CN114841980A - Insulator defect detection method and system based on line patrol aerial image - Google Patents
Insulator defect detection method and system based on line patrol aerial image Download PDFInfo
- Publication number
- CN114841980A CN114841980A CN202210544889.4A CN202210544889A CN114841980A CN 114841980 A CN114841980 A CN 114841980A CN 202210544889 A CN202210544889 A CN 202210544889A CN 114841980 A CN114841980 A CN 114841980A
- Authority
- CN
- China
- Prior art keywords
- insulator
- image
- line patrol
- region
- aerial
- 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
- 239000012212 insulator Substances 0.000 title claims abstract description 161
- 230000007547 defect Effects 0.000 title claims abstract description 68
- 238000001514 detection method Methods 0.000 title claims abstract description 62
- 238000013136 deep learning model Methods 0.000 claims abstract description 22
- 230000002950 deficient Effects 0.000 claims abstract description 20
- 238000012545 processing Methods 0.000 claims abstract description 19
- 238000007781 pre-processing Methods 0.000 claims abstract description 9
- 230000002708 enhancing effect Effects 0.000 claims abstract description 3
- 238000000034 method Methods 0.000 claims description 35
- 238000012549 training Methods 0.000 claims description 26
- 238000004590 computer program Methods 0.000 claims description 15
- 238000007689 inspection Methods 0.000 claims description 11
- 230000008569 process Effects 0.000 claims description 11
- 238000003860 storage Methods 0.000 claims description 9
- 230000011218 segmentation Effects 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000002776 aggregation Effects 0.000 claims description 5
- 238000004220 aggregation Methods 0.000 claims description 5
- 238000003709 image segmentation Methods 0.000 claims description 3
- 238000010606 normalization Methods 0.000 claims 1
- 238000005070 sampling Methods 0.000 claims 1
- 238000010586 diagram Methods 0.000 description 10
- 238000004422 calculation algorithm Methods 0.000 description 7
- 230000006870 function Effects 0.000 description 5
- 230000008859 change Effects 0.000 description 4
- 238000002360 preparation method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 238000002372 labelling Methods 0.000 description 2
- 230000005012 migration Effects 0.000 description 2
- 238000013508 migration Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000000354 decomposition reaction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000009413 insulation Methods 0.000 description 1
- 238000011068 loading method Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 230000009467 reduction Effects 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The invention relates to an insulator defect detection method and system based on line patrol aerial images, which comprises the following steps: acquiring a line patrol aerial image, and acquiring an image of an area where an insulator is located in the line patrol aerial image based on the trained deep learning model; enhancing the image of the region where the insulator is located to obtain an enhanced image of the region where the insulator is located and preprocessing the enhanced image; and acquiring edge information of the insulators in the image based on the preprocessed image of the region where the insulators are located, calculating by using an integral projection curve to obtain a curve image which takes the axis of the insulator string as a reference and takes an insulator edge coordinate set as an output, wherein the region where the variation of the insulator edge coordinate in the image exceeds a set range is the identified defective insulator. The deep learning model and the classical image processing are used in a cascade mode, respective advantages are exerted, the difficulty in small target detection when the defect region of the insulator is detected directly can be overcome, and good instantaneity can be obtained.
Description
Technical Field
The invention relates to the technical field of image recognition, in particular to a method and a system for detecting insulator defects based on line patrol aerial images.
Background
The statements in this section merely provide background information related to the present disclosure and may not constitute prior art.
The insulator is an important part serving as an insulation and mechanical support function in the power transmission line, and the traditional insulator defect detection is monitored on site by means of a detection tool manually or is further analyzed and monitored after an unmanned aerial vehicle aerial photography device is adopted to collect images of the power transmission line.
At present, an insulator defect detection method is generally an end-to-end defect direct detection method, a target detection algorithm of a deep network is generally adopted, a deep network model is trained through a large number of insulator defect images, and an optimal network architecture and parameter configuration are obtained; and then, the obtained model is adopted to test and detect the new aerial image, and in the mode, the deep network model training is seriously dependent on a large amount of high-quality insulator defect marking data, so that the requirements on data preparation and calculation power are high, and the application is difficult in practice.
