CN112861817A - Instrument noise image processing method - Google Patents
Instrument noise image processing method Download PDFInfo
- Publication number
- CN112861817A CN112861817A CN202110345875.5A CN202110345875A CN112861817A CN 112861817 A CN112861817 A CN 112861817A CN 202110345875 A CN202110345875 A CN 202110345875A CN 112861817 A CN112861817 A CN 112861817A
- Authority
- CN
- China
- Prior art keywords
- image
- noise
- information
- input
- image information
- 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
- 238000003672 processing method Methods 0.000 title claims description 8
- 238000001914 filtration Methods 0.000 claims abstract description 24
- 238000000034 method Methods 0.000 claims abstract description 12
- 239000006002 Pepper Substances 0.000 claims abstract description 10
- 230000002146 bilateral effect Effects 0.000 claims abstract description 4
- 238000003708 edge detection Methods 0.000 claims abstract description 4
- 238000000605 extraction Methods 0.000 claims abstract description 4
- 238000012545 processing Methods 0.000 abstract description 8
- 238000007689 inspection Methods 0.000 description 13
- 230000000694 effects Effects 0.000 description 3
- 238000012423 maintenance Methods 0.000 description 3
- 235000002566 Capsicum Nutrition 0.000 description 2
- 241000722363 Piper Species 0.000 description 2
- 235000016761 Piper aduncum Nutrition 0.000 description 2
- 235000017804 Piper guineense Nutrition 0.000 description 2
- 235000008184 Piper nigrum Nutrition 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 238000012544 monitoring process Methods 0.000 description 2
- 150000003839 salts Chemical class 0.000 description 2
- QNRATNLHPGXHMA-XZHTYLCXSA-N (r)-(6-ethoxyquinolin-4-yl)-[(2s,4s,5r)-5-ethyl-1-azabicyclo[2.2.2]octan-2-yl]methanol;hydrochloride Chemical compound Cl.C([C@H]([C@H](C1)CC)C2)CN1[C@@H]2[C@H](O)C1=CC=NC2=CC=C(OCC)C=C21 QNRATNLHPGXHMA-XZHTYLCXSA-N 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000009776 industrial production 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
- 238000011946 reduction process Methods 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/12—Classification; Matching
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2218/00—Aspects of pattern recognition specially adapted for signal processing
- G06F2218/02—Preprocessing
- G06F2218/04—Denoising
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Signal Processing (AREA)
- Artificial Intelligence (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a method for processing instrument noise images, which comprises the following steps: step 1, dividing a shot image into input images for information extraction and judgment; step 2, performing edge detection on the input image information, if the input image information contains edge details, judging that the input image is not qualified, skipping the judgment of the next input image, and if the input image information does not contain the edge details, extracting an image without the edge information to form an extracted image; step 3, carrying out noise discrimination on the extracted image, and confirming whether the noise type of the extracted image accords with a salt-pepper noise model or a Gaussian noise model; step 4.1, filtering and denoising the salt-pepper noise model by adopting a median filtering algorithm; step 4.2, filtering and denoising the Gaussian noise model by adopting a bilateral filtering algorithm; and 5, inputting the denoised image information into an identification module for intelligent identification of the image information. The invention can realize the noise reduction processing of the polling shot image.
Description
Technical Field
The invention relates to an instrument noise image processing method used in the field of intelligent inspection of a transformer substation.
Background
High quality and timely operation and maintenance are the prerequisites for ensuring safe and reliable operation of the power system. Modern degree of transformer substation is higher and higher nowadays, and the equipment that increases in a large number leads to artifical daily cost of patrolling and examining to increase day by day, and the problem that traditional artifical daily mode of patrolling and examining is prominent just more but not neglected. Once misjudgment and missed judgment occur in daily routing inspection, great economic loss is caused. Along with the rapid development of subjects such as electronic information technology, automation level and precise control, a large amount of monitoring cameras are installed in a transformer substation, but the traditional camera system only transmits images and is mainly used for security and environmental monitoring, and the device inspection work is hardly helped. The large application of the substation inspection automation equipment is the future development trend of substation automatic inspection. The existing substation inspection operation and maintenance equipment is low in intelligent degree, can execute inspection tasks, shoots key positions of inspection equipment and instrument and meter panels, and still needs to read equipment states and instrument and meter indexes manually, so that the efficiency is low. Due to the fact that a large amount of image noise is usually accompanied with the substation instrument image shot by the inspection robot, the application of follow-up intelligent identification of the inspection image is seriously influenced.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provides a meter noise image processing method which can realize the noise reduction processing of the polling shot image.
