CN110726725A - Transmission line hardware corrosion detection method and device - Google Patents
Transmission line hardware corrosion detection method and device Download PDFInfo
- Publication number
- CN110726725A CN110726725A CN201911013484.2A CN201911013484A CN110726725A CN 110726725 A CN110726725 A CN 110726725A CN 201911013484 A CN201911013484 A CN 201911013484A CN 110726725 A CN110726725 A CN 110726725A
- Authority
- CN
- China
- Prior art keywords
- image
- hardware
- transmission line
- corrosion
- power transmission
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- 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
- 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
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/194—Segmentation; Edge detection involving foreground-background segmentation
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- 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
- G06T2207/10024—Color 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
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20084—Artificial neural networks [ANN]
-
- 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
Abstract
The invention relates to a method and a device for detecting the corrosion of a power transmission line hardware fitting, wherein the method comprises the steps of firstly obtaining an image of the power transmission line, and processing the image to obtain a target hardware fitting image; then, carrying out segmentation processing on the obtained target hardware fitting image to obtain a foreground image and a background image; performing gamma conversion on the foreground image, and performing gray processing on the foreground image subjected to gamma conversion by adopting a hyper-red algorithm to obtain a gray image of the foreground image; and finally, determining the corrosion condition of the hardware according to the gray level image of the foreground image. The method and the device aim at performing gamma conversion on the foreground image to strengthen the hardware in the target hardware image, can adjust the influence of over-strong light or over-weak light on the hardware in the target hardware image, so as to more accurately judge the corrosion conditions such as the corrosion degree, the corrosion area and the like of the hardware, provide all-around corrosion defect information for operation and maintenance personnel, and provide an effective technical means for realizing intellectualization of electric power operation and maintenance.
Description
Technical Field
The invention belongs to the technical field of hardware corrosion detection, and particularly relates to a method and a device for detecting the hardware corrosion of a power transmission line.
Background
Power equipment is exposed in outdoor environment for a long time, is influenced by uncertain factors such as sunshine, rainwater, foreign matters, external force and the like, easily generates various equipment faults, and seriously influences the reliability of a power grid. The transmission line is used as an important ring of power transmission, and a large number of metal devices in the transmission line are easy to generate corrosion under the influence of rain and snow weather and water systems. The corrosion of the hardware has great influence on the power transmission performance and the safety of the circuit and becomes a serious potential safety hazard in the operation of a power grid. With the large-scale growth of power transmission lines, the traditional manual inspection mode cannot adapt to the development of power grids due to sudden increase of workload and detection precision and efficiency. In recent years, the computer vision technology is rapidly developed, an unmanned aerial vehicle is used for inspecting the power transmission line, and the aerial image is intelligently processed to form a new breakthrough of power grid operation inspection development.
The authors are a Master academic paper of Zhanghong talent, "helicopter patrol inspection electric transmission line rust defect identification method research", which improves the existing super green algorithm and provides a super red algorithm, and the graying formula is as follows: ExR (i, j) ═ 2.0R (i, j) -G (i, j) -B (i, j), ExR (x, y) is a super red color value, R (i, j), G (i, j) and B (i, j) are three-color component matrixes respectively, a super red color algorithm is applied to power transmission line corrosion detection to obtain a gray level image of the power transmission line, and binarization processing is carried out on the gray level image to determine the corrosion condition of the power transmission line. Due to the fact that the image shooting conditions of the power transmission line are different, the situations that the image is overexposed due to too strong light or the image is unclear and abnormal due to too weak light and even the target and the background cannot be clearly recognized often occur, and if the super red algorithm is directly adopted to conduct gray level processing on the image of the power transmission line, corrosion defect detection of the power transmission line is inaccurate.
Disclosure of Invention
The invention provides a method and a device for detecting the corrosion of a power transmission line hardware fitting, which are used for solving the problem that the detection of the corrosion defect of the power transmission line is inaccurate because the gray level processing is directly carried out on the image of the power transmission line in the prior art.
