the latitude direction; Determining the correspondence between the image position and the geographical position according to the geographical positions of the at least two reference objects and the image positions of the at least two reference points includes: Determining the equivalent values in the longitude direction and the latitude direction corresponding to one pixel unit according to the geographical positions of the second reference object and the third reference object and the image positions of the second reference point and the third reference point; or Determining the equivalent value of the geographical distance corresponding to one pixel unit according to the image positions of the first reference point and the second reference point and the geographical distance between the first reference object and the second reference object.

4. The method according to claim 3, wherein, Determining the equivalent values in the longitude direction and the latitude direction corresponding to one pixel unit according to the geographical positions of the second reference object and the third reference object and the image positions of the second reference point and the third reference point includes: Calculating the equivalent values ug(ugx, ugy) in the longitude direction and the latitude direction corresponding to one pixel unit by using the following formula: or Determining the equivalent value of the geographical distance corresponding to one pixel unit according to the image positions of the first reference point and the second reference point and the geographical distance between the first reference object and the second reference object includes: Calculating the equivalent value pd(pdx, pdy) of the geographical distance corresponding to one pixel unit by using the following formula: where gy 1 is the latitude coordinate of the geographical location of the first reference object, (gx 2 , gy 2 ) is the geographical location of the second reference object, gx 3 is the longitude coordinate of the geographical location of the third reference object, py 1 is the vertical coordinate in the image position of the first reference point, (px 2 , py 2 ) is the image position of the second reference point, px 3 is the horizontal coordinate in the image position of the third reference point, xd is the geographical distance between the second reference object and the third reference object, and yd is the geographical distance between the first reference object and the second reference object.

5. The method according to claim 3, wherein, Determining the geographical position of the abnormal point according to the image position of the abnormal point, the geographical position corresponding to the infrared image, and the pre-established correspondence between the image position and the geographical position includes: Determining the geographical position of the abnormal point according to the image position of the abnormal point, the geographical position corresponding to the infrared image, and the equivalent values in the longitude direction and the latitude direction corresponding to one pixel unit in the infrared image.

6. The method according to claim 5, wherein, Determining the geographical position of the abnormal point according to the image position of the abnormal point, the geographical position corresponding to the infrared image, and the equivalent values in the longitude direction and the latitude direction corresponding to one pixel unit in the infrared image includes: Calculating the geographical position (gx, gy) of the abnormal point by using the following formula: where (cgx, cgy) is the geographical position corresponding to the infrared image, (ugx, ugy) is the equivalent values in the longitude direction and the latitude direction corresponding to one pixel unit in the infrared image, (cpx, cpy) is the image position of the center point of the infrared image, and (px, py) is the image position of the abnormal point.

7. The method according to claim 3, wherein, Determining the geographical position of the abnormal point according to the image position of the abnormal point, the geographical position corresponding to the infrared image, and the pre-established correspondence between the image position and the geographical position includes: Determining the geographical distance increment of the abnormal point according to the image position of the abnormal point and the equivalent value of the geographical distance corresponding to one pixel unit in the infrared image; Determine the geographical location increments of the abnormal point in the longitude direction and the latitude direction according to the geographical distance increment and the equivalent values of the geographical distance corresponding to the longitude direction and the latitude direction; Determine the geographical location of the abnormal point according to the geographical location increment and the geographical location corresponding to the infrared image.

8. The method according to claim 7, wherein, the step of determining the geographical distance increment of the abnormal point according to the image position of the abnormal point and the equivalent value of the geographical distance corresponding to one pixel unit in the infrared image includes: calculating the geographical distance increment (dx, dy) of the abnormal point by using the following formula: the step of determining the geographical location increments of the abnormal point in the longitude direction and the latitude direction according to the geographical distance increment and the equivalent values of the geographical distance corresponding to the longitude direction and the latitude direction includes: calculating the geographical location increments (zx, zy) of the abnormal point in the longitude direction and the latitude direction by using the following formula: the step of determining the geographical location of the abnormal point according to the geographical location increment and the geographical location corresponding to the infrared image includes: calculating the geographical location of the abnormal point by using the following formula: where (cpx, cpy) is the image position of the center point of the infrared image, (px, py) is the image position of the abnormal point, (pdx, pdy) is the equivalent value of the geographical distance corresponding to one pixel unit in the infrared image, (dgx, dgy) is the equivalent value of the geographical distance corresponding to the longitude direction and the latitude direction, and (cgx, cgy) is the geographical location corresponding to the infrared image.

9. The method according to claim 1, wherein, the abnormal point is a hot spot; the step of marking the abnormal point on the map includes: determining the hot spot level; marking the hot spot on the map by using a corresponding display method according to the hot spot level.

10. A detection device for a photovoltaic power station, wherein, it includes a processor and a memory connected to the processor, wherein, the memory stores program instructions; the processor is configured to execute the program instructions stored in the memory to implement the method according to any one of claims 1-9.

11. A computer-readable storage medium, wherein, the computer-readable storage medium stores program instructions, and when the program instructions are executed, the method according to any one of claims 1-9 is implemented.

Images