One technical scheme for achieving the above purpose is as follows: a meter noise image processing method comprises the following steps:
step 1, dividing a shot image into input images for information extraction and judgment;
step 2, performing edge detection on the input image information, if the input image information contains edge details, judging that the input image is not qualified, skipping the judgment of the next input image, and if the input image information does not contain the edge details, extracting an image without the edge information to form an extracted image;
step 3, carrying out noise discrimination on the extracted image, and confirming whether the noise type of the extracted image accords with a salt-pepper noise model or a Gaussian noise model;
step 4.1, filtering and denoising the salt-pepper noise model by adopting a median filtering algorithm;
step 4.2, filtering and denoising the Gaussian noise model by adopting a bilateral filtering algorithm;
and 5, inputting the denoised image information into an identification module for intelligent identification of the image information.
Further, in the step 4.2, the method for denoising by the median filtering algorithm is to set the gray value of each pixel point of the extracted image as the median of the gray values of all pixel points in a certain neighborhood window of the point, and define the following formula:
g(x,y)=median{f(x-i,y-i)}x,y∈W
wherein g (x, y) and f (x-i, y-i) are single-channel values of the output and input pixels respectively, and W is a two-dimensional sliding window.
Further, the two-dimensional sliding window is rectangular, cross-shaped, circular or rhombic.
According to the instrument noise image processing method, after the image is input, the image is classified into two different noise types, and classification processing is performed by corresponding noise reduction methods, so that the denoising effect of the image is greatly improved.
Drawings
FIG. 1 is a schematic diagram showing various noises generated during the image acquisition process of a transformer substation instrument;
FIG. 2 is a flow chart of a method for processing a noise image of a meter according to the present invention.
Detailed Description
In order to better understand the technical solution of the present invention, the following detailed description is made by specific examples:
through the automatic inspection means, including the fixed point camera and the inspection robot, the instrument and meter of transformer substation is shot to obtain image information, and the image information is a precondition for carrying out follow-up image intelligent identification analysis and intelligent inspection operation and maintenance.
However, the substation instrument image is affected by various factors, and various noises are generated, as shown in fig. 1.
Under the interference of a complex background environment, the acquired image contains a lot of noises, and most of the noises are generated in an image acquisition process, a system imaging process and a signal transmission process. If the forming factors of the noises can be accurately analyzed, the influence of the noises can be purposefully eliminated. Wherein, speckle noise is generated by the transmission of electric signals in the sensor, and the speckle noise is filtered and filtered by a structural tuple with multi-azimuth function to carry out morphological filtering; shot noise is introduced by a CCD industrial camera when an acquired image is imaged; the hardware components of the camera may also contribute to thermal noise or fixed pattern noise. The several noises often introduced in industrial production environments described above are roughly distributed according to two kinds of noises, namely gaussian noise and salt and pepper noise: the modeling of thermal noise and the like can adopt a Gaussian model; modeling of speckle noise, etc. may employ a model of salt and pepper noise. Therefore, according to different classification processing of noise, the denoising effect is improved.
Referring to fig. 2, a method for processing a noise image of a meter according to the present invention includes the following steps:
step 1, dividing the shot image into input images for information extraction and judgment.
And 2, performing edge detection on the input image information, if the input image information contains edge details, judging that the input image is not qualified, skipping judgment of the next input image, and if the input image information does not contain the edge details, extracting an image without the edge information to form an extracted image.
And 3, carrying out noise discrimination on the extracted image, and confirming whether the noise type of the extracted image accords with a salt-pepper noise model or a Gaussian noise model.
And 4.1, filtering and denoising the salt-pepper noise model by adopting a median filtering algorithm. The method for denoising by the median filtering algorithm is that the gray value of each pixel point of the extracted image is set as the median of the gray values of all pixel points in a certain neighborhood window of the point, and the median is defined as the following formula:
g(x,y)=median{f(x-i,y-i)}x,y∈W
wherein g (x, y) and f (x-i, y-i) are single-channel values of the output and input pixels respectively, and W is a two-dimensional sliding window. By using different two-dimensional sliding windows, different filtering effects can be achieved. Common two-position sliding windows are rectangular, cross-shaped, circular and diamond-shaped.