Disclosure of Invention
In order to solve the technical problems in the background art, the invention provides an insulator defect detection method and system based on line patrol aerial images, an efficient deep learning model is used for directly detecting a large insulator target, then secondary image processing and identification are carried out on a positioned insulator region, the insulator defect is determined, the difficult problem of directly detecting the small insulator target defect is solved, the detection precision is improved due to the influence of external environment change, and meanwhile, the detection efficiency can be effectively improved due to the adoption of two-step detection model cascade.
In order to achieve the purpose, the invention adopts the following technical scheme:
the invention provides an insulator defect detection method based on line patrol aerial images, which comprises the following steps:
acquiring a line patrol aerial image, and acquiring and preprocessing an image of an area where an insulator is located in the line patrol aerial image based on a trained deep learning model;
acquiring edge information of the insulators in the image based on the preprocessed image of the region where the insulators are located, and obtaining a curve image which takes the axis of the insulator string as a reference and takes an insulator edge coordinate set as an output through integral projection curve calculation, wherein the region where the variation of the insulator edge coordinate in the image exceeds a set range is the identified defective insulator;
and marking the area where the defective insulator is located, and determining the position of the defective insulator in the image.
The training process of the deep learning model comprises the following steps:
constructing a training set and a testing set by using the inspection aerial image with the insulator defect;
normalizing the image size in the training set;
and inputting the improved YOLOv3 depth model into the normalized training set to obtain a trained deep learning model.
The improved YOLOv3 depth model introduces the shallow information of the backbone network into the PANet path aggregation module through branch F4, and forms an aggregation with the features in the original network, which together serve as the input of the attention module.
The preprocessing process comprises the steps of carrying out image segmentation after enhancing the image of the region where the insulator is located, and obtaining an image after binary segmentation.
And after the position of the insulator defect area is obtained, outputting a rectangular window according to the edge coordinates of the insulator to realize the marking of the detection result.
A second aspect of the present invention provides a system for implementing the above method, comprising:
an insulator region detection module configured to: acquiring a line patrol aerial image, and acquiring and preprocessing an image of an area where an insulator is located in the line patrol aerial image based on a trained deep learning model;
an insulator defect detection module configured to: acquiring edge information of the insulators in the image based on the preprocessed image of the region where the insulators are located, calculating by using an integral projection curve to obtain a curve image which takes the axis of the insulator string as a reference and takes an insulator edge coordinate set as an output, wherein the region where the variation of the insulator edge coordinate in the image exceeds a set range is the identified defective insulator; and marking the area where the defective insulator is located, and determining the position of the defective insulator in the image.
A third aspect of the invention provides a computer-readable storage medium.
A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for inspecting insulator defects based on aerial images of patrolling lines as described above.
A fourth aspect of the invention provides a computer apparatus.
A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps in the method for detecting insulator defects based on aerial images of line patrol when executing the program.
Compared with the prior art, the above one or more technical schemes have the following beneficial effects:
the deep learning model and the classical image processing are used in a cascade mode, respective advantages are exerted, the difficulty in small target detection when the defect region of the insulator is detected directly can be overcome, and good instantaneity can be obtained.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
Fig. 1 is a flow chart of insulator defect detection provided by one or more embodiments of the present invention;
FIGS. 2(a) - (d) are aerial images of a line patrol with a defective insulator according to one or more embodiments of the present invention;
fig. 3 is an improved YOLOv3 insulator location detection network topology provided by one or more embodiments of the present invention;
fig. 4(a) - (b) are schematic diagrams illustrating the insulator positioning detection effect according to one or more embodiments of the present invention;
FIG. 5 is a schematic view of insulator segmentation results and integral projection curves provided by one or more embodiments of the present invention;
fig. 6 is a schematic diagram illustrating the effect of detecting a defective insulator after positioning according to one or more embodiments of the present invention.
Detailed Description
The invention is further described with reference to the following figures and examples.
