CN116883433B - Photovoltaic module surface temperature distribution real-time monitoring system - Google Patents
Photovoltaic module surface temperature distribution real-time monitoring system Download PDFInfo
- Publication number
- CN116883433B CN116883433B CN202311132166.4A CN202311132166A CN116883433B CN 116883433 B CN116883433 B CN 116883433B CN 202311132166 A CN202311132166 A CN 202311132166A CN 116883433 B CN116883433 B CN 116883433B
- Authority
- CN
- China
- Prior art keywords
- gray
- gray value
- image area
- image
- seed pixel
- 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
- 238000012544 monitoring process Methods 0.000 title claims abstract description 51
- 230000011218 segmentation Effects 0.000 claims abstract description 56
- 238000012545 processing Methods 0.000 claims abstract description 23
- 238000003709 image segmentation Methods 0.000 claims abstract description 15
- 238000004364 calculation method Methods 0.000 claims description 39
- 239000013598 vector Substances 0.000 claims description 25
- 238000012790 confirmation Methods 0.000 claims description 2
- 238000010586 diagram Methods 0.000 description 14
- 238000000034 method Methods 0.000 description 11
- 238000004422 calculation algorithm Methods 0.000 description 8
- 230000002829 reductive effect Effects 0.000 description 7
- 238000011524 similarity measure Methods 0.000 description 4
- 238000001931 thermography Methods 0.000 description 4
- 238000005286 illumination Methods 0.000 description 3
- 239000002184 metal Substances 0.000 description 3
- 238000005457 optimization Methods 0.000 description 3
- 238000010248 power generation Methods 0.000 description 3
- 238000013459 approach Methods 0.000 description 2
- 239000003086 colorant Substances 0.000 description 2
- 238000013461 design Methods 0.000 description 2
- 238000012423 maintenance Methods 0.000 description 2
- 230000002441 reversible effect Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000002860 competitive effect Effects 0.000 description 1
- 239000000306 component Substances 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 239000008358 core component Substances 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000001514 detection method Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005684 electric field Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000009499 grossing Methods 0.000 description 1
- 230000017525 heat dissipation Effects 0.000 description 1
- 238000003064 k means clustering Methods 0.000 description 1
- 230000000670 limiting effect Effects 0.000 description 1
- 230000000873 masking effect Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/0096—Radiation pyrometry, e.g. infrared or optical thermometry for measuring wires, electrical contacts or electronic systems
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J5/48—Thermography; Techniques using wholly visual means
- G01J5/485—Temperature profile
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01J—MEASUREMENT OF INTENSITY, VELOCITY, SPECTRAL CONTENT, POLARISATION, PHASE OR PULSE CHARACTERISTICS OF INFRARED, VISIBLE OR ULTRAVIOLET LIGHT; COLORIMETRY; RADIATION PYROMETRY
- G01J5/00—Radiation pyrometry, e.g. infrared or optical thermometry
- G01J2005/0077—Imaging
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10048—Infrared image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20076—Probabilistic image processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
-
- 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
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Geometry (AREA)
- Image Analysis (AREA)
Abstract
The application relates to the field of machine vision, in particular to a real-time monitoring system for surface temperature distribution of a photovoltaic module, which comprises the following components: the segmentation module is used for carrying out image segmentation processing on the photovoltaic module image to obtain an initial segmentation image; the determining module is used for determining the fastest growing direction and the slowest growing direction of the pixel points of the preset number of basic seeds; the calculating module is used for calculating a first gray level change rate and a second gray level change rate corresponding to the basic seed pixel points; the estimation module is used for calculating a first cut-off distance and a second cut-off distance of the basic seed pixel point in the fastest growth direction and the slowest growth direction; the confirming module is used for confirming the number of the newly added seed pixel points of the seed pixel points in the slowest growth direction; the monitoring module is used for carrying out region growth processing on the photovoltaic module image to obtain a final segmentation image so as to carry out temperature monitoring on the photovoltaic module, thereby improving the accuracy of the temperature monitoring and reducing the working cost of the temperature monitoring.
Description
Technical Field
The application relates to the field of machine vision, in particular to a real-time monitoring system for surface temperature distribution of a photovoltaic module.
Background
A photovoltaic module is a device that converts solar energy into electrical energy, also known as a solar panel or photovoltaic panel. The photovoltaic module is a core component of a photovoltaic power generation system, consists of a plurality of photovoltaic cells and is connected together in a serial or parallel mode. The working principle of the photovoltaic module is to convert sunlight into electric energy by utilizing the photovoltaic effect. When light is irradiated onto the photovoltaic cell, the energy of the photons is absorbed by the semiconductor material in the cell, exciting electrons. These excited electrons flow under the influence of an electric field, forming an electric current. By connecting multiple photovoltaic cells in series or parallel, the output of voltage and current can be increased, resulting in higher electrical energy output. The photovoltaic module is widely applied to the fields of solar power generation systems, photovoltaic power stations, household photovoltaic systems, mobile charging equipment and the like. With the continuous development of solar energy technology, the efficiency and performance of the photovoltaic module are also continuously improved, so that solar power generation is more and more competitive and feasible.
Temperature monitoring of photovoltaic modules is one of the important tasks in photovoltaic systems, and monitoring of photovoltaic module temperature can help to optimize operation and maintenance of the photovoltaic systems, such as taking heat dissipation measures in high temperature environments, adjusting the operating temperature range of the modules, and the like. Meanwhile, the temperature monitoring can also be used for early warning and fault detection, timely finding out abnormal conditions of the components and taking corresponding maintenance measures. The temperature monitoring system of the traditional photovoltaic module is characterized in that a high-precision thermal imaging infrared camera and a high-definition visual camera are assembled on an unmanned aerial vehicle, a photovoltaic module image is collected, conventional threshold segmentation is carried out on the image, the conventional threshold segmentation can only roughly segment the photovoltaic module image, and the temperature distribution area of the photovoltaic module image cannot be accurately segmented, namely, the temperature monitoring accuracy of the temperature monitoring system of the traditional photovoltaic module is lower.
Disclosure of Invention
In view of the above, it is necessary to provide a real-time monitoring system for surface temperature distribution of a photovoltaic module, which improves accuracy of temperature monitoring and further reduces working cost of temperature monitoring compared with a conventional real-time monitoring system for temperature distribution of a photovoltaic module.
