CN113379671A - Partial discharge diagnosis system and diagnosis method for switch equipment - Google Patents
Partial discharge diagnosis system and diagnosis method for switch equipment Download PDFInfo
- Publication number
- CN113379671A CN113379671A CN202110399286.5A CN202110399286A CN113379671A CN 113379671 A CN113379671 A CN 113379671A CN 202110399286 A CN202110399286 A CN 202110399286A CN 113379671 A CN113379671 A CN 113379671A
- Authority
- CN
- China
- Prior art keywords
- value
- image
- bispectrum
- gray
- unit
- 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
- 238000003745 diagnosis Methods 0.000 title claims abstract description 31
- 208000028659 discharge Diseases 0.000 title claims description 31
- 238000000034 method Methods 0.000 title claims description 22
- 238000001914 filtration Methods 0.000 claims abstract description 47
- 235000002566 Capsicum Nutrition 0.000 claims abstract description 17
- 239000006002 Pepper Substances 0.000 claims abstract description 17
- 241000722363 Piper Species 0.000 claims abstract description 17
- 235000016761 Piper aduncum Nutrition 0.000 claims abstract description 17
- 235000017804 Piper guineense Nutrition 0.000 claims abstract description 17
- 235000008184 Piper nigrum Nutrition 0.000 claims abstract description 17
- 150000003839 salts Chemical class 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims description 63
- 230000009466 transformation Effects 0.000 claims description 56
- 230000011218 segmentation Effects 0.000 claims description 25
- 239000012535 impurity Substances 0.000 claims description 18
- 238000007781 pre-processing Methods 0.000 claims description 18
- 238000009825 accumulation Methods 0.000 claims description 14
- 238000012935 Averaging Methods 0.000 claims description 9
- 238000013507 mapping Methods 0.000 claims description 8
- 238000001514 detection method Methods 0.000 abstract description 8
- 238000002405 diagnostic procedure Methods 0.000 abstract description 3
- 230000000694 effects Effects 0.000 abstract description 3
- 238000000605 extraction Methods 0.000 description 4
- 238000007689 inspection Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000009413 insulation Methods 0.000 description 2
- 238000001228 spectrum Methods 0.000 description 2
- 239000000654 additive Substances 0.000 description 1
- 230000000996 additive effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015556 catabolic process Effects 0.000 description 1
- 239000004020 conductor Substances 0.000 description 1
- 238000009421 internal insulation Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000006467 substitution reaction 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
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01R—MEASURING ELECTRIC VARIABLES; MEASURING MAGNETIC VARIABLES
- G01R31/00—Arrangements for testing electric properties; Arrangements for locating electric faults; Arrangements for electrical testing characterised by what is being tested not provided for elsewhere
- G01R31/12—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing
- G01R31/1227—Testing dielectric strength or breakdown voltage ; Testing or monitoring effectiveness or level of insulation, e.g. of a cable or of an apparatus, for example using partial discharge measurements; Electrostatic testing of components, parts or materials
-
- 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
- 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
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10004—Still image; Photographic image
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20024—Filtering details
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20048—Transform domain processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a diagnostic system and a diagnostic method for partial discharge of switch equipment, belonging to the technical field of power equipment detection. By converting the original gray image into a high-frequency subgraph and a low-frequency subgraph, because the high-frequency subgraph reflects the edge information of the original gray image and Gaussian noise is also separated to the high-frequency subgraph, the high-frequency subgraph is filtered for the first time, the Gaussian noise can be effectively separated from the image, and the detail integrity of the output image is ensured; and then, secondary filtering is carried out on the reconstructed image to remove salt and pepper noise, and because the Gaussian noise is removed before, the influence of the Gaussian noise on the secondary filtering can be avoided, and the local distortion of the output image is avoided. Through the two filtering, the effect of effectively removing the mixed noise of the Gaussian noise and the salt and pepper noise on the basis of keeping the image details is realized, and the follow-up diagnosis of the power equipment is facilitated.
Description
Technical Field
The invention relates to the technical field of power equipment detection, in particular to a partial discharge diagnosis system and a diagnosis method for switch equipment.
Background
Partial discharge phenomenon easily takes place in the inside of current power equipment, and the partial discharge phenomenon indicates that high voltage power equipment's insulating inside can be because of different factors, obvious insulating defect phenomenon appears, for example, common bubble, impurity and conductor burr etc..
The partial discharge phenomenon is a very common phenomenon, for example, a switching device which is a key device in a power transmission and distribution network often generates a condition that internal insulation is wetted and aged during operation, resulting in a problem of partial discharge, and if the switching device is in a partial discharge state for a long time, once affected by different factors, the switching device inevitably causes a reduction in the insulation strength of the related power equipment, even damages to the equipment, and further causes a serious device failure problem due to insulation breakdown.
In the prior art, images of power equipment are acquired through ultraviolet light detection, sound wave detection, infrared detection and other modes, and operation and inspection personnel can diagnose whether a local diagnosis phenomenon occurs or not; however, the diagnosis method has high requirements on the personnel for operation and inspection, because many noises, such as gaussian noise and salt and pepper noise, exist in the image obtained by the current detection method; the noises may cause interference to the operation personnel, for example, salt and pepper noises may cause many black and white dots in the image, which is not beneficial for the operation personnel to determine whether the local discharge phenomenon occurs inside the power equipment, resulting in a low detection efficiency of the current diagnosis mode.
