CN115063581A - Method for judging local overexposure image of insulator string in transformer substation environment - Google Patents
Method for judging local overexposure image of insulator string in transformer substation environment Download PDFInfo
- Publication number
- CN115063581A CN115063581A CN202210608613.8A CN202210608613A CN115063581A CN 115063581 A CN115063581 A CN 115063581A CN 202210608613 A CN202210608613 A CN 202210608613A CN 115063581 A CN115063581 A CN 115063581A
- Authority
- CN
- China
- Prior art keywords
- image
- insulator string
- insulator
- overexposure
- judging
- 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
- 239000012212 insulator Substances 0.000 title claims abstract description 128
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000005070 sampling Methods 0.000 claims abstract description 9
- 238000007781 pre-processing Methods 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims description 9
- 235000014676 Phragmites communis Nutrition 0.000 claims description 3
- 238000012937 correction Methods 0.000 claims description 3
- 238000001514 detection method Methods 0.000 abstract description 4
- 238000013528 artificial neural network Methods 0.000 abstract 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 4
- 238000013135 deep learning Methods 0.000 description 3
- 238000000605 extraction Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 3
- 238000005406 washing Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007796 conventional method Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000011010 flushing procedure Methods 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/25—Determination of region of interest [ROI] or a volume of interest [VOI]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/457—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by analysing connectivity, e.g. edge linking, connected component analysis or slices
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/07—Target detection
Abstract
The invention relates to a method for judging a local overexposure image of an insulator string in a transformer substation environment, and belongs to the field of target detection. The method comprises the following steps: step one, preprocessing operation is carried out on the image output by the neural network. And step two, extracting image characteristics, extracting left and right edges and a central line of the insulator string, and fitting the theoretical central line of the insulator string by using a random sampling consistency algorithm. And step three, calculating characteristic parameters, calculating the number of insulator sheets based on the gray curve characteristics, calculating a deviation value of the fitted theoretical central line, and calculating the overexposure degree of the image by combining the calculated characteristic parameters and the calculated deviation value. According to the method, the insulator string missing condition caused by the image overexposure can be identified, and the image overexposure degree can be judged.
Description
Technical Field
The invention relates to the field of target detection, in particular to a method for judging a local overexposure image of an insulator string in a transformer substation environment.
Background
For a substation insulator string, due to the influence of high voltage of current bearing for a long time and natural environment change, the reduction of the insulation capacity of the substation insulator string can cause safety accidents. The surface dirt can cause flashover accidents, and in order to prevent electric power safety accidents, the dirt on the surface of the insulator string needs to be washed by water. The current trend is to use a robot to replace a human to complete the insulator string washing task, and to use the robot to wash the insulator string with water, the position of the insulator string needs to be recognized firstly.
For a traditional insulator string detection method, most of the insulator strings are detected by using a characteristic design algorithm of the insulator strings such as textures, shapes and the like; for the insulator string method based on deep learning, a rectangular frame containing insulator string position information is mostly output, and a further algorithm is often needed to extract accurate contour coordinates of the insulator string. In the actual water washing task of the transformer substation, the vision sensor shoots from bottom to top, so that the vision sensor can look directly at the sun easily, and the shot image is partially over-exposed, so that the insulator string on the image is partially lost. In the conventional method or the deep learning-based method, complete insulator string information can be detected by default, and the condition is not processed, so that the detected insulator string is incomplete and wrong. Therefore, in order to complete the task of automatic water flushing subsequently, the robot needs to be able to identify the insulator sheet missing condition caused by such image overexposure, be able to judge the degree of the image overexposure, and then adjust the shot exposure coefficient to obtain a complete insulator string image.
Disclosure of Invention
The invention solves the problem that whether the insulator string image is lost due to overexposure or not is judged when a deep learning detection method is used. Calculating coordinates of a central line of the insulator string through the detected left and right outlines of the insulator string, fitting the coordinates of the central line by using a random sampling consistency algorithm, and calculating deviation of the central line; and calculating the number of the insulator pieces by using a gray curve, and combining the insulator pieces and the gray curve to obtain an overexposure degree parameter of the image.