The application provides a real-time monitoring system for surface temperature distribution of a photovoltaic module, which is applied to the field of temperature monitoring of the photovoltaic module, and comprises: the segmentation module is used for carrying out image segmentation processing on the photovoltaic module image to obtain an initial segmentation image, wherein the initial segmentation image comprises a preset number of image areas; the determining module is used for determining the fastest growing direction and the slowest growing direction of the preset number of basic seed pixel points based on the pixel point gray values of the preset number of image areas, wherein the preset number of basic seed pixel points are in one-to-one correspondence with the preset number of image areas; the calculation module is used for calculating a first gray level change rate and a second gray level change rate corresponding to the basic seed pixel points according to the pixel point gray level value difference value sequence corresponding to the fastest growth direction and the slowest growth direction in the corresponding image area of the basic seed pixel points; the estimation module is used for calculating a first cut-off distance and a second cut-off distance of the basic seed pixel point in the fastest growth direction and the slowest growth direction based on the position of the basic seed pixel point in the image area; the confirming module is used for confirming the number of newly added seed pixel points of the seed pixel points in the slowest growth direction through the first gray level change rate, the second gray level change rate, the first cut-off distance and the second cut-off distance corresponding to the basic seed pixel points; and the monitoring module is used for carrying out region growth processing on the photovoltaic module image based on the number of the basic seed pixel points and the newly added seed pixel points, and obtaining a final segmentation image so as to monitor the temperature of the photovoltaic module.
In one embodiment, the determining module is configured to determine, based on the pixel gray values of the preset number of image areas, a fastest growth direction and a slowest growth direction of a preset number of base seed pixels, where the preset number of base seed pixels corresponds to the preset number of image areas one to one, and specifically includes: the first sub-determining module is used for counting the gray values of the pixel points of the image areas with the preset number and confirming the gray value interval of the image areas; the second sub-determination module is used for obtaining an average gray value probability value corresponding to the image area through the ratio of the sum of gray value probability values of pixel points in the gray value interval of the image area to the interval length corresponding to the gray value interval; the third sub-determining module is used for determining a preset number of basic seed pixel points corresponding to the preset number of image areas one by one based on the pixel point gray value probability of the image areas and the corresponding average gray value probability value; a fourth sub-determining module, configured to calculate a gray value gradient vector corresponding to the base seed pixel according to gray values of the base seed pixel and other pixels in a preset neighborhood window; and a fifth sub-determining module, configured to determine a fastest growth direction and a slowest growth direction of a preset number of base seed pixel points respectively according to the gray value gradient vectors corresponding to the base seed pixel points.
In one embodiment, the second determining module is configured to obtain, by using a ratio of a sum of gray-value probability values of pixel points in a gray-value interval of an image area to an interval length corresponding to the gray-value interval, an average gray-value probability value corresponding to the image area, and specifically includes:
wherein,average gray value probability value corresponding to each image region,/->Is->Right end point of gray value interval corresponding to each image area, < >>Is->Left end point of gray value interval corresponding to each image area, < >>Is->The gray value interval corresponding to the image area is +.>Gray value probability values for individual pixels.
In one embodiment, the third sub-determining module is configured to determine, based on the pixel gray value probability of the image area and the corresponding average gray value probability value, a preset number of base seed pixels corresponding to the preset number of image areas one to one, and specifically includes: the confirming unit is used for calculating the difference value between the gray value probability of the pixel point of the image area and the corresponding average gray value probability value and confirming the gray value probability difference value corresponding to the pixel point of the image area; and the comparison unit is used for comparing the gray value probability differences corresponding to all the pixel points in the image area, and confirming the pixel point corresponding to the smallest gray value probability difference as the basic seed pixel point of the current image area.
In one embodiment, the comparing unit is configured to compare gray value probability differences corresponding to all pixels in the image area, and confirm the pixel corresponding to the smallest gray value probability difference as a base seed pixel of the current image area, and specifically includes:
wherein,is->Basic seed pixels of individual image areas, < >>Is->First->Gray value probability difference value corresponding to each pixel point,/>Is->First->Pixel point corresponding to the minimum gray value probability difference value corresponding to each pixel point,/->Is->The gray value interval corresponding to the image area is +.>Gray value probability value of individual pixels, < ->Is->Average gray value probability values corresponding to the individual image areas.
In one embodiment, the fourth sub-determining module is configured to calculate, according to gray values of the base seed pixel point and other pixels in a preset neighborhood window, a gray value gradient vector corresponding to the base seed pixel point, where the fourth sub-determining module specifically includes: the acquisition unit is used for respectively carrying out difference calculation on the gray values of the basic seed pixel points and the gray values of other pixel points in a preset neighborhood window to acquire gray value difference values corresponding to the other pixel points; and the calculating unit is used for summing and calculating the gray value difference values corresponding to the other pixel points and calculating the gray value gradient vector corresponding to the basic seed pixel point.
In one embodiment, the preset neighborhood window is 3*3, and the corresponding calculating unit is configured to sum and calculate gray value differences corresponding to the other pixel points, and calculate gray value gradient vectors corresponding to the base seed pixel point, and specifically includes:
wherein,is->Basic seed pixel of each image area +.>Corresponding gray value gradient vector, +.>Is->Basic seed pixel of each image area +.>Gray value of +.>Is->Basic seed pixel of each image area +.>Gray values of other corresponding pixels, < >>Calculation constant approaching 0, +.>For a first calculation coefficient having a value of 0 or 1,>for a second calculation factor of value 0 or 1.
In one embodiment, the calculating module is configured to calculate, according to a pixel gray value difference value corresponding to the base seed pixel in a fastest growth direction in a corresponding image area, a first gray change rate corresponding to the base seed pixel, and specifically includes: the first sub-calculation module is used for counting the gray value of the pixel point of the base seed pixel point in the fastest growth direction in the corresponding image area; the second sub-calculation module is used for calculating the difference value between the gray values of two adjacent pixels in the fastest growth direction, and the gray value difference value of the corresponding pixel in the fastest growth direction of the basic seed in the corresponding image area; and the third sub-calculation module is used for calculating the first gray change rate corresponding to the basic seed pixel point based on the gray value difference value of the pixel point corresponding to the basic seed pixel point in the fastest growth direction and the gray value interval of the image area corresponding to the basic seed pixel point.
In one embodiment, the third sub-calculating module is configured to calculate, based on the pixel gray value difference value corresponding to the base seed pixel and the gray value interval of the image area corresponding to the pixel gray value difference value, a first gray change rate corresponding to the base seed pixel, and specifically includes:
wherein,is->Basic seed pixel of each image area +.>A corresponding first gray scale rate of change, +.>And->Is the basic seed pixel point->In->Two adjacent pixels in the fastest growth direction in the individual image areas, +.>Is->Right end point of gray value interval corresponding to each image area, < >>Is->The left end point of the gray value interval corresponding to each image area.
In one embodiment, the determining module is configured to determine, by the first gray scale change rate, the second gray scale change rate, the first cut-off distance, and the second cut-off distance corresponding to the base seed pixel, a number of newly added seed pixels of the seed pixel in a slowest growth direction, and specifically includes:
wherein,is->Basic seed pixel of each image area +.>The number of newly added seed pixels in the slowest growth direction,/->Is->Basic seed pixel of each image area +. >A corresponding first gray scale rate of change, +.>Is->Basic seed pixel of each image area +.>A corresponding second gray level rate of change, < >>Is->Basic seed pixel of each image area +.>Corresponding first cut-off distance, < >>Is->Basic seed pixel of each image area +.>A corresponding second cut-off distance.