Disclosure of Invention
The invention aims to provide a switch equipment partial discharge diagnosis system and a diagnosis method, and is characterized in that the switch equipment partial discharge diagnosis system comprises a sensor module, a shear wave transformation module, a first filtering module, a shear wave inverse transformation module and a second filtering module;
the sensor module is used for providing an original gray-scale image;
the shear wave transformation module is used for carrying out shear wave transformation on the original gray level image to obtain a high-frequency subgraph and a low-frequency subgraph; the system is also used for carrying out shear wave transformation on the output segmentation image to obtain a transformation subimage;
the first filtering module is used for carrying out first filtering on the high-frequency subgraph to remove Gaussian noise in the high-frequency subgraph so as to obtain a de-noised high-frequency subgraph;
the shear wave inverse transformation module is used for carrying out shear wave inverse transformation on the denoised high-frequency subgraph and the denoised low-frequency subgraph to obtain a reconstructed image; the edge sub-image acquisition module is also used for carrying out shear wave inverse transformation on the edge sub-image to obtain an edge image;
and the second filtering module is used for carrying out second filtering on the reconstructed image to remove salt and pepper noise in the reconstructed image and obtain an output image.
The first filtering module comprises a window setting unit, an area setting unit, a Fourier transform unit, a summation unit, a mean value unit and an inverse Fourier transform unit;
the window setting unit is used for setting a preprocessing window in the region where the high-frequency sub-image is located, one preprocessing window comprises 9 high-frequency sub-image pixel points, and the 9 high-frequency sub-image pixel points comprise a middle pixel and 8 boundary pixels distributed around the middle pixel;
the area setting unit is used for setting 4 square processing areas in the area where the preprocessing window is located; the processing area is formed by enclosing a middle pixel and 3 boundary pixels;
the Fourier transform unit is used for respectively carrying out Fourier transform of the third-order accumulation amount on each processing region to obtain bispectrum amplitude values and bispectrum phase values corresponding to all high-frequency sub-pixel points in each processing region;
the summing unit is used for summing all the bispectrum amplitude values and bispectrum phase values in each processing area respectively to obtain bispectrum total amplitude values and bispectrum total phase values of each processing area;
the averaging unit is used for selecting a processing area with the minimum bispectrum total amplitude value, and respectively averaging the bispectrum total amplitude value and the bispectrum total phase value to obtain an output bispectrum amplitude value and an output bispectrum phase value;
and the inverse Fourier transform unit is used for performing inverse Fourier transform of the third-order accumulation quantity on the output bispectrum amplitude value and the output bispectrum phase value to obtain a denoising high-frequency subgraph.
The second filtering module comprises a filter area setting unit, a gray value obtaining unit, a median judgment unit, a filter expanding unit, a center judgment unit, a filter area judgment unit and a gray level adjusting unit;
the filter region setting unit is used for setting filter regions in regions where reconstructed images are located, each filter region comprises a reconstruction pixel point, and the reconstruction pixel point comprises a central pixel and an edge pixel; the central pixel is located in the center of the filter area;
the gray value acquisition unit is used for acquiring the minimum gray value Z in the filter regionminMaximum gray value ZmaxAnd median value of gray Zmed(ii) a And is also used for acquiring the minimum gray value Z in the filter region when the expanded filter region is smaller than the preset region threshold valueminMaximum gray value ZmaxAnd median value of gray Zmed；
The median judging unit is used for judging the gray median ZmedWhether or not it is at the minimum gray value ZminAnd the maximum gray value ZmaxTo (c) to (d);
the filter expansion unit is used for expanding the gray median value ZmedNot at the minimum grey value ZminAnd the maximum gray value ZmaxIn the meantime, the filter area is enlarged to the periphery of the filter area according to a preset proportion;
the central judging unit is used for judging the gray median value ZmedAt the minimum gray value ZminAnd the maximum gray value ZmaxIn between, the gray value Z of the central pixel is judgedxyWhether or not it is at the minimum gray value ZminAnd the maximum gray value ZmaxTo (c) to (d);
the filter area judging unit is used for judging whether the expanded filter area is smaller than a preset area threshold value or not;
the gray scale adjusting unit is used for adjusting the gray scale value Z of the central pixelxyNot at the minimum grey value ZminAnd the maximum gray value ZmaxWhen the filter area between or after the expansion is not less than the preset area threshold value, the gray value of the central pixel is adjusted to be the gray median value Zmed。
The switch equipment partial discharge diagnosis system also comprises a threshold segmentation module and an edge processing module;
the threshold segmentation module is used for performing threshold segmentation on the output image to obtain an output segmentation image;
and the edge processing module is used for carrying out edge processing on the transformed sub-image through a Canny operator to obtain an edge sub-image.
The diagnosis method of the partial discharge diagnosis system of the switch equipment comprises the following steps:
step 100: providing an original gray level image;
step 200: carrying out shear wave transformation on the original gray level image to obtain a high-frequency subgraph and a low-frequency subgraph;
step 300: carrying out primary filtering on the high-frequency subgraph, and removing Gaussian noise in the high-frequency subgraph to obtain a de-noised high-frequency subgraph;
step 400: carrying out shear wave inverse transformation on the denoised high-frequency subgraph and the denoised low-frequency subgraph to obtain a reconstructed image;
step 500: and carrying out secondary filtering on the reconstructed image to remove salt and pepper noise in the reconstructed image so as to obtain an output image.
step 301: setting a preprocessing window in the region where the high-frequency subgraph is located;
step 302: setting 4 square processing areas in the area where the preprocessing window is located;
step 303: respectively carrying out Fourier transform of the third-order accumulation quantity on each processing region to obtain bispectrum amplitude values and bispectrum phase values corresponding to all high-frequency sub-image pixel points in each processing region;
step 304: summing all the bispectrum amplitude values and bispectrum phase values in each processing area respectively to obtain bispectrum total amplitude values and bispectrum total phase values of each processing area;
step 305: selecting a processing area with the minimum bispectrum total amplitude value, and respectively averaging the bispectrum total amplitude value and the bispectrum total phase value to obtain an output bispectrum amplitude value and an output bispectrum phase value;
step 306: and performing Fourier inverse transformation of the third-order accumulation quantity on the output bispectrum amplitude value and the output bispectrum phase value to obtain a denoising high-frequency subgraph.
