CN116758425A - Automatic acceptance checking method and device for large-base photovoltaic power station - Google Patents
Automatic acceptance checking method and device for large-base photovoltaic power station Download PDFInfo
- Publication number
- CN116758425A CN116758425A CN202310765961.0A CN202310765961A CN116758425A CN 116758425 A CN116758425 A CN 116758425A CN 202310765961 A CN202310765961 A CN 202310765961A CN 116758425 A CN116758425 A CN 116758425A
- Authority
- CN
- China
- Prior art keywords
- image
- defect
- camera
- photovoltaic power
- foreground
- 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.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000007547 defect Effects 0.000 claims abstract description 84
- 230000011218 segmentation Effects 0.000 claims abstract description 30
- 238000007689 inspection Methods 0.000 claims abstract description 25
- 238000000605 extraction Methods 0.000 claims abstract description 24
- 239000011159 matrix material Substances 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 9
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000003708 edge detection Methods 0.000 claims description 5
- 238000002372 labelling Methods 0.000 claims description 5
- 241000237858 Gastropoda Species 0.000 claims description 4
- PXFBZOLANLWPMH-UHFFFAOYSA-N 16-Epiaffinine Natural products C1C(C2=CC=CC=C2N2)=C2C(=O)CC2C(=CC)CN(C)C1C2CO PXFBZOLANLWPMH-UHFFFAOYSA-N 0.000 claims description 3
- 238000001914 filtration Methods 0.000 claims description 3
- 238000005070 sampling Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 230000003044 adaptive effect Effects 0.000 claims description 2
- 238000010248 power generation Methods 0.000 description 3
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000003384 imaging method Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 208000037656 Respiratory Sounds Diseases 0.000 description 1
- 230000002159 abnormal effect Effects 0.000 description 1
- 239000000306 component Substances 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000010438 heat treatment Methods 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000003466 welding Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/176—Urban or other man-made structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/10—Image acquisition
- G06V10/12—Details of acquisition arrangements; Constructional details thereof
- G06V10/14—Optical characteristics of the device performing the acquisition or on the illumination arrangements
- G06V10/147—Details of sensors, e.g. sensor lenses
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/77—Processing image or video features in feature spaces; using data integration or data reduction, e.g. principal component analysis [PCA] or independent component analysis [ICA] or self-organising maps [SOM]; Blind source separation
- G06V10/80—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level
- G06V10/803—Fusion, i.e. combining data from various sources at the sensor level, preprocessing level, feature extraction level or classification level of input or preprocessed data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
Abstract
The invention provides an automatic acceptance method and device for a large-base photovoltaic power station, wherein the method comprises the following steps: setting and shooting by using a first camera and a second camera according to a routing inspection route of the unmanned aerial vehicle, and acquiring a visible light image and an infrared image of the photovoltaic panel; judging whether the photovoltaic panel has defects according to the visible light image, and shooting the defect positions of the photovoltaic panel by using a third camera to obtain a defect image; after pretreatment, carrying out foreground segmentation and extraction by an Ojin method to obtain a foreground region image; performing hot spot segmentation extraction on the foreground region image to obtain a hot spot region image; performing image matching according to the geographic coordinates, and determining the defect type of the photovoltaic panel; registering the acquired image with the virtual simulation scene image of the photovoltaic power station, marking the defect type, and generating an acceptance report. The invention acquires the defect image by using the long-focus camera, has high image definition, is convenient for the later image identification and matching, is convenient for technicians to accurately identify the defect type, and improves the inspection efficiency of the photovoltaic panel.
Description
Technical Field
The invention relates to the technical field of inspection of photovoltaic power stations, in particular to an automatic acceptance method and device for a large-base photovoltaic power station.
Background
With the rapid expansion of the photovoltaic power generation industry scale in recent years, the daily operation and maintenance pressure of photovoltaic power stations is increasing. The photovoltaic panel is used as a core component of the photovoltaic power generation system, is exposed to the natural environment for a long time in daily operation, and inevitably generates various defects such as cracks, snail lines, damages, welding strip faults, stains, vegetation shielding, local heating and the like, and timely discovers the defects of the panel and makes manual intervention significant for guaranteeing the power generation efficiency of the photovoltaic power station.
