CN111598109B - Intelligent identification method for reading of transformer substation pointer instrument - Google Patents
Intelligent identification method for reading of transformer substation pointer instrument Download PDFInfo
- Publication number
- CN111598109B CN111598109B CN202010377687.6A CN202010377687A CN111598109B CN 111598109 B CN111598109 B CN 111598109B CN 202010377687 A CN202010377687 A CN 202010377687A CN 111598109 B CN111598109 B CN 111598109B
- Authority
- CN
- China
- Prior art keywords
- image
- pointer instrument
- reading
- pointer
- current 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
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
- G06V10/40—Extraction of image or video features
- G06V10/48—Extraction of image or video features by mapping characteristic values of the pattern into a parameter space, e.g. Hough transformation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- 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
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V2201/00—Indexing scheme relating to image or video recognition or understanding
- G06V2201/02—Recognising information on displays, dials, clocks
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Biophysics (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The invention relates to an intelligent identification method for reading of a pointer instrument of a transformer substation, which comprises the steps of image acquisition, image correction, graying, median filtering denoising, Gaussian filtering denoising, bilateral filtering denoising, image binarization, canny operator edge detection, corrosion operation, expansion operation, Hough circle transformation detection dial and circle center, Hough linear transformation detection pointer detection and reading output identification. The method can accurately identify the readings of various pointer instruments of the transformer substation in a complex environment, including the lightning arrester ammeter with thin pointers, can automatically identify the instrument type and configure a corresponding identification method after the instrument picture is shot, and accurately identifies the readings of the instrument.
Description
Technical Field
The invention belongs to the technical field of reading of a pointer instrument of a transformer substation, and particularly relates to an intelligent identification method for the reading of the pointer instrument of the transformer substation.
Background
With the development of the times, pointer instruments are replaced by digital instruments in most scenes, but electromagnetic interference usually exists in a transformer substation, and the digital instruments are easily affected, so that the pointer instruments in the transformer substation are still the first choice, and most of the transformer substation conservator oil level meters, the circuit breaker pressure meters, the lightning arrester ampere meters and the like are the pointer instruments. The pointer instrument has the defects of needing manual reading, having certain errors and even possibly causing some accidents due to misjudgment.
In addition, manual recording also requires manual data input into a computer, which is very cumbersome and does not allow real-time display of the meter readings, thereby bringing about some potential hidden dangers.
The application number (CN201610661013.2) discloses a method for automatically identifying the reading of a pointer instrument of a transformer substation, and the technology provides an automatic image shooting and wireless transmission device, and is used for preprocessing a shot image, positioning a pointer of the processed picture, automatically interpreting the positioned pointer instrument value, storing the image if the reading exceeds a measuring range or cannot be identified, and manually reading the image. However, the method has some defects, firstly, the method can only be used for one pointer instrument, but a transformer substation usually has a plurality of pointer instruments, an oil level gauge of an oil conservator and a pressure gauge of a circuit breaker belong to common instruments, and an arrester ammeter inputs a thin pointer instrument, so the method has no universality; secondly, only the illumination problem is processed, the pretreatment on the image of the fine pointer instrument is insufficient, and the robustness in a complex environment is poor; thirdly, the problem of reading error when the acquisition angle is inclined is not considered.
Disclosure of Invention
The invention provides a method for accurately identifying the reading of various pointer instruments of a transformer substation under a complex environment by improving and innovating the defects and problems in the background technology, which comprises a lightning arrester ammeter with a thin pointer, can automatically identify the type of the instrument and configure a corresponding identification method after the picture of the instrument is shot, and accurately identifies the reading of the instrument.