Step 500 comprises the following sub-steps:
step 501: setting filter regions in the region of the reconstructed image, wherein each filter region comprises a reconstructed pixel point, and each reconstructed pixel point comprises a central pixel and an edge pixel; the central pixel is located in the center of the filter area;
step 502: obtaining a minimum grey value Z within a filter areaminMaximum gray value ZmaxAnd median value of gray Zmed；
Step 503: judging the median Z of the gray scalemedWhether or not it is at the minimum gray value ZminAnd the maximum gray value ZmaxTo (c) to (d);
if median value of gray scale ZmedNot at the minimum grey value ZminAnd the maximum gray value ZmaxExpanding the filter area to the periphery of the filter area according to a preset proportion, and then judging whether the expanded filter area is smaller than a preset area threshold value or not; if the expanded filter region is smaller than the preset region threshold, step 502 is executed, otherwise, the gray value of the central pixel is adjusted to the gray median value Zmed；
If median value of gray scale ZmedAt the minimum gray value ZminAnd the maximum gray value ZmaxIn between, the gray value Z of the central pixel is judgedxyWhether or not it is at the minimum gray value ZminAnd the maximum gray value ZmaxTo (c) to (d); if the gray value Z of the central pixelxyAt the minimum gray value ZminAnd the maximum gray value ZmaxOtherwise, adjusting the gray value of the central pixel to the median value Zmed。
Step 500 is followed by the steps of:
step 601: performing threshold segmentation on the output image to obtain an output segmented image;
step 602: carrying out shear wave transformation on the output segmentation image to obtain a transformation subimage;
step 603: performing edge processing on the transformed sub-image through a Canny operator to obtain an edge sub-image;
step 604: carrying out shear wave inverse transformation on the edge sub-image to obtain an edge image; extracting characteristic parameters of the edge image; judging whether the characteristic parameters exceed a preset threshold value or not; if so, acquiring the equipment ID with the partial discharge risk according to the mapping relation and the original gray level image corresponding to the characteristic parameters; and sending an early warning signal to an operator according to the characteristic parameters and the equipment ID.
The extracting of the feature parameters of the edge image in step 604 specifically includes: counting the number value of impurity pixels corresponding to the impurities of the edge image; and calculating the area S, the perimeter L and the roundness C of the corresponding impurities according to the number value of the impurity pixels.
The invention has the beneficial effects that:
the original gray image is converted into a high-frequency subgraph and a low-frequency subgraph, the high-frequency subgraph reflects the edge information of the original gray image, Gaussian noise is separated to the high-frequency subgraph, the high-frequency subgraph is filtered for the first time, the Gaussian noise can be effectively separated from the image, and the detail integrity of an output image is guaranteed; and then, secondary filtering is carried out on the reconstructed image to remove salt and pepper noise, and because the Gaussian noise is removed before, the influence of the Gaussian noise on the secondary filtering can be avoided, and the local distortion of the output image is avoided. Through the two filtering, the effect of effectively removing the mixed noise of the Gaussian noise and the salt and pepper noise on the basis of keeping the image details can be realized, and the follow-up diagnosis of the power equipment is facilitated.
Drawings
Fig. 1 is a schematic structural diagram of a power equipment diagnosis system according to an embodiment of the present invention;
in the figure: 1-a sensor module; 2-a shear wave transformation module; 3-a first filtering module; 4-a shear wave inverse transformation module; 5-second filtering module.
Fig. 2 is a schematic flowchart of a power equipment diagnosis method according to a second embodiment of the present invention;
fig. 3 is a partial schematic flow chart of a power equipment diagnosis method according to a second embodiment of the present invention;
FIG. 4 is a diagram of a partial discharge diagnostic implementation;
fig. 5 is a flow chart of switch partial discharge diagnostics.
Detailed Description
The invention provides a diagnostic system and a diagnostic method for partial discharge of switch equipment, and the invention is further explained by combining the drawings and the specific embodiments.
Example 1
As shown in fig. 1, the power equipment diagnosis system provided by the present embodiment includes a sensor module, a shear wave transformation module, a first filtering module, a shear wave inverse transformation module, and a second filtering module;
a sensor module for providing an original grayscale image;
the shear wave transformation module is used for carrying out shear wave transformation on the original gray level image to obtain a high-frequency subgraph and a low-frequency subgraph;
the first filtering module is used for carrying out first filtering on the high-frequency subgraph and removing Gaussian noise in the high-frequency subgraph to obtain a de-noised high-frequency subgraph;
the shear wave inverse transformation module is used for carrying out shear wave inverse transformation on the denoised high-frequency subgraph and the denoised low-frequency subgraph to obtain a reconstructed image;
and the second filtering module is used for carrying out second filtering on the reconstructed image to remove salt and pepper noise in the reconstructed image and obtain an output image.
The first filtering module comprises a window setting unit, an area setting unit, a Fourier transform unit, a summation unit, a mean value unit and an inverse Fourier transform unit;
the window setting unit is used for setting a plurality of preprocessing windows in the region where the high-frequency subgraphs are located, wherein one preprocessing window comprises 9 high-frequency sub-image pixel points, and the 9 high-frequency sub-image pixel points comprise a middle pixel and 8 boundary pixels surrounding the middle pixel respectively;
the area setting unit is used for setting 4 square processing areas in the area where the preprocessing window is located; the processing area is formed by enclosing 3 boundary pixels and a middle pixel;
the Fourier transform unit is used for respectively carrying out Fourier transform of the third-order accumulation amount on each processing region to obtain bispectrum amplitude values and bispectrum phase values corresponding to all high-frequency sub-pixel points in each processing region;
the summing unit is used for summing all the bispectrum amplitudes in each processing area respectively and summing all the bispectrum phase values in each processing area respectively to obtain a bispectrum total amplitude value and a bispectrum total phase value of each processing area;
the averaging unit is used for selecting a processing area with the minimum bispectrum total amplitude value, and respectively averaging the bispectrum total amplitude value and the bispectrum total phase value to obtain an output bispectrum amplitude value and an output bispectrum phase value;
and the inverse Fourier transform unit is used for performing inverse Fourier transform of the third-order accumulation quantity on the output bispectrum amplitude value and the output bispectrum phase value to obtain a denoising high-frequency subgraph.
