CN115661466B - Photovoltaic panel positioning method and device based on deep learning image segmentation - Google Patents
Photovoltaic panel positioning method and device based on deep learning image segmentation Download PDFInfo
- Publication number
- CN115661466B CN115661466B CN202211602512.6A CN202211602512A CN115661466B CN 115661466 B CN115661466 B CN 115661466B CN 202211602512 A CN202211602512 A CN 202211602512A CN 115661466 B CN115661466 B CN 115661466B
- Authority
- CN
- China
- Prior art keywords
- image
- photovoltaic panel
- photovoltaic
- row
- area
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000013135 deep learning Methods 0.000 title claims abstract description 36
- 238000003709 image segmentation Methods 0.000 title claims abstract description 36
- 238000012545 processing Methods 0.000 claims abstract description 25
- 230000006870 function Effects 0.000 claims description 10
- 238000001514 detection method Methods 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 9
- 230000000712 assembly Effects 0.000 claims description 5
- 238000000429 assembly Methods 0.000 claims description 5
- 238000010248 power generation Methods 0.000 abstract description 7
- 238000004590 computer program Methods 0.000 description 9
- 230000008569 process Effects 0.000 description 5
- 230000002950 deficient Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000011218 segmentation Effects 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000003703 image analysis method Methods 0.000 description 1
- 239000003550 marker Substances 0.000 description 1
- 238000013178 mathematical model Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000001931 thermography Methods 0.000 description 1
Images
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/50—Photovoltaic [PV] energy
Landscapes
- Image Analysis (AREA)
Abstract
The invention discloses a photovoltaic panel positioning method based on deep learning image segmentation, which comprises the following steps: acquiring attribute effective data of the area image through the area image shot by the unmanned aerial vehicle, and positioning the image of the photovoltaic panel on the same row by adopting a proper program rule; acquiring the number of rows of the photovoltaic panel in the area based on the number of rows of the area image and a photovoltaic panel row number mapping program in the area; and carrying out image segmentation on the photovoltaic panel image of any row based on the U2-net deep learning network to obtain a photovoltaic panel image mask, processing the photovoltaic panel image mask to obtain the parameter of any single photovoltaic panel component in the photovoltaic panel image, and thus obtaining the precise row and column coordinate position of the photovoltaic panel. When the photovoltaic board breaks down, can accurate location fault point, reduce the power generation enterprise trouble photovoltaic board fortune dimension cost, reach the purpose that increases energy and fall this, fix a position the fault point fast, improve the operating efficiency of power generation enterprise greatly, reduce economic loss.
Description
Technical Field
The patent application relates to the technical field of image recognition, in particular to a photovoltaic panel positioning method and device based on deep learning image segmentation.
Background
Photovoltaic power plant is in stable, last, efficient power generation in-process, because photovoltaic board problem itself or other problems lead to the generated energy to descend, need patrol and examine the photovoltaic board, and present efficiency is the highest to shoot infrared and visible light through unmanned aerial vehicle and patrol and examine. After the photovoltaic panel detection is completed, the defective photovoltaic panel needs to be replaced and maintained, and the capacity of a common power station is dozens of MW, hundreds of MW or even GW. The number of photovoltaic panels is hundreds of thousands, millions or even more, and it is not easy to find the defective photovoltaic panel in the photovoltaic panels at the fastest speed.
Acquiring an infrared image of a photovoltaic panel in the air by using a multi-rotor unmanned aerial vehicle carrying a thermal imaging camera, and processing the infrared image by using an onboard processor to judge whether a hot spot fault exists; calculating an optimal routing inspection path of the unmanned aerial vehicle, and correcting the position of the unmanned aerial vehicle in the flight process to ensure that the unmanned aerial vehicle is on the planned routing inspection path; acquiring the real-time position of the unmanned aerial vehicle through the airborne positioning equipment, positioning the fault position by combining the position (longitude and latitude information) of the unmanned aerial vehicle and the position of the fault in the image when the fault is found, and storing and uploading related information; the unmanned aerial vehicle is accurately landed at a fixed point and automatically charged through the ground marker, and further automation of the whole process is realized.