The technical scheme of the invention is to construct an intelligent reading identification method for a pointer instrument of a transformer substation, which comprises the following steps:
s1: acquiring an image of a pointer instrument of a transformer substation;
s2: detecting a dial frame based on Hough transformation, acquiring an inclination angle and correcting an image, selecting polar coordinates, controlling an extracted straight line by using a threshold value, removing the inclination angle out of the threshold value range, calculating a proper angle by using a least square method for the inclination angle within the threshold value, and setting the remained inclination angle theta1,θ2θ3θ4...θnThe most suitable angle is theta, (theta-theta)1)2+(θ-θ2)2+(θ-θn)2Minimum, using least square method to find the most suitable angle
S3: identifying a pointer instrument in the image;
s4: graying, median filtering denoising and Gaussian filtering denoising are carried out on the image, if the image is identified as a thin pointer, bilateral filtering denoising is also needed,
graying: gray ═ R0.299 + G0.587 + B0.114;
median filtering and denoising: sorting the gray levels of all pixels in a small window taking a current pixel as a center from small to large, and taking the middle value of a sorting result as the gray level of the pixel;
adding bilateral filtering denoising:
wherein, ω isijIs the current pixel weight, PijFor current pixel information, PiIs the current pixel neighborhood mean, CijAs current pixel position information, CiFor the current pixel mean position information, σ1And σ2Respectively representing the current pixel information and the standard deviation of the current pixel position;
and (3) Gaussian filtering denoising:
wherein, sigma is the standard deviation of normal distribution, the value of which determines the variation amplitude of the Gaussian function, and the corresponding value is the weight of the filter;
s5: image binarization and canny operator edge detection (x, y);
s6: opening operation is carried out on the image aiming at the problem of reading error when the collection angle is inclined;
s7: carrying out Hough circle transformation, detecting a dial and a circle center, and adopting polar coordinates:
y=y0+r sinθ
y=y0+r sinθ,
converting each pixel point to the center of a circle corresponding to the polar coordinate, accumulating the intensity of the polar coordinate, normalizing the intensity value in a polar coordinate space to make the intensity range between 0 and 255, searching the point with the maximum intensity, and drawing a detection result according to the center point.
S8: and (3) carrying out Hough linear transformation, detecting a pointer and acquiring an angle, and adopting a polar coordinate:
r=x cosθ+y sinθ,
wherein r is the distance from the straight line to the origin, theta is the included angle between the straight line and the x axis, the number of curves intersected at one point is searched for on the plane theta-r through the straight line for detection, and a threshold value is set to determine the straight line and the angle.
Preferably, the pointer instrument in the image is identified in S3, and the fine pointer instrument and the non-fine pointer instrument are identified by using the model trained by the artificial neural network.
Preferably, Canny operator edge detection in S5: calculating the gradient strength and direction of each pixel point in the graph, applying non-maximum value inhibition, eliminating stray response caused by edge detection, applying double-threshold detection to determine true and potential edges, and finishing edge detection by inhibiting isolated weak edges.
Preferably, the opening operation in S6 is an erosion operation and then an expansion operation.
The invention has the beneficial effects that:
the method can accurately read the reading of the pointer instrument of the transformer substation in a complex environment, different identification methods are configured for different pointer instruments, the method has strong universality and robustness, and the problems that the manual reading of the pointer instrument of the transformer substation is complicated and the existing reading method is not intelligent are solved.
Drawings
FIG. 1 is a flow chart of the method of the present invention;
FIG. 2 is an original view of a meter;
FIG. 3 is a grayed image;
FIG. 4 is a median filtered denoised image;
FIG. 5 is a bilateral filtered denoised image;
FIG. 6 is a Gaussian filtered denoised image;
FIG. 7 is a post-edge detection image;
FIG. 8 is a Hough circle transformation detection disc and circle center;
fig. 9 is a hough line transformation detection pointer.
Detailed Description
The present invention will be described in further detail with reference to fig. 1 to 9 of the drawings of the examples and the specification, but the embodiments of the present invention are not limited thereto. The embodiments of the present invention are not limited to the embodiments described above, and any other changes, modifications, substitutions, combinations, and simplifications which do not depart from the spirit and principle of the present invention should be construed as equivalents thereof, and they are included in the scope of the present invention.