The second filtering module comprises a filter area setting unit, a gray value obtaining unit, a median judgment unit, a filter expanding unit, a center judgment unit, a filter area judgment unit and a gray level adjusting unit;
the device comprises a filter area setting unit, a reconstruction image processing unit and a processing unit, wherein the filter area setting unit is used for setting a plurality of filter areas in the area where the reconstruction image is located, each filter area comprises a plurality of reconstruction pixel points, and the plurality of reconstruction pixel points comprise a central pixel and a plurality of edge pixels; the central pixel is located in the center of the filter area;
a gray value acquisition unit for acquiring a minimum gray value Z in the filter regionminMaximum gray value ZmaxAnd median value of gray Zmed；
A median judgment unit for judging the grayscale median ZmedWhether or not it is at the minimum gray value ZminAnd the maximum gray value ZmaxTo (c) to (d);
filter expanding unit forWhen median value of gray scale ZmedNot at the minimum grey value ZminAnd the maximum gray value ZmaxIn the meantime, the filter area is enlarged to the periphery of the filter area according to a preset proportion;
a center judgment unit for judging the median Z of gray scalemedAt the minimum gray value ZminAnd the maximum gray value ZmaxIn between, the gray value Z of the central pixel is judgedxyWhether or not it is at the minimum gray value ZminAnd the maximum gray value ZmaxTo (c) to (d);
the filter area judging unit is used for judging whether the expanded filter area is smaller than a preset area threshold value or not;
a gray value obtaining unit, further used for obtaining the minimum gray value Z in the filter region when the expanded filter region is smaller than the preset region thresholdminMaximum gray value ZmaxAnd median value of gray Zmed；
A gray scale adjusting unit for adjusting gray scale value Z of the central pixelxyNot at the minimum grey value ZminAnd the maximum gray value ZmaxWhen the filter area between or after the expansion is not less than the preset area threshold value, the gray value of the central pixel is adjusted to be the gray median value Zmed。
The power equipment diagnosis system also comprises a threshold segmentation module and an edge processing module;
the threshold segmentation module is used for performing threshold segmentation on the output image to obtain a plurality of output segmentation images;
the shear wave transformation module is also used for carrying out shear wave transformation on the output segmentation image to obtain a plurality of transformation sub-images;
the edge processing module is used for carrying out edge processing on the plurality of transformation sub-images through a Canny operator to obtain a plurality of edge sub-images;
and the shear wave inverse transformation module is used for carrying out shear wave inverse transformation on the plurality of edge sub-images to obtain edge images.
The power diagnosis system also comprises a pre-established mapping relation between the original gray level image and the equipment ID, a parameter extraction module, a parameter judgment module, an equipment ID acquisition module and an early warning module;
the parameter extraction module is used for extracting characteristic parameters of the edge image;
the parameter judgment module is used for judging whether the characteristic parameter exceeds a preset threshold value or not;
the equipment ID acquisition module is used for acquiring the equipment ID with the partial discharge risk according to the mapping relation and the original gray level image corresponding to the characteristic parameters;
and the early warning module is used for sending an early warning signal to an operator according to the characteristic parameters and the equipment ID.
The parameter extraction module comprises a pixel statistics module and a calculation module:
the pixel counting module is used for counting the impurity pixel quantity value corresponding to the impurities of the edge image;
and the calculating module is used for calculating the corresponding area S, perimeter L and roundness C of the impurities according to the number value of the impurity pixels.
In a specific embodiment, the power diagnostic system comprises a perception layer, a network layer, a platform layer and an application layer; the sensing layer comprises a sensor module, a shear wave transformation module, a first filtering module, a shear wave inverse transformation module, a second filtering module, a threshold segmentation module, an edge processing module, a parameter extraction module, a parameter judgment module, an equipment ID acquisition module and an early warning module; the network layer comprises a power private network and a public network and is used for transmitting data; and the operating personnel receives the uploaded data through the platform layer, analyzes the service data, provides a corresponding strategy through the application layer, makes the operation personnel process the strategy and marks the corresponding equipment ID. As shown in fig. 4.
In summary, the power equipment diagnosis system of the embodiment performs preprocessing and preliminary diagnosis on the original gray level image through the above contents, so that an operator can conveniently grasp the operation status of the power system, and the diagnosis efficiency is improved.
Example 2
As shown in fig. 2 and 3, the present embodiment provides a power equipment diagnosis method, including:
and S100, providing an original gray image.
S200, carrying out shear wave transformation on the original gray level image to obtain a high-frequency subgraph and a low-frequency subgraph. The high-frequency subgraph and the low-frequency subgraph are both gray level graphs, the number of pixels is the same as that of the original gray level image, the high-frequency subgraph mainly reflects the edge and texture information of the original gray level image, and the low-frequency subgraph mainly reflects the outline information of the original gray level image, so Gaussian noise is also located in the high-frequency subgraph.
S300, carrying out primary filtering on the high-frequency subgraph, and removing Gaussian noise in the high-frequency subgraph to obtain a de-noised high-frequency subgraph.
S400, performing shear wave inverse transformation on the denoised high-frequency subgraph and the denoised low-frequency subgraph to obtain a reconstructed image.
And S500, carrying out secondary filtering on the reconstructed image, and removing salt and pepper noise in the reconstructed image to obtain an output image.