The current positioning method can detect the faults of the photovoltaic system to a certain extent and find out the position of the faulted photovoltaic panel, but certain defects still exist, such as difficulty in establishing a model based on a mathematical model method and great limitation; and the infrared image analysis method is greatly interfered by the environment, and the GPS information causes the problems of insufficient positioning precision and the like.
The photovoltaic panel has obvious random characteristics when being broken down, the construction area of the photovoltaic panel is gradually increased along with the increasing of the solar photovoltaic power generation capacity, the probability of the photovoltaic panel breaking down is increased immediately, the manual maintenance cost is increased gradually, but the existing GPS positioning precision is difficult to meet the requirements of quickness and accuracy, and the position correction is usually carried out manually, so that the cost for maintaining the broken-down photovoltaic panel of a power generation enterprise is high, and the safe operation and the effective scheduling of a photovoltaic power system are reduced.
Disclosure of Invention
The invention aims to solve at least one of technical problems in the related technology to a certain extent, and therefore, the first purpose of the invention is to provide a photovoltaic panel positioning method and device based on deep learning image segmentation, the technology is simple and efficient to realize, and the positioning accuracy of a photovoltaic panel is effectively improved, so that when the photovoltaic panel breaks down, a fault point can be accurately positioned, the operation and maintenance cost of the broken-down photovoltaic panel of a power generation enterprise is reduced, the purposes of increasing energy and reducing cost are achieved, the fault point is quickly positioned, the operation efficiency of the power generation enterprise is greatly improved, and the economic loss is reduced.
The second purpose of the invention is to provide a photovoltaic panel positioning device based on deep learning image segmentation.
A third object of the invention is to propose an electronic device.
A fourth object of the invention is to propose a storage medium.
In order to achieve the above object, an embodiment of a first aspect of the present invention provides a method for positioning a photovoltaic panel based on deep learning image segmentation, where the method includes:
acquiring attribute effective data of the area image through the area image shot by the unmanned aerial vehicle, and positioning the image of the photovoltaic panel on the same row by adopting a proper program rule;
acquiring the number of rows of the photovoltaic panel in the area based on the number of rows of the area image and a photovoltaic panel row number mapping program in the area;
and carrying out image segmentation on the photovoltaic panel image of any row based on the U2-net deep learning network to obtain a photovoltaic panel image mask, processing the photovoltaic panel image mask to obtain the parameter of any single photovoltaic panel component in the photovoltaic panel image, and thus obtaining the precise row and column coordinate position of the photovoltaic panel.
Further, the attribute valid data includes the characteristics of "CreateDate", "FlightXSpeed", "FlightYSpeed" and "flightzsped" of the acquired photovoltaic panel image, where CreateDate is the photographing time of the photographed photovoltaic panel image, flightXSpeed is the speed in the x-axis direction when the photographed photovoltaic panel image is photographed, that is, the north speed in the space, flightYSpeed is the speed in the y-axis direction when the photographed photovoltaic panel image is photographed, that is, the east speed in the space, and flightzsped is the speed in the z-axis direction when the photographed photovoltaic panel image is photographed, that is, the down speed in the space;
the appropriate program rules are: when the differences of three direction values of 'FlightXSpeed', 'FlightYSpeed' and 'FlightZpeed' of the images of the adjacent photovoltaic panels are within 1.3 and the number of the continuous images is more than 4, the photovoltaic panels in the same row are judged, and the row number of the photovoltaic panels is coded from top to bottom.
According to the photovoltaic panel positioning method based on deep learning image segmentation, the mapping program comprises the following steps: and each photovoltaic panel image comprises m rows of photovoltaic panels, one row of photovoltaic panels is overlapped longitudinally, and the number of rows of the photovoltaic panel image is n rows, so that the number of rows of the photovoltaic panels is = (m-1) × n +1.
According to the photovoltaic panel positioning method based on deep learning image segmentation, the photovoltaic panel image mask processing mode comprises the following steps: and determining the coordinate parameters of the single assemblies of the photovoltaic panel images in any row by adopting outline detection of opencv.