The system comprises a segmentation module, a segmentation module and a segmentation module, wherein the segmentation module is used for carrying out image segmentation processing on the photovoltaic module image to obtain an initial segmentation image, and the initial segmentation image comprises a preset number of image areas; the determining module is used for determining the fastest growing direction and the slowest growing direction of the preset number of basic seed pixel points based on the pixel point gray values of the preset number of image areas, wherein the preset number of basic seed pixel points are in one-to-one correspondence with the preset number of image areas; the calculation module is used for calculating a first gray level change rate and a second gray level change rate corresponding to the basic seed pixel point according to the gray level value difference value of the pixel point corresponding to the fastest growth direction and the slowest growth direction of the basic seed pixel point in the corresponding image area; the estimation module is used for calculating a first cut-off distance and a second cut-off distance of the basic seed pixel point in the fastest growth direction and the slowest growth direction based on the position of the basic seed pixel point in the image area; the confirming module is used for confirming the number of newly added seed pixel points of the seed pixel points in the slowest growth direction through the first gray level change rate, the second gray level change rate, the first cut-off distance and the second cut-off distance corresponding to the basic seed pixel points; and the monitoring module is used for carrying out region growth processing on the photovoltaic module image based on the number of the basic seed pixel points and the newly added seed pixel points, and obtaining a final segmentation image so as to monitor the temperature of the photovoltaic module. The photovoltaic module image is subjected to region growth processing through the basic seed pixel points and the newly-increased seed pixel points with newly-increased preset quantity, so that the photovoltaic module image can be accurately segmented, the accuracy of temperature monitoring is improved, and the working cost of the temperature monitoring is reduced.
Drawings
Fig. 1 is a schematic block diagram of a real-time monitoring system for surface temperature distribution of a photovoltaic module according to an embodiment of the present application.
Fig. 2 is a schematic diagram of a first sub-block diagram of a real-time monitoring system for surface temperature distribution of a photovoltaic module according to an embodiment of the present application.
Fig. 3 is a schematic diagram of a second sub-block diagram of a real-time monitoring system for surface temperature distribution of a photovoltaic module according to an embodiment of the present application.
Fig. 4 is a schematic diagram of a third sub-block diagram of a real-time monitoring system for surface temperature distribution of a photovoltaic module according to an embodiment of the present application.
Fig. 5 is a fourth sub-block schematic diagram of a real-time monitoring system for surface temperature distribution of a photovoltaic module according to an embodiment of the present application.
Fig. 6 is an exemplary schematic diagram of a photovoltaic module surface temperature distribution real-time monitoring system according to an embodiment of the present application.
Detailed Description
In describing embodiments of the present application, words such as "exemplary," "or," "such as," and the like are used to mean serving as an example, instance, or illustration. Any embodiment or design described herein as "exemplary" or "for example" should not be construed as preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary," "or," "such as," and the like are intended to present related concepts in a concrete fashion.
Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used in the description of the application herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. It is to be understood that, unless otherwise indicated, a "/" means or. For example, A/B may represent A or B. The "and/or" in the present application is merely one association relationship describing the association object, indicating that three relationships may exist. For example, a and/or B may represent: a exists alone, A and B exist simultaneously, and B exists alone. "at least one" means one or more. "plurality" means two or more than two. For example, at least one of a, b or c may represent: seven cases of a, b, c, a and b, a and c, b and c, a, b and c.
It should be further noted that the terms "first" and "second" in the description and claims of the present application and the accompanying drawings are used for respectively similar objects, and are not used for describing a specific order or sequence. The method disclosed in the embodiments of the present application or the method shown in the flowchart, including one or more steps for implementing the method, may be performed in an order that the steps may be interchanged with one another, and some steps may be deleted without departing from the scope of the claims.
The embodiment of the application firstly provides a real-time monitoring system for the surface temperature distribution of a photovoltaic module, which is applied to the field of temperature monitoring of the photovoltaic module, and referring to the attached figure 1, the system comprises:
the segmentation module 1 is used for carrying out image segmentation processing on the photovoltaic module image to obtain an initial segmentation image, wherein the initial segmentation image comprises a preset number of image areas.
The photovoltaic module image is a thermal imaging image acquired by matching a special thermal imager with the unmanned aerial vehicle. Typically, the thermal imaging image acquired by the photovoltaic module generally includes three areas, namely an orange-red area, a yellow area and a purple area, where different colors represent different illumination intensities. The orange-red region indicates a region with weaker light intensity, the yellow region indicates a portion with the strongest light intensity, and the purple region indicates a region with the weakest light intensity, indicating that the distribution of light in this region is small. However, in the thermal imaging image, the edges of the areas divided by different colors are blurred, and the areas with distributed illumination intensity cannot be accurately distinguished, so that the subsequent processing for outputting the photovoltaic module image for multiple times is required.
Specifically, the image segmentation processing of the photovoltaic module image may be that super-pixel segmentation is performed on the photovoltaic module image to obtain an initial segmented image including a preset number of image areas. It should be noted that, the super-pixel segmentation may further perform image segmentation according to the illumination intensity distribution of the photovoltaic module image, so as to obtain an initial segmented image of a preset number of image areas.
Further, the super-pixel segmentation is to segment the image into tight regions with similar features to reduce redundant information in the image and increase computational efficiency. The principle of super-pixel segmentation is as follows:
1. initializing: first, the image is divided into initial small regions, each of which is called a superpixel. This can be achieved by using a pixel grid based approach (e.g. a uniform grid) or a pixel similarity based approach (e.g. K-means clustering).
2. Similarity measure: for each superpixel, a similarity measure with surrounding superpixels is calculated. The similarity measure may be calculated based on features such as color, texture, gradient, etc. Common similarity measurement methods include euclidean distance, color histogram, gradient difference, and the like.
3. Merging similar superpixels: based on the similarity measure, similar superpixels are merged into larger superpixels. The merging process may be implemented using a minimum spanning tree algorithm in graph theory (e.g., prim algorithm or Kruskal algorithm). The merged superpixels have a larger area and have a higher similarity.
4. Optimizing: and for the merged superpixels, optimization operation can be performed to further improve the quality of the superpixels. Common optimization methods include iterative optimization, boundary smoothing, region growing, and the like.
5. And (3) generating a result: and finally, generating a final super-pixel segmentation result according to the merging and optimizing result. The superpixel segmentation result may be represented as a label or boundary map of the image.
The advantage of super-pixel segmentation is that redundant information in the image can be reduced, computational efficiency is improved, and local structures in the image can be better captured. The specific segmentation process is not further limited and described in detail, and the steps are performed in the prior art.
It should be noted that, referring to fig. 6, since the photovoltaic module includes a plurality of metal frames with grid shapes, in the photovoltaic module image, the plurality of metal frames with grid shapes may affect the subsequent calculation. Therefore, the processing of a plurality of grid-shaped metal frame areas in the photovoltaic module image is required, which may be specifically: and (3) carrying out template matching by using a photovoltaic panel grid, establishing masks for all edges, and splicing non-mask parts, so that the gray level image is presented as a gray level gradual change image without edge dividing lines, and masking the grid edges in the gray level image through the masks to make the image smooth.