Specifically, by converting the original gray image into a high-frequency subgraph and a low-frequency subgraph, because the high-frequency subgraph reflects the edge information of the original gray image and the Gaussian noise is also separated to the high-frequency subgraph, the high-frequency subgraph is filtered for the first time, the Gaussian noise can be effectively separated from the image, and the detail integrity of the output image is ensured; and then, secondary filtering is carried out on the reconstructed image to remove salt and pepper noise, and because the Gaussian noise is removed before, the influence of the Gaussian noise on the secondary filtering can be avoided, and the local distortion of the output image is avoided. Through the two filtering, the effect of effectively removing the mixed noise of the Gaussian noise and the salt and pepper noise on the basis of keeping the image details is realized, and the follow-up diagnosis of the power equipment is facilitated.
Further, step S300: carrying out primary filtering on the high-frequency subgraph, removing Gaussian noise in the high-frequency subgraph to obtain a de-noised high-frequency subgraph, and specifically comprising the following steps:
s301, setting a plurality of preprocessing windows in the region where the high-frequency subgraph is located; wherein, a preprocessing window includes 9 high-frequency sub-image pixel points, and the 9 high-frequency sub-image pixel points include a middle pixel and 8 boundary pixels distributed around the middle pixel.
S302, setting 4 square processing areas in the area where the preprocessing window is located; the processing area is formed by enclosing a middle pixel and 3 boundary pixels.
S303, performing Fourier transform of the third-order accumulation amount on each processing region respectively to obtain the bispectrum amplitude values and bispectrum phase values corresponding to all high-frequency sub-image pixel points in each processing region. For example, the 4 pixels in one of the processing regions are (x) respectively1,y1,c1)、(x2,y2,c2)、(x3,y3,c3) And (x)4,y4,c4) X is the horizontal coordinate value of the pixel, y is the vertical coordinate value of the pixel, and c is the gray value of the pixel;
let X (ω) be the fourier transform of { X (N) } (N0, 1, …, N) (1), with magnitude | X (ω) | and phase
Substituting the abscissa value and the gray value of the pixel point into the formula (1) to obtain X (omega)1) Substituting the longitudinal coordinate values and gray values of the pixel points into the formula (1) to obtain X (omega)2)。
The fourier transform of the third order cumulant is shown in equation (2):
Bx(ω1,ω2)＝X(ω1)X(ω2)X*(ω1+ω2) (2)
bispectrum amplitude | Bx(ω1,ω2) I and bispectrum phase position
Expressed as:
|Bx(ω1,ω2)|＝|X(ω1)||X(ω2)|·|X(ω1+ω2)| (3)
subsequently, X (ω)1) And X (ω)2) Substitute for Chinese traditional medicineEntering the formulas (3) and (4), the pixel point (x) can be obtained1,y1,c1)、(x2,y2,c2)、(x3,y3,c3) And (x)4,y4,c4) Respectively corresponding dual-spectrum amplitude value and dual-spectrum phase value.
S304, summing all the bispectrum amplitudes in each processing area respectively, and summing all the bispectrum phase values in each processing area respectively to obtain the bispectrum total amplitude and the bispectrum total phase value of each processing area.
S305, selecting a processing area with the minimum bispectrum total amplitude, and respectively averaging the bispectrum total amplitude and the bispectrum total phase value to obtain an output bispectrum amplitude and an output bispectrum phase value. Namely, the output bispectrum amplitude value and the output bispectrum phase value are respectively used as the bispectrum amplitude value and the bispectrum phase of the middle pixel.
S306, carrying out Fourier inverse transformation of the third-order accumulation quantity on the output bispectrum amplitude value and the output bispectrum phase value to obtain a denoising high-frequency subgraph.
It should be noted that after the fourier transform of the third-order accumulation amount in step S303 is performed, the gaussian noise in the high-frequency sub-graph is still in gaussian distribution, that is, after the fourier transform of the third-order accumulation amount, the bispectral amplitude of the gaussian noise is 0, so that the additive gaussian noise can be removed after the bispectral transform and the processing, and the details of the original image can be fully retained.
Further, step S500, performing a second filtering on the reconstructed image to remove salt and pepper noise in the reconstructed image, and obtaining an output image, specifically including:
s501, setting a plurality of filter areas in an area where a reconstructed image is located, wherein each filter area comprises a plurality of reconstructed pixel points, and each reconstructed pixel point comprises a central pixel and a plurality of edge pixels; the central pixel is located in the center of the filter area;
s502, acquiring the minimum gray value Z in the filter areaminMaximum gray value ZmaxAnd median value of gray Zmed；
S503, judging the gray median value ZmedWhether or not it is at the minimum gray value ZminAnd the maximum gray value ZmaxTo (c) to (d);
s504, if not, expanding the filter area to the periphery of the filter area according to a preset proportion;
s505, if yes, judging the gray value Z of the central pixelxyWhether or not it is at the minimum gray value ZminAnd the maximum gray value ZmaxTo (c) to (d);
s504, after expanding the filter area to the periphery of the filter area according to a preset proportion, the method further comprises the following steps:
s506, judging whether the expanded filter area is smaller than a preset area threshold value;
if yes, S502 is executed to obtain the minimum gray value Z in the filter areaminMaximum gray value ZmaxAnd median value of gray Zmed；
S507, if not, adjusting the gray value of the central pixel to be a gray median value Zmed；
S503, judging the gray value Z of the central pixelxyWhether or not it is at the minimum gray value ZminAnd the maximum gray value ZmaxAfter, still include:
s507, if not, adjusting the gray value of the central pixel to be a gray median value Zmed；
And S508, if yes, not adjusting the gray value of the central pixel.
The initial filter region has the least pixel points, and the edge details of the image subjected to secondary filtering can be fully reserved; and then, if the median of the gray levels is not between the minimum gray level and the maximum gray level, expanding the range of the filter according to a preset proportion, and removing salt and pepper noise on the basis of ensuring the edge details of the image.