The invention provides an intelligent identification method for the reading of a pointer instrument of a transformer substation. An engineer in the field can write a program according to the method disclosed by the invention, and the written program is downloaded to intelligent equipment such as a computer to realize accurate intelligent reading with stronger universality and robustness, and the flow chart of the invention is shown in fig. 1.
Example 1:
a method for intelligently identifying the reading of a pointer instrument of a transformer substation comprises the following steps:
s1: acquiring an image of a pointer instrument of a transformer substation;
s2: detecting a dial frame based on Hough transformation, acquiring an inclination angle and correcting an image, selecting polar coordinates, controlling a threshold value of an extracted straight line, removing the inclination angle out of the threshold value range, calculating a proper angle by using a least square method for the inclination angle within the threshold value, and setting the remained inclination angle theta1,θ2θ3θ4...θnThe most suitable angle is theta, (theta-theta)1)2+(θ-θ2)2+(θ-θn)2Minimum, using least square method to find the most suitable angle
S3: identifying a pointer instrument in the image;
s4: graying, median filtering denoising and Gaussian filtering denoising are carried out on the image, if the image is identified as a thin pointer, bilateral filtering denoising is also needed,
graying: gray ═ R0.299 + G0.587 + B0.114;
median filtering and denoising: sorting the gray levels of all pixels in a small window taking the current pixel as the center from small to large, and taking the middle value of a sorting result as the gray level of the pixel;
bilateral filtering and denoising:
wherein, ω isijIs the current pixel weight, PijFor current pixel information, PiIs the current pixel neighborhood mean, CijAs current pixel position information, CiFor the current pixel mean position information, σ1And σ2Respectively representing the current pixel information and the standard deviation of the current pixel position;
gaussian filtering denoising:
wherein, σ is the standard deviation of normal distribution, the value of which determines the variation amplitude of the Gaussian function, and the weight of the filter is corresponded;
s5: image binarization and canny operator edge detection (x, y);
s6: opening operation is carried out on the image aiming at the problem of reading error when the collection angle is inclined;
s7: and (3) carrying out Hough circle transformation, detecting a dial and a circle center, and adopting polar coordinates:
y=y0+r sinθ
y=y0+r sinθ,
converting each pixel point to the center of a circle corresponding to the polar coordinate, accumulating the intensity of the polar coordinate, normalizing the intensity value in a polar coordinate space to make the intensity range between 0 and 255, searching the point with the maximum intensity, and drawing a detection result according to the center point.
S8: and (3) carrying out Hough linear transformation, detecting a pointer and acquiring an angle, and adopting a polar coordinate:
r=x cosθ+y sinθ,
wherein r is the distance from the straight line to the origin, theta is the included angle between the straight line and the x axis, the number of curves intersected at one point is searched for on the plane theta-r through the straight line for detection, and a threshold value is set to determine the straight line and the angle.
S1, providing an image acquisition module for acquiring the image of the pointer instrument of the transformer substation;
the median filtering denoising method in the S4 is a nonlinear filtering method, and can well maintain the image edge while filtering the noise;
the bilateral filtering denoising in the S4 considers not only the pixel information but also the pixel position information;
the purpose of the step of gaussian filtering and denoising in S4 is to expand the edge of the image, so as to reduce the gray scale of the noise point, thereby reducing the noise amount in the edge detection;
s6, aiming at the problem of reading errors when the acquisition angle is inclined, carrying out opening operation (firstly carrying out corrosion operation and then carrying out expansion operation) on the image to reduce the influence caused by pointer shadows when the acquisition angle is inclined;
the point of maximum intensity described in S7 is typically the center point of a generally circular shape.
Example 2:
on the basis of the embodiment 1, the pointer instrument in the image is identified in S3, and a fine pointer instrument and a non-fine pointer instrument are identified by using the model trained by the artificial neural network.
Example 3:
based on embodiment 1, Canny operator edge detection in S5: calculating the gradient strength and direction of each pixel point in the graph, applying non-maximum value inhibition, eliminating stray response caused by edge detection, applying double-threshold detection to determine true and potential edges, and finishing edge detection by inhibiting isolated weak edges.