The determining module 2 is configured to determine a fastest growing direction and a slowest growing direction of a preset number of base seed pixels based on the pixel gray values of the preset number of image areas, where the preset number of base seed pixels corresponds to the preset number of image areas one by one.
The basic seed pixel point refers to a pixel in an image area, and is used as a starting point of an image segmentation or area growth algorithm. The seed pixel points are typically selected as pixels having a particular attribute or characteristic, such as color, brightness, texture, or the like. In image segmentation, seed pixels are used to mark different regions or objects in an image for further processing or analysis. Seed pixels are also commonly used in region growing algorithms to classify pixels with similar features into the same region by growing neighboring pixels step by step starting from the seed pixel. The selection of seed pixels has an important impact on the outcome of the image segmentation or region growing algorithm, so that the selection of the appropriate seed pixels is required according to the specific application scenario and requirements. The growth direction of the seed pixel point depends on the judging condition of the similarity or the difference in the area growth algorithm, and in this embodiment, the fastest growth direction of the base seed pixel point depends on the gray value gradient direction, that is, the gray value gradient direction of the seed pixel, that is, the fastest growth direction of the base seed pixel point. This is because the image change is more obvious in the gray value gradient direction of the basic seed pixel points, and the difference condition is easier to satisfy in the growth process. The slowest growth direction of the basic seed pixel points refers to the direction perpendicular to the fastest growth direction of the basic seed pixel points, and the image change in the direction is least obvious, so that the growth speed is slowest.
It should be noted that, the basic seed pixel points are further calculated by the pixel point gray values of the preset number of image areas, and the basic seed pixel points are in one-to-one correspondence with the preset number of image areas, that is, each image area corresponds to one basic seed pixel point.
And the calculating module 3 is used for calculating a first gray level change rate and a second gray level change rate corresponding to the basic seed pixel point according to the gray level value difference value of the pixel point corresponding to the fastest growth direction and the slowest growth direction in the corresponding image area of the basic seed pixel point.
The first gray scale change rate corresponding to the basic seed pixel point corresponds to the fastest growth direction, and the second gray scale change rate corresponding to the basic seed pixel point corresponds to the slowest growth direction. The difference value of the gray value of the pixel point corresponding to the fastest growing direction and the slowest growing direction in the corresponding image area of the basic seed pixel point refers to the gray value difference value of the pixel point corresponding to the fastest growing direction and the slowest growing direction in the image area according to the position of the basic seed pixel point in the corresponding image area and the rough image area obtained by the super-pixel segmentation.
It should be noted that the gray value change rate may be measured by calculating the gray difference between adjacent pixels, and a common calculation method is to calculate the gray gradient of the surrounding area of the pixel using a difference operator, such as a Sobel operator or a Prewitt operator. The gray gradient represents the rate at which the gray value changes, and its size and direction can provide information about the edges in the image.
And the estimation module 4 is used for calculating a first cut-off distance and a second cut-off distance corresponding to the basic seed pixel point based on the fastest growth direction and the slowest growth direction of the basic seed pixel point in the corresponding image area.
The first cut-off distance corresponding to the basic seed pixel point corresponds to the fastest growth direction of the basic seed pixel point, the second cut-off distance corresponding to the basic seed pixel point corresponds to the slowest growth direction of the basic seed pixel point, and the cut-off distance refers to the growth cut-off distance of the basic seed pixel point in a corresponding image area. After the fastest growth direction and the slowest growth direction of the basic seed pixel point in the corresponding image area are obtained, the image area is obtained by super-pixel segmentation based on the position of the basic seed pixel point, so that a first cut-off distance corresponding to the basic seed pixel point can be further calculated Second cut-off distance->。
And the confirming module 5 is used for confirming the number of the newly added seed pixel points of the basic seed pixel point in the slowest growth direction through the first gray scale change rate, the second gray scale change rate, the first cut-off distance and the second cut-off distance corresponding to the basic seed pixel point.
The newly added seed pixel points are seed pixel points added in the slowest growth direction of the basic seed pixel points, and the purpose is that the growth rate of the basic seed pixel points in the fastest growth direction is equal to that in the slowest growth direction, so that the calculation time is reduced, and meanwhile, more accurate segmentation images can be further obtained. The number of the newly increased seed pixels is obtained according to a preset calculation algorithm through four calculation parameters, namely a first gray level change rate, a second gray level change rate, a first cut-off distance and a second cut-off distance, corresponding to the basic seed pixels.
And the monitoring module 6 is used for carrying out region growth processing on the photovoltaic module image based on the number of the basic seed pixel points and the newly added seed pixel points to obtain a final segmentation image so as to monitor the temperature of the photovoltaic module.
After obtaining the number of the newly-increased seed pixel points in the slowest growth direction of the basic seed pixel points, the newly-increased seed pixel points in the slowest growth direction of the basic seed pixel points are arranged at equal intervals, and then the region growth processing is carried out on the photovoltaic module image based on the basic seed pixel points and the newly-increased seed pixel points so as to obtain a final segmentation image. Based on the final segmentation image, the temperature of the photovoltaic module is monitored, and the accuracy of the temperature monitoring of the corresponding photovoltaic module is higher due to the higher accuracy of the final segmentation image, so that the working cost of the temperature monitoring of the photovoltaic module is reduced.
The system comprises a segmentation module, a segmentation module and a segmentation module, wherein the segmentation module is used for carrying out image segmentation processing on the photovoltaic module image to obtain an initial segmentation image, and the initial segmentation image comprises a preset number of image areas; the determining module is used for determining the fastest growing direction and the slowest growing direction of the preset number of basic seed pixel points based on the pixel point gray values of the preset number of image areas, wherein the preset number of basic seed pixel points are in one-to-one correspondence with the preset number of image areas; the calculation module is used for calculating a first gray level change rate and a second gray level change rate corresponding to the basic seed pixel point according to the gray level value difference value of the pixel point corresponding to the fastest growth direction and the slowest growth direction of the basic seed pixel point in the corresponding image area; the estimation module is used for calculating a first cut-off distance and a second cut-off distance of the basic seed pixel point in the fastest growth direction and the slowest growth direction based on the position of the basic seed pixel point in the image area; the confirming module is used for confirming the number of newly added seed pixel points of the seed pixel points in the slowest growth direction through the first gray level change rate, the second gray level change rate, the first cut-off distance and the second cut-off distance corresponding to the basic seed pixel points; and the monitoring module is used for carrying out region growth processing on the photovoltaic module image based on the number of the basic seed pixel points and the newly added seed pixel points, and obtaining a final segmentation image so as to monitor the temperature of the photovoltaic module. The photovoltaic module image is subjected to region growth processing through the basic seed pixel points and the newly-increased seed pixel points with newly-increased preset quantity, so that the photovoltaic module image can be accurately segmented, the accuracy of temperature monitoring is improved, and the working cost of the temperature monitoring is reduced.
