CN115358951A - Intelligent ring main unit monitoring system based on image recognition - Google Patents
Intelligent ring main unit monitoring system based on image recognition Download PDFInfo
- Publication number
- CN115358951A CN115358951A CN202211276445.3A CN202211276445A CN115358951A CN 115358951 A CN115358951 A CN 115358951A CN 202211276445 A CN202211276445 A CN 202211276445A CN 115358951 A CN115358951 A CN 115358951A
- Authority
- CN
- China
- Prior art keywords
- noise
- monitoring
- type
- noise reduction
- main 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.)
- Granted
Links
- 238000012544 monitoring process Methods 0.000 title claims abstract description 106
- 230000009467 reduction Effects 0.000 claims abstract description 89
- 238000012545 processing Methods 0.000 claims abstract description 51
- 238000000034 method Methods 0.000 claims abstract description 14
- 230000005540 biological transmission Effects 0.000 claims abstract description 12
- 230000007547 defect Effects 0.000 claims description 16
- 150000001875 compounds Chemical class 0.000 claims description 8
- 238000001914 filtration Methods 0.000 claims description 5
- 230000002146 bilateral effect Effects 0.000 claims description 4
- 239000013307 optical fiber Substances 0.000 claims 1
- 230000008569 process Effects 0.000 abstract description 6
- 238000000354 decomposition reaction Methods 0.000 description 9
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000032683 aging Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 239000002184 metal Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229910052755 nonmetal Inorganic materials 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 238000003672 processing method Methods 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
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- 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
- G06V10/70—Arrangements for image or video recognition or understanding using pattern recognition or machine learning
- G06V10/764—Arrangements for image or video recognition or understanding using pattern recognition or machine learning using classification, e.g. of video objects
-
- 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
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30232—Surveillance
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Artificial Intelligence (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an intelligent ring main unit monitoring system based on image recognition, which comprises a shooting module, a transmission module and a monitoring module, wherein the shooting module is used for shooting a picture; the shooting module is used for acquiring a monitoring image of equipment inside the ring main unit; the transmission module is used for transmitting the monitoring image to the monitoring module; the monitoring module is used for processing the monitoring image as follows to obtain a first monitoring result: carrying out noise monitoring on the monitoring image to obtain noise pixel points; carrying out noise reduction processing on the noise pixel points according to the position types of the noise pixel points to obtain noise reduction images; and carrying out image identification processing on the noise reduction image to obtain a first monitoring result. In the process of monitoring the ring main unit, when the noise reduction processing is carried out on the monitoring image, the type of the noise pixel point is judged firstly, and then the corresponding noise reduction function is selected according to the type of the noise pixel point for carrying out the noise reduction processing, so that the accuracy of the noise reduction result is effectively improved, and the accuracy of the monitoring result for monitoring the ring main unit is improved.
Description
Technical Field
The invention relates to the technical field of image monitoring, in particular to an intelligent ring main unit monitoring system based on image identification.
Background
The ring main unit is a group of high-voltage switch equipment for power transmission and distribution, which is installed in a metal or nonmetal insulation cabinet or is made into a ring main power supply unit with assembly intervals. The device has the advantages of simple structure, small occupied space, low price, capability of effectively guaranteeing power supply safety and the like. The ring main unit is widely applied to distribution stations and transformer substations in houses, buildings, factories and other places.
In the prior art, when monitoring the ring main unit, because the contact sensors such as the temperature sensor can only monitor the contact part and cannot monitor cracks, aging and the like, when monitoring the running state of the ring main unit, a camera is also adopted for monitoring, and whether the running state of the ring main unit is abnormal or not is judged by analyzing the obtained images.
When the monitoring image in the acquired ring main unit is processed, the conventional ring main unit monitoring system generally adopts a single noise reduction mode to reduce noise, and the difference of the positions of noise pixel points is not considered, so that the noise reduction result is not accurate enough, and the accuracy of the monitoring result is influenced.
Disclosure of Invention
The invention aims to disclose an intelligent ring main unit monitoring system based on image recognition, which solves the problems that in the prior art, when a ring main unit is monitored, a single noise reduction mode is adopted to perform noise reduction processing on a monitored image, and the difference of positions of noise pixel points is not considered, so that the noise reduction result is not accurate enough, and the accuracy of the monitoring result is influenced.