In order to solve the technical problems, the technical scheme and the beneficial effects of the invention are as follows:
the invention discloses a method for detecting the corrosion of a power transmission line hardware fitting, which comprises the following steps:
1) acquiring an image of the power transmission line, finding a target hardware fitting position, and cutting the image of the power transmission line according to the target hardware fitting position to obtain a target hardware fitting image; 2) carrying out segmentation processing on the obtained target hardware image to obtain a foreground image and a background image of the target hardware image; 3) performing gamma conversion on the foreground image to obtain a foreground image after gamma conversion; the gamma value of the gamma conversion is related to the average brightness value of the background image, the larger the average brightness value of the background image is, the larger the gamma value is, and the gamma value is greater than 1 when the average brightness value of the background image is greater than a set brightness threshold, wherein the set brightness threshold is greater than 100 and less than 150; 4) extracting red features of the foreground image after gamma conversion, and performing gray processing to obtain a gray image of the foreground image; 5) and determining the corrosion condition of the hardware according to the gray level image of the foreground image.
The beneficial effects are as follows: according to the method, the target hardware image is segmented to obtain the foreground image and the background image of the target hardware image, the gamma conversion is performed aiming at the foreground image, the hardware in the target hardware image is enhanced, the influence of over-strong light or over-weak light on the hardware in the target hardware image can be adjusted, so that the corrosion conditions such as the corrosion degree and the area of the hardware can be judged more accurately, all-around corrosion defect information is provided for operation and maintenance personnel, and an effective technical means is provided for realizing the intellectualization of electric power operation and maintenance. In addition, when the method performs gamma conversion on the foreground image, the gamma value of the method is related to the average brightness value of the background image and is unrelated to the average brightness value of the foreground image, the factors of the foreground image are discharged outside, the brightness degree of the foreground image is automatically adjusted in a self-adaptive mode according to the change of the external light environment, the subsequent gray level processing of the foreground image is facilitated, and the accuracy of the detection of the corrosion defect of the power transmission line is improved.
As a further improvement of the method, in order to eliminate the influence of various factors such as external noise, interference and the like in the power transmission line, the method further comprises the step of preprocessing the image of the power transmission line before finding the target hardware fitting position in the step 1); the pre-processing comprises at least one of the following image processing: the Gauss filter removes noise, color image histogram equalization and logarithmic transformation.
As a further improvement of the method, in order to accurately obtain the target hardware image, in step 1), the process of finding the target hardware position includes: acquiring a historical power transmission line image containing hardware fittings, and labeling the hardware fittings in the historical power transmission line image; constructing a neural network, and training the constructed neural network by using the historical power transmission line image marked with the hardware to obtain a target hardware detection model; and acquiring an image of the power transmission line, and inputting the image of the power transmission line into the hardware fitting target detection model to obtain the position of the target hardware fitting.
As a further improvement of the method, the neural network model is a deep convolutional neural network model.
As a further improvement of the method, in order to accurately obtain the foreground image and the background image of the target hardware image, in step 2), an interactive segmentation algorithm is adopted to perform segmentation processing on the obtained target hardware image.
As a further improvement of the method, in step 3), the γ value is a ratio of an average luminance value of the background image to the set brightness threshold.
As a further improvement of the method, in order to accurately judge the corrosion degree of the hardware, in step 5), the grayscale image of the foreground image is subjected to binarization processing to obtain the value of each pixel point in the grayscale image of the foreground image, so as to obtain the proportion of the area of a corrosion area in the grayscale image of the foreground image, which is the corrosion rate, and the corrosion condition of the hardware is determined according to the corrosion rate.
As a further improvement of the method, in order to accurately judge the corrosion area of the hardware and the corrosion degree of different areas, the gray value is divided into different levels, and each level corresponds to a thermal color; drawing a hardware successive rust thermodynamic diagram according to the color corresponding to the grade of the gray value of each pixel point in the foreground image; and determining the corrosion condition of the hardware according to the hardware successive corrosion thermodynamic diagram.