Example 4:
in addition to the embodiment 1, the opening operation in S6 is an erosion operation and then an expansion operation. Small and meaningless targets are eliminated through corrosion operation, a target area is enlarged through expansion operation, and the influence caused by pointer shadows when the acquisition angle is inclined can be eliminated.
Claims (4)
1. An intelligent identification method for reading of a pointer instrument of a transformer substation is characterized by comprising the following steps:
s1: acquiring a pointer instrument image of a transformer substation;
s2: detecting the dial frame based on Hough transformation, obtaining the inclination angle and correcting the image, selecting polar coordinates,
the extracted straight line is subjected to threshold control, the inclination angles outside the threshold range are removed, the inclination angles within the threshold are determined to be appropriate angles by using the least square method, and the remaining inclination angle θ is set1,θ2θ3θ4...θnThe most suitable angle is theta, the minimum variance is stable, and the variance isThen, the least square method is utilized to obtain the most suitable angle
S3: identifying a pointer instrument in the image;
s4: graying, median filtering denoising and Gaussian filtering denoising are carried out on the image, if the image is identified as a thin pointer, bilateral filtering denoising is also needed,
graying: gray ═ R0.299 + G0.587 + B0.114;
median filtering and denoising: sorting the gray levels of all pixels in a small window taking a current pixel as a center from small to large, and taking the middle value of a sorting result as the gray level of the pixel;
adding bilateral filtering denoising:
wherein, ω isijIs the current pixel weight, PijFor current pixel information, PiIs the current pixel neighborhood mean, CijAs current pixel position information, CiFor the current pixel mean position information, σ1And σ2Respectively representing the current pixel information and the standard deviation of the current pixel position;
and (3) Gaussian filtering denoising:
wherein, σ is the standard deviation of normal distribution, the value of which determines the variation amplitude of the Gaussian function, and the weight of the filter is corresponded;
s5: image binarization and canny operator edge detection (x, y);
s6: performing opening operation on the image aiming at the problem of reading errors when the acquisition angle is inclined;
s7: and (3) carrying out Hough circle transformation, detecting a dial and a circle center, and adopting polar coordinates:
x=x0+r cosθ
y=y0+r sinθ,
converting each pixel point to the center of a circle corresponding to the polar coordinate, accumulating the intensity of the polar coordinate, normalizing the intensity value in a polar coordinate space to make the intensity range between 0 and 255, searching a point with the maximum intensity, and drawing a detection result according to the center point;
s8: and (3) carrying out Hough linear transformation, detecting a pointer and acquiring an angle, and adopting a polar coordinate:
r=x cosθ+y sinθ,
wherein r is the distance from the straight line to the origin, the number of curves intersecting at one point is searched for on the plane theta-r through the straight line to detect, and a threshold value is set to determine the straight line and the angle.
2. The intelligent substation pointer instrument reading identification method according to claim 1, wherein the pointer instrument in the identification image in S3 is identified by using a model trained by an artificial neural network, so as to identify a fine pointer instrument and a non-fine pointer instrument.
3. The intelligent identification method for the reading of the substation pointer instrument according to claim 1, characterized in that in S5, Canny operator edge detection: calculating the gradient strength and direction of each pixel point in the graph, applying non-maximum suppression, eliminating stray sound caused by edge detection, applying double-threshold detection to determine true and potential edges, and finishing edge detection by suppressing isolated weak edges.