According to the photovoltaic panel positioning method based on deep learning image segmentation, the outline detection of the opencv comprises the following steps: a findcounters function in opencv obtains coordinates of 4 vertex pixels of the image assembly by using a photovoltaic panel image mask, numbers the small assemblies in sequence, and cuts original images of the area images according to the coordinates to obtain coordinate parameters of the assembly images.
According to the photovoltaic panel positioning method based on the deep learning image segmentation, the area image comprises a visible light image and an infrared image.
The embodiment of the second aspect of the invention provides a photovoltaic panel positioning device based on deep learning image segmentation, which comprises:
the image processing module is used for acquiring attribute effective data of the area image through the area image shot by the unmanned aerial vehicle and positioning the image of the same row of photovoltaic panels by adopting a proper program rule;
the mapping module is used for acquiring the number of lines of the photovoltaic panel in the area based on the number of lines of the area image and a photovoltaic panel line number mapping program in the area;
and the processing and positioning module is used for carrying out image segmentation on the photovoltaic panel image of any row based on the U2-net deep learning network to obtain a photovoltaic panel image mask, processing the photovoltaic panel image mask to obtain the parameter of any photovoltaic panel single component in the photovoltaic panel image, and further obtaining the accurate row and column coordinate position of the photovoltaic panel.
According to an embodiment of the present invention, the attribute valid data obtained by the image processing module includes characteristics of "createdadate", "FlightXSpeed", "FlightYSpeed", and flightzsped "for obtaining the photovoltaic panel image, createDate is a photographing time for photographing the photovoltaic panel image, flightXSpeed is an x-axis direction speed when photographing the photovoltaic panel image, that is, a north-direction speed in space, flightYSpeed is a y-axis direction speed when photographing the photovoltaic panel image, that is, an east-direction speed in space, and flightzsped is a z-axis direction speed when photographing the photovoltaic panel image, that is, a down-direction speed in space;
the suitable program rules in the image processing module are: when the differences of three direction values of 'FlightXSpeed', 'FlightYSpeed' and 'FlightZpeed' of the images of the adjacent photovoltaic panels are within 1.3 and the number of the continuous images is more than 4, the photovoltaic panels in the same row are judged, and the row number of the photovoltaic panels is coded from top to bottom.
According to an embodiment of the invention, the mapping program of the mapping module comprises: each photovoltaic panel image comprises m rows of photovoltaic panels, one row of photovoltaic panels is longitudinally overlapped, and the number of rows of the photovoltaic panel image is n rows, so that the number of rows of the photovoltaic panels is = (m-1) × n +1.
According to one embodiment of the invention, the processing and positioning module adopts opencv contour detection to determine the coordinate parameters of the single photovoltaic panel image components in any row;
specifically, a findcount function in opencv obtains coordinates of 4 vertex pixels of an image component by using a photovoltaic panel image mask, numbers small components in sequence, and cuts an original image of an area image according to the coordinates to obtain coordinate parameters of the component image, wherein the area image comprises a visible light image and an infrared image.
In an embodiment of a third aspect of the present invention, an electronic device is provided, which includes a memory and a processor, where the memory stores a computer program, and the computer program is configured to implement, when executed in runtime, the method for positioning a photovoltaic panel based on deep learning image segmentation as set forth in the embodiment of the first aspect of the present invention;
the processor is configured to implement the method for positioning a photovoltaic panel based on deep learning image segmentation as set forth in an embodiment of the first aspect of the present invention when the computer program is executed.
A fourth aspect of the present invention provides a storage medium, in which a computer program is stored, where the computer program is configured to, when running, implement the method for positioning a photovoltaic panel based on deep learning image segmentation as set forth in the first aspect of the present invention.
Compared with the prior art, the invention has the beneficial effects that: according to the photovoltaic panel positioning method, the effective attribute data of the area image is obtained through the area image shot by the unmanned aerial vehicle, and the images of the photovoltaic panels in the same row are positioned by adopting a proper program rule; acquiring the number of lines of the photovoltaic panel in the area based on the number of lines of the area image and a photovoltaic panel line number mapping program in the area; and then, carrying out image segmentation on the photovoltaic panel image of any row through a U2-net-based deep learning network to obtain a photovoltaic panel image mask, processing the photovoltaic panel image mask to obtain the parameter of any photovoltaic panel single component in the photovoltaic panel image, and obtaining the accurate row and column coordinate position of the photovoltaic panel.