In view of this, the invention provides an intelligent ring main unit monitoring system based on image recognition, which comprises a shooting module, a transmission module and a monitoring module;
the shooting module is used for acquiring a monitoring image of equipment inside the ring main unit;
the transmission module is used for transmitting the monitoring image to the monitoring module;
the monitoring module is used for processing the monitoring image as follows to obtain a first monitoring result:
carrying out noise monitoring on the monitoring image to obtain noise pixel points;
carrying out noise reduction processing on the noise pixel points according to the position types of the noise pixel points to obtain noise reduction images;
and carrying out image identification processing on the noise reduction image to obtain a first monitoring result.
Preferably, the intelligent ring main unit monitoring system based on image recognition further comprises a sensor module;
the sensor module is used for acquiring monitoring data of equipment inside the ring main unit.
Preferably, the transmission module is further configured to transmit the monitoring data to a monitoring module.
Preferably, the monitoring data includes temperature, humidity and current.
Preferably, the monitoring module is further configured to analyze the monitoring data to obtain a second monitoring result.
Preferably, the performing noise reduction processing on the noise pixel point according to the position type of the noise pixel point to obtain a noise-reduced image includes:
judging the position type of the noise pixel point;
and respectively carrying out noise reduction processing on each noise pixel point by adopting the following modes to obtain a noise reduction image:
if the position type of the noise pixel point is the first type, carrying out noise reduction treatment on the noise pixel point by using the following mode:
in the formula (I), the compound is shown in the specification,
representing noisy pixels
In the central position of the device, the device is,
a set of pixel values for pixel points within the size range,
express get
The middle value of the element(s) in (b),
representing the noise pixel point with the first type of position after noise reduction processing
Pixel values in the noise-reduced image;
if the position type of the noise pixel point is the second type, carrying out noise reduction treatment on the noise pixel point by using the following mode:
in the formula (I), the compound is shown in the specification,
representing the noise pixel point with the position type of the second type after the noise reduction processing is carried out
Pixel values in the noise-reduced image;
、
respectively represent a preset weight parameter,
；
representation Using non-local mean Filter Algorithm pairs
After the noise reduction treatment is carried out,
the value of the pixel of (a) is,
representing bilateral filtering algorithm pairs
After the noise reduction treatment is carried out,
a pixel value of (a);
if the position type of the noise pixel point is the third type, noise reduction processing is carried out on the noise pixel point by using a self-adaptive wavelet noise reduction algorithm, and the noise pixel point with the position type of the third type is obtained after the noise reduction processing is carried out
Pixel values in the noise-reduced image.
Preferably, the determining the position type of the noise pixel point includes:
if only one noise pixel point exists in the pixels with the radius of Q and no edge pixel point exists in the range with the noise pixel point as the circle center, the position type of the noise pixel point is a first type;
if the number of the noise pixel points in the pixel points with the radius of Q is smaller than Thre1 and the number of the edge pixel points is smaller than Thre2 by taking the noise pixel points as the circle center, the position type of the noise pixel points is a second type;
and if the number of the noise pixel points in the pixel points with the radius of Q is more than or equal to Thre1 and the number of the edge pixel points is more than or equal to Thre2 by taking the noise pixel points as the circle center, the position type of the noise pixel points is a third type.
Preferably, the first monitoring result indicates that the equipment inside the ring main unit has a first type of defect or does not have the first type of defect.
Preferably, the second monitoring result indicates that the equipment inside the ring main unit has a defect of a second type or does not have a defect of a second type.
According to the technical scheme, the invention has the following advantages:
in the process of monitoring the ring main unit, when the noise reduction processing is carried out on the monitoring image, the type of the noise pixel point is judged firstly, and then the corresponding noise reduction function is selected according to the type of the noise pixel point for carrying out the noise reduction processing.
Drawings
Fig. 1 is a schematic structural diagram of an intelligent ring main unit monitoring system based on image recognition according to an embodiment of the present invention;
fig. 2 is another schematic structural diagram of an intelligent ring main unit monitoring system based on image recognition according to an embodiment of the present invention.