In one embodiment of the present application, referring to fig. 2, the determining module 2 is configured to determine, based on the gray values of the pixels of the preset number of image areas, a fastest growing direction and a slowest growing direction of a preset number of base seed pixels, where the preset number of base seed pixels corresponds to the preset number of image areas one by one, and specifically includes:
the first sub-determining module 21 is configured to count gray values of pixels of the preset number of image areas, and confirm a gray value interval with the image areas.
The gray value interval of the image area refers to a gray value interval range in which the gray value of the pixel point of the image area is located, and one image area corresponds to one gray value interval. For example, the gray value interval corresponding to the first image region is (0, 84), the gray value interval corresponding to the second image region is (84, 168), and the gray value interval corresponding to the third image region is (168, 255).
The second sub-determining module 22 is configured to obtain an average gray value probability value corresponding to the image area according to a ratio of a sum of gray value probability values of pixel points in a gray value interval of the image area to a length of the interval corresponding to the gray value interval.
The gray value probability value of the pixel point in the gray value interval of the image area refers to the probability that the gray value of the pixel point appears in the gray value interval of the current image area, and can be obtained by the ratio of the number of times that the gray value of the pixel point appears to all the times of the gray value interval of the current image area where the pixel point is located. The sum of the gray value probability values of the pixels in the gray value interval of the image area refers to the sum of the gray value probability values corresponding to all the pixels in the gray value interval of the image area. The average gray value probability value corresponding to the image area refers to an average value of occurrence probabilities of gray values of each pixel in the image area in the whole image area. In a gray scale image, the gray scale value of each pixel is typically between 0 and 255, representing varying degrees of black to white. The average gray value probability value may be used to describe the overall brightness distribution of the image.
Specifically, the second determining module 22 is configured to obtain, by using a ratio of a sum of gray-level probability values of pixel points in a gray-level interval of an image area to an interval length corresponding to the gray-level interval, an average gray-level probability value corresponding to the image area, and specifically includes:
Wherein,is->Average gray value probability value corresponding to each image region,/->Is->Right end point of gray value interval corresponding to each image area, < >>Is->Left end point of gray value interval corresponding to each image area, < >>Is->The gray value interval corresponding to the image area is +.>Gray value probability values for individual pixels. It should be noted that, because the boundary of the segment after the super-pixel segmentation is blurred, the boundary point cannot be accurately distinguished, and the pixel point of the boundary may not be calculated in the calculation, so as to reduce the error.
The third sub-determining module 23 is configured to determine a preset number of base seed pixels corresponding to the preset number of image areas one-to-one based on the pixel gray value probability of the image areas and the corresponding average gray value probability value.
And when the basic seed pixel point corresponding to the second image area is calculated, the basic seed pixel point corresponding to the second image area is calculated only through the pixel point parameter corresponding to the second image area, and the two calculations are completely independent.
Specifically, referring to fig. 3, the third determining module 23 is configured to determine, based on the pixel gray value probability of the image area and the corresponding average gray value probability value, a preset number of base seed pixels corresponding to the preset number of image areas one to one, and specifically includes:
a confirming unit 231, configured to calculate a difference between the gray value probability of the pixel point of the image area and the corresponding average gray value probability value, and confirm the gray value probability difference corresponding to the pixel point of the image area;
the comparing unit 232 is configured to compare gray value probability differences corresponding to all pixels in the image area, and confirm the pixel corresponding to the smallest gray value probability difference as the base seed pixel of the current image area.
Specifically, the comparing unit 232 is configured to compare gray value probability differences corresponding to all pixels in the image area, and confirm the pixel corresponding to the smallest gray value probability difference as the base seed pixel of the current image area, and specifically includes:
wherein,is->Basic seed pixels of individual image areas, < >>Is->First->Gray value probability difference value corresponding to each pixel point,/>Is- >First->Pixel point corresponding to the minimum gray value probability difference value corresponding to each pixel point,/->Is->The gray value interval corresponding to the image area is +.>Gray value probability value of individual pixels, < ->Is->Average gray value probability values corresponding to the individual image areas.
It should be noted that, the minimum value of the gray value probability difference corresponding to the pixel point of the image area is used as the basic seed pixel point of the current image area, that is, the pixel point corresponding to the gray value with the largest occurrence frequency in the image area is used as the basic seed pixel point of the current image area, so as to reduce the error of the area growth of the subsequent image area and further improve the accuracy of the subsequent image segmentation.
And the fourth sub-determining module 24 is configured to calculate a gray value gradient vector corresponding to the base seed pixel according to the gray values of the base seed pixel and other pixels in the preset neighborhood window.
The preset neighborhood window is a window which takes a basic seed pixel point as a center and selects pixels in a certain range around the basic seed pixel point as a processing window. The neighborhood window may be square, rectangular, circular or other shape, and the size of the window may be selected according to specific needs. A square 3*3 neighborhood window is preferred in this embodiment. The gray value gradient vector corresponding to the basic seed pixel point refers to a vector of the gray value change rate and the gray value change direction of the basic seed pixel point, and is used for describing the gray change condition of the basic seed pixel point in an image. The positive and negative of the gray value gradient vector represent the direction of curvature change of the surrounding area of the basic seed pixel point in the image, and the magnitude of the gray value gradient vector represents the gray value change rate in the direction.
Specifically, referring to fig. 4, the fourth determining sub-module 24 is configured to calculate, according to gray values of the base seed pixel point and other pixels in a preset neighborhood window, a gray value gradient vector corresponding to the base seed pixel point, where the method specifically includes:
and the obtaining unit 241 is configured to perform difference calculation on the gray values of the base seed pixel point and gray values of other pixel points in a preset neighborhood window, so as to obtain gray value difference values corresponding to the other pixel points.
And respectively carrying out difference calculation on the gray values of other pixels in a preset neighborhood window corresponding to the basic seed pixel point and the gray values of the basic seed pixel point to obtain a preset number of gray value difference values, wherein each other pixel point corresponds to one gray value difference value. The positive and negative of the gray value difference value represent the direction of the current other pixels relative to the basic seed pixel point, and the magnitude of the gray value difference value represents the gray value change rate of the current other pixels relative to the basic seed pixel point.
And a calculating unit 242, configured to sum and calculate the gray value differences corresponding to the other pixel points, and calculate the gray value gradient vector corresponding to the base seed pixel point.
Specifically, when the parsing is performed with the preset neighborhood window 3*3, the corresponding calculating unit 242 is configured to sum and calculate the gray value differences corresponding to the other pixels, and calculate the gray value gradient vector corresponding to the base seed pixel, and specifically includes:
wherein,is->Basic seed pixel of each image area +.>Corresponding gray value gradient vector, +.>Is->Basic seed pixel of each image area +.>Gray value of +.>Is->Basic seed pixel of each image area +.>Gray values of other corresponding pixels, < >>Calculation constant approaching 0, +.>For a first calculation coefficient having a value of 0 or 1,>for a second calculation factor of value 0 or 1.
And a fifth sub-determining module 25, configured to determine a fastest growing direction and a slowest growing direction of a preset number of base seed pixel points respectively according to the gray value gradient vectors corresponding to the base seed pixel points.