As a further improvement of the method, in step 4), a hyper-red algorithm is adopted to extract red features of the foreground image after gamma conversion.
The invention also provides a device for detecting the hardware corrosion of the power transmission line, which comprises a memory and a processor, wherein the processor is used for executing the instructions stored in the memory to realize the method and achieve the same effect as the method.
Drawings
FIG. 1 is a method flow diagram in a method embodiment of the invention;
FIG. 2 is a schematic representation of a Gamma transform in an embodiment of the method of the present invention;
fig. 3-1 is an image of a local transmission line inspection tour in an embodiment of the method of the present invention;
3-2 are images of target hardware in method embodiments of the invention;
FIG. 4-1 is a foreground image after image segmentation in an embodiment of the method of the present invention;
FIG. 4-2 is a background image after image segmentation in an embodiment of the method of the present invention;
FIG. 5 is an image of a foreground image after Gamma transformation in an embodiment of the method of the present invention;
FIG. 6 is a gray scale image after dark-red feature extraction in a method embodiment of the invention;
FIG. 7-1 is an image after the rust region binarization processing in the method embodiment of the present invention;
fig. 7-2 is a corrosion thermodynamic diagram derived for different corrosion confidences in an embodiment of the method of the present invention.
Detailed Description
The method comprises the following steps:
the embodiment provides a method for detecting corrosion of power transmission line hardware, and the method is described in detail below with reference to fig. 1.
Firstly, acquiring an image of the power transmission line, and performing normalization and equalization preprocessing on the image of the power transmission line to remove the influence of interference, noise and brightness on the image as shown in fig. 3-1. The image preprocessing comprises image enhancement algorithms such as Gauss filter noise removal, color image histogram equalization, logarithm transformation and the like.
And secondly, inputting the preprocessed power transmission line image into a target hardware fitting detection model to obtain the position of the target hardware fitting. After the hardware target position is obtained, the power transmission line image is cut to obtain a target hardware image (one or more small-sized images), as shown in fig. 3-2, so that the influence of a complex environment is eliminated, the calculation complexity of subsequent processing is reduced, and the accuracy of the subsequent processing is improved. The target hardware fitting detection model is constructed as follows:
1. a large number of historical transmission line images containing hardware are obtained, the hardware in the historical transmission line images are labeled and used as samples, 80% of the historical transmission line images can be used for training, and 20% of the historical transmission line images can be used for testing and verifying.
2. And constructing a fast R-CNN deep convolution neural network, and training the constructed neural network by using the sample to obtain a target hardware fitting detection model.
And thirdly, segmenting the target hardware image by adopting an interactive segmentation algorithm GrabCT algorithm to obtain a foreground image and a background image of the target hardware image, which are respectively shown in the figures 4-1 and 4-2.
Fourthly, the background image is converted from the RGB model to the HIS model, and the average value of all pixel points of the bright I channel (namely the average brightness value I of the background image) is calculatedmean) (ii) a Average brightness value I based on background imagemeanPerforming Gamma conversion (Gamma conversion) on the foreground image to complete the normalization of the image, wherein the Gamma-converted foreground image is as shown in fig. 5, such that the larger the average brightness value of the background image is, the larger the Gamma value of the Gamma conversion is, and the average brightness value I of the background image ismeanGreater than a set brightness threshold IsetThe gamma value is greater than 1. I issetThe value can range as follows: 100 < Iset< 150. Specifically, the method comprises the following steps:
1. the pixel value I (i.j) of each pixel point of the I channel and the average brightness value I of the background imagemeanRespectively as follows:
in the formula, R (i, j), G (i, j), and B (i, j) are pixel values of three color channels of the foreground image, respectively, and k is the number of all pixels with brightness different from 0.