The traditional method is mainly to monitor the generated current of the panel, and when the generated power is abnormal, the panel defect may exist. Due to cost limitation, the method can limit faults within a certain range, accurate fault positioning also needs to rely on manual investigation, and has low detection efficiency and large labor capacity. Therefore, some unmanned aerial vehicle inspection methods are adopted, but most unmanned aerial vehicle inspection methods usually only shoot visible light images and infrared images in the shooting stage, and the images are analyzed and processed after shooting is completed. The unmanned aerial vehicle has the advantages that due to the fact that the photovoltaic module is subjected to terrain factors, the altitude difference exists in installation, the flying height and the speed of the unmanned aerial vehicle are required to be adjusted at any time, the influence of strong light and air flow is easy to occur during shooting, the shot image definition is poor, the omission ratio in the image matching stage is high, the matching effect is poor, accurate positioning and defect type determination cannot be achieved in the defect identification positioning stage, therefore, technicians are required to be arranged to check the area with missing or blurred images, and the workload of operation and maintenance staff is increased.
Disclosure of Invention
In view of the above problems, the invention provides an automatic acceptance method and device for a large-base photovoltaic power station, which solve the problems that in the prior art, the shot image has poor definition, so that the omission ratio in the image matching stage is higher, the matching effect is poor, and accurate positioning and defect type determination cannot be realized in the defect identification positioning stage.
In order to solve the technical problems, the invention adopts the following technical scheme: an automatic acceptance method for a large-base photovoltaic power station comprises the following steps: acquiring a boundary area of a photovoltaic power station, and setting a routing inspection route of the unmanned aerial vehicle according to the boundary area; according to the inspection route, a first camera and a second camera are utilized to shoot the photovoltaic panel to be detected, and a visible light image and an infrared image of the photovoltaic panel are obtained; according to the visible light image, primarily judging whether the photovoltaic panel has defects, if so, shooting the defect positions of the photovoltaic panel by using a third camera to obtain a defect image; preprocessing the infrared image, and then carrying out foreground segmentation extraction on the preprocessed image by using an Ojin method to obtain a foreground region image; performing hot spot segmentation extraction on the foreground region image by adopting a self-adaptive dynamic threshold algorithm to obtain a hot spot region image; according to geographic coordinates, matching the hot spot area image with a visible light image and a defect image, and determining the defect type of the photovoltaic panel; registering the visible light image and/or the defect image with the virtual simulation scene image of the photovoltaic power station, marking the defect type, and generating an acceptance report.
As a preferred solution, setting a routing inspection route of the unmanned aerial vehicle according to the boundary area includes: arranging a plurality of control points in the boundary area, and shooting above the control points by using an unmanned aerial vehicle to obtain control point images, wherein the control point images record geographic coordinates; fitting the boundary region of the photovoltaic power station according to the control point image to obtain a fitting surface of the photovoltaic power station; and determining the shooting gesture and the tour inspection route of the unmanned aerial vehicle according to the vector angle of the fitting surface and the shooting parameters of the camera.
Preferably, the first camera is a wide-angle camera, the second camera is an infrared camera, and the third camera is a tele camera.
As a preferred solution, the defect includes a crack, a snail line, a damage, a stain and a vegetation shielding, and the step of primarily judging whether the photovoltaic panel has the defect according to the visible light image includes: the visible light image is obtained and gray scale processing is carried out on the visible light image; processing the gray level image by adopting a canny edge detection algorithm to obtain a binarized image; acquiring a local image on the binarized image by adopting a sliding window; carrying out spatial clustering on the local images, determining the category with the most similar data, and obtaining an external matrix of the category; and determining the defect position of the photovoltaic panel according to the set longest edge threshold value of the external matrix.
As a preferable scheme, preprocessing the infrared image specifically includes: and carrying out gray scale processing on the infrared image, and then carrying out median filtering processing.
Preferably, the oxford method calculates a segmentation threshold when the inter-class variance between the foreground image and the background image is maximum, and if the inter-class variance is g
g＝ω 0 (μ 0 -μ) 2 +ω 1 (μ 1 -μ) 2 ；
In the above, ω 0 ，ω 1 The pixel number of the foreground image and the pixel number of the background image are respectively the proportion of the pixel number of the whole image, mu 0 ，μ 1 The average gray scale of the foreground image and the background image are respectively, and mu is the average gray scale of the whole image.