In order to solve the problems in the prior art, the invention adopts the technical scheme that:
a method for judging a local overexposure image of an insulator string in a transformer substation environment comprises the following steps.
Step 1: preprocessing the collected insulator string local overexposure original image in the environment of the transformer substation to obtain a foreground image containing the outline position of the insulator string;
step 2: extracting image characteristics from the foreground image, and fitting a theoretical central line of the insulator string by adopting a random sampling consistency algorithm;
and 3, step 3: and calculating the number of insulator sheets based on the gray curve characteristics, calculating the deviation value of the fitted theoretical central line, and calculating the overexposure degree of the image by combining the number of insulator sheets and the deviation value.
The image preprocessing is to filter the background of the environmental factors, convert the background into a binary image and distinguish the foreground and background information of the insulator string.
The image features are the outline and the central line of the left edge and the right edge of the insulator string.
Extracting the left and right edges of the insulator string comprises:
calculate left contour:
calculating the right contour:
wherein Ledge is a set of points { l ] of the left edge of the insulator string 1 ,l 2 ,...l n Reed is the set of points at the right edge of the insulator string { r } 1 ,r 2 ,...r n },(li k ,lj k ) For the left edge point l of the insulator chain k Abscissa and ordinate of (ri) k ,rj k ) For right edge point r of insulator chain k Abscissa and ordinate of (t) min And t max Is the upper and lower bounds of the ordinate of the position of the insulator string in the image, the set of insulator string image points C ═ C 1 ,c 2 ,...c N In which insulator string image point c k Has the coordinates of (ci) k ,cj k )。
The line coordinates of the insulator string are as follows:
wherein Medge old Set table as central line pointThe x-axis coordinate and the y-axis coordinate of the point on the centerline with index k. (li) k ,lj k ) Is the coordinate point of the contour of the left side edge of the insulator string, (ri) k ,rj k ) Is the coordinate point of the right edge profile of the insulator string.
And fitting a theoretical central line of the insulator string, wherein the fitting comprises:
fitting the center line points by adopting a random sampling consistency algorithm to obtain a fitted straight line:
y=ax+b (4)
obtaining a theoretical centerline point m after fitting correction k Coordinate set Medge new The following were used:
wherein (mi) k ,mj k ) For any corrected theoretical centerline point m k The abscissa and the ordinate.
Calculating the number of insulator pieces, including:
for Medge new Upper point, characteristic curve:
f(x k ,y k )=0 (6)
wherein
And (5) calculating the number m of the maximum points of the curve, namely the number of insulator pieces of the insulator string in the image.
Calculating the deviation between the fitted and corrected central line and the original central line:
calculating an overexposure parameter comprising:
judging the parameter value of the overexposure degree according to the deviation of the central line and whether the film is missing:
where k1 and k2 are scaling factors, σ is the centerline deviation, m is the number of insulator strings detected, N is t Representing the total number of insulator strings of type t; as a result, δ is a parameter indicating the degree of overexposure of the insulator string, and the larger the value thereof, the more serious the overexposure of the image.
A judgment system for insulator string local overexposure images in a substation environment comprises a processing part and a storage part, wherein programs are stored in the storage part, the processing part loads the programs and executes the steps of the method, and therefore the identification of insulator string missing conditions caused by image overexposure is achieved, and the degree of image overexposure is judged.
The invention has the following beneficial effects and advantages:
1, influence of tower pole lines and the like in a background area can be effectively removed through pretreatment, and the method is the basis of subsequent treatment.
2. And fitting the centerline of the insulator string by using a random sampling consistency algorithm, so that the influence of interference noise during edge extraction can be effectively removed.