Detailed Description
In order to make those skilled in the art better understand the technical solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
For convenience of understanding, please refer to fig. 1, the intelligent ring main unit monitoring system based on image recognition provided by the present invention includes a shooting module, a transmission module and a monitoring module;
the shooting module is used for acquiring a monitoring image of equipment inside the ring main unit;
the transmission module is used for transmitting the monitoring image to the monitoring module;
the monitoring module is used for processing the monitoring image as follows to obtain a first monitoring result:
carrying out noise monitoring on the monitoring image to obtain noise pixel points;
carrying out noise reduction processing on the noise pixel points according to the position types of the noise pixel points to obtain noise reduction images;
and carrying out image recognition processing on the noise reduction image to obtain a first monitoring result.
In the process of monitoring the ring main unit, when the noise reduction processing is carried out on the monitoring image, the type of the noise pixel point is judged firstly, and then the corresponding noise reduction function is selected according to the type of the noise pixel point for carrying out the noise reduction processing.
In a specific embodiment, as shown in fig. 2, the intelligent ring main unit monitoring system based on image recognition further includes a sensor module;
the sensor module is used for acquiring monitoring data of equipment inside the ring main unit.
In particular, the sensor module mainly acquires monitoring data, such as current, voltage and the like, which can be obtained only by contact. Or the temperature, the humidity and the like in the ring main unit.
In a specific embodiment, the transmission module is further configured to transmit the monitoring data to a monitoring module.
In a specific embodiment, the monitoring data includes temperature, humidity, and current.
In a specific embodiment, the monitoring module is further configured to analyze the monitoring data to obtain a second monitoring result.
In a specific embodiment, the performing noise reduction processing on the noise pixel according to the position type of the noise pixel to obtain a noise-reduced image includes:
judging the position type of the noise pixel point;
and respectively carrying out noise reduction processing on each noise pixel point by adopting the following modes to obtain a noise reduction image:
if the position type of the noise pixel point is the first type, carrying out noise reduction treatment on the noise pixel point by using the following mode:
in the formula (I), the compound is shown in the specification,
representing pixels by noise
In the central position of the device, the device is,
a set of pixel values for pixel points within a range of sizes,
show to get
The middle value of the element(s) in (b),
representing the noise pixel point with the first type of position after the noise reduction treatment
Pixel values in the noise-reduced image;
if the position type of the noise pixel point is the second type, carrying out noise reduction treatment on the noise pixel point by using the following mode:
in the formula (I), the compound is shown in the specification,
representing the noise pixel point with the position type of the second type after the noise reduction treatment is carried out
Pixel values in the noise-reduced image;
、
respectively, represent a preset weight parameter that is,
；
representation Using non-local mean Filter Algorithm pairs
After the noise reduction treatment is carried out,
the value of the pixel of (a) is,
representing bilateral filtering algorithm pairs
After the noise reduction treatment is carried out,
the pixel value of (a);
if the position type of the noise pixel point is a third type, noise reduction processing is carried out on the noise pixel point by using a self-adaptive wavelet denoising algorithm, and the noise pixel point with the position type of the third type is obtained after the noise reduction processing is carried out
Pixel values in the noise-reduced image.
When the noise reduction processing is carried out, the noise pixel points are classified according to the position types, then different noise reduction processing modes are selected for the noise pixel points of each position type for noise reduction processing, and the accuracy of the noise reduction processing result can be effectively improved. The existing noise reduction processing generally uses the same noise reduction method to perform noise reduction processing on all pixel points, and a single noise reduction processing method cannot adapt to the diversity of noise pixel point types, so that the noise reduction result is not accurate enough, and the pixel value of an edge pixel point in an image is easily reduced mistakenly, so that the detail information contained in the noise-reduced image is influenced.
Specifically, for the noise pixel point of the first type, because no other noise pixel point exists nearby and no edge pixel point is included, the noise pixel point of the first type is subjected to noise reduction processing by adopting a mode of taking an intermediate value, and an accurate noise reduction result can be quickly obtained.
For the second type of noise pixel points, because a small number of noise pixel points and a small number of edge pixel points are possibly included, the method adopts a mode of combining non-local mean noise reduction and bilateral filtering noise reduction to perform value reduction processing, and the final noise reduction result is obtained by weighting the results of the two noise reduction algorithms. Therefore, the detail information of the edge is reserved, and effective noise reduction processing is realized.