As a preferred solution, the performing hot spot segmentation extraction on the foreground region image by adopting an adaptive dynamic threshold algorithm includes: selecting first local windows on the foreground region image, calculating the enhancement coefficient of each first local window, and taking the enhancement coefficient as a new pixel of a central pixel point of the first local window to obtain an enhanced foreground image; selecting second local windows on the enhanced foreground image, calculating Gaussian weighted sum of pixels in each second local window, and subtracting a dynamic threshold value to obtain a segmentation threshold value of the pixel point; and dividing the pixel points on the enhanced foreground image according to the dividing threshold value to obtain a hot spot area image.
Preferably, the pixel point on the enhanced foreground image is denoted as F (i，j) When F (i，j) When the pixel is=1, the pixel is the pixel of the hot spot area image;
T(i，j)＝max(λ dev d(i，j)，C)；
in the above, G (i，j) Is the Gaussian weighted sum of pixel points, T (i，j) Is a dynamic threshold, lambda dev And C is an absolute dynamic threshold, and d (i, j) is the coordinates of the pixel point.
Preferably, registering the visible light image and/or the defect image with the virtual simulation scene image of the photovoltaic power station includes: and matching the feature point positions of the two images with corresponding descriptors by using a BF Matcher method, removing unqualified feature matching point pairs according to a random sampling coincidence algorithm ransac, and solving an affine transformation matrix by using residual matching feature point pairs so as to realize registration.
The invention also discloses an automatic acceptance device of the large-base photovoltaic power station, which comprises the following components: the route setting module is used for obtaining a boundary area of the photovoltaic power station and setting a routing inspection route of the unmanned aerial vehicle according to the boundary area; the image shooting module shoots the photovoltaic panel to be detected by using the first camera and the second camera according to the inspection route, and obtains a visible light image and an infrared image of the photovoltaic panel; the defect judging module is used for preliminarily judging whether the photovoltaic panel has defects according to the visible light image, and if so, shooting the defect positions of the photovoltaic panel by using a third camera to obtain a defect image; the foreground segmentation module is used for preprocessing the infrared image, and then carrying out foreground segmentation extraction on the preprocessed image by the Ojin method to obtain a foreground region image; the hot spot extraction module is used for carrying out hot spot segmentation extraction on the foreground region image by adopting a self-adaptive dynamic threshold algorithm to obtain a hot spot region image; the defect determining module is used for matching the hot spot area image with the visible light image and the defect image according to the geographic coordinates to determine the defect type of the photovoltaic panel; and the registration labeling module is used for registering the visible light image and/or the defect image with the virtual simulation scene image of the photovoltaic power station, labeling the defect type and generating an acceptance report.
Compared with the prior art, the invention has the beneficial effects that: through installing wide angle, infrared and long burnt camera on unmanned aerial vehicle, when shooing the visible light image, utilize canny edge detection algorithm preliminary discernment to have the region of defect, the long focal length of long burnt camera of reuse is fit for shooting the characteristics of distant place object, acquires the defect image, and defect image definition that this mode obtained is high, and the recognition of later stage image of being convenient for matches, makes things convenient for the type of technician accurate discernment defect, has improved the inspection efficiency of photovoltaic board. The infrared image is preprocessed and then subjected to foreground segmentation extraction by an Ojin method, and then the foreground region image is subjected to hot spot segmentation extraction by adopting a self-adaptive dynamic threshold algorithm, so that the hot spot region image is obtained, the influence of imaging difference caused by light intensity along with weather changes can be reduced, and the defect recognition rate is improved.
Drawings
The disclosure of the present invention is described with reference to the accompanying drawings. It is to be understood that the drawings are designed solely for the purposes of illustration and not as a definition of the limits of the invention. In the drawings, like reference numerals are used to refer to like parts. Wherein:
FIG. 1 is a schematic flow chart of an automatic acceptance method for a large-base photovoltaic power station according to an embodiment of the invention;
FIG. 2 is a schematic structural diagram of an automatic acceptance device for a large-base photovoltaic power station according to an embodiment of the invention;
Detailed Description
It is to be understood that, according to the technical solution of the present invention, those skilled in the art may propose various alternative structural modes and implementation modes without changing the true spirit of the present invention. Accordingly, the following detailed description and drawings are merely illustrative of the invention and are not intended to be exhaustive or to limit the invention to the precise form disclosed.