2. Gamma transformation is a nonlinear operation performed on the gray value of an input image, so that the gray value of the output image and the gray value of the input image are in an exponential relationship:
y＝xγ
in the formula, γ is a normal number, and the input and output relationship curves of different γ values are shown in fig. 2: when gamma is larger than 1, the gray scale of a brighter area is stretched, the gray scale of a darker area is compressed to be darker, and the whole image becomes dark; when γ <1, the gray scale of the bright area is compressed, the gray scale of the dark area is stretched to be bright, and the whole image becomes bright.
Setting IsetIf the average brightness value of the background image is more than 128, reducing the brightness of the foreground image by using Gamma transformation; similarly, if the average brightness value of the background image is less than 128, the brightness of the foreground image is improved by using Gamma transformation, that is:
because the corrosion condition of the foreground image is unknown, for example, when the light of the external environment is too bright, if the hardware is not corroded, the hardware is overexposed, if the hardware is corroded, the hardware cannot reflect light, and therefore the brightness of the light of the external environment cannot be overexposed, the average brightness value of the foreground image cannot truly reflect the brightness of the light of the external environment, and therefore in the step, the gamma conversion is performed on the foreground image based on the average brightness value of the background image instead of performing the gamma conversion on the foreground image by adopting the overall average brightness value of the image, or the gamma conversion is performed on the foreground image by adopting the average brightness value of the foreground image. That is, the light is too bright in the external environment, which causes the background of the target hardware image to be overexposed, so that the average pixel value of the background image of the target hardware image is too high, but since the hardware itself is corroded, the hardware itself cannot reflect light to cause overexposure, and the average pixel value of the foreground image of the target hardware image is lower than the average pixel value of the background image. In order to adjust the brightness of the foreground image according to the actual brightness of the light, in the above formula of the method, the gamma value of the gamma conversion is only related to the average pixel value of the background image, but not related to the average pixel value of the foreground image, so as to adjust the foreground image and compensate the influence of the actual light on the foreground image.
Fifthly, extracting dark red characteristics of the rust area by using a hyper red algorithm to obtain a gray image of the foreground image, as shown in fig. 6.
The super-red color algorithm is improved on the basis of a super-green color algorithm proposed by G.E.Meyer, Wobeebbeck and the like. The ultragreen algorithm is characterized in that the background of an image acquired under natural light is obviously different from a plant, and the three primary colors are known from the principle that the G value of the plant is greatly different from the B value of the background in R, G, B three colors of a color image, so that an effective image is obtained from R, G, B sub-images, and the formula is as follows:
ExR(i,j)＝2.0G(i,j)-R(i,j)-B(i,j)
in the formula, ExR (i, j) is a super green value, and R (i, j), G (i, j), and B (i, j) are three-color component matrices, respectively.
The rust area of the rust image is obviously different from other background scenes under natural light, the contrast between the rust area and the non-rust area of the R component image in the RGB color image is obtained by a large number of pictures, and the R value of the rust area in the image is greatly different from the R values of other unrelated scenes, so that the super red algorithm provides the following formula for graying the rust image:
ExR(i,j)＝2.0R(i,j)-G(i,j)-B(i,j)
because the rusty area is red and the contrast ratio of the gray value of the rusty area and other scenes is obvious, part of complex backgrounds can be eliminated by applying the super red algorithm, and a foundation is laid for the next processing.
And sixthly, determining the corrosion condition of the hardware according to the gray level image of the foreground image. The rust condition of the hardware can be determined by adopting the following two methods:
1. and (3) performing binarization processing on the gray level image of the foreground image, as shown in fig. 7-1, obtaining the pixel value of each pixel point in the gray level image of the foreground image, further obtaining the proportion of the area of a corrosion region in the gray level image of the foreground image, namely the corrosion rate, and determining the corrosion condition of the hardware according to the corrosion rate.