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
As described in the background art, deep network model training depends heavily on a large amount of high-quality insulator defect labeling data, so that the data preparation and calculation requirements are high, and the deep network model training is difficult to apply in practice.
The two-step insulator defect detection is performed by dividing insulator positioning and defect identification into two steps, and the difficulty of data preparation is effectively relieved because the acquisition of the insulator image is easier to realize than the acquisition of the insulator defect area image. Meanwhile, the defect of the insulator detected in the image belongs to the typical small target detection problem, and the prior art adopts an end-to-end direct detection method with lower precision. And the insulator positioning belongs to the typical target detection problem, the technology is relatively mature, the accurate positioning is easy to realize, if the classical image processing and segmentation algorithm is combined, the more accurate defect region detection and marking can be realized, and the detection precision and efficiency are greatly improved because the defect region segmentation only aims at the insulator image.
Therefore, the following embodiments provide a method and a system for detecting insulator defects based on line patrol aerial images, a high-efficiency deep learning model is used for directly detecting a large insulator target, secondary image processing and identification are carried out on a positioned insulator region, the insulator defects are determined, the problem of directly detecting the small insulator target defects is solved, the detection precision is improved due to the influence of external environment changes, and meanwhile, the detection efficiency can be effectively improved by adopting two-step detection model cascade.
The first embodiment is as follows:
as shown in fig. 1 to 5, the method for detecting the defect of the insulator based on the line patrol aerial image comprises the following steps:
acquiring a line patrol aerial image, and acquiring and preprocessing an image of an area where an insulator is located in the line patrol aerial image based on a trained deep learning model;
and acquiring edge information of the insulator in the image based on the preprocessed image of the region where the insulator is located, and obtaining the position of the defective region of the insulator through an integral projection curve.
Specifically, the method comprises the following steps:
1. data preparation
In order to fully explain the steps and effectiveness of the insulator defect detection method based on the line patrol aerial image, the embodiment uses a line patrol aerial image set acquired by a certain power company, as shown in fig. 2(a) - (d), based on the image set, an insulator training sample set and a test sample set are respectively labeled and constructed, and image file names and insulator region vertex coordinate information are respectively stored in a labeled text.
In this embodiment, 2000 images are selected from the images to mark the insulator region, and the label information is stored to form a training sample set. Then, 1000 images are selected to form an insulator detection algorithm test sample set. Note that a certain number of defective insulator images should be included in the constructed training sample set and test sample set.
2. Insulator target detection model training based on depth YOLO framework
An improved YOLOv3 deep network architecture model is built, fine tuning training is carried out on parameters of the improved YOLOv3 model by utilizing the built insulator training image set and by means of the migration idea of the model architecture, and the insulator large target area positioning detection model based on the routing inspection aerial image is obtained.
(1) And constructing an improved YOLOv3 insulator detection positioning network model by adopting a YOLO network architecture. The improved YOLOV3 architecture adopted in this embodiment is formed by a Backbone network, a PANet path aggregation module, and a CANet attention module, and the network architecture is formed by adding a shallow information branch F4 on the basis of an original network connection branch F1, F2, and F3, and the four branches aggregate different scale features of the Backbone network, so that the effect of shallow position information is enhanced, and the target detection accuracy is improved; finally, outputting three characteristics with different scales through an attention module to obtain a final detection result; fig. 3 shows a network topology adopted in the present embodiment.
(2) Normalizing image sizes in insulator training sample set to 416 x 416
(3) The pre-training parameters of the improved YOLOv3 model trained based on the VOC data set (one of the standard data sets commonly used in the field of target detection) are migrated into the network structure of this embodiment as the initial parameters of the network. The settings were made in conjunction with the main parameters given in table 1 and the parameters modified during migration.
Table 1: parameter setting
(4) And inputting the normalized insulator training image into an improved YOLOv3 depth model, realizing network parameter fine tuning training, and obtaining an insulator positioning detection network model.
3. Insulator defect detection integrating YOLO network architecture and image processing
(1) The insulator test image containing defects is normalized to 416 x 416.
(2) And (3) loading the improved YOLOv3 of the insulator positioning detection model obtained by training in the step (2).