3. The insulator string overexposure image judging method provided by the invention can effectively judge whether the insulator string image is overexposed and the intensity of the overexposure degree, and provides effective reference for subsequent insulator string identification work.
Drawings
FIG. 1 is a flow chart of method steps;
FIG. 2 is an original image to be processed;
FIG. 3 is a preprocessed binary image;
FIG. 4 shows the left and right contour points and the center line point obtained by extraction;
fig. 5 is a corrected centerline image.
Detailed Description
The following detailed description of embodiments of the present invention is provided in connection with the accompanying drawings and examples. The following examples are intended to illustrate the present invention, but do not limit the scope of the present invention.
The first embodiment of the invention:
as shown in fig. 1, a flow chart of method steps. As shown in fig. 2, for a local overexposure original image of an insulator string in a to-be-processed substation environment, local overexposure occurs in the upper left corner of a visible image.
An edge extraction method for a substation insulator string under a local overexposure condition is shown in fig. 1, and the method comprises the following specific implementation steps:
step 1: and carrying out image preprocessing operation to obtain the basic outline position of the insulator string.
And (3) carrying out image preprocessing operation in the step (1) in a construction mode of filtering the image by using median filtering, then carrying out binarization by using an OTSU algorithm, and then filtering backgrounds such as tower and pole lines by using morphological processing.
After the image is preprocessed, a binary image of the outline of the insulator string from white to black and a black background can be obtained, as shown in fig. 3.
And 2, step: and (3) extracting image features, extracting left and right edges and central lines of the insulator string, and fitting the theoretical central line of the insulator string by using a random sampling consistency algorithm as shown in figure 4.
For the operation of extracting the image characteristics in the step 2, the specific method is as follows
Step 21, calculating a left contour:
calculating the right contour:
wherein Ledge is a set of points { l ] of the left edge of the insulator string 1 ,l 2 ,...l n Reed is the set of points at the right edge of the insulator string { r } 1 ,r 2 ,...r n },(li k ,lj k ) For the left edge point l of the insulator chain k Abscissa and ordinate of (ri) k ,rj k ) For right edge point r of insulator chain k Abscissa and ordinate of (t) min And t max Is the upper and lower bounds of the ordinate of the position of the insulator string in the image, the set of insulator string image points C ═ C 1 ,c 2 ,...c N In which insulator string image points c k Has the coordinates of (ci) k ,cj k )。
And step 22, calculating the line coordinates of the insulator string by using the following formula.
Medge therein old Is a collection of centerline pointsThe x-axis coordinate and the y-axis coordinate of the point on the centerline with index k. (li) k ,lj k ) Is the coordinate point of the contour of the left side edge of the insulator string, (ri) k ,rj k ) Is the coordinate point of the right edge contour of the insulator string, wherein the points of the left contour and the right contour extracted by the method are the same, so that the points of the same k and li are the same k And ri k The values of (c) are the same.
Step 23, fitting the center line points by using a random sampling consistency algorithm to obtain a fitted straight line, as shown in fig. 5;
y=ax+b (4)
obtaining a theoretical centerline point m after fitting correction k Coordinates of the objectMedge Collection new The following were used:
wherein (mi) k ,mj k ) For any corrected theoretical centerline point m k The abscissa and the ordinate.
And 3, step 3: calculating characteristic parameters: and calculating the number of insulator sheets based on the gray curve characteristics, calculating the deviation value of the fitted theoretical central line, and calculating the overexposure degree of the image by combining the number of insulator sheets and the deviation value.
Step 31, firstly, calculating the number of insulator pieces, and for Medge new Upper point, characteristic curve:
f(x k ,y k )=0 (6)
wherein
And (5) calculating the number m of the maximum points of the curve, namely the number of insulator pieces of the insulator string in the image.
And 32, calculating the deviation between the fitted and corrected central line and the original central line.