And 4.2, filtering and denoising the Gaussian noise model by adopting a bilateral filtering algorithm. The gaussian filtering is a linear smooth filtering, is suitable for eliminating gaussian noise, and is widely applied to a noise reduction process of image processing. The main method of gaussian filtering is to convolve the image with a gaussian kernel.
And 5, inputting the denoised image information into an identification module for intelligent identification of the image information.
It should be understood by those skilled in the art that the above embodiments are only for illustrating the present invention and are not to be used as a limitation of the present invention, and that changes and modifications to the above described embodiments are within the scope of the claims of the present invention as long as they are within the spirit and scope of the present invention.
Claims (3)
1. A meter noise image processing method is characterized by comprising the following steps:
step 1, dividing a shot image into input images for information extraction and judgment;
step 2, performing edge detection on the input image information, if the input image information contains edge details, judging that the input image is not qualified, skipping the judgment of the next input image, and if the input image information does not contain the edge details, extracting an image without the edge information to form an extracted image;
step 3, carrying out noise discrimination on the extracted image, and confirming whether the noise type of the extracted image accords with a salt-pepper noise model or a Gaussian noise model;
step 4.1, filtering and denoising the salt-pepper noise model by adopting a median filtering algorithm;
step 4.2, filtering and denoising the Gaussian noise model by adopting a bilateral filtering algorithm;
and 5, inputting the denoised image information into an identification module for intelligent identification of the image information.
2. The method of claim 1, wherein in step 4.2, the median filtering algorithm is used to perform denoising, in which the gray-level value of each pixel in the extracted image is set as the median of the gray-level values of all pixels in a neighborhood window of the pixel, and the formula is defined as follows:
g(x,y)=median{f(x-i,y-i)}x,y∈W
wherein g (x, y) and f (x-i, y-i) are single-channel values of the output and input pixels respectively, and W is a two-dimensional sliding window.
3. The instrument noise image processing method according to claim 2, wherein said two-dimensional sliding window is rectangular, cross-shaped, circular or diamond-shaped.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110345875.5A CN112861817A (en) | 2021-03-31 | 2021-03-31 | Instrument noise image processing method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110345875.5A CN112861817A (en) | 2021-03-31 | 2021-03-31 | Instrument noise image processing method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN112861817A true CN112861817A (en) | 2021-05-28 |
Family
ID=75991971
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110345875.5A Pending CN112861817A (en) | 2021-03-31 | 2021-03-31 | Instrument noise image processing method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN112861817A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114565540A (en) * | 2022-04-30 | 2022-05-31 | 深圳市巨力方视觉技术有限公司 | Machine vision integrated system for denoising based on multi-path contrast images |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101087365A (en) * | 2006-06-10 | 2007-12-12 | 中兴通讯股份有限公司 | A method for filtering image mixed noise |
CN101860667A (en) * | 2010-05-06 | 2010-10-13 | 中国科学院西安光学精密机械研究所 | Method for quickly removing mixed noise in image |
CN106441428A (en) * | 2016-08-31 | 2017-02-22 | 杭州申昊科技股份有限公司 | Substation polling method |
US20170236024A1 (en) * | 2016-02-15 | 2017-08-17 | Pictometry International Corp. | Automated system and methodology for feature extraction |
WO2018142228A2 (en) * | 2017-01-19 | 2018-08-09 | Mindmaze Holding Sa | Systems, methods, apparatuses and devices for detecting facial expression and for tracking movement and location including for at least one of a virtual and augmented reality system |
CN109685728A (en) * | 2018-11-30 | 2019-04-26 | 中南大学 | Digital image processing method based on local time-frequency domain conversation |
CN109699074A (en) * | 2017-10-20 | 2019-04-30 | 上海朗帛通信技术有限公司 | A kind of user equipment that be used to wirelessly communicate, the method and apparatus in base station |
CN110188786A (en) * | 2019-04-11 | 2019-08-30 | 广西电网有限责任公司电力科学研究院 | A kind of robot graphics' recognizer for tank-type lightning arrester leakage current |