2. Obtaining the gray value of each pixel point in the gray image of the foreground image, and drawing the hardware successive corrosion thermodynamic diagram according to the color corresponding to the gray value of each pixel point, as shown in fig. 7-2; and determining the corrosion condition of the hardware according to the hardware successive corrosion thermodynamic diagram. The concept of the rust confidence is introduced, five colors can be set, if the colors are from light to dark, the colors can be respectively set to gray-orange yellow-pink-red-dark red, if the colors are from light to dark, the darker the colors are, the larger the corresponding gray value (namely the rust confidence) is, and the more serious the rust condition of the hardware fitting is.
On the whole, the method is a corrosion detection method based on technologies such as target detection, image segmentation, background HSI conversion, foreground Gamma conversion and the like, the method considers the corrosion detection method of background brightness, and can realize self-adaptive normalization processing under extreme conditions such as different brightness, serious image distortion, complex background and the like so as to obtain corrosion rate and corrosion thermodynamic diagram, provide all-around corrosion defect information for operation and maintenance personnel, and provide effective technical means for realizing intellectualization of electric power operation and maintenance.
In the implementation, the power transmission line image is processed by adopting a mode of constructing a deep convolutional neural network model so as to obtain the target hardware fitting position. Of course, other neural network models known in the art, such as a radial basis function neural network model, may also be used. Moreover, other image processing methods in the prior art, such as a SIFT feature extraction method, can be adopted to find the target hardware position instead of adopting the mode.
In this embodiment, an interactive segmentation algorithm is adopted to perform segmentation processing on the obtained target hardware image so as to obtain a foreground image and a background image of the target hardware image. Other image segmentation methods known in the art, such as adaptive thresholding, may also be used as other embodiments.
In this embodiment, the gamma value of the gamma conversion is set to γ ═ Imean/IsetIn another embodiment, other expression schemes may be used to achieve a larger value of γ with a larger value of Imean, and a larger value of γ with both a value of 0 < γ <1 and a value of γ ≧ 1, such as γ ═ I (Imean-I)1)/(Iset-I1)，I1The value setting is not too large.
In this embodiment, the existing hyper-red algorithm is adopted to extract red features of the foreground image after gamma conversion. As other implementation methods, the existing color tracking method can be adopted, but the color tracking method has higher algorithm complexity compared with the super red algorithm, and the super red algorithm can be well processed to obtain the rust thermodynamic diagram representing the rust degree.
The embodiment of the device is as follows:
the embodiment provides a transmission line hardware corrosion detection device which comprises a memory and a processor, wherein the memory and the processor are directly or indirectly electrically connected to realize data transmission or interaction. The processor may be a general-purpose processor, such as a central processing unit CPU, or may be another programmable logic device, such as a digital signal processor DSP, where the processor is configured to execute instructions stored in a memory to implement the method for detecting corrosion of an electric transmission line hardware described in the method embodiment.
While the present invention has been described in detail with reference to the preferred embodiments, it should be understood that the above description should not be taken as limiting the invention. Various modifications and alterations to this invention will become apparent to those skilled in the art upon reading the foregoing description. Accordingly, the scope of the invention should be determined from the following claims.
Claims (10)
1. A transmission line hardware corrosion detection method is characterized by comprising the following steps:
1) acquiring an image of the power transmission line, finding a target hardware fitting position, and cutting the image of the power transmission line according to the target hardware fitting position to obtain a target hardware fitting image;
2) carrying out segmentation processing on the obtained target hardware image to obtain a foreground image and a background image of the target hardware image;
3) performing gamma conversion on the foreground image to obtain a foreground image after gamma conversion; the gamma value of the gamma conversion is related to the average brightness value of the background image, the larger the average brightness value of the background image is, the larger the gamma value is, and the gamma value is greater than 1 when the average brightness value of the background image is greater than a set brightness threshold, wherein the set brightness threshold is greater than 100 and less than 150;
4) extracting red features of the foreground image after gamma conversion, and performing gray processing to obtain a gray image of the foreground image;
5) and determining the corrosion condition of the hardware according to the gray level image of the foreground image.