For the third type of noise pixel points, because the number of the noise pixel points and the number of the edge pixel points are more, the conventional noise reduction mode cannot achieve the balance between detail preservation and effective noise reduction, and therefore the method adopts a self-adaptive wavelet noise reduction mode to perform effective noise reduction processing.
In a specific embodiment, the denoising processing is performed on the noise pixel points by using an adaptive wavelet denoising algorithm, which includes:
the method takes the noise pixel point as the center,
regional images composed of pixels within the size range;
performing Q-layer wavelet decomposition processing on the regional image to obtain 1 wavelet low-frequency coefficient and Q wavelet high-frequency coefficient;
performing denoising treatment on each wavelet high-frequency coefficient respectively by adopting the following mode to obtain denoised wavelet high-frequency coefficients:
and (3) for the wavelet high-frequency coefficient of the q-th layer, q belongs to [1, Q ], carrying out denoising treatment to obtain the wavelet high-frequency coefficient of the q-th layer after denoising:
if it is
Then, the q-th layer wavelet high frequency coefficient is processed by using the following function
And (3) carrying out noise reduction treatment:
if it is
Then, the q-th layer wavelet high frequency coefficient is processed by using the following function
And (3) carrying out noise reduction treatment:
in the formula (I), the compound is shown in the specification,
wavelet high frequency coefficients representing the denoised q-th layer,
representing the q-th layer wavelet high frequency coefficients before denoising,
a function of the sign is represented by,
the parameters of the index are represented by,
，
represents a preset first constant coefficient that is,
the value of the adaptive threshold is represented by,
，
representing the variance of the noise estimate made on the region image,
represents a second constant parameter; p represents a preset proportion parameter, and belongs to (0, 1);
performing wavelet reconstruction based on the wavelet low-frequency coefficient and Q denoised wavelet high-frequency coefficients to obtain a denoised region image, and taking the pixel value of the pixel point at the corresponding position of the noise pixel point in the denoised region image as the pixel value for performing wavelet reconstructionAfter the noise reduction treatment, the position type is the noise pixel point of the third type
Pixel values in the noise-reduced image.
When denoising, the invention determines the number of layers of wavelet decomposition in a self-adaptive mode, then performs denoising layer by adopting a reverse denoising processing mode starting from a wavelet high-frequency function with the number of layers, and finally performs wavelet reconstruction to obtain a final denoising result. In the process of denoising, the invention sets the self-adaptive threshold value which can be self-adaptively changed along with the change of the layer number, thereby respectively generating the corresponding threshold values for the wavelet high-frequency coefficients of different layers. The self-adaptive threshold value can select different processing functions for the wavelet high-level coefficients in different states to perform denoising, and the accuracy of a denoising result is effectively improved.
In one embodiment, the number of layers of the wavelet decomposition is determined as follows:
respectively calculating the quality parameters of the t-th layer wavelet high-frequency coefficient and the t + 1-th layer wavelet high-frequency coefficient
And
；
if it is
Stopping wavelet decomposition of the t +1 th layer wavelet low-frequency coefficient to obtain the number of layers t +1 of wavelet decomposition,
if it is
And continuing to perform wavelet decomposition on the wavelet low-frequency coefficients of the t +1 th layer.
Is a preset comparison threshold。
The layer number of the invention is adaptively determined according to the actual pixel value distribution of the image, thereby avoiding the processing of the problem of insufficient noise reduction or noise reduction transition caused by manual pre-designation and being beneficial to improving the accuracy of the noise reduction result. When the difference between the wavelet high-frequency coefficients of two adjacent layers is smaller than a comparison threshold value, the wavelet decomposition is in place, and the wavelet decomposition is stopped immediately at the moment, so that decomposition transition is avoided, the calculation efficiency is prevented from being influenced, and the noise is reduced excessively.
In one embodiment, the quality parameter is for the t-th layer wavelet high frequency coefficient
The following formula is used for calculation:
in the formula (I), the compound is shown in the specification,
the scale factor is expressed in terms of a ratio,
，
represents the collection of pixel points in the t-th layer wavelet high frequency coefficient,
to represent
The pixel value of the pixel point j in (a),
to represent
The number of the pixel points in (1),
to represent
The maximum value of the pixel point in (1).
