CN112116600A - Photovoltaic panel counting method based on image processing - Google Patents
Photovoltaic panel counting method based on image processing Download PDFInfo
- Publication number
- CN112116600A CN112116600A CN202010825092.2A CN202010825092A CN112116600A CN 112116600 A CN112116600 A CN 112116600A CN 202010825092 A CN202010825092 A CN 202010825092A CN 112116600 A CN112116600 A CN 112116600A
- Authority
- CN
- China
- Prior art keywords
- image
- photovoltaic panel
- photovoltaic
- counting method
- color
- 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 36
- 238000012545 processing Methods 0.000 title claims abstract description 16
- 238000000605 extraction Methods 0.000 claims abstract description 18
- 238000010276 construction Methods 0.000 claims abstract description 8
- 238000004458 analytical method Methods 0.000 claims abstract description 7
- 238000001914 filtration Methods 0.000 claims abstract description 6
- 238000012216 screening Methods 0.000 claims abstract description 3
- 238000001514 detection method Methods 0.000 claims description 5
- 238000003708 edge detection Methods 0.000 claims description 4
- 230000010339 dilation Effects 0.000 claims description 2
- 230000003628 erosive effect Effects 0.000 claims description 2
- 239000000284 extract Substances 0.000 claims description 2
- 238000004364 calculation method Methods 0.000 claims 1
- 230000011218 segmentation Effects 0.000 claims 1
- 238000005260 corrosion Methods 0.000 abstract description 3
- 230000007797 corrosion Effects 0.000 abstract description 3
- 238000011161 development Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000005530 etching Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000000638 solvent extraction Methods 0.000 description 1
Images
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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration by the use of local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/13—Edge detection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/90—Determination of colour characteristics
-
- 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
- G06T2207/10024—Color 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30242—Counting objects in image
Abstract
The invention provides a photovoltaic panel counting method, and particularly relates to a photovoltaic panel counting method based on image processing. The method comprises the following steps: acquiring a picture of a photovoltaic engineering construction site and loading the picture into an image processing system; segmenting a photovoltaic panel area in a picture and extracting effective edge information by methods of color analysis extraction, filtering operation, edge extraction, corrosion expansion, position-based operation and the like; and extracting the outline of each photovoltaic panel, and obtaining the number of the photovoltaic panels in the image by carrying out secondary screening on the outlines. The method is suitable for counting the number of photovoltaic panels in photovoltaic laying field images, and improves the management efficiency of engineering projects.
Description
Technical Field
The invention relates to the field of image processing, in particular to a photovoltaic panel counting method based on image processing.
Background
With the increasing scarcity of fossil energy, the development and utilization of renewable energy sources are receiving wide attention from people. Solar energy is the most abundant and clean energy form, and with the strong support of relevant national policies, the development of the photovoltaic industry in China is vigorous. Photovoltaic engineering generally has the characteristics that the construction scale reaches greatly, construction cycle is short, and the management degree of difficulty of engineering project is great. In the link of installing and laying the photovoltaic modules, construction managers usually reflect the project progress of a current project by counting the number of photovoltaic panels which are already laid, and the currently adopted method is mainly based on artificial vision and realized by carrying out on-site inspection statistics or manually counting after an unmanned aerial vehicle shoots a project on-site picture. However, the construction range of the photovoltaic power station can reach hundreds or even thousands of hectares, the number of photovoltaic panels is large in number, the manual statistics mode wastes time and labor, and the requirement of project management intelligent development cannot be met.
Disclosure of Invention
In order to solve the problems, the invention provides a photovoltaic panel counting method based on image processing, which can automatically identify photovoltaic panel objects in a photovoltaic panel laying field image and count the number of the photovoltaic panel objects, and improve the management efficiency of engineering projects.
In order to achieve the purpose, the invention adopts the following technical scheme:
step S1: collecting photovoltaic engineering construction site images as a data source of the method;
step S2: preliminarily segmenting a photovoltaic panel area in the image through color analysis;
step S3, obtaining the edge information of the image through an edge extraction algorithm;
step S4: and (4) carrying out contour searching operation on the image obtained in the step (S3), screening out the contours belonging to the photovoltaic panels according to conditions such as polygon approximation, contour area and the like, and counting the number of the contours to obtain the number of the photovoltaic panels in the image.