An embodiment according to the invention is shown in connection with fig. 1. An automatic acceptance method for a large-base photovoltaic power station comprises the following steps:
s101, acquiring a boundary area of a photovoltaic power station, and setting a routing inspection route of the unmanned aerial vehicle according to the boundary area.
Specifically, setting an inspection route of the unmanned aerial vehicle according to the boundary area, including:
arranging a plurality of control points in the boundary area, shooting above the control points by using an unmanned aerial vehicle, and obtaining control point images, wherein the control point images record geographic coordinates;
fitting the photovoltaic power station boundary region according to the control point image to obtain a photovoltaic power station fitting surface;
and determining the shooting gesture and the inspection route of the unmanned aerial vehicle according to the vector angle of the fitting surface and the shooting parameters of the camera.
S102, shooting the photovoltaic panel to be detected by using a first camera and a second camera according to the inspection route, and obtaining a visible light image and an infrared image of the photovoltaic panel.
And S103, primarily judging whether the photovoltaic panel has defects according to the visible light image, and if so, shooting the defect positions of the photovoltaic panel by using a third camera to obtain a defect image.
Above-mentioned photovoltaic board defect includes crackle, snail line, damage, stain and vegetation shelter from, then whether the photovoltaic board exists the defect according to the visible light image, including:
(1) Obtaining a visible light image and carrying out gray scale treatment on the visible light image;
(2) Processing the gray level image by adopting a canny edge detection algorithm to obtain a binarized image;
(3) And acquiring a local image on the binarized image by adopting a sliding window.
(4) And carrying out spatial clustering on the local images, determining the category with the most similar data, and obtaining the external matrix of the category.
(5) And determining the defect position of the photovoltaic panel according to the set longest edge threshold value of the external matrix.
In the embodiment of the invention, the first camera is a wide-angle camera, the second camera is an infrared camera, and the third camera is a tele camera.
S104, preprocessing the infrared image, and then carrying out foreground segmentation extraction on the preprocessed image by using an Ojin method to obtain a foreground region image. Preprocessing an infrared image, specifically: and carrying out gray scale treatment on the infrared image, and then carrying out median filtering treatment.
The Ojin method is to calculate the segmentation threshold when the inter-class variance of the foreground image and the background image is maximum, and let the inter-class variance be g
g＝ω 0 (μ 0 -μ) 2 +ω 1 (μ 1 -μ) 2 ；
In the above, ω 0 ，ω 1 The pixel number of the foreground image and the pixel number of the background image are respectively the proportion of the pixel number of the whole image, mu 0 ，μ 1 The average gray scale of the foreground image and the background image are respectively, and mu is the average gray scale of the whole image.
S105, performing hot spot segmentation and extraction on the foreground region image by adopting a self-adaptive dynamic threshold algorithm to obtain a hot spot region image.
The method for carrying out hot spot segmentation extraction on the foreground region image by adopting the self-adaptive dynamic threshold algorithm comprises the following steps:
(1) Selecting first local windows on the foreground region image, calculating the enhancement coefficient of each first local window, and taking the enhancement coefficient as a new pixel of the central pixel point of the first local window to obtain an enhanced foreground image;
(2) Selecting second local windows on the enhanced foreground image, calculating Gaussian weighted sum of pixels in each second local window, and subtracting a dynamic threshold value to obtain a segmentation threshold value of the pixel point;
(3) And dividing the pixel points on the enhanced foreground image according to the dividing threshold value to obtain a hot spot area image.
The pixel point on the enhanced foreground image is denoted as F (i，j) When F (i，j) When the pixel is=1, the pixel is the pixel of the hot spot area image;
T(i，j)＝max(λ dev d(i，j)，C)；
in the above, G (i，j) Is the Gaussian weighted sum of pixel points, T (i，j) Is a dynamic threshold, lambda dev And C is an absolute dynamic threshold, and d (i, j) is the coordinates of the pixel point.
And S106, matching the hot spot area image with the visible light image and the defect image according to the geographic coordinates, and determining the defect type of the photovoltaic panel.
And S107, registering the visible light image and/or the defect image with the virtual simulation scene image of the photovoltaic power station, marking the defect type, and generating an acceptance report.