The gray value gradient vector corresponding to the basic seed pixel point is a result obtained by deriving the gray value of the basic seed pixel point and the gray values of other pixel points in a preset field window, and the positive value and the negative value of the gray value gradient vector represent the overall growth direction, namely the fastest growth direction of the basic seed pixel point. And the vertical direction of the fastest growth direction of the basic seed pixel point is the slowest growth direction of the basic seed pixel point.
In the embodiment of the application, the fastest growth direction and the slowest growth direction of the subsequent region growth are confirmed through the gray value gradient vector of the basic seed pixel point, so that the subsequent further control of the growth speed and the precision of the region can be facilitated, and the accuracy of the subsequent image segmentation is improved.
In an embodiment of the present application, referring to fig. 5, a calculation process of a first gray scale change rate and a second gray scale change rate corresponding to the base seed pixel point is the same as logic, and the case is described by taking calculating the first gray scale change rate as an example, and the corresponding calculation module 3 is configured to calculate, according to a pixel point gray scale value difference sequence corresponding to the base seed pixel point in a fastest growth direction in a corresponding image area, the first gray scale change rate corresponding to the base seed pixel point, specifically including:
the first sub-calculation module 31 is configured to count the gray value of the pixel point in the fastest growth direction of the base seed pixel point in the corresponding image area.
And obtaining the gray value of the pixel point corresponding to the pixel point of the base seed pixel point in the fastest growth direction in the corresponding image area based on the position of the base seed pixel point in the corresponding image area and the edge of the current image area.
And the second sub-calculation module 32 is configured to calculate a difference value between two adjacent pixel gray values in the fastest growth direction, and calculate a corresponding pixel gray value difference sequence in the fastest growth direction of the base seed in the corresponding image area.
And after obtaining the pixel gray value of the basic seed pixel in the fastest growth direction in the corresponding image area, performing difference calculation on two adjacent pixel gray values to obtain a plurality of pixel gray value differences, and constructing a pixel gray value difference sequence corresponding to the basic seed in the fastest growth direction in the corresponding image area based on the plurality of pixel gray value differences.
The third sub-calculating module 33 is configured to calculate a first gray scale change rate corresponding to the base seed pixel based on a gray scale value difference value of the pixel corresponding to the base seed pixel in the fastest growth direction and a gray scale value interval of the image area corresponding to the pixel.
Specifically, the third sub-calculating module 33 is configured to calculate, based on the difference value between the gray values of the pixels corresponding to the base seed pixels and the gray value interval of the image area corresponding to the difference value, a first gray change rate corresponding to the base seed pixels, and specifically includes:
Wherein,is->Basic seed pixel of each image area +.>A corresponding first gray scale rate of change, +.>And->Is the basic seed pixel point->In->Two adjacent pixels in the fastest growth direction in the individual image areas, +.>Is->Right end point of gray value interval corresponding to each image area, < >>Is->The left end point of the gray value interval corresponding to each image area.
It should be noted that, since the calculation process of the first gray scale change rate and the second gray scale change rate corresponding to the basic seed pixel point is the same as the logic, the first gray scale change rate and the second gray scale change rate can be correspondingly calculated according to the same logicBasic seed pixel of each image area +.>Corresponding second gray level change rate +.>。
In one embodiment of the present application, the confirmation module 5 is configured to confirm, by the first gray scale change rate, the second gray scale change rate, the first cut-off distance, and the second cut-off distance corresponding to the base seed pixel, the number of newly added seed pixels of the base seed pixel in the slowest growth direction, and specifically includes:
wherein,is->Basic seed pixel of each image area +.>The number of newly added seed pixels in the slowest growth direction,/->Is->Basic seed pixel of each image area +. >A corresponding first gray scale rate of change, +.>Is->Basic seed pixel of each image area +.>A corresponding second gray level rate of change, < >>Is->Basic seed pixel of each image area +.>Corresponding first cut-off distance, < >>Is->Basic seed pixel of each image area +.>A corresponding second cut-off distance.
In addition, after calculating the firstBasic seed pixel of each image area +.>Corresponding first gray scale rate of change->Second gray level change rate->First cut-off distance->Second cut-off distance->Then, inputting the fourth calculation parameter into the preset calculation formula to calculate the +.>Basic seed pixel of each image area +.>Number of newly added seed pixels in slowest growth direction +.>。
In an ideal state (i.e., when the above-described superpixel segmentation is sufficiently accurate), the base seed pixel point is in the slowest growth directionWhen the number of the newly-increased seed pixel points is equal to the ratio of the second cut-off distance to the first cut-off distance, the corresponding slowest growth direction is the same as the area growth speed in the fastest growth direction, and the whole operation efficiency can be saved to the greatest extent. However, since the super-pixel segmentation is roughly performed, the accuracy is somewhat erroneous, and thus And->The Euler norm of (2) is used as the number of newly added sub-pixel points, so that errors caused by super-pixel segmentation can be reduced to the greatest extent, and the accuracy of subsequent image segmentation is further improved.
The system comprises a segmentation module, a segmentation module and a segmentation module, wherein the segmentation module is used for carrying out image segmentation processing on the photovoltaic module image to obtain an initial segmentation image, and the initial segmentation image comprises a preset number of image areas; the determining module is used for determining the fastest growing direction and the slowest growing direction of the preset number of basic seed pixel points based on the pixel point gray values of the preset number of image areas, wherein the preset number of basic seed pixel points are in one-to-one correspondence with the preset number of image areas; the calculation module is used for calculating a first gray level change rate and a second gray level change rate corresponding to the basic seed pixel point according to the gray level value difference value of the pixel point corresponding to the fastest growth direction and the slowest growth direction of the basic seed pixel point in the corresponding image area; the estimation module is used for calculating a first cut-off distance and a second cut-off distance of the basic seed pixel point in the fastest growth direction and the slowest growth direction based on the position of the basic seed pixel point in the image area; the confirming module is used for confirming the number of newly added seed pixel points of the seed pixel points in the slowest growth direction through the first gray level change rate, the second gray level change rate, the first cut-off distance and the second cut-off distance corresponding to the basic seed pixel points; and the monitoring module is used for carrying out region growth processing on the photovoltaic module image based on the number of the basic seed pixel points and the newly added seed pixel points, and obtaining a final segmentation image so as to monitor the temperature of the photovoltaic module. The photovoltaic module image is subjected to region growth processing through the basic seed pixel points and the newly-increased seed pixel points with newly-increased preset quantity, so that the photovoltaic module image can be accurately segmented, the accuracy of temperature monitoring is improved, and the working cost of the temperature monitoring is reduced.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. In the description corresponding to the flowcharts and block diagrams in the figures, operations or steps corresponding to different blocks may also occur in different orders than that disclosed in the description, and sometimes no specific order exists between different operations or steps. For example, two consecutive operations or steps may actually be performed substantially in parallel, they may sometimes be performed in reverse order, which may be dependent on the functions involved. Each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
It will be evident to those skilled in the art that the application is not limited to the details of the foregoing illustrative embodiments, and that the present application may be embodied in other specific forms without departing from the spirit or essential characteristics thereof. The above-described embodiments of the application are, therefore, to be considered in all respects as illustrative and not restrictive, the scope of the application being indicated by the appended claims rather than by the foregoing description, and all changes which come within the meaning and range of equivalency of the claims are therefore intended to be embraced therein.