Further, step S500: and carrying out secondary filtering on the reconstructed image, removing salt and pepper noise in the reconstructed image, and obtaining an output image, wherein the method further comprises the following steps:
s601, performing threshold segmentation on the output image to obtain a plurality of output segmented images;
s602, performing shear wave transformation on the output segmentation image to obtain a plurality of transformation sub-images;
s603, performing edge processing on the plurality of transformed sub-images through a Canny operator to obtain a plurality of edge sub-images;
and S604, performing shear wave inverse transformation on the plurality of edge sub-images to obtain edge images.
The method comprises the steps of decomposing each output segmentation image along different directions through shear wave transformation to obtain transformation sub-images, carrying out edge processing on the transformation sub-images, and accurately obtaining edge images of the transformation sub-images, wherein each edge image corresponds to one output segmentation image and marks the edge of each output segmentation image.
Further, before providing the original grayscale image in step S100, the method includes: pre-establishing a mapping relation between an original gray image and an equipment ID;
further, after performing inverse shear wave transform on the plurality of edge sub-images to obtain an edge image in step S604, the method further includes:
s701, extracting characteristic parameters of the edge image;
s702, judging whether the characteristic parameters exceed a preset threshold value;
s703, if yes, acquiring the equipment ID with the partial discharge risk according to the mapping relation and the original gray level image corresponding to the characteristic parameters;
and S704, sending an early warning signal to an operator according to the characteristic parameters and the equipment ID. Additionally, an operator can perform service data analysis according to the equipment ID, the characteristic parameters and the edge image, and make a corresponding processing strategy; additionally, when the characteristic parameters exceed the threshold, the sink node or the access node can actively call the equipment data in the database, wherein the equipment data comprise live detection data, bad working condition data, operation information data, corresponding fault case data and the like, so that operators can conveniently make a more optimal processing strategy according to the equipment data; and then, the processing strategy is transmitted to the operation and inspection personnel, and the operation and inspection personnel can immediately process the related hidden dangers, so that the safe and stable operation of the system is ensured.
Specifically, the step S701 of extracting the feature parameters of the edge image specifically includes:
s7011, counting the number value of impurity pixels corresponding to the impurities of the edge image;
and S7012, calculating the area S, the perimeter L and the roundness C of the corresponding impurities according to the number value of the impurity pixels. Wherein, the roundness
The larger the roundness is, the more serious the impurity or defect is, and the operator can be helped to quickly know the equipment condition.
In a specific implementation mode, an original gray image of embedded infrared image acquisition equipment is firstly passed, then the original gray image is preprocessed to obtain an edge image and characteristic parameters, and preliminary diagnosis is carried out (S702-S703), then the edge image and the characteristic parameters are uploaded to an operator and discharge early warning is sent out according to conditions, the operator carries out service data analysis on the uploaded content, and a corresponding matching monitoring strategy is manufactured. As shown in fig. 5.
In summary, the diagnostic method for the power equipment according to the embodiment performs preprocessing and preliminary diagnosis on the original gray-scale image through the above contents, so that an operator can conveniently grasp the operation status of the power system, and the diagnostic efficiency is improved.
The present invention is not limited to the above embodiments, and any changes or substitutions that can be easily made by those skilled in the art within the technical scope of the present invention are also within the scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the protection scope of the claims.
Claims (10)
1. A partial discharge diagnosis system for switch equipment is characterized by comprising a sensor module, a shear wave transformation module, a first filtering module, a shear wave inverse transformation module and a second filtering module;
the sensor module is used for providing an original gray-scale image;
the shear wave transformation module is used for carrying out shear wave transformation on the original gray level image to obtain a high-frequency subgraph and a low-frequency subgraph; the system is also used for carrying out shear wave transformation on the output segmentation image to obtain a transformation subimage;
the first filtering module is used for carrying out first filtering on the high-frequency subgraph to remove Gaussian noise in the high-frequency subgraph so as to obtain a de-noised high-frequency subgraph;
the shear wave inverse transformation module is used for carrying out shear wave inverse transformation on the denoised high-frequency subgraph and the denoised low-frequency subgraph to obtain a reconstructed image; the edge sub-image acquisition module is also used for carrying out shear wave inverse transformation on the edge sub-image to obtain an edge image;
and the second filtering module is used for carrying out second filtering on the reconstructed image to remove salt and pepper noise in the reconstructed image and obtain an output image.
2. The system for diagnosing partial discharge of switch-type equipment according to claim 1, wherein the first filtering module comprises a window setting unit, a region setting unit, a fourier transform unit, a summation unit, a mean value unit and an inverse fourier transform unit;
the window setting unit is used for setting a preprocessing window in the region where the high-frequency sub-image is located, one preprocessing window comprises 9 high-frequency sub-image pixel points, and the 9 high-frequency sub-image pixel points comprise a middle pixel and 8 boundary pixels distributed around the middle pixel;
the area setting unit is used for setting 4 square processing areas in the area where the preprocessing window is located; the processing area is formed by enclosing a middle pixel and 3 boundary pixels;
the Fourier transform unit is used for respectively carrying out Fourier transform of the third-order accumulation amount on each processing region to obtain bispectrum amplitude values and bispectrum phase values corresponding to all high-frequency sub-pixel points in each processing region;
the summing unit is used for summing all the bispectrum amplitude values and bispectrum phase values in each processing area respectively to obtain bispectrum total amplitude values and bispectrum total phase values of each processing area;
the averaging unit is used for selecting a processing area with the minimum bispectrum total amplitude value, and respectively averaging the bispectrum total amplitude value and the bispectrum total phase value to obtain an output bispectrum amplitude value and an output bispectrum phase value;
and the inverse Fourier transform unit is used for performing inverse Fourier transform of the third-order accumulation quantity on the output bispectrum amplitude value and the output bispectrum phase value to obtain a denoising high-frequency subgraph.