Optionally, in the step S1, the determination of the detection range is suitable for the case where the target area occupies a small area in the picture and requires statistical local data or background interference is large, and this step is not necessary.
Optionally, in the step S2, the image color analysis extracts all the pixel points in the image that need to be traversed, and converts them into HSV color space. And extracting a color area where the photovoltaic panel is located through threshold setting, wherein the color threshold is automatically obtained by analyzing a color histogram of the image.
Optionally, in step S3, the edge extraction may adopt a Canny operator edge detection method or a Sobel operator edge detection method, which has the advantages of simple algorithm and high detection accuracy.
Alternatively, in the steps S2 and S3, it is recommended to perform image binarization processing on the image by using the maximum inter-class variance method (Ostu method) to find the threshold T. Meanwhile, the gray scale value of the pixel with the gray scale value larger than the threshold value T is adjusted to be 255, and the gray scale value of the pixel with the gray scale value smaller than the threshold value T is adjusted to be 0.
Optionally, the images extracted in steps S2 and S3 are subjected to erosion, expansion, filtering, and the like to eliminate noise, obtain a complete photovoltaic panel region and clear edge information, and obtain a clear edge image of the photovoltaic panel region by bitwise and operation.
The invention has the following beneficial effects:
according to the method, the photovoltaic panel area in the image is extracted in a mode of combining edge extraction and color extraction, the number of the photovoltaic panels is obtained through contour extraction, the number of the photovoltaic panels in the image is automatically counted, the accuracy is high, and a theoretical basis and an implementation method are provided for intelligent engineering supervision of photovoltaic engineering.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the invention, and that other drawings can be derived from them by a person skilled in the art without inventive effort.
Fig. 1 is a schematic flow chart of a system according to an embodiment of the present invention.
Fig. 2(a) is an original drawing of an engineering field diagram of a photovoltaic panel according to an embodiment of the present invention.
Fig. 2(b) is a result obtained after the image processing method provided by the embodiment of the present invention is used for segmenting the photovoltaic panel region, wherein the blue region is the identified photovoltaic panel region.
Fig. 3(a) is an original drawing (partial) of a photovoltaic panel engineering field diagram provided by an embodiment of the present invention;
FIG. 3(b) is a region of the photovoltaic panel preliminarily divided by color analysis based on FIG. 3 (a);
fig. 3(c) is edge information extracted after edge extraction is performed on the basis of fig. 3 (a);
FIG. 3(d) is an edge image of a photovoltaic panel area obtained after performing the dilation etching and the bitwise AND operation in conjunction with FIGS. 3(b) and 3 (c);
fig. 3(e) is a photovoltaic panel profile obtained after performing profile extraction and polygon approximation on the basis of fig. 3 (d).
Detailed Description
The invention provides a photovoltaic panel counting method based on image processing, which can automatically count the number of photovoltaic panels in a photovoltaic laying site image and improve the efficiency of project progress management in the process of installing and laying photovoltaic components.
In order to make the objects, features and advantages of the present invention more obvious and understandable, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It is to be understood that the following description is only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the present invention without any inventive step, are within the scope of the present invention.
As shown in fig. 1, an embodiment of the present invention provides a photovoltaic panel counting method based on image processing, including the following steps:
step 1: an input image is acquired.
The images of the photovoltaic engineering construction site can be obtained by direct shooting of a camera or aerial shooting of an unmanned aerial vehicle and the like. The picture is as clear as possible, the color is bright, no obvious reflection, blurring or shading exists, and the edge of the photovoltaic plate is obvious. And taking the shot images as a data source of the method, and counting the number of the photovoltaic panels in the images. And for the condition that the occupation ratio of the target area of the photovoltaic panel in the image is small and the number of the photovoltaic panels in the local area only needs to be counted or the background interference is large, the detection range is suggested to be determined manually so as to accelerate the image processing speed and improve the detection precision.