In the embodiment of the invention, registering the visible light image and/or the defect image with the virtual simulation scene image of the photovoltaic power station comprises the following steps: and matching the feature point positions of the two images with corresponding descriptors by using a BF Matcher method, removing unqualified feature matching point pairs according to a random sampling coincidence algorithm ransac, and solving an affine transformation matrix by using residual matching feature point pairs so as to realize registration.
Referring to fig. 2, the invention also discloses an automatic acceptance device of the large-base photovoltaic power station, which comprises:
the route setting module 101 is used for obtaining a boundary area of the photovoltaic power station and setting a routing inspection route of the unmanned aerial vehicle according to the boundary area;
the image shooting module 102 shoots a photovoltaic panel to be detected by using a first camera and a second camera according to the inspection route, and obtains a visible light image and an infrared image of the photovoltaic panel;
the defect judging module 103 is used for preliminarily judging whether the photovoltaic panel has defects according to the visible light image, and if so, shooting the defect positions of the photovoltaic panel by using a third camera to obtain a defect image;
the foreground segmentation module 104 is used for preprocessing the infrared image, and then carrying out foreground segmentation extraction on the preprocessed image by the Ojin method to obtain a foreground region image;
the hot spot extraction module 105 performs hot spot segmentation extraction on the foreground region image by adopting a self-adaptive dynamic threshold algorithm to obtain a hot spot region image;
the defect determining module 106 is used for matching the hot spot area image with the visible light image and the defect image according to the geographic coordinates to determine the defect type of the photovoltaic panel;
the registration labeling module 107 is configured to register the visible light image and/or the defect image with the virtual simulation scene image of the photovoltaic power station, label the defect type, and generate an acceptance report.
It will be clear to those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, and are not repeated herein.
In summary, the beneficial effects of the invention include: through installing wide angle, infrared and long burnt camera on unmanned aerial vehicle, when shooing the visible light image, utilize canny edge detection algorithm preliminary discernment to have the region of defect, the long focal length of long burnt camera of reuse is fit for shooting the characteristics of distant place object, acquires the defect image, and defect image definition that this mode obtained is high, and the recognition of later stage image of being convenient for matches, makes things convenient for the type of technician accurate discernment defect, has improved the inspection efficiency of photovoltaic board. The infrared image is preprocessed and then subjected to foreground segmentation extraction by an Ojin method, and then the foreground region image is subjected to hot spot segmentation extraction by adopting a self-adaptive dynamic threshold algorithm, so that the hot spot region image is obtained, the influence of imaging difference caused by light intensity along with weather changes can be reduced, and the defect recognition rate is improved.
It should be appreciated that the integrated units, if implemented in the form of software functional units and sold or used as stand-alone products, may be stored in a computer readable storage medium. Based on such understanding, the technical solution of the present invention is essentially or a part contributing to the prior art, or all or part of the technical solution may be embodied in the form of a software product stored in a storage medium, comprising several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
The technical scope of the present invention is not limited to the above description, and those skilled in the art may make various changes and modifications to the above-described embodiments without departing from the technical spirit of the present invention, and these changes and modifications should be included in the scope of the present invention.
Claims (10)
1. An automatic acceptance method for a large-base photovoltaic power station is characterized by comprising the following steps:
acquiring a boundary area of a photovoltaic power station, and setting a routing inspection route of the unmanned aerial vehicle according to the boundary area;
according to the inspection route, a first camera and a second camera are utilized to shoot the photovoltaic panel to be detected, and a visible light image and an infrared image of the photovoltaic panel are obtained;
according to the visible light image, primarily judging whether the photovoltaic panel has defects, if so, shooting the defect positions of the photovoltaic panel by using a third camera to obtain a defect image;
preprocessing the infrared image, and then carrying out foreground segmentation extraction on the preprocessed image by using an Ojin method to obtain a foreground region image;
performing hot spot segmentation extraction on the foreground region image by adopting a self-adaptive dynamic threshold algorithm to obtain a hot spot region image;
according to geographic coordinates, matching the hot spot area image with a visible light image and a defect image, and determining the defect type of the photovoltaic panel;
registering the visible light image and/or the defect image with the virtual simulation scene image of the photovoltaic power station, marking the defect type, and generating an acceptance report.