2. The method for detecting the corrosion of the hardware of the power transmission line according to claim 1, wherein in the step 1), before the target hardware position is found, a step of preprocessing an image of the power transmission line is further included; the pre-processing comprises at least one of the following image processing: the Gauss filter removes noise, color image histogram equalization and logarithmic transformation.
3. The method for detecting the corrosion of the power transmission line hardware fitting according to claim 1, wherein in the step 1), the process of finding the position of the target hardware fitting comprises the following steps:
acquiring a historical power transmission line image containing hardware fittings, and labeling the hardware fittings in the historical power transmission line image;
constructing a neural network, and training the constructed neural network by using the historical power transmission line image marked with the hardware to obtain a target hardware detection model;
and acquiring an image of the power transmission line, and inputting the image of the power transmission line into the hardware fitting target detection model to obtain the position of the target hardware fitting.
4. The transmission line hardware rust detection method of claim 3, wherein the neural network model is a deep convolution neural network model.
5. The method for detecting the corrosion of the power transmission line hardware according to claim 1, wherein in the step 2), an interactive segmentation algorithm is adopted to perform segmentation processing on the obtained target hardware image.
6. The method for detecting the corrosion of the power transmission line hardware according to claim 1, wherein in the step 3), the gamma value is a ratio of an average brightness value of the background image to the set brightness threshold value.
7. The method for detecting the corrosion of the hardware of the power transmission line according to any one of claims 1 to 6, wherein in the step 5), the gray level image of the foreground image is subjected to binarization processing to obtain values of all pixel points in the gray level image of the foreground image, so that the proportion of the area of a corrosion area in the gray level image of the foreground image is obtained, the proportion is the corrosion rate, and the corrosion condition of the hardware is determined according to the corrosion rate.
8. The transmission line hardware rust detection method according to any one of claims 1 to 6, wherein in step 5), the gray values are divided into different levels, and each level corresponds to a color of a thermodynamic diagram; drawing a hardware successive rust thermodynamic diagram according to the color corresponding to the grade of the gray value of each pixel point in the foreground image; and determining the corrosion condition of the hardware according to the hardware successive corrosion thermodynamic diagram.
9. The transmission line hardware rust detection method according to any one of claims 1 to 6, characterized in that in step 4), a hyper-red algorithm is adopted to extract red features of the foreground image after gamma conversion.
10. The device for detecting the corrosion of the hardware of the power transmission line is characterized by comprising a memory and a processor, wherein the processor is used for executing instructions stored in the memory so as to realize the method for detecting the corrosion of the hardware of the power transmission line according to any one of claims 1 to 9.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911013484.2A CN110726725A (en) | 2019-10-23 | 2019-10-23 | Transmission line hardware corrosion detection method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911013484.2A CN110726725A (en) | 2019-10-23 | 2019-10-23 | Transmission line hardware corrosion detection method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110726725A true CN110726725A (en) | 2020-01-24 |
Family
ID=69222909