And step 33, finally obtaining an overexposure degree parameter, and judging the overexposure degree parameter value according to the deviation of the central line and whether the film is missing:
wherein k is 1 And k 2 Is the proportionality coefficient, σ is the centerline deviation, m is the number of insulator strings detected, N t Representing the total number of insulator strings of type t. The result delta is an indication of overexposure of the insulator stringThe larger the value of the parameter of degree, the more serious the overexposure of the image is.
And step 34, dividing into overexposure degree types according to the parameter value delta.
Get k 1 Is 2, k 2 And the value of delta is 100, and the value of delta obtained according to the final calculation can provide reference for subsequent work by using a formula under the condition that the type of the insulator string, namely the number of insulator strings is known.
The surface image has been affected by light when δ is greater than 300 and has been severely missing when δ exceeds 2500.
The second embodiment of the invention:
a judgment system for insulator string local overexposure images in a substation environment comprises a processing part and a storage part, wherein programs are stored in the storage part, the processing part loads the programs and executes the steps of the method, and therefore the identification of insulator string missing conditions caused by image overexposure is achieved, and the degree of image overexposure is judged.
The third embodiment of the invention:
the utility model provides a judge device of insulator chain local overexposure image under transformer substation's environment, includes image acquisition equipment, host computer, and image acquisition equipment is intelligent terminal such as high definition camera, host computer. The upper computer comprises a processing part and a storage part, wherein the storage part stores programs, the processing part loads the programs and executes the method steps, and the recognition of insulator string missing conditions caused by image overexposure is realized, and the degree of the image overexposure is judged.
While the foregoing is directed to the preferred embodiment of the present invention, it will be appreciated by those skilled in the art that various changes and modifications may be made therein without departing from the principles of the invention as set forth in the appended claims.
Claims (10)
1. A method for judging a local overexposure image of an insulator string in a transformer substation environment is characterized by comprising the following steps.
Step 1: preprocessing the collected insulator string local overexposure original image in the environment of the transformer substation to obtain a foreground image containing the outline position of the insulator string;
step 2: extracting image characteristics from the foreground image, and fitting a theoretical central line of the insulator string by adopting a random sampling consistency algorithm;
and step 3: and calculating the number of insulator sheets based on the gray curve characteristics, calculating the deviation value of the fitted theoretical central line, and calculating the overexposure degree of the image by combining the number of insulator sheets and the deviation value.
2. The method for judging the local overexposure image of the insulator string in the transformer substation environment according to claim 1, wherein the image preprocessing is to filter an environment factor background and convert the environment factor background into a binary image for distinguishing foreground and background information of the insulator string.
3. The method for judging the local overexposure image of the insulator string in the transformer substation environment according to claim 1, wherein the image features are outlines of left and right edges of the insulator string and a central line.
4. The method for judging the local overexposure image of the insulator string in the transformer substation environment according to claim 3, wherein the step of extracting the left edge and the right edge of the insulator string comprises the following steps:
calculate left contour:
calculating the right contour:
wherein Ledge is a set of points { l ] of the left edge of the insulator string 1 ,l 2 ,…l n Reed is the set of points at the right edge of the insulator string { r } 1 ,r 2 ,…r n },(li k ,lj k ) For the left edge point l of the insulator chain k Abscissa and ordinate of (ri) k ,rj k ) For right edge point r of insulator chain k Abscissa and ordinate of (t) min And t max Is the upper and lower bounds of the ordinate of the position of the insulator string in the image, the set of insulator string image points C ═ C 1 ,c 2 ,…c N In which insulator string image points c k Has the coordinates of (ci) k ,cj k )。
5. The method for judging the local overexposure image of the insulator string in the transformer substation environment according to claim 4, wherein the line coordinates of the insulator string are as follows:
wherein Medge old Is a set of centerline points The x-axis coordinate and the y-axis coordinate of the point on the centerline with index k. (li) k ,lj k ) Is the coordinate point of the contour of the left side edge of the insulator string, (ri) k ,rj k ) Is the coordinate point of the right edge profile of the insulator string.