CN111160256A (en) * | 2019-12-30 | 2020-05-15 | 武汉科技大学 | Automatic identification method and system for transformer substation pointer instrument |
CN111292321A (en) * | 2020-03-13 | 2020-06-16 | 广东工业大学 | Method for identifying defect image of insulator of power transmission line |
-
2021
- 2021-03-31 CN CN202110345875.5A patent/CN112861817A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101087365A (en) * | 2006-06-10 | 2007-12-12 | 中兴通讯股份有限公司 | A method for filtering image mixed noise |
CN101860667A (en) * | 2010-05-06 | 2010-10-13 | 中国科学院西安光学精密机械研究所 | Method for quickly removing mixed noise in image |
US20170236024A1 (en) * | 2016-02-15 | 2017-08-17 | Pictometry International Corp. | Automated system and methodology for feature extraction |
CN106441428A (en) * | 2016-08-31 | 2017-02-22 | 杭州申昊科技股份有限公司 | Substation polling method |
WO2018142228A2 (en) * | 2017-01-19 | 2018-08-09 | Mindmaze Holding Sa | Systems, methods, apparatuses and devices for detecting facial expression and for tracking movement and location including for at least one of a virtual and augmented reality system |
CN109699074A (en) * | 2017-10-20 | 2019-04-30 | 上海朗帛通信技术有限公司 | A kind of user equipment that be used to wirelessly communicate, the method and apparatus in base station |
CN109685728A (en) * | 2018-11-30 | 2019-04-26 | 中南大学 | Digital image processing method based on local time-frequency domain conversation |
CN110188786A (en) * | 2019-04-11 | 2019-08-30 | 广西电网有限责任公司电力科学研究院 | A kind of robot graphics' recognizer for tank-type lightning arrester leakage current |
CN111160256A (en) * | 2019-12-30 | 2020-05-15 | 武汉科技大学 | Automatic identification method and system for transformer substation pointer instrument |
CN111292321A (en) * | 2020-03-13 | 2020-06-16 | 广东工业大学 | Method for identifying defect image of insulator of power transmission line |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114565540A (en) * | 2022-04-30 | 2022-05-31 | 深圳市巨力方视觉技术有限公司 | Machine vision integrated system for denoising based on multi-path contrast images |
CN114565540B (en) * | 2022-04-30 | 2022-07-22 | 深圳市巨力方视觉技术有限公司 | Machine vision integrated system for denoising based on multi-path contrast images |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111325721A (en) | Gas leakage detection method and system based on infrared thermal imaging | |
CN103185730B (en) | Method for building rule of thumb of defect classification, and methods for classifying defect and judging killer defect | |
CN104749184A (en) | Automatic optical detection method and automatic optical detection system | |
CN116433666A (en) | Board card line defect online identification method, system, electronic equipment and storage medium | |
CN112419261B (en) | Visual acquisition method and device with abnormal point removing function | |
CN109378279A (en) | Wafer detection method and wafer detection system | |
CN103824257A (en) | Two-dimensional code image preprocessing method | |
CN112014407A (en) | Method for detecting surface defects of integrated circuit wafer | |
CN104749801A (en) | High-precision automatic optical detection method and high-precision automatic optical detection system | |
CN112861817A (en) | Instrument noise image processing method | |
CN114820626A (en) | Intelligent detection method for automobile front part configuration | |
Wang et al. | Design of machine vision applications in detection of defects in high-speed bar copper | |
CN114863311A (en) | Automatic tracking method and system for inspection target of transformer substation robot | |
CN112967224A (en) | Electronic circuit board detection system, method and medium based on artificial intelligence | |
CN117079286A (en) | Identification method and identification system for pointer instrument | |
CN114266719B (en) | Hough transform-based product detection method | |
CN116993654A (en) | Camera module defect detection method, device, equipment, storage medium and product | |
CN115343313A (en) | Visual identification method based on artificial intelligence | |
Chen et al. | An adaptive edge detection method for extracting images of defect steel plates under complex background | |
CN109919863B (en) | Full-automatic colony counter, system and colony counting method thereof | |
CN111861997A (en) | Method, system and device for detecting circular hole size of pattern board | |
CN110706204B (en) | Commodity invalid detection and judgment scheme based on container door position | |
CN116385353B (en) | Camera module abnormality detection method | |
CN109146806A (en) | Gauge pointer position detection recognition methods based on shadow removing optimization in remote monitoriong of electric power | |
CN111445495B (en) | Uneven-illumination image edge 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 | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20210528 |