The quality parameter is mainly calculated from two aspects of the distribution uniformity degree of the pixel values and the upper limit of the pixel values, and the larger the quality parameter is, the more uniform the distribution of the pixel values of the wavelet high-frequency coefficient representing the current layer number is.
In a specific embodiment, the determining the position type of the noise pixel includes:
if only one noise pixel point exists in the pixel points within the range with the radius of Q and no edge pixel point exists in the pixel points with the noise pixel points as the circle centers, the position type of the noise pixel point is a first type;
if the number of noise pixel points in the pixel points within the radius of Q is smaller than Thre1 and the number of edge pixel points is smaller than Thre2 by taking the noise pixel points as the circle centers, the position type of the noise pixel points is a second type;
and if the number of the noise pixel points in the pixel points with the radius of Q is more than or equal to Thre1 and the number of the edge pixel points is more than or equal to Thre2 by taking the noise pixel points as the circle center, the position type of the noise pixel points is a third type.
Where, thread 1 and thread 2 represent a preset first quantity threshold and a second quantity threshold, respectively.
In a specific embodiment, the first monitoring result indicates that the equipment inside the ring main unit has a first type of defect or does not have the first type of defect.
Specifically, if the monitored data exceeds the set numerical range, it indicates that the first type of defect exists.
In a specific embodiment, the second monitoring result indicates that the equipment inside the ring main unit has the defect of the second type or does not have the defect of the second type.
Specifically, if the noise-reduced image has a problem such as a crack or aging after the image recognition processing, it indicates that the second type of defect exists.
In a specific embodiment, the intelligent ring main unit monitoring system based on image recognition further comprises an alarm module;
the alarm module is used for sending an alarm prompt to an operator on duty when the first monitoring result indicates that the equipment in the ring main unit has the first type of defect and/or the second monitoring result indicates that the equipment in the ring main unit has the second type of defect.
It is clear to those skilled in the art that, for convenience and brevity of description, the specific working processes of the above-described systems, apparatuses and units may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
In the embodiments provided in the present invention, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described apparatus embodiments are merely illustrative, and for example, the division of the units is only one logical division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another system, or some features may be omitted, or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
The units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present invention may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit may be implemented in the form of hardware, or may also be implemented in the form of a software functional unit.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (9)
1. An intelligent ring main unit monitoring system based on image recognition is characterized by comprising a shooting module, a transmission module and a monitoring module;
the shooting module is used for acquiring a monitoring image of equipment inside the ring main unit;
the transmission module is used for transmitting the monitoring image to the monitoring module;
the monitoring module is used for processing the monitoring image as follows to obtain a first monitoring result:
carrying out noise monitoring on the monitoring image to obtain noise pixel points;
carrying out noise reduction processing on the noise pixel points according to the position types of the noise pixel points to obtain noise reduction images;
and carrying out image identification processing on the noise reduction image to obtain a first monitoring result.
2. The intelligent ring main unit monitoring system based on image recognition as claimed in claim 1, further comprising a sensor module;
the sensor module is used for acquiring monitoring data of equipment inside the ring main unit.
3. The intelligent ring main unit monitoring system based on image recognition as claimed in claim 2, wherein the transmission module is further configured to transmit the monitoring data to the monitoring module.
4. The intelligent ring main unit monitoring system based on image recognition as claimed in claim 2, wherein the monitoring data includes temperature, humidity and current.
5. The intelligent ring main unit monitoring system based on image recognition as claimed in claim 3, wherein the monitoring module is further configured to analyze the monitoring data to obtain a second monitoring result.