6. The method for judging the local overexposure image of the insulator string in the transformer substation environment according to claim 5, wherein the fitting of the theoretical centerline of the insulator string comprises the following steps:
fitting the center line points by adopting a random sampling consistency algorithm to obtain a fitted straight line:
y=ax+b (4)
obtaining a theoretical centerline point m after fitting correction k Coordinate set Medge new The following were used:
wherein (mi) k ,mj k ) For any corrected theoretical centerline point m k The abscissa and the ordinate of (c).
7. The method for judging the local overexposure image of the insulator string in the transformer substation environment according to claim 1, wherein the step of calculating the number of the insulator pieces comprises the following steps:
for Medge new Upper point, characteristic curve:
f(x k, y k )=0 (6)
wherein
And (5) calculating the number m of the maximum points of the curve, namely the number of insulator pieces of the insulator string in the image.
9. the method for judging the local overexposure image of the insulator string in the transformer substation environment according to claim 1, wherein the step of calculating the overexposure degree parameter comprises the following steps:
judging the parameter value of the overexposure degree according to the deviation of the central line and whether the film is missing:
wherein k is 1 And k 2 Is the proportionality coefficient, σ is the centerline deviation, m is the number of insulator strings detected, N t Representing the total number of insulator strings of type t; as a result, δ is a parameter indicating the degree of overexposure of the insulator string, and the larger the value thereof, the more serious the overexposure of the image.
10. A system for judging a local overexposure image of an insulator string in a substation environment is characterized by comprising a processing part and a storage part, wherein a program is stored in the storage part, the processing part loads the program and executes the method steps of any one of claims 1 to 9, so that the identification of the insulator string missing condition caused by the overexposure of the image is realized, and the overexposure degree of the image is judged.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210608613.8A CN115063581A (en) | 2022-05-31 | 2022-05-31 | Method for judging local overexposure image of insulator string in transformer substation environment |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210608613.8A CN115063581A (en) | 2022-05-31 | 2022-05-31 | Method for judging local overexposure image of insulator string in transformer substation environment |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115063581A true CN115063581A (en) | 2022-09-16 |
Family
ID=83198962
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210608613.8A Pending CN115063581A (en) | 2022-05-31 | 2022-05-31 | Method for judging local overexposure image of insulator string in transformer substation environment |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115063581A (en) |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4974017A (en) * | 1988-09-27 | 1990-11-27 | Fuji Photo Film Co., Ltd. | Method of determining exposure |
CN106093069A (en) * | 2016-08-15 | 2016-11-09 | 国网山西省电力公司电力科学研究院 | A kind of monitoring method of the filthy fault of High-Voltage Insulation substring insulation |
CN106980816A (en) * | 2017-02-22 | 2017-07-25 | 贵州电网有限责任公司凯里供电局 | Insulator chain automatic identifying method based on optical imagery |
CN111598889A (en) * | 2020-05-26 | 2020-08-28 | 南方电网数字电网研究院有限公司 | Grading ring inclination fault identification method and device and computer equipment |
WO2021190056A1 (en) * | 2020-03-26 | 2021-09-30 | 国网湖北省电力有限公司电力科学研究院 | Infrared zero value diagnosis method and system for porcelain insulator string |
CN113781498A (en) * | 2021-08-24 | 2021-12-10 | 南昌大学 | Intelligent diagnosis method for composite insulator |
CN114387448A (en) * | 2021-12-24 | 2022-04-22 | 鞍钢集团矿业有限公司 | Edge contour extraction method for transformer substation strut-type insulator string |