Claims (10)
1. The utility model provides a photovoltaic module surface temperature distribution real-time monitoring system, is applied to photovoltaic module temperature monitoring field, its characterized in that, the system includes:
the segmentation module is used for carrying out image segmentation processing on the photovoltaic module image to obtain an initial segmentation image, wherein the initial segmentation image comprises a preset number of image areas;
the determining module is used for determining the fastest growing direction and the slowest growing direction of the preset number of basic seed pixel points based on the pixel point gray values of the preset number of image areas, wherein the preset number of basic seed pixel points are in one-to-one correspondence with the preset number of image areas; the fastest growth direction is the gradient direction of the corresponding seed pixel point, and the slowest growth direction is the vertical direction of the fastest growth direction;
The calculation module is used for calculating a first gray level change rate and a second gray level change rate corresponding to the basic seed pixel points according to the pixel point gray level value difference value sequence corresponding to the fastest growth direction and the slowest growth direction in the corresponding image area of the basic seed pixel points;
the estimation module is used for calculating a first cut-off distance and a second cut-off distance corresponding to the basic seed pixel point based on the fastest growth direction and the slowest growth direction of the basic seed pixel point in the corresponding image area; the first cut-off distance is the growth cut-off distance of the seed pixel point in the fastest growth direction of the image area, and the second cut-off distance is the growth cut-off distance of the seed pixel point in the slowest growth direction of the image area;
the confirming module is used for confirming the number of newly-added seed pixel points of the basic seed pixel point in the slowest growth direction through the first gray level change rate, the second gray level change rate, the first cut-off distance and the second cut-off distance corresponding to the basic seed pixel point;
and the monitoring module is used for carrying out region growth processing on the photovoltaic module image based on the number of the basic seed pixel points and the newly added seed pixel points, and obtaining a final segmentation image so as to monitor the temperature of the photovoltaic module.
2. The system for monitoring the surface temperature distribution of the photovoltaic module according to claim 1, wherein the determining module is configured to determine a fastest growth direction and a slowest growth direction of a preset number of base seed pixels based on the pixel gray values of the preset number of image areas, where the preset number of base seed pixels corresponds to the preset number of image areas one by one, and specifically includes:
the first sub-determining module is used for counting the gray values of the pixel points of the image areas with the preset number and confirming the gray value interval of the image areas;
the second sub-determination module is used for obtaining an average gray value probability value corresponding to the image area through the ratio of the sum of gray value probability values of pixel points in the gray value interval of the image area to the interval length corresponding to the gray value interval;
the third sub-determining module is used for determining a preset number of basic seed pixel points corresponding to the preset number of image areas one by one based on the pixel point gray value probability of the image areas and the corresponding average gray value probability value;
a fourth sub-determining module, configured to calculate a gray value gradient vector corresponding to the base seed pixel according to gray values of the base seed pixel and other pixels in a preset neighborhood window;
And a fifth sub-determining module, configured to determine a fastest growth direction and a slowest growth direction of a preset number of base seed pixel points respectively according to the gray value gradient vectors corresponding to the base seed pixel points.
3. The system for monitoring the surface temperature distribution of the photovoltaic module in real time according to claim 2, wherein the second sub-determining module is configured to obtain the average gray value probability value corresponding to the image area by using a ratio of a sum of gray value probability values of pixel points in the gray value interval of the image area to an interval length corresponding to the gray value interval, and specifically includes:
wherein,is->Average gray value probability value corresponding to each image region,/->Is->Right end point of gray value interval corresponding to each image area, < >>Is->Left end point of gray value interval corresponding to each image area, < >>Is->The gray value interval corresponding to the image area is +.>Gray value probability values for individual pixels.
4. The system for monitoring the surface temperature distribution of the photovoltaic module in real time according to claim 3, wherein the third sub-determining module is configured to determine a preset number of basic seed pixels corresponding to the preset number of image areas one by one based on the pixel gray value probability of the image areas and the corresponding average gray value probability value, and specifically includes:
The confirming unit is used for calculating the difference value between the gray value probability of the pixel point of the image area and the corresponding average gray value probability value and confirming the gray value probability difference value corresponding to the pixel point of the image area;
and the comparison unit is used for comparing the gray value probability differences corresponding to all the pixel points in the image area, and confirming the pixel point corresponding to the smallest gray value probability difference as the basic seed pixel point of the current image area.
5. The system for monitoring the surface temperature distribution of the photovoltaic module in real time according to claim 4, wherein the comparing unit is configured to compare gray value probability differences corresponding to all pixels in the image area, and confirm the pixel corresponding to the smallest gray value probability difference as the basic seed pixel of the current image area, and specifically includes:
wherein,is->Basic seed pixels of individual image areas, < >>Is->First->Gray value probability difference value corresponding to each pixel point,/>Is->First->Pixel point corresponding to the minimum gray value probability difference value corresponding to each pixel point,/->Is->The gray value interval corresponding to the image area is +.>Gray value probability value of individual pixels, < - >Is->Average gray value probability values corresponding to the individual image areas.
6. The system for monitoring the surface temperature distribution of a photovoltaic module in real time according to claim 5, wherein the fourth sub-determining module is configured to calculate a gray value gradient vector corresponding to the base seed pixel according to gray values of the base seed pixel and other pixels in a preset neighborhood window of the base seed pixel, and specifically includes:
the acquisition unit is used for respectively carrying out difference calculation on the gray values of the basic seed pixel points and the gray values of other pixel points in a preset neighborhood window to acquire gray value difference values corresponding to the other pixel points;
and the calculating unit is used for summing and calculating the gray value difference values corresponding to the other pixel points and calculating the gray value gradient vector corresponding to the basic seed pixel point.
7. The system for monitoring the surface temperature distribution of the photovoltaic module in real time according to claim 6, wherein the preset neighborhood window is 3*3, and the calculating unit is configured to sum and calculate gray value differences corresponding to the other pixel points, and calculate gray value gradient vectors corresponding to the base seed pixel points, and specifically includes:
wherein, Is->Basic seed pixel of each image area +.>Corresponding gray value gradient vector, +.>Is->Basic seed pixel of each image area +.>Gray value of +.>Is->Basic seed pixel of each image area +.>Gray values of other corresponding pixels, < >>Calculation constant approaching 0, +.>For a first calculation coefficient having a value of 0 or 1,>for a second calculation factor of value 0 or 1.