Drawings
FIG. 1 is a schematic flow chart of a photovoltaic panel positioning method based on deep learning image segmentation according to the present invention;
FIG. 2 is a schematic structural diagram of a photovoltaic panel positioning device based on deep learning image segmentation according to the present invention;
fig. 3 is a schematic structural diagram of an electronic device provided in the present invention.
Detailed Description
The following description of the embodiments of the present application is provided by way of specific examples, and other advantages and effects of the present application will be readily apparent to those skilled in the art from the disclosure herein. The present application is capable of other and different embodiments and its several details are capable of modifications and variations in various respects, all without departing from the spirit of the present application. It should be noted that the embodiments and features of the embodiments in the present application may be combined with each other without conflict.
The photovoltaic panel positioning method and device based on deep learning image segmentation according to the embodiments of the present invention will be described in detail with reference to the drawings and specific embodiments.
Fig. 1 is a flowchart of a photovoltaic panel positioning method based on deep learning image segmentation according to an embodiment of the present invention, and as shown in fig. 1, the photovoltaic panel positioning method includes:
s1, obtaining attribute effective data of an area image shot by an unmanned aerial vehicle, wherein the area image comprises a visible light image and an infrared image, and positioning the images of the same row of photovoltaic panels by adopting a proper program rule;
specifically, the attribute valid data includes the characteristics of "CreateDate", "flightxseed", "FlightYSpeed", and flightzsped "of the acquired photovoltaic panel image, where CreateDate is the photographing time of the photographed photovoltaic panel image, flightXSpeed is the speed in the x-axis direction when the photographed photovoltaic panel image is photographed, that is, the north speed in the space, flightYSpeed is the speed in the y-axis direction when the photographed photovoltaic panel image is photographed, that is, the east speed in the space, and flightzsped is the speed in the z-axis direction when the photographed photovoltaic panel image is photographed, that is, the down speed in the space;
suitable program rules are: when the differences of three direction values of 'flight XSpeed', 'flight YSpeed' and 'flight Zsped' of adjacent photovoltaic panel images are within 1.3 and the number of the continuous images is larger than 4, the photovoltaic panels in the same row are judged, the row numbers of the photovoltaic panels are numbered from top to bottom, and the photovoltaic panels are numbered quickly according to the creating time and the direction value deviation when the photovoltaic panels are shot.
S2, acquiring the number of lines of the photovoltaic panel in the area based on the number of lines of the area image and a photovoltaic panel line number mapping program in the area;
the mapping program comprises: each image of the photovoltaic panel includes m rows of photovoltaic panels, one row of the photovoltaic panels is overlapped in the longitudinal direction, and the number of rows of the image of the photovoltaic panel is n rows, then the number of rows of the photovoltaic panel = (m-1) × n +1, for example, when each image includes 2 rows of the number of rows of the photovoltaic panels, and one row of the photovoltaic panels is overlapped in the longitudinal direction, then the number of rows of the photovoltaic panels is equal to the number of rows of the image plus 1.
S3, image segmentation is carried out on the photovoltaic panel image of any line based on a U2-net deep learning network, the photovoltaic panel visible light image and the infrared image are input into the U2-net network, a black-and-white contour map of the photovoltaic panel assembly is obtained through U2net model identification and segmentation, namely the black-and-white contour map of the photovoltaic panel assembly is obtained through a model for the main purpose, in the training process, the loss function loss value is smaller than 0.005 storage model, and a photovoltaic panel image mask is obtained; and then carrying out outline detection of opencv on the photovoltaic panel image mask to obtain parameters of any single photovoltaic panel component in the photovoltaic panel image, so as to obtain the accurate row-column coordinate position of the photovoltaic panel.
In the step, a findcount function in opencv obtains coordinates of 4 vertex pixels of the image component by using a photovoltaic panel image mask, numbers the small components in sequence, and cuts an original image of the area image according to the coordinates to obtain coordinate parameters of the component image.