-
2022
- 2022-05-31 CN CN202210608613.8A patent/CN115063581A/en active Pending
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US4974017A (en) * | 1988-09-27 | 1990-11-27 | Fuji Photo Film Co., Ltd. | Method of determining exposure |
CN106093069A (en) * | 2016-08-15 | 2016-11-09 | 国网山西省电力公司电力科学研究院 | A kind of monitoring method of the filthy fault of High-Voltage Insulation substring insulation |
CN106980816A (en) * | 2017-02-22 | 2017-07-25 | 贵州电网有限责任公司凯里供电局 | Insulator chain automatic identifying method based on optical imagery |
WO2021190056A1 (en) * | 2020-03-26 | 2021-09-30 | 国网湖北省电力有限公司电力科学研究院 | Infrared zero value diagnosis method and system for porcelain insulator string |
CN111598889A (en) * | 2020-05-26 | 2020-08-28 | 南方电网数字电网研究院有限公司 | Grading ring inclination fault identification method and device and computer equipment |
CN113781498A (en) * | 2021-08-24 | 2021-12-10 | 南昌大学 | Intelligent diagnosis method for composite insulator |
CN114387448A (en) * | 2021-12-24 | 2022-04-22 | 鞍钢集团矿业有限公司 | Edge contour extraction method for transformer substation strut-type insulator string |
Non-Patent Citations (2)
Title |
---|
方挺 等: "航拍图像中绝缘子串的轮廓提取和故障检测", 《上海交通大学学报》, vol. 47, no. 12, 31 December 2013 (2013-12-31), pages 1818 - 1822 * |
逯海军 等: "基于不变性广义霍夫变换的绝缘子串风偏角检测", 《水电能源科学》, vol. 31, no. 10, 31 October 2013 (2013-10-31), pages 185 - 188 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107895376A (en) | Based on the solar panel recognition methods for improving Canny operators and contour area threshold value | |
CN107727662B (en) | Battery piece EL black spot defect detection method based on region growing algorithm | |
CN107185854B (en) | The algorithm of photovoltaic cell acetes chinensis and color classification based on RGB channel | |
CN109035195B (en) | Fabric defect detection method | |
CN107843600B (en) | Method for detecting appearance fingerprint defects of polycrystalline silicon solar cell | |
CN113313677B (en) | Quality detection method for X-ray image of wound lithium battery | |
CN110245555B (en) | Power system terminal box condensation determination method and system based on image recognition | |
CN106680285A (en) | Infrared image-assisted method of recognizing contamination condition of insulator by visible light image | |
CN114241364A (en) | Method for quickly calibrating foreign object target of overhead transmission line | |
CN114881956A (en) | Cell panel grid line self-adaptive extraction method and system based on Hough transform | |
CN110348461A (en) | A kind of Surface Flaw feature extracting method | |
CN107610090A (en) | A kind of detection algorithm of photovoltaic cell surface grid line skew | |
CN112819784A (en) | Method and system for detecting broken strands and scattered strands of wires of distribution line | |
CN112435272A (en) | High-voltage transmission line connected domain removing method based on image contour analysis | |
CN112529853A (en) | Method and device for detecting damage of netting of underwater aquaculture net cage | |
CN111667473A (en) | Insulator hydrophobicity grade judging method based on improved Canny algorithm | |
CN113487563B (en) | EL image-based self-adaptive detection method for hidden cracks of photovoltaic module | |
CN108734709B (en) | Insulator flange shape parameter identification and damage detection method | |
CN112102189B (en) | Line structure light bar center line extraction method | |
CN115063581A (en) | Method for judging local overexposure image of insulator string in transformer substation environment | |
CN116630321B (en) | Intelligent bridge health monitoring system based on artificial intelligence | |
CN111507347A (en) | Electrical equipment infrared image enhancement and segmentation method based on partial differential equation | |
CN106960437B (en) | Liquid level detection method for oil-immersed power transformer of power inspection robot | |
CN116091996A (en) | Identification method, device, equipment and storage medium for disconnecting link switching state | |
CN110766675B (en) | Solar cell panel defect detection method |
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 |