3. The system for diagnosing partial discharge of switching equipment according to claim 1, wherein the second filtering module includes a filter region setting unit, a gray value obtaining unit, a median determining unit, a filter expanding unit, a center determining unit, a filter region determining unit, and a gray adjusting unit;
the filter region setting unit is used for setting filter regions in regions where reconstructed images are located, each filter region comprises a reconstruction pixel point, and the reconstruction pixel point comprises a central pixel and an edge pixel; the central pixel is located in the center of the filter area;
the gray value acquisition unit is used for acquiring the minimum gray value Z in the filter regionminMaximum gray value ZmaxAnd median value of gray Zmed(ii) a And is also used for acquiring the minimum gray value Z in the filter region when the expanded filter region is smaller than the preset region threshold valueminMaximum gray value ZmaxAnd median value of gray Zmed；
The median judging unit is used for judging the gray median ZmedWhether or not it is at the minimum gray value ZminAnd the maximum gray value ZmaxTo (c) to (d);
the filter expansion unit is used for expanding the gray median value ZmedNot at the minimum grey value ZminAnd the maximum gray value ZmaxIn the meantime, the filter area is enlarged to the periphery of the filter area according to a preset proportion;
the central judging unit is used for judging the gray median value ZmedAt the minimum gray value ZminAnd the maximum gray value ZmaxIn between, the gray value Z of the central pixel is judgedxyWhether or not it is at the minimum gray value ZminAnd the maximum gray value ZmaxTo (c) to (d);
the filter area judging unit is used for judging whether the expanded filter area is smaller than a preset area threshold value or not;
the gray scale adjusting unit is used for adjusting the gray scale value Z of the central pixelxyNot at the minimum grey value ZminAnd the maximum gray value ZmaxWhen the filter area between or after the expansion is not less than the preset area threshold value, the gray value of the central pixel is adjusted to be the gray median value Zmed。
4. The system for diagnosing partial discharge of switching equipment according to claim 2, further comprising a threshold segmentation module and an edge processing module;
the threshold segmentation module is used for performing threshold segmentation on the output image to obtain an output segmentation image;
and the edge processing module is used for carrying out edge processing on the transformed sub-image through a Canny operator to obtain an edge sub-image.
5. A method for diagnosing the partial discharge diagnostic system of the switching equipment according to claim 1, comprising the steps of:
step 100: providing an original gray level image;
step 200: carrying out shear wave transformation on the original gray level image to obtain a high-frequency subgraph and a low-frequency subgraph;
step 300: carrying out primary filtering on the high-frequency subgraph, and removing Gaussian noise in the high-frequency subgraph to obtain a de-noised high-frequency subgraph;
step 400: carrying out shear wave inverse transformation on the denoised high-frequency subgraph and the denoised low-frequency subgraph to obtain a reconstructed image;
step 500: and carrying out secondary filtering on the reconstructed image to remove salt and pepper noise in the reconstructed image so as to obtain an output image.
6. The method for diagnosing system for diagnosing partial discharge of switch-type equipment as claimed in claim 5, wherein said step 300 comprises the sub-steps of:
step 301: setting a preprocessing window in the region where the high-frequency subgraph is located;
step 302: setting 4 square processing areas in the area where the preprocessing window is located;
step 303: respectively carrying out Fourier transform of the third-order accumulation quantity on each processing region to obtain bispectrum amplitude values and bispectrum phase values corresponding to all high-frequency sub-image pixel points in each processing region;
step 304: summing all the bispectrum amplitude values and bispectrum phase values in each processing area respectively to obtain bispectrum total amplitude values and bispectrum total phase values of each processing area;
step 305: selecting a processing area with the minimum bispectrum total amplitude value, and respectively averaging the bispectrum total amplitude value and the bispectrum total phase value to obtain an output bispectrum amplitude value and an output bispectrum phase value;
step 306: and performing Fourier inverse transformation of the third-order accumulation quantity on the output bispectrum amplitude value and the output bispectrum phase value to obtain a denoising high-frequency subgraph.
7. The method for diagnosing system for diagnosing partial discharge of switch-type equipment as claimed in claim 5, wherein said step 500 comprises the sub-steps of:
step 501: setting filter regions in the region of the reconstructed image, wherein each filter region comprises a reconstructed pixel point, and each reconstructed pixel point comprises a central pixel and an edge pixel; the central pixel is located in the center of the filter area;
step 502: obtaining a minimum grey value Z within a filter areaminMaximum gray value ZmaxAnd median value of gray Zmed；
Step 503: judging the median Z of the gray scalemedWhether or not it is at the minimum gray value ZminAnd the maximum gray value ZmaxTo (c) to (d);
if median value of gray scale ZmedNot at the minimum grey value ZminAnd the maximum gray value ZmaxExpanding the filter area to the periphery of the filter area according to a preset proportion, and then judging whether the expanded filter area is smaller than a preset area threshold value or not; if the expanded filter region is smaller than the preset region threshold, execute step 502, otherwise, determine the gray level of the central pixelAdjusted to the median value of gray level Zmed；
If median value of gray scale ZmedAt the minimum gray value ZminAnd the maximum gray value ZmaxIn between, the gray value Z of the central pixel is judgedxyWhether or not it is at the minimum gray value ZminAnd the maximum gray value ZmaxTo (c) to (d); if the gray value Z of the central pixelxyAt the minimum gray value ZminAnd the maximum gray value ZmaxOtherwise, adjusting the gray value of the central pixel to the median value Zmed。
8. The method for diagnosing the partial discharge diagnostic system of the switching equipment according to claim 5, wherein the step 100 is preceded by the steps of: and pre-establishing a mapping relation between the original gray image and the equipment ID.
9. The method for diagnosing the partial discharge diagnostic system of the switching equipment according to claim 5, wherein the step 500 is followed by the steps of:
step 601: performing threshold segmentation on the output image to obtain an output segmented image;
step 602: carrying out shear wave transformation on the output segmentation image to obtain a transformation subimage;
step 603: performing edge processing on the transformed sub-image through a Canny operator to obtain an edge sub-image;
step 604: carrying out shear wave inverse transformation on the edge sub-image to obtain an edge image; extracting characteristic parameters of the edge image; judging whether the characteristic parameters exceed a preset threshold value or not; if so, acquiring the equipment ID with the partial discharge risk according to the mapping relation and the original gray level image corresponding to the characteristic parameters; and sending an early warning signal to an operator according to the characteristic parameters and the equipment ID.