An embodiment of the present invention further provides a photovoltaic panel positioning apparatus based on deep learning image segmentation, as shown in fig. 2, including an image processing module 610, a mapping module 620, and a processing and positioning module 630.
In this embodiment, the image processing module 610 is configured to obtain the attribute valid data of the area image through the area image shot by the unmanned aerial vehicle, where the area image includes a visible light image and an infrared image, and position the image of the same row of photovoltaic panels by using a suitable program rule;
in this step, the attribute valid data obtained by the image processing module 610 includes the features of "CreateDate", "FlightXSpeed", "FlightYSpeed", and "flightzsped" of the obtained photovoltaic panel image, where CreateDate is the photographing time of the photographed photovoltaic panel image, flightXSpeed is the speed in the x-axis direction when the photovoltaic panel image is photographed, that is, the north speed in space, flightYSpeed is the speed in the y-axis direction when the photovoltaic panel image is photographed, that is, the east speed in space, and flightzsped is the speed in the z-axis direction when the photovoltaic panel image is photographed, that is, the down speed in space; suitable program rules in the image processing module 610 are: when the differences of three direction values of 'FlightXSpeed', 'FlightYSpeed' and 'FlightZpeed' of the images of the adjacent photovoltaic panels are within 1.3 and the number of the continuous images is more than 4, the photovoltaic panels in the same row are judged, and the row number of the photovoltaic panels is coded from top to bottom.
In this embodiment, the mapping module 620 is configured to obtain the number of rows of photovoltaic panels in the area based on the number of rows of the area image and the number of rows of photovoltaic panels in the area; the mapping procedure of the mapping module 610 includes: in the step, when each image contains 2 rows of photovoltaic panels and one row of photovoltaic panels is longitudinally overlapped, the number of the rows of the photovoltaic panels is equal to the number of the rows of the image plus 1.
In this embodiment, the processing and positioning module 630 is configured to perform image segmentation on a photovoltaic panel image of any row based on a U2-net deep learning network, input a visible light image and an infrared image of the photovoltaic panel into the U2-net network, and obtain a black-and-white profile of the photovoltaic panel assembly through U2net model identification and segmentation, that is, obtain a black-and-white profile of the photovoltaic panel assembly through the model, in a training process, a loss function loss value is smaller than 0.005 storage model, obtain a photovoltaic panel image mask, perform opencv profile detection on the photovoltaic panel image mask, obtain a parameter of any single photovoltaic panel assembly in the photovoltaic panel image, and thus obtain an accurate row-column coordinate position of the photovoltaic panel.
The findcount function in opencv obtains the pixel coordinates of 4 vertexes of the image assembly by using the image mask of the photovoltaic panel, numbers the small assemblies in sequence, and cuts the original image of the area image according to the coordinates to obtain the coordinate parameters of the assembly image.
In some embodiments, as shown in fig. 3, an electronic device 700 is further provided in an embodiment of the present application, and includes a processor 701, a memory 702, and a computer program stored in the memory 702 and capable of being executed on the processor 701, where the computer program, when executed by the processor 701, implements each process of the ultra-short term prediction method for wind power, and can achieve the same technical effect, and is not described herein again to avoid repetition.
It should be noted that the electronic device in the embodiment of the present application includes the mobile electronic device and the non-mobile electronic device described above.
An embodiment of the present invention further provides a storage medium, where a computer program is stored in the storage medium, and the computer program is configured to, when running, implement the photovoltaic panel positioning method based on deep learning image segmentation as provided in the embodiment of the present invention.
It should be noted that the logic and/or steps shown in the flowcharts or otherwise described herein, such as an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the invention. In this specification, the schematic representations of the terms used above do not necessarily refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
In the description of the present invention, it is to be understood that the terms "central," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," "counterclockwise," "axial," "radial," "circumferential," and the like are used in the orientations and positional relationships indicated in the drawings for convenience in describing the invention and to simplify the description, and are not intended to indicate or imply that the referenced devices or elements must have a particular orientation, be constructed and operated in a particular orientation, and are therefore not to be considered limiting of the invention.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present invention, "a plurality" means at least two, e.g., two, three, etc., unless explicitly specified otherwise.