2. The automatic acceptance method of a large-base photovoltaic power station according to claim 1, wherein setting a routing inspection route of an unmanned aerial vehicle according to the boundary area comprises:
arranging a plurality of control points in the boundary area, and shooting above the control points by using an unmanned aerial vehicle to obtain control point images, wherein the control point images record geographic coordinates;
fitting the boundary region of the photovoltaic power station according to the control point image to obtain a fitting surface of the photovoltaic power station;
and determining the shooting gesture and the tour inspection route of the unmanned aerial vehicle according to the vector angle of the fitting surface and the shooting parameters of the camera.
3. The automatic acceptance method of a large base photovoltaic power plant of claim 1, wherein the first camera is a wide-angle camera, the second camera is an infrared camera, and the third camera is a tele camera.
4. The automatic acceptance method of a large-base photovoltaic power plant according to claim 1, wherein the defects include cracks, snails, damages, stains and vegetation shielding, and the preliminary judging of whether the photovoltaic panel has the defects according to the visible light image comprises:
the visible light image is obtained and gray scale processing is carried out on the visible light image;
processing the gray level image by adopting a canny edge detection algorithm to obtain a binarized image;
acquiring a local image on the binarized image by adopting a sliding window;
carrying out spatial clustering on the local images, determining the category with the most similar data, and obtaining an external matrix of the category;
and determining the defect position of the photovoltaic panel according to the set longest edge threshold value of the external matrix.
5. The automatic acceptance method of a large-base photovoltaic power station according to claim 1, wherein the infrared image is preprocessed, specifically: and carrying out gray scale processing on the infrared image, and then carrying out median filtering processing.
6. The automatic acceptance method of a large-base photovoltaic power station according to claim 1, wherein the oxford method is to calculate a segmentation threshold when the inter-class variance of a foreground image and a background image is maximum, and if the inter-class variance is g
g＝ω 0 (μ 0 -μ) 2 +ω 1 (μ 1 -μ) 2 ；
In the above, ω 0 ，ω 1 The pixel number of the foreground image and the pixel number of the background image are respectively the proportion of the pixel number of the whole image, mu 0 ，μ 1 The average gray scale of the foreground image and the background image are respectively, and mu is the average gray scale of the whole image.
7. The automatic acceptance method of a large-base photovoltaic power station according to claim 1, wherein the performing hot spot segmentation extraction on the foreground region image by adopting an adaptive dynamic threshold algorithm comprises:
selecting first local windows on the foreground region image, calculating the enhancement coefficient of each first local window, and taking the enhancement coefficient as a new pixel of a central pixel point of the first local window to obtain an enhanced foreground image;
selecting second local windows on the enhanced foreground image, calculating Gaussian weighted sum of pixels in each second local window, and subtracting a dynamic threshold value to obtain a segmentation threshold value of the pixel point;
and dividing the pixel points on the enhanced foreground image according to the dividing threshold value to obtain a hot spot area image.
8. The method of automatic acceptance of a large base photovoltaic power plant of claim 7, wherein the pixels on the enhanced foreground image are represented as F (i，j) When F (i，j) When the pixel is=1, the pixel is the pixel of the hot spot area image;
T(i，j)＝max(λ dev d(i，j)，C)；
in the above, G (i，j) Is the Gaussian weighted sum of pixel points, F (i，j) Is a dynamic threshold, lambda dev And C is an absolute dynamic threshold, and d (i, j) is the coordinates of the pixel point.
9. The method of automatic acceptance of a large base photovoltaic power plant of claim 1, wherein registering the visible light image and/or defect image with a photovoltaic power plant virtual simulation scene image comprises: and matching the feature point positions of the two images with corresponding descriptors by using a BF Matcher method, removing unqualified feature matching point pairs according to a random sampling coincidence algorithm ransac, and solving an affine transformation matrix by using residual matching feature point pairs so as to realize registration.