8. The system according to claim 7, wherein the calculating module is configured to calculate a first gray scale change rate corresponding to the base seed pixel according to a gray scale value difference sequence of the pixel corresponding to the base seed pixel in a fastest growth direction in the corresponding image area, and specifically includes:
the first sub-calculation module is used for counting the gray value of the pixel point of the base seed pixel point in the fastest growth direction in the corresponding image area;
the second sub-calculation module is used for calculating a pixel gray value difference sequence corresponding to the base seed in the fastest growth direction in the corresponding image area according to the difference value between two adjacent pixel gray values in the fastest growth direction;
And the third sub-calculation module is used for calculating the first gray change rate corresponding to the basic seed pixel point based on the gray value difference value of the pixel point corresponding to the basic seed pixel point in the fastest growth direction and the gray value interval of the image area corresponding to the basic seed pixel point.
9. The system for monitoring the surface temperature distribution of the photovoltaic module in real time according to claim 8, wherein the third sub-calculation module is configured to calculate the first gray scale change rate corresponding to the base seed pixel based on the gray scale value difference value of the pixel corresponding to the base seed pixel and the gray scale value interval of the image area corresponding to the difference value, and specifically includes:
wherein,is->Basic seed pixel of each image area +.>A corresponding first gray scale rate of change, +.>And->Is the basic seed pixel point->In->Two adjacent pixels in the fastest growth direction in the individual image areas, +.>Is->Gray value interval right corresponding to each image regionEndpoint (S)>Is->The left end point of the gray value interval corresponding to each image area.
10. The system according to claim 9, wherein the confirmation module is configured to confirm the number of newly added seed pixels of the base seed pixels in the slowest growth direction by using the first gray scale change rate, the second gray scale change rate, the first cut-off distance and the second cut-off distance corresponding to the base seed pixels, and specifically includes:
Wherein,is->Basic seed pixel of each image area +.>The number of newly added seed pixels in the slowest growth direction,/->Is->Basic seed pixel of each image area +.>A corresponding first gray scale rate of change, +.>Is->Basic seed pixel of each image area +.>A corresponding second gray level rate of change, < >>Is->Basic seed pixel of each image area +.>Corresponding first cut-off distance, < >>Is->Basic seed pixel of each image area +.>A corresponding second cut-off distance.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311132166.4A CN116883433B (en) | 2023-09-05 | 2023-09-05 | Photovoltaic module surface temperature distribution real-time monitoring system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311132166.4A CN116883433B (en) | 2023-09-05 | 2023-09-05 | Photovoltaic module surface temperature distribution real-time monitoring system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116883433A CN116883433A (en) | 2023-10-13 |
| CN116883433B true CN116883433B (en) | 2023-12-01 |
Family
ID=88271812
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311132166.4A Active CN116883433B (en) | 2023-09-05 | 2023-09-05 | Photovoltaic module surface temperature distribution real-time monitoring system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116883433B (en) |
Families Citing this family (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117629422B (en) * | 2024-01-25 | 2024-05-10 | 徐州日托新能源科技有限公司 | Temperature measurement method and system for photovoltaic module |
| CN118565634B (en) * | 2024-07-31 | 2024-10-11 | 瑞安市瑞鑫电器有限公司 | Online monitoring method and system for temperature of generator carbon brush holder |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004044683A2 (en) * | 2002-11-06 | 2004-05-27 | Simmonds Precision Products, Inc. | Method for detection and recognition of fog presence within an aircraft compartment using video images |
| CN112215818A (en) * | 2020-10-13 | 2021-01-12 | 周婷婷 | Delamination detection method and system for photovoltaic cell panel and control equipment |
| CN112446863A (en) * | 2020-11-24 | 2021-03-05 | 黄静 | Photovoltaic array hot spot detection method and detection system based on image processing |
| CN115409833A (en) * | 2022-10-28 | 2022-11-29 | 一道新能源科技(衢州)有限公司 | Hot spot defect detection method of photovoltaic panel based on unsharp mask algorithm |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220077820A1 (en) * | 2020-09-04 | 2022-03-10 | Mgit | Method and system for soar photovoltaic power station monitoring |
-
2023
- 2023-09-05 CN CN202311132166.4A patent/CN116883433B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2004044683A2 (en) * | 2002-11-06 | 2004-05-27 | Simmonds Precision Products, Inc. | Method for detection and recognition of fog presence within an aircraft compartment using video images |
| CN112215818A (en) * | 2020-10-13 | 2021-01-12 | 周婷婷 | Delamination detection method and system for photovoltaic cell panel and control equipment |
| CN112446863A (en) * | 2020-11-24 | 2021-03-05 | 黄静 | Photovoltaic array hot spot detection method and detection system based on image processing |
| CN115409833A (en) * | 2022-10-28 | 2022-11-29 | 一道新能源科技(衢州)有限公司 | Hot spot defect detection method of photovoltaic panel based on unsharp mask algorithm |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116883433A (en) | 2023-10-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116883433B (en) | Photovoltaic module surface temperature distribution real-time monitoring system | |
| CN109416413B (en) | Solar energy forecast | |
| Di Tommaso et al. | A multi-stage model based on YOLOv3 for defect detection in PV panels based on IR and visible imaging by unmanned aerial vehicle | |
| CN110266268B (en) | Photovoltaic module fault detection method based on image fusion recognition | |
| CN102252623B (en) | Measurement method for lead/ground wire icing thickness of transmission line based on video variation analysis | |
| CN106290388A (en) | A kind of insulator breakdown automatic testing method | |
| CN115115634B (en) | Photovoltaic array hot spot detection method based on infrared image | |
| Mao et al. | Development of power transmission line defects diagnosis system for UAV inspection based on binocular depth imaging technology | |
| CN105262441B (en) | Infrared image-based photovoltaic array fault grading method | |
| Prabhakaran et al. | Deep Learning-Based Model for Defect Detection and Localization on Photovoltaic Panels. | |
| CN112053322B (en) | Method for segmenting and detecting surface shielding of photovoltaic cell panel | |
| CN115202404B (en) | Maintenance and inspection method for photovoltaic power generation set based on unmanned aerial vehicle | |
| Zhang et al. | Cloud motion tracking system using low-cost sky imager for PV power ramp-rate control | |
| CN114743115A (en) | Shelter recognition method and fault early warning system for photovoltaic electronic equipment | |
| CN113609901A (en) | Power transmission and transformation equipment fault monitoring method and system | |
| Magnone et al. | Cloud motion identification algorithms based on all-sky images to support solar irradiance forecast | |
| Guerriero et al. | Automatic edge identification for accurate analysis of thermographic images of solar panels | |
| CN114792328A (en) | Infrared thermal imaging image processing and analyzing method | |
| CN115423810B (en) | Blade icing form analysis method for wind generating set | |
| Li et al. | Insulator infrared image segmentation algorithm based on dynamic mask and box annotation | |
| Hwang et al. | Soiling detection for photovoltaic modules based on an intelligent method with image processing | |
| CN107194313A (en) | A kind of parallel intelligent object-oriented classification method | |
| CN115330787B (en) | Photovoltaic module icing area detection method based on image recognition | |
| Zhang et al. | Defect Detection and Classification of Photovoltaic Modules Based on Image Fusion Analysis | |
| Arosh et al. | Composite imagery-based non-uniform illumination sensing for system health monitoring of solar power plants |
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 |