In the present invention, unless otherwise explicitly stated or limited, the terms "mounted," "connected," "fixed," and the like are to be construed broadly, e.g., as being permanently connected, detachably connected, or integral; can be mechanically or electrically connected; they may be directly connected or indirectly connected through intervening media, or they may be connected internally or in any other suitable relationship, unless expressly stated otherwise. The specific meanings of the above terms in the present invention can be understood by those skilled in the art according to specific situations.
In the present invention, unless expressly stated or limited otherwise, the first feature "on" or "under" the second feature may be directly contacting the second feature or the first and second features may be indirectly contacting each other through intervening media. Also, a first feature "on," "over," and "above" a second feature may be directly or diagonally above the second feature, or may simply indicate that the first feature is at a higher level than the second feature. A first feature being "under," "below," and "beneath" a second feature may be directly under or obliquely under the first feature, or may simply mean that the first feature is at a lesser elevation than the second feature.
Although embodiments of the present invention have been shown and described above, it will be understood that the above embodiments are exemplary and not to be construed as limiting the present invention, and that changes, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.
Claims (8)
1. A photovoltaic panel positioning method based on deep learning image segmentation is characterized by comprising the following steps:
obtaining attribute effective data of the area image through the area image shot by the unmanned aerial vehicle, and positioning the image of the same row of photovoltaic panels by adopting a proper program rule;
acquiring the number of rows of the photovoltaic panel in the area based on the number of rows of the area image and a photovoltaic panel row number mapping program in the area;
carrying out image segmentation on the photovoltaic panel image of any row based on a U2-net deep learning network to obtain a photovoltaic panel image mask, processing the photovoltaic panel image mask to obtain parameters of any single photovoltaic panel component in the photovoltaic panel image, and thus obtaining an accurate row coordinate position of the photovoltaic panel;
the attribute valid data comprises the characteristics of 'CreateDate', 'flight xspeed', 'flight speed' and 'flight zsped' of the obtained photovoltaic panel image, wherein CreateDate is the photographing time of the photographed photovoltaic panel image, flight xspeed is the speed of the photovoltaic panel image in the x-axis direction when the photographed image is taken, namely the north speed in the space, flight is the speed of the photovoltaic panel image in the y-axis direction when the photographed image is taken, namely the east speed in the space, and flight zsped is the speed of the photovoltaic panel image in the z-axis direction when the photographed image is taken, namely the down speed in the space;
the appropriate program rules are: when the difference of three direction values of 'flight XSpeed', 'flight YSpeed' and 'flight Zsped' of adjacent photovoltaic panel images is within 1.3 and the number of continuous images is more than 4, the photovoltaic panels in the same row are judged, and the row number of the photovoltaic panels is coded from top to bottom.
2. The deep learning image segmentation-based photovoltaic panel positioning method according to claim 1, wherein the mapping procedure comprises: and each photovoltaic panel image comprises m rows of photovoltaic panels, one row of photovoltaic panels is overlapped longitudinally, and the number of rows of the photovoltaic panel image is n rows, so that the number of rows of the photovoltaic panels is = (m-1) × n +1.
3. The photovoltaic panel positioning method based on deep learning image segmentation as claimed in claim 1, wherein the photovoltaic panel image mask processing manner includes: and determining the coordinate parameters of the single assemblies of the photovoltaic panel images in any row by adopting outline detection of opencv.
4. The photovoltaic panel positioning method based on deep learning image segmentation as claimed in claim 3, wherein the outline detection of opencv comprises: the findcount function in opencv obtains the pixel coordinates of 4 vertexes of the image assembly by using the image mask of the photovoltaic panel, numbers the small assemblies in sequence, and cuts the original image of the area image according to the coordinates to obtain the coordinate parameters of the assembly image.