10. Automatic acceptance device of big base photovoltaic power plant, characterized by includes:
the route setting module is used for obtaining a boundary area of the photovoltaic power station and setting a routing inspection route of the unmanned aerial vehicle according to the boundary area;
the image shooting module shoots the photovoltaic panel to be detected by using the first camera and the second camera according to the inspection route, and obtains a visible light image and an infrared image of the photovoltaic panel;
the defect judging module is used for preliminarily judging whether the photovoltaic panel has defects according to the visible light image, and if so, shooting the defect positions of the photovoltaic panel by using a third camera to obtain a defect image;
the foreground segmentation module is used for preprocessing the infrared image, and then carrying out foreground segmentation extraction on the preprocessed image by the Ojin method to obtain a foreground region image;
the hot spot extraction module is used for carrying out hot spot segmentation extraction on the foreground region image by adopting a self-adaptive dynamic threshold algorithm to obtain a hot spot region image;
the defect determining module is used for matching the hot spot area image with the visible light image and the defect image according to the geographic coordinates to determine the defect type of the photovoltaic panel;
and the registration labeling module is used for registering the visible light image and/or the defect image with the virtual simulation scene image of the photovoltaic power station, labeling the defect type and generating an acceptance report.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310765961.0A CN116758425A (en) | 2023-06-26 | 2023-06-26 | Automatic acceptance checking method and device for large-base photovoltaic power station |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310765961.0A CN116758425A (en) | 2023-06-26 | 2023-06-26 | Automatic acceptance checking method and device for large-base photovoltaic power station |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116758425A true CN116758425A (en) | 2023-09-15 |
Family
ID=87947617
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310765961.0A Pending CN116758425A (en) | 2023-06-26 | 2023-06-26 | Automatic acceptance checking method and device for large-base photovoltaic power station |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116758425A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117252840A (en) * | 2023-09-26 | 2023-12-19 | 西安交通大学 | Photovoltaic array defect elimination evaluation method and device and computer equipment |
-
2023
- 2023-06-26 CN CN202310765961.0A patent/CN116758425A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117252840A (en) * | 2023-09-26 | 2023-12-19 | 西安交通大学 | Photovoltaic array defect elimination evaluation method and device and computer equipment |
| CN117252840B (en) * | 2023-09-26 | 2024-04-05 | 西安交通大学 | Photovoltaic array defect elimination evaluation method and device and computer equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107704844B (en) | Power transmission line icing thickness identification method based on binocular parallax images of unmanned aerial vehicle | |
| CN107543828B (en) | Workpiece surface defect detection method and system | |
| CN109615611B (en) | Inspection image-based insulator self-explosion defect detection method | |
| US20200175673A1 (en) | Method and device for detecting defect of meal box, server, and storage medium | |
| CN103543394A (en) | Discharge ultraviolet imaging quantization parameter extraction method of high-voltage electric equipment | |
| CN110610483B (en) | Crack image acquisition and detection method, computer equipment and readable storage medium | |
| CN115359239A (en) | Wind power blade defect detection and positioning method and device, storage medium and electronic equipment | |
| CN116758425A (en) | Automatic acceptance checking method and device for large-base photovoltaic power station | |
| CN111899219A (en) | Image identification method and system for power transmission line machine patrol | |
| CN115294031A (en) | Photovoltaic module fault image identification method based on infrared thermal imaging analysis | |
| CN111046950A (en) | Image processing method and device, storage medium and electronic device | |
| CN116665080B (en) | Unmanned aerial vehicle deteriorated insulator detection method and system based on target recognition | |
| CN111667470A (en) | Industrial pipeline flaw detection inner wall detection method based on digital image | |
| CN112288682A (en) | Electric power equipment defect positioning method based on image registration | |
| CN113487563B (en) | EL image-based self-adaptive detection method for hidden cracks of photovoltaic module | |
| CN115639248A (en) | System and method for detecting quality of building outer wall | |
| CN113705564B (en) | Pointer type instrument identification reading method | |
| CN114359251A (en) | Automatic identification method for concrete surface damage | |
| CN112541478A (en) | Insulator string stain detection method and system based on binocular camera | |
| CN111738264A (en) | Intelligent acquisition method for data of display panel of machine room equipment | |
| CN116342391A (en) | Infrared image side unfolding method and device for pillar porcelain insulator | |
| CN111242889A (en) | Hot spot identification method and device for photovoltaic module | |
| CN115619796A (en) | Method and device for obtaining photovoltaic module template and nonvolatile storage medium | |
| CN114821035A (en) | Distance parameter identification method for infrared temperature measurement equipment of power equipment | |
| CN111815560B (en) | Photovoltaic power station fault detection method and device, portable detection equipment and storage medium |
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 |