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911013484.2A Pending CN110726725A (en) | 2019-10-23 | 2019-10-23 | Transmission line hardware corrosion detection method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110726725A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112419298A (en) * | 2020-12-04 | 2021-02-26 | 中冶建筑研究总院（深圳）有限公司 | Bolt node plate corrosion detection method, device, equipment and storage medium |
| CN114354337A (en) * | 2021-12-10 | 2022-04-15 | 广东电网有限责任公司 | Method and device for detecting tensile strength of hardware in corrosion state and terminal equipment |
| CN114792299A (en) * | 2021-01-25 | 2022-07-26 | 山东信通电子股份有限公司 | Method and device for detecting abnormal state of power transmission line |
| CN114842006A (en) * | 2022-07-04 | 2022-08-02 | 南方电网科学研究院有限责任公司 | Digital twin station power line detection method and related device thereof |
| CN115760854A (en) * | 2023-01-09 | 2023-03-07 | 佰聆数据股份有限公司 | Deep learning-based power equipment defect detection method and device and electronic equipment |
| CN115760858A (en) * | 2023-01-10 | 2023-03-07 | 东南大学附属中大医院 | Kidney pathological section cell identification method and system based on deep learning |
| CN117607019A (en) * | 2023-12-06 | 2024-02-27 | 广东恒威通电力科技有限公司 | Intelligent detection method and detection system for electric power fitting surface |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102254325A (en) * | 2011-07-21 | 2011-11-23 | 清华大学 | Method and system for segmenting motion blur scene and extracting foreground |
| CN106023185A (en) * | 2016-05-16 | 2016-10-12 | 国网河南省电力公司电力科学研究院 | Power transmission equipment fault diagnosis method |
| CN108416771A (en) * | 2018-03-07 | 2018-08-17 | 南京工业大学 | A kind of metal material corrosion area detection method based on monocular camera |
| CN108446705A (en) * | 2017-02-16 | 2018-08-24 | 华为技术有限公司 | The method and apparatus of image procossing |
| CN109193468A (en) * | 2018-11-19 | 2019-01-11 | 国网四川省电力公司成都供电公司 | A kind of transmission line of electricity O&M monitoring method based on unmanned air vehicle technique |
| CN109255776A (en) * | 2018-07-23 | 2019-01-22 | 中国电力科学研究院有限公司 | A kind of transmission line of electricity split pin defect automatic identifying method |
| CN109325935A (en) * | 2018-07-24 | 2019-02-12 | 国网浙江省电力有限公司杭州供电公司 | A kind of transmission line faultlocating method based on unmanned plane image |
| CN109598772A (en) * | 2018-11-23 | 2019-04-09 | 华南理工大学 | Based on the single defect automatic marking image data source extending method of overhead transmission line |
| CN109961430A (en) * | 2018-12-13 | 2019-07-02 | 长春理工大学 | A kind of fitting surface corrosion method for extracting region |
-
2019
- 2019-10-23 CN CN201911013484.2A patent/CN110726725A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102254325A (en) * | 2011-07-21 | 2011-11-23 | 清华大学 | Method and system for segmenting motion blur scene and extracting foreground |
| CN106023185A (en) * | 2016-05-16 | 2016-10-12 | 国网河南省电力公司电力科学研究院 | Power transmission equipment fault diagnosis method |
| CN108446705A (en) * | 2017-02-16 | 2018-08-24 | 华为技术有限公司 | The method and apparatus of image procossing |
| CN108416771A (en) * | 2018-03-07 | 2018-08-17 | 南京工业大学 | A kind of metal material corrosion area detection method based on monocular camera |
| CN109255776A (en) * | 2018-07-23 | 2019-01-22 | 中国电力科学研究院有限公司 | A kind of transmission line of electricity split pin defect automatic identifying method |
| CN109325935A (en) * | 2018-07-24 | 2019-02-12 | 国网浙江省电力有限公司杭州供电公司 | A kind of transmission line faultlocating method based on unmanned plane image |
| CN109193468A (en) * | 2018-11-19 | 2019-01-11 | 国网四川省电力公司成都供电公司 | A kind of transmission line of electricity O&M monitoring method based on unmanned air vehicle technique |
| CN109598772A (en) * | 2018-11-23 | 2019-04-09 | 华南理工大学 | Based on the single defect automatic marking image data source extending method of overhead transmission line |
| CN109961430A (en) * | 2018-12-13 | 2019-07-02 | 长春理工大学 | A kind of fitting surface corrosion method for extracting region |
Non-Patent Citations (3)
| Title |
|---|
| 刘占文: "《基于视觉显著性的图像分割》", 31 March 2019, 西安电子科技大学出版社 * |
| 张洪才: "直升机巡检输电线路锈蚀缺陷识别方法研究", 《万方硕士论文数据库》 * |
| 牛金海: "《超声原理及生物医学工程应用 生物医学超声学》", 31 January 2017, 上海交通大学出版社 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112419298A (en) * | 2020-12-04 | 2021-02-26 | 中冶建筑研究总院（深圳）有限公司 | Bolt node plate corrosion detection method, device, equipment and storage medium |