(3) And inputting the normalized insulator test image into an improved YOLOv3 model to realize the detection and positioning of the large target area of the insulator. As shown in fig. 4, which is a graph of the results of insulator region detection.
(4) And performing image enhancement processing on the detected insulator region image by adopting a Retinex filtering algorithm, and eliminating the interference of factors such as ambient light and the like.
(5) Performing image segmentation on the image of the insulator sub-region by adopting an OTSU segmentation algorithm to obtain a binary segmentation result of the insulator sub-region; and integral projection curve calculation in the vertical direction and the horizontal direction is respectively carried out aiming at the binary segmentation result, and after a projection curve is obtained, the boundary of the defect area can be determined through the boundary of the projection curve, so that the defect area detection is realized.
In this embodiment, as shown in fig. 5, the image of the insulator image and the integral projection curve obtained by binarization decomposition are shown, the insulator in the image after binarization division is shown as white, the background is black, the insulator with the defect is covered by the black background, the result obtained after integral projection curve calculation is output by drawing a rectangular window with boundary coordinates, and an insulator edge curve graph with the axis of the insulator string as a reference line can be shown, the normal insulator edge shows a certain regular change, the insulator edge coordinate information also shows a regular change within a set range, while the edge of the insulator with the defect has an obvious defect in the curve graph, and the change of the corresponding insulator edge coordinate exceeds the set range, so that the identified defective insulator can be labeled by using the corresponding coordinate of the curve of the defect portion.
Fig. 6 shows the detection and labeling result of the defective insulator region.
The process constructs an image set specially used for inspecting defects of the insulator in line patrol aerial photography, and provides basic data for solving the defects of the insulator.
By comprehensively considering the advantages of high accuracy and rapidity of the YOLOv3 depth network in large target detection, a two-stage defect detection framework fusing an improved YOLOv3 depth model and a classical image processing algorithm is designed.
The improved YOLOv3 model is used for detecting an insulator sub-region (large target region), so that shallow layer position information can be fully and reasonably utilized, the problem of detection omission caused by the fact that the target region is too small when the model is directly used for detecting a defect region is solved, and the detection precision can be improved; the defect region (small target region) is detected by using a classical image processing algorithm, so that the reliable detection of the small target region can be ensured, and better real-time performance can be obtained due to the reduction of the detection range.
By utilizing the constructed insulator training sample set, fine adjustment is performed on the improved YOLOv3 depth model parameters, and the training efficiency of the depth network is improved.
The deep learning model and the classical image processing are used in a cascade mode in the process, respective advantages are exerted, the difficulty in small target detection when the defect region of the insulator is detected directly can be overcome, and good instantaneity can be obtained.
Example two:
the embodiment provides a system for implementing the method, which includes:
an insulator region detection module configured to: acquiring a line patrol aerial image, and acquiring and preprocessing an image of an area where an insulator is located in the line patrol aerial image based on a trained deep learning model;
an insulator defect detection module configured to: and acquiring edge information of the insulator in the image based on the preprocessed image of the region where the insulator is located, and obtaining the position of the defective region of the insulator through an integral projection curve.
The system uses the deep learning model and the classical image processing in a cascade mode, the advantages of the deep learning model and the classical image processing are respectively exerted, the difficulty in small target detection when an insulator defect area is directly detected can be overcome, and good instantaneity can be obtained.
EXAMPLE III
The present embodiment provides a computer-readable storage medium, on which a computer program is stored, which when executed by a processor implements the steps in the inspection method for insulator defects based on aerial images of line patrol as proposed in the first embodiment above.
In the insulator defect detection method based on the line patrol aerial image executed by the computer program in the embodiment, the deep learning model and the classical image processing are used in a cascade mode, so that respective advantages are exerted, the difficulty in detecting small targets when the insulator defect area is detected directly can be overcome, and good real-time performance can be obtained.
Example four
The embodiment provides a computer device, which comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor executes the program to implement the steps in the inspection method for the insulator defect based on the aerial image of the line patrol as proposed in the embodiment.
In the insulator defect detection method based on the line patrol