4. The intelligent identification method for the reading of the pointer instrument of the substation as claimed in claim 1, wherein the opening operation in S6 is a corrosion operation followed by an expansion operation.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010377687.6A CN111598109B (en) | 2020-05-07 | 2020-05-07 | Intelligent identification method for reading of transformer substation pointer instrument |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010377687.6A CN111598109B (en) | 2020-05-07 | 2020-05-07 | Intelligent identification method for reading of transformer substation pointer instrument |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111598109A CN111598109A (en) | 2020-08-28 |
CN111598109B true CN111598109B (en) | 2022-07-22 |
Family
ID=72185250
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010377687.6A Active CN111598109B (en) | 2020-05-07 | 2020-05-07 | Intelligent identification method for reading of transformer substation pointer instrument |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111598109B (en) |
Families Citing this family (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112529840A (en) * | 2020-11-06 | 2021-03-19 | 广东电网有限责任公司中山供电局 | SF6 inflation equipment pressure drop defect image recognition device |
CN112836726B (en) * | 2021-01-12 | 2022-06-07 | 云南电网有限责任公司电力科学研究院 | Pointer instrument indication reading method and device based on video information |
CN113449599A (en) * | 2021-05-27 | 2021-09-28 | 国网河北省电力有限公司行唐县供电分公司 | Intelligent operation and maintenance auxiliary device of indoor substation based on image recognition technology |
CN113792616A (en) * | 2021-08-26 | 2021-12-14 | 南方电网深圳数字电网研究院有限公司 | Remote meter reading system based on edge calculation and working method thereof |
CN113837312B (en) * | 2021-09-30 | 2023-04-07 | 南方电网电力科技股份有限公司 | Method and device for evaluating running state of zinc oxide arrester |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103927507A (en) * | 2013-01-12 | 2014-07-16 | 山东鲁能智能技术有限公司 | Improved multi-instrument reading identification method of transformer station inspection robot |
CN104392206A (en) * | 2014-10-24 | 2015-03-04 | 南京航空航天大学 | Image processing method for automatic pointer-type instrument reading recognition |
CN104751187A (en) * | 2015-04-14 | 2015-07-01 | 山西科达自控股份有限公司 | Automatic meter-reading image recognition method |
CN105550683A (en) * | 2015-12-07 | 2016-05-04 | 重庆大学 | Vision-based pointer instrument automatic reading system and method |
CN107092863A (en) * | 2017-03-24 | 2017-08-25 | 重庆邮电大学 | A kind of readings of pointer type meters recognition methods of Intelligent Mobile Robot |
CN107609557A (en) * | 2017-08-24 | 2018-01-19 | 华中科技大学 | A kind of readings of pointer type meters recognition methods |
CN108053374A (en) * | 2017-12-05 | 2018-05-18 | 天津大学 | A kind of underwater picture Enhancement Method of combination bilateral filtering and Retinex |
CN108960231A (en) * | 2018-05-31 | 2018-12-07 | 广东工业大学 | A kind of thin pointer watch dial identification number reading method based on machine vision |
CN109146974A (en) * | 2018-09-07 | 2019-01-04 | 广东中粤电力科技有限公司 | A kind of readings of pointer type meters recognition methods and system |
JP6522869B1 (en) * | 2019-01-21 | 2019-05-29 | 株式会社ソルネット | Automatic reading system and reading method of indication value of pointer of analog meter |
CN110490145A (en) * | 2019-08-22 | 2019-11-22 | 国网四川省电力公司信息通信公司 | A kind of readings of pointer type meters recognition methods |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US7865017B2 (en) * | 2007-06-08 | 2011-01-04 | Seiko Epson Corporation | Selection of regions within an image |
-
2020
- 2020-05-07 CN CN202010377687.6A patent/CN111598109B/en active Active
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103927507A (en) * | 2013-01-12 | 2014-07-16 | 山东鲁能智能技术有限公司 | Improved multi-instrument reading identification method of transformer station inspection robot |
CN104392206A (en) * | 2014-10-24 | 2015-03-04 | 南京航空航天大学 | Image processing method for automatic pointer-type instrument reading recognition |
CN104751187A (en) * | 2015-04-14 | 2015-07-01 | 山西科达自控股份有限公司 | Automatic meter-reading image recognition method |