Step 2: and partitioning the photovoltaic panel area.
The photovoltaic panel is relatively uniform in color and obvious in edge characteristics, so that the target area can be divided by combining color extraction and edge extraction.
In the method, an input image needs to be converted from an RGB color space to an HSV color space, a photovoltaic panel region (marked as fig. 2a) is preliminarily extracted through color analysis and threshold setting, and noise is eliminated through filtering and corrosion expansion operations.
The input image is binarized and edge extraction is performed to obtain edge information of the image (denoted as fig. 2 b). And (3) filtering, opening and closing, corroding, expanding and the like are carried out on the graph 2b, so that the influence of noise and weak edges is removed, and the edge information is clearer.
On the basis of the operation, the operations of bitwise and operation are carried out on the images 3a and 3b to obtain the edge image of the photovoltaic panel area, and the smooth lines are removed through the operations of corrosion expansion, filtering and the like to remove noise, so that the clear and complete edge characteristic image of the photovoltaic panel area is obtained.
And step 3: extracting contours and counting
Further extracting the outline of the divided photovoltaic panel area to obtain a multi-dimensional vector containing all outline information of the image, wherein each element in the vector is an outline point; by setting a circulating structure, taking a polygon approximation result and the outline area as judgment conditions, further removing noise interference, extracting the outline which conforms to the shape characteristics of the photovoltaic panel, and finally obtaining the number of the photovoltaic panels.
While the present disclosure provides several embodiments, it should be understood that the disclosed systems and methods may be embodied in many other specific forms without departing from the spirit or scope of the present disclosure. The present examples are to be considered as illustrative and not restrictive, and the intention is not to be limited to the details given herein. For example, the present description does not specify a specific algorithm for links such as edge extraction and contour extraction, and a user may select an appropriate implementation method according to convenience. Any modification, equivalent replacement, sub-combination, and improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (8)
1. A photovoltaic panel counting method based on image processing is characterized by comprising the following steps:
step S1: acquiring a photovoltaic engineering construction site picture as a data source;
step S2: preliminarily segmenting a photovoltaic panel area in the image through color analysis;
step S3: obtaining edge information of the image through an edge extraction algorithm;
step S4: and (5) performing contour searching operation on the image obtained in the step (S3), and performing secondary screening on the contour through polygon approximation and area calculation to obtain the number of the photovoltaic panels in the image.
2. The image processing-based photovoltaic panel counting method according to claim 1, characterized in that: in step S1, the method further includes determining the detection range as needed.
3. The photovoltaic panel counting method according to claim 1, characterized in that: in the step S2, the color analysis and extraction image needs to traverse all the pixel points in the image, convert the pixel points into HSV color space, and set and extract the color region where the photovoltaic panel is located through the color threshold.
4. The image-processing-based photovoltaic panel counting method according to claim 3, characterized in that: the color threshold is automatically obtained by analyzing a color histogram of the image.
5. The photovoltaic panel counting method according to claim 1, characterized in that: in step S3, the edge extraction adopts a Canny operator edge detection method or a Sobel operator edge detection method.
6. The photovoltaic panel counting method according to claim 1, characterized in that: in the steps S2 and S3, the image binarization processing is performed on the image by using the maximum inter-class variance method, so as to obtain the threshold value T.
7. The photovoltaic panel counting method according to claim 6, characterized in that: the gray scale value of the pixel with the gray scale value larger than the threshold value T is adjusted to be 255, and the gray scale value of the pixel with the gray scale value smaller than the threshold value T is adjusted to be 0.