6. The intelligent ring main unit monitoring system based on image recognition according to claim 1, wherein the noise reduction processing is performed on the noise pixel points according to the position types of the noise pixel points to obtain a noise-reduced image, and the method comprises the following steps:
judging the position type of the noise pixel point;
and respectively carrying out noise reduction processing on each noise pixel point by adopting the following modes to obtain a noise reduction image:
if the position type of the noise pixel point is the first type, carrying out noise reduction treatment on the noise pixel point by using the following mode:
in the formula (I), the compound is shown in the specification,
representing pixels by noise
The number of the optical fibers is the center,
a set of pixel values for pixel points within a range of sizes,
show to get
The middle value of the element(s) in (b),
representing the noise pixel point with the first type of position after the noise reduction treatment
Pixel values in the noise-reduced image;
if the position type of the noise pixel point is a second type, carrying out noise reduction treatment on the noise pixel point by using the following method:
in the formula (I), the compound is shown in the specification,
representing the noise pixel point with the position type of the second type after the noise reduction processing is carried out
Pixel values in the noise-reduced image;
、
respectively, represent a preset weight parameter that is,
；
representing using non-local mean filtering algorithmsTo pair
After the noise reduction treatment is carried out,
the value of the pixel of (a) is,
representing bilateral filtering algorithm pairs
After the noise reduction treatment is carried out,
the pixel value of (a);
if the position type of the noise pixel point is the third type, noise reduction processing is carried out on the noise pixel point by using a self-adaptive wavelet noise reduction algorithm, and the noise pixel point with the position type of the third type is obtained after the noise reduction processing is carried out
Pixel values in the noise-reduced image.
7. The system according to claim 6, wherein the determining the position type of the noise pixel point comprises:
if only one noise pixel point exists in the pixels with the radius of Q and no edge pixel point exists in the range with the noise pixel point as the circle center, the position type of the noise pixel point is a first type;
if the number of noise pixel points in the pixel points within the radius of Q is smaller than Thre1 and the number of edge pixel points is smaller than Thre2 by taking the noise pixel points as the circle centers, the position type of the noise pixel points is a second type;
and if the number of the noise pixel points in the pixel points with the radius of Q is more than or equal to Thre1 and the number of the edge pixel points is more than or equal to Thre2 by taking the noise pixel points as the circle center, the position type of the noise pixel points is a third type.
8. The intelligent ring main unit monitoring system based on image recognition as claimed in claim 1, wherein the first monitoring result is that the equipment inside the ring main unit has a defect of a first type or does not have a defect of a first type.
9. The intelligent ring main unit monitoring system based on image recognition as claimed in claim 1, wherein the second monitoring result is that the equipment inside the ring main unit has a defect of a second type or does not have a defect of a second type.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211276445.3A CN115358951B (en) | 2022-10-19 | 2022-10-19 | Intelligent ring main unit monitoring system based on image recognition |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211276445.3A CN115358951B (en) | 2022-10-19 | 2022-10-19 | Intelligent ring main unit monitoring system based on image recognition |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115358951A true CN115358951A (en) | 2022-11-18 |
| CN115358951B CN115358951B (en) | 2023-01-24 |
Family
ID=84008668
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211276445.3A Active CN115358951B (en) | 2022-10-19 | 2022-10-19 | Intelligent ring main unit monitoring system based on image recognition |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115358951B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116862918A (en) * | 2023-09-05 | 2023-10-10 | 浙江奔月电气科技有限公司 | Real-time detection method for condensation inside ring main unit based on artificial intelligence |
| CN117351276A (en) * | 2023-09-28 | 2024-01-05 | 国网江苏省电力有限公司南通供电分公司 | Intelligent monitoring method and system for ring main unit |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008060870A (en) * | 2006-08-31 | 2008-03-13 | Sharp Corp | Noise-reduced digital image signal processor |