CN105550683A (en) * | 2015-12-07 | 2016-05-04 | 重庆大学 | Vision-based pointer instrument automatic reading system and method |
CN107092863A (en) * | 2017-03-24 | 2017-08-25 | 重庆邮电大学 | A kind of readings of pointer type meters recognition methods of Intelligent Mobile Robot |
CN107609557A (en) * | 2017-08-24 | 2018-01-19 | 华中科技大学 | A kind of readings of pointer type meters recognition methods |
CN108053374A (en) * | 2017-12-05 | 2018-05-18 | 天津大学 | A kind of underwater picture Enhancement Method of combination bilateral filtering and Retinex |
CN108960231A (en) * | 2018-05-31 | 2018-12-07 | 广东工业大学 | A kind of thin pointer watch dial identification number reading method based on machine vision |
CN109146974A (en) * | 2018-09-07 | 2019-01-04 | 广东中粤电力科技有限公司 | A kind of readings of pointer type meters recognition methods and system |
JP6522869B1 (en) * | 2019-01-21 | 2019-05-29 | 株式会社ソルネット | Automatic reading system and reading method of indication value of pointer of analog meter |
CN110490145A (en) * | 2019-08-22 | 2019-11-22 | 国网四川省电力公司信息通信公司 | A kind of readings of pointer type meters recognition methods |
Non-Patent Citations (3)
Title |
---|
Lightning Arrester Monitor Pointer Meter and Digits Reading Recognition Based on Image Processing;Kai Wen等;《2018 IEEE 3rd Advanced Information Technology, Electronic and Automation Control Conference》;20181217;2381-2387页 * |
一种适用于变电站巡检机器人的仪表识别算法;房桦等;《自动化与仪表》;20130515(第05期);1-15页 * |
基于图像处理的细指针表盘识别方法研究;张芳健等;《计算机测量与控制》;20190925;第27卷(第9期);272-277页 * |
Also Published As
Publication number | Publication date |
---|---|
CN111598109A (en) | 2020-08-28 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111598109B (en) | Intelligent identification method for reading of transformer substation pointer instrument | |
CN110580480B (en) | Meter reading identification method based on image processing | |
CN112149667B (en) | Automatic reading method of pointer instrument based on deep learning | |
Jiale et al. | Reading recognition method of analog measuring instruments based on improved hough transform | |
CN106778734A (en) | A kind of insulator based on rarefaction representation falls to go here and there defect inspection method | |
CN109508709B (en) | Single pointer instrument reading method based on machine vision | |
CN111738229B (en) | Automatic reading method for scale of pointer dial | |
CN108564085A (en) | A kind of method of automatic reading pointer type instrument reading | |
Zhang et al. | A pointer meter recognition algorithm based on deep learning | |
CN111368906A (en) | Pointer type oil level indicator reading identification method based on deep learning | |
CN108764253A (en) | Pointer instrument digitizing solution | |
CN112215060A (en) | Hough transform-based high-precision mechanical instrument reading identification method | |
CN110633620A (en) | Pointer instrument scale identification method and electronic equipment | |
CN113408519B (en) | Method and system for pointer instrument reading based on template rotation matching | |
CN110414521A (en) | Oil level gauge for transformer registration recognition methods in a kind of substation | |
CN116958514B (en) | Sub-pixel positioning method for shock wave position of optical image | |
CN113610041A (en) | Reading identification method and device for pointer instrument | |
CN113705350A (en) | Pointer instrument reading identification method and device for transformer substation, medium and electronic equipment | |
CN117475154A (en) | Instrument image recognition method and system based on optimized Canny edge detection | |
CN112560839A (en) | Automatic identification method and system for reading of pointer instrument | |
CN116403085A (en) | Multi-pointer instrument identification method and device for transformer substation based on multitasking | |
CN106778515B (en) | Automatic identification method for axial magnetic flux leakage array signal of flange | |
CN115311447A (en) | Pointer instrument indicating number identification method based on deep convolutional neural network | |
CN115761606A (en) | Box electric energy meter identification method and device based on image processing | |
CN115100485A (en) | Instrument abnormal state identification method based on power inspection robot |
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 |