5. The method according to claim 4, wherein the area image comprises a visible light image and an infrared image.
6. A photovoltaic panel positioning device based on deep learning image segmentation is characterized by comprising:
the image processing module is used for acquiring the attribute effective data of the area image through the area image shot by the unmanned aerial vehicle and positioning the image of the same row of photovoltaic panels by adopting a proper program rule;
the mapping module is used for acquiring the number of lines of the photovoltaic panel in the area based on the number of lines of the area image and a photovoltaic panel line number mapping program in the area;
the processing and positioning module is used for carrying out image segmentation on the photovoltaic panel image of any row based on the U2-net deep learning network to obtain a photovoltaic panel image mask, processing the photovoltaic panel image mask to obtain the parameter of any single photovoltaic panel component in the photovoltaic panel image, and accordingly obtaining the accurate row and column coordinate position of the photovoltaic panel;
the attribute valid data acquired by the image processing module comprises characteristics of 'CreateDate', 'flight xspeed', 'flight speed predicted' and 'flight speed predicted' of the photovoltaic panel image, wherein CreateDate is shooting time of the photovoltaic panel image, flight xspeed is speed in the x-axis direction when the photovoltaic panel image is shot, namely north speed in space, flight is speed in the y-axis direction when the photovoltaic panel image is shot, namely east speed in space, and flight zsped is speed in the z-axis direction when the photovoltaic panel image is shot, namely downward speed in space;
the suitable program rules in the image processing module are: when the differences of three direction values of 'FlightXSpeed', 'FlightYSpeed' and 'FlightZpeed' of the images of the adjacent photovoltaic panels are within 1.3 and the number of the continuous images is more than 4, the photovoltaic panels in the same row are judged, and the row number of the photovoltaic panels is coded from top to bottom.
7. The deep learning image segmentation-based photovoltaic panel positioning device according to claim 6, wherein the mapping program of the mapping module comprises: each photovoltaic panel image comprises m rows of photovoltaic panels, one row of photovoltaic panels is longitudinally overlapped, and the number of rows of the photovoltaic panel image is n rows, so that the number of rows of the photovoltaic panels is = (m-1) × n +1.
8. The photovoltaic panel positioning device based on deep learning image segmentation as claimed in claim 6, wherein the processing and positioning module adopts opencv contour detection to determine coordinate parameters of individual components of photovoltaic panel images in any row;
specifically, a findcount function in opencv obtains 4 vertex pixel coordinates of image components by using a photovoltaic panel image mask, sequentially numbers small components, cuts out original images of area images according to the coordinates, and obtains coordinate parameters of the component images, wherein the area images comprise visible light images and infrared images.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211602512.6A CN115661466B (en) | 2022-12-14 | 2022-12-14 | Photovoltaic panel positioning method and device based on deep learning image segmentation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211602512.6A CN115661466B (en) | 2022-12-14 | 2022-12-14 | Photovoltaic panel positioning method and device based on deep learning image segmentation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115661466A CN115661466A (en) | 2023-01-31 |
| CN115661466B true CN115661466B (en) | 2023-03-17 |
Family
ID=85023570
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211602512.6A Active CN115661466B (en) | 2022-12-14 | 2022-12-14 | Photovoltaic panel positioning method and device based on deep learning image segmentation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115661466B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115797336A (en) * | 2023-02-01 | 2023-03-14 | 尚特杰电力科技有限公司 | Fault detection method and device of photovoltaic module, electronic equipment and storage medium |
Family Cites Families (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR3044187B1 (en) * | 2015-11-24 | 2017-12-22 | Electricite De France | LOCATION OF A SUBGROUP OF FAILURE MODULES IN A PHOTOVOLTAIC PARK |
| CN212301900U (en) * | 2020-05-08 | 2021-01-05 | 国家电投集团江西电力有限公司 | Photovoltaic board positioning system based on unmanned aerial vehicle of photovoltaic power plant fixed point is patrolled and examined |