| CN112419298B (en) * | 2020-12-04 | 2024-01-19 | 中冶建筑研究总院（深圳）有限公司 | Bolt node plate rust detection method, device, equipment and storage medium |
| CN114792299A (en) * | 2021-01-25 | 2022-07-26 | 山东信通电子股份有限公司 | Method and device for detecting abnormal state of power transmission line |
| CN114354337A (en) * | 2021-12-10 | 2022-04-15 | 广东电网有限责任公司 | Method and device for detecting tensile strength of hardware in corrosion state and terminal equipment |
| CN114354337B (en) * | 2021-12-10 | 2023-09-05 | 广东电网有限责任公司 | Tensile strength detection method and device for hardware fitting in rust state and terminal equipment |
| CN114842006A (en) * | 2022-07-04 | 2022-08-02 | 南方电网科学研究院有限责任公司 | Digital twin station power line detection method and related device thereof |
| CN114842006B (en) * | 2022-07-04 | 2022-10-14 | 南方电网科学研究院有限责任公司 | Digital twin station power line detection method and related device thereof |
| CN115760854A (en) * | 2023-01-09 | 2023-03-07 | 佰聆数据股份有限公司 | Deep learning-based power equipment defect detection method and device and electronic equipment |
| CN115760858A (en) * | 2023-01-10 | 2023-03-07 | 东南大学附属中大医院 | Kidney pathological section cell identification method and system based on deep learning |
| CN117607019A (en) * | 2023-12-06 | 2024-02-27 | 广东恒威通电力科技有限公司 | Intelligent detection method and detection system for electric power fitting surface |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110726725A (en) | Transmission line hardware corrosion detection method and device | |
| CN111260616A (en) | Insulator crack detection method based on Canny operator two-dimensional threshold segmentation optimization | |
| CN111008961B (en) | Transmission line equipment defect detection method and system, equipment and medium thereof | |
| CN106682665B (en) | Seven-segment type digital display instrument number identification method based on computer vision | |
| CN103442209A (en) | Video monitoring method of electric transmission line | |
| CN111862143B (en) | Automatic monitoring method for river dike collapse | |
| CN109472788B (en) | Method for detecting flaw on surface of airplane rivet | |
| CN113989257A (en) | Electric power comprehensive pipe gallery settlement crack identification method based on artificial intelligence technology | |
| CN112561899A (en) | Electric power inspection image identification method | |
| CN116758081B (en) | Unmanned aerial vehicle road and bridge inspection image processing method | |
| CN113888462A (en) | Crack identification method, system, readable medium and storage medium | |
| CN115601379A (en) | Surface crack accurate detection technology based on digital image processing | |
| CN117036255A (en) | Pipeline defect detection and evaluation method and device based on deep learning | |
| CN111667473A (en) | Insulator hydrophobicity grade judging method based on improved Canny algorithm | |
| CN112884795A (en) | Power transmission line inspection foreground and background segmentation method based on multi-feature significance fusion | |
| CN115115950A (en) | Unmanned aerial vehicle image duplicate checking method based on image histogram features | |
| CN116630321B (en) | Intelligent bridge health monitoring system based on artificial intelligence | |
| CN113378672A (en) | Multi-target detection method for defects of power transmission line based on improved YOLOv3 | |
| CN117351017A (en) | Visual defect detection method for photovoltaic steel structure component | |
| CN111310899B (en) | Power defect identification method based on symbiotic relation and small sample learning | |
| CN114581407B (en) | Self-adaptive defect detection method for photovoltaic module | |
| CN114120061A (en) | Small target defect detection method and system for power inspection scene | |
| Khan et al. | Shadow removal from digital images using multi-channel binarization and shadow matting | |
| CN113155247A (en) | Object weighing method, state evaluation method, weighing system and state evaluation system | |
| CN112580642A (en) | Image hybrid segmentation method and device combining edge features and texture features |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200124 |