8. The image processing-based photovoltaic panel counting method according to claim 1, characterized in that: and performing erosion dilation, filtering and bitwise AND operation on the color segmentation image and the edge extraction image obtained in the steps S2 and S3 to obtain a clear edge image of the photovoltaic panel area.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010825092.2A CN112116600A (en) | 2020-08-17 | 2020-08-17 | Photovoltaic panel counting method based on image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010825092.2A CN112116600A (en) | 2020-08-17 | 2020-08-17 | Photovoltaic panel counting method based on image processing |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112116600A true CN112116600A (en) | 2020-12-22 |
Family
ID=73804835
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010825092.2A Pending CN112116600A (en) | 2020-08-17 | 2020-08-17 | Photovoltaic panel counting method based on image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112116600A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| IT202100008570A1 (en) * | 2021-04-07 | 2022-10-07 | Jp Droni S R L | MONITORING METHOD OF LINEAR STRUCTURES, SUCH AS PHOTOVOLTAIC PANELS, RAILWAYS, CABLE DUCTIONS OR SIMILAR |
| EP4290454A1 (en) * | 2022-06-10 | 2023-12-13 | Commissariat à l'énergie atomique et aux énergies alternatives | Method and device for segmenting at least one color source image representative of a photovoltaic plant |
-
2020
- 2020-08-17 CN CN202010825092.2A patent/CN112116600A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| IT202100008570A1 (en) * | 2021-04-07 | 2022-10-07 | Jp Droni S R L | MONITORING METHOD OF LINEAR STRUCTURES, SUCH AS PHOTOVOLTAIC PANELS, RAILWAYS, CABLE DUCTIONS OR SIMILAR |
| EP4071664A1 (en) * | 2021-04-07 | 2022-10-12 | JP Droni S.r.l. | Method for monitoring linear structures, such as photovoltaic panels, railways, cable conduits |
| EP4290454A1 (en) * | 2022-06-10 | 2023-12-13 | Commissariat à l'énergie atomique et aux énergies alternatives | Method and device for segmenting at least one color source image representative of a photovoltaic plant |
| FR3136576A1 (en) * | 2022-06-10 | 2023-12-15 | Commissariat à l'énergie atomique et aux énergies alternatives | Method and device for segmenting at least one source color image representative of a photovoltaic power plant |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111260616A (en) | Insulator crack detection method based on Canny operator two-dimensional threshold segmentation optimization | |
| CN111179232A (en) | Steel bar size detection system and method based on image processing | |
| Jiang et al. | Some further results of experimental comparison of range image segmentation algorithms | |
| CN109781737B (en) | Detection method and detection system for surface defects of hose | |
| CN106780526A (en) | A kind of ferrite wafer alligatoring recognition methods | |
| CN112116600A (en) | Photovoltaic panel counting method based on image processing | |
| CN111292321A (en) | Method for identifying defect image of insulator of power transmission line | |
| CN115294031A (en) | Photovoltaic module fault image identification method based on infrared thermal imaging analysis | |
| CN111401364A (en) | License plate positioning algorithm based on combination of color features and template matching | |
| CN113487563B (en) | EL image-based self-adaptive detection method for hidden cracks of photovoltaic module | |
| CN113971681A (en) | Edge detection method for belt conveyor in complex environment | |
| CN111178405A (en) | Similar object identification method fusing multiple neural networks | |
| CN111539330B (en) | Transformer substation digital display instrument identification method based on double-SVM multi-classifier | |
| CN112381794A (en) | Printing defect detection method based on deep convolution generation network | |
| CN112560574A (en) | River black water discharge detection method and recognition system applying same | |
| CN115761613B (en) | Automatic tunnel crack detection method based on convolutional network | |
| CN111832565B (en) | Decision tree-based nixie tube identification method | |
| CN108362693B (en) | Method for detecting qualified rate of insulators on conveyor belt based on image processing | |
| CN117132531A (en) | Lightweight-based YOLOv5 insulator defect detection method | |
| CN114627463B (en) | Non-contact power distribution data identification method based on machine identification | |
| CN110766675B (en) | Solar cell panel defect detection method | |
| CN110189301B (en) | Foreign matter detection method for generator stator core steel sheet stacking platform | |
| CN110276260B (en) | Commodity detection method based on depth camera | |
| CN112651936A (en) | Steel plate surface defect image segmentation method and system based on image local entropy | |
| WANG et al. | Visual Tracking Inspection Method of Transmission Line based on Infrared Thermal Imaging. |
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 |