10. The method for diagnosing a partial discharge diagnostic system of a switching device according to claim 9, wherein the extracting the feature parameters of the edge image in step 604 specifically includes: counting the number value of impurity pixels corresponding to the impurities of the edge image; and calculating the area S, the perimeter L and the roundness C of the corresponding impurities according to the number value of the impurity pixels.
Applications Claiming Priority (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110203029X | 2021-02-23 | ||
| CN202110203029 | 2021-02-23 |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113379671A true CN113379671A (en) | 2021-09-10 |
Family
ID=77570033
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110399286.5A Pending CN113379671A (en) | 2021-02-23 | 2021-04-14 | Partial discharge diagnosis system and diagnosis method for switch equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113379671A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113989509A (en) * | 2021-12-27 | 2022-01-28 | 衡水学院 | Crop insect pest detection method, crop insect pest detection system and crop insect pest detection equipment based on image recognition |
| CN116701842A (en) * | 2023-05-24 | 2023-09-05 | 国网江苏省电力有限公司南京供电分公司 | Partial discharge signal denoising method and device, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101070832B1 (en) * | 2011-07-22 | 2011-10-10 | 김영일 | A method for detecting an abnormality of distributing board |
| WO2014066231A1 (en) * | 2012-10-26 | 2014-05-01 | Siemens Healthcare Diagnostics Inc. | Cell identification method and device, and urine analyzer |
| CN111178388A (en) * | 2019-12-05 | 2020-05-19 | 上海交通大学 | Partial discharge phase distribution detection method based on NSCT photoelectric fusion atlas |
| CN111724315A (en) * | 2020-05-09 | 2020-09-29 | 中国人民解放军63686部队 | Infrared image noise removing method based on self-adaptive weighted median filtering |
-
2021
- 2021-04-14 CN CN202110399286.5A patent/CN113379671A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR101070832B1 (en) * | 2011-07-22 | 2011-10-10 | 김영일 | A method for detecting an abnormality of distributing board |
| WO2014066231A1 (en) * | 2012-10-26 | 2014-05-01 | Siemens Healthcare Diagnostics Inc. | Cell identification method and device, and urine analyzer |
| CN111178388A (en) * | 2019-12-05 | 2020-05-19 | 上海交通大学 | Partial discharge phase distribution detection method based on NSCT photoelectric fusion atlas |
| CN111724315A (en) * | 2020-05-09 | 2020-09-29 | 中国人民解放军63686部队 | Infrared image noise removing method based on self-adaptive weighted median filtering |
Non-Patent Citations (1)
| Title |
|---|
| 王涤等: "基于P-CNN 的局部放电绝缘故障融合诊断", 《高电压技术》, vol. 46, no. 8, 31 August 2020 (2020-08-31), pages 2897 - 2905 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113989509A (en) * | 2021-12-27 | 2022-01-28 | 衡水学院 | Crop insect pest detection method, crop insect pest detection system and crop insect pest detection equipment based on image recognition |
| CN113989509B (en) * | 2021-12-27 | 2022-03-04 | 衡水学院 | Crop insect pest detection method, crop insect pest detection system and crop insect pest detection equipment based on image recognition |
| CN116701842A (en) * | 2023-05-24 | 2023-09-05 | 国网江苏省电力有限公司南京供电分公司 | Partial discharge signal denoising method and device, electronic equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109035166B (en) | Electrical equipment infrared image enhancement method based on non-subsampled shear wave transformation | |
| Liu et al. | A no-reference metric for perceived ringing artifacts in images | |
| CN108921800B (en) | Non-local mean denoising method based on shape self-adaptive search window | |
| Feng et al. | Measurement of ringing artifacts in JPEG images | |
| CN106780486B (en) | Steel plate surface defect image extraction method | |
| CN110895806A (en) | Method and system for detecting screen display defects | |
| CN113379671A (en) | Partial discharge diagnosis system and diagnosis method for switch equipment | |
| CN112991297B (en) | Power transmission line fault diagnosis method, system, electronic equipment and storage medium | |
| CN109544464A (en) | A kind of fire video image analysis method based on contours extract | |
| CN115375588B (en) | Power grid transformer fault identification method based on infrared imaging | |
| CN106023204A (en) | Method and system for removing mosquito noise based on edge detection algorithm | |
| CN108564597A (en) | A kind of video foreground target extraction method of fusion gauss hybrid models and H-S optical flow methods | |
| CN112070717B (en) | Power transmission line icing thickness detection method based on image processing | |
| CN101123683A (en) | Restraint method for SAR image spot noise combining visual light image information | |
| CN111311508B (en) | Noise reduction method for pavement crack image with noise | |
| CN106254723B (en) | A kind of method of real-time monitoring video noise interference | |
| CN114778574A (en) | Method for detecting and identifying internal defects of in-transit high-voltage cable through X-ray digital imaging | |
| CN102118547A (en) | Image weighted filtering method | |
| Chen et al. | Edge preservation ratio for image sharpness assessment | |
| CN110348442A (en) | A kind of shipborne radar image sea oil film recognition methods based on support vector machines | |
| Barland et al. | Blind quality metric using a perceptual importance map for JPEG-20000 compressed images | |
| CN106846262B (en) | Method and system for removing mosquito noise | |
| CN111598794A (en) | Image imaging method and device for removing underwater overlapping condition | |
| Ahmed | Image enhancement and noise removal by using new spatial filters | |
| CN102622731B (en) | Contourlet domain Wiener filtering image denoising method based on two-dimensional Otsu |
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 |