| CN111740699A (en) * | 2020-05-29 | 2020-10-02 | 南京航空航天大学 | Photovoltaic panel fault detection and identification method and device and unmanned aerial vehicle |
| US20220077820A1 (en) * | 2020-09-04 | 2022-03-10 | Mgit | Method and system for soar photovoltaic power station monitoring |
| CN113989258A (en) * | 2021-11-09 | 2022-01-28 | 浙江浙能嘉华发电有限公司 | Photovoltaic panel hot spot positioning method based on unmanned aerial vehicle and thermal imaging |
| CN114463308A (en) * | 2022-02-09 | 2022-05-10 | 广东数字生态科技有限责任公司 | Visual detection method, device and processing equipment for visual angle photovoltaic module of unmanned aerial vehicle |
| CN114627122A (en) * | 2022-05-16 | 2022-06-14 | 北京东方国信科技股份有限公司 | Defect detection method and device |
-
2022
- 2022-12-14 CN CN202211602512.6A patent/CN115661466B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN115661466A (en) | 2023-01-31 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110703800A (en) | Unmanned aerial vehicle-based intelligent identification method and system for electric power facilities | |
| CN111260615B (en) | Laser and machine vision fusion-based method for detecting apparent diseases of unmanned aerial vehicle bridge | |
| CN111311597A (en) | Unmanned aerial vehicle inspection method and system for defective insulator | |
| CN110908401A (en) | Unmanned aerial vehicle autonomous inspection method for unknown tower structure | |
| CN115661466B (en) | Photovoltaic panel positioning method and device based on deep learning image segmentation | |
| CN112327906A (en) | Intelligent automatic inspection system based on unmanned aerial vehicle | |
| CN111244822B (en) | Fixed-wing unmanned aerial vehicle line patrol method, system and device in complex geographic environment | |
| CN116501091B (en) | Fan inspection control method and device based on unmanned aerial vehicle automatic adjustment route | |
| CN110750107A (en) | Photovoltaic power station unmanned aerial vehicle inspection method based on optical identification | |
| CN116192044A (en) | Fault photovoltaic panel numbering and positioning method and device, electronic equipment and storage medium | |
| CN115442532A (en) | Method, system, equipment and storage medium for inspecting fan without stopping | |
| CN111932618A (en) | Transmission tower infrared shooting route generation method and related device | |
| CN112184903A (en) | Method, device, equipment and medium for detecting high-voltage line tree obstacle risk points | |
| CN116893685A (en) | Unmanned aerial vehicle route planning method and system | |
| CN114723184B (en) | Wind driven generator measuring method, device and equipment based on visual perception | |
| CN116486290A (en) | Unmanned aerial vehicle monitoring and tracking method and device, electronic equipment and storage medium | |
| CN116339383A (en) | Unmanned aerial vehicle-based autonomous planning method for routing inspection route of distribution network | |
| JP7018540B2 (en) | Patrol inspection system and patrol inspection method | |
| CN112197748B (en) | Method for detecting electric clearance of power transmission equipment by utilizing photogrammetry | |
| CN115345446A (en) | Unmanned aerial vehicle line patrol and point cloud data-based project completion acceptance method | |
| CN114241257A (en) | Power transmission line inspection method and system based on image recognition | |
| CN114035608A (en) | Unmanned aerial vehicle-based inspection training method and system, training terminal and storage medium | |
| KR20180082166A (en) | The Apparatus For Detecting Solar Panel | |
| CN117392571B (en) | Aerial power transmission and distribution line acceptance method and aerial power transmission and distribution line acceptance system based on unmanned aerial vehicle image | |
| CN117452970A (en) | Unmanned aerial vehicle inspection control method, device, equipment and medium based on artificial intelligence |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| TR01 | Transfer of patent right |
Effective date of registration: 20231229 Address after: 750411 Ningxia Ningdong Energy and Chemical Base, Yinchuan City, Ningxia Hui Autonomous Region West side of Yuanfeng Road in Huimin Lane and south side of Yuanyanghu Railway Patentee after: Guoneng Ningdong New Energy Co.,Ltd. Address before: 230088 Room 1701, Block C, Building 1, Zone J, Phase II, Hefei Innovation Industrial Park, High-tech Zone, Hefei City, Anhui Province Patentee before: SNEGRID ELECTRIC TECHNOLOGY Co.,Ltd. Patentee before: Guoneng Ningdong New Energy Co.,Ltd. |
|
| TR01 | Transfer of patent right |