| CN101853499A (en) * | 2010-04-30 | 2010-10-06 | 浙江大学 | Clear picture synthesis method based on detail detection |
| CN111325694A (en) * | 2020-02-25 | 2020-06-23 | 深圳市景阳科技股份有限公司 | Image noise removing method and device |
| CN112016420A (en) * | 2020-08-19 | 2020-12-01 | 云南电网有限责任公司临沧供电局 | Ring main unit video image identification system and method |
| CN112150371A (en) * | 2019-06-28 | 2020-12-29 | 浙江宇视科技有限公司 | Image noise reduction method, device, equipment and storage medium |
| CN112614078A (en) * | 2020-12-30 | 2021-04-06 | 长春长光辰芯光电技术有限公司 | Image noise reduction method and storage medium |
| CN112630585A (en) * | 2020-11-06 | 2021-04-09 | 国网山东省电力公司济宁供电公司 | Distribution cable partial discharge live detection system and detection method |
| CN112782504A (en) * | 2020-12-29 | 2021-05-11 | 湖北铁能电气集团有限公司 | Ventilation cooling ring main unit fault diagnosis method |
-
2022
- 2022-10-19 CN CN202211276445.3A patent/CN115358951B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008060870A (en) * | 2006-08-31 | 2008-03-13 | Sharp Corp | Noise-reduced digital image signal processor |
| CN101853499A (en) * | 2010-04-30 | 2010-10-06 | 浙江大学 | Clear picture synthesis method based on detail detection |
| CN112150371A (en) * | 2019-06-28 | 2020-12-29 | 浙江宇视科技有限公司 | Image noise reduction method, device, equipment and storage medium |
| CN111325694A (en) * | 2020-02-25 | 2020-06-23 | 深圳市景阳科技股份有限公司 | Image noise removing method and device |
| CN112016420A (en) * | 2020-08-19 | 2020-12-01 | 云南电网有限责任公司临沧供电局 | Ring main unit video image identification system and method |
| CN112630585A (en) * | 2020-11-06 | 2021-04-09 | 国网山东省电力公司济宁供电公司 | Distribution cable partial discharge live detection system and detection method |
| CN112782504A (en) * | 2020-12-29 | 2021-05-11 | 湖北铁能电气集团有限公司 | Ventilation cooling ring main unit fault diagnosis method |
| CN112614078A (en) * | 2020-12-30 | 2021-04-06 | 长春长光辰芯光电技术有限公司 | Image noise reduction method and storage medium |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116862918A (en) * | 2023-09-05 | 2023-10-10 | 浙江奔月电气科技有限公司 | Real-time detection method for condensation inside ring main unit based on artificial intelligence |
| CN116862918B (en) * | 2023-09-05 | 2023-11-24 | 浙江奔月电气科技有限公司 | Real-time detection method for condensation inside ring main unit based on artificial intelligence |
| CN117351276A (en) * | 2023-09-28 | 2024-01-05 | 国网江苏省电力有限公司南通供电分公司 | Intelligent monitoring method and system for ring main unit |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115358951B (en) | 2023-01-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115358951B (en) | Intelligent ring main unit monitoring system based on image recognition | |
| CN110458839B (en) | Effective wire and cable monitoring system | |
| CN115345802B (en) | Remote monitoring method for operation state of electromechanical equipment | |
| CN1767638B (en) | Visible image monitoring method for protecting privacy right and its system | |
| CN112991297A (en) | Power transmission line fault diagnosis method and system, electronic equipment and storage medium | |
| CN107742301B (en) | Image classification-based power transmission line image processing method under complex background | |
| CN116012346B (en) | Power transmission line monitoring method and system | |
| CN115375588B (en) | Power grid transformer fault identification method based on infrared imaging | |
| CN108280386B (en) | Monitoring scene detection method and device | |
| CN113411573A (en) | Power grid monitoring system detection method and device, computer equipment and medium | |
| CN116567395A (en) | Security equipment linkage operation regulation and control method and computer storage medium | |
| CN116647643B (en) | Intelligent security monitoring system | |
| CN111161177A (en) | Image self-adaptive noise reduction method and device | |
| CN110570404A (en) | Sobel operator-based cloth defect detection method | |
| CN114596683A (en) | Intrusion detection method and device | |
| CN111192332A (en) | Smoke detection-based smoke machine control method and smoke machine | |
| CN113724167A (en) | Self-adaptive acquisition and image processing method for high-definition video information | |
| CN118366140A (en) | Method for detecting abnormal state of civil air defense door based on machine vision | |
| CN105447827A (en) | Image noise reduction method and system thereof | |
| CN103095967B (en) | A kind of video noise Quantitative Calculation Method and system | |
| CN111091108B (en) | Cable resistance detecting system | |
| CN113674271B (en) | Transformer monitoring system based on cloud computing | |
| CN106488079B (en) | A kind of method and device of video denoising | |
| CN116681703B (en) | Intelligent switch quality rapid detection method | |
| US20030016874A1 (en) | Image analyzing method for detecting significant changes in a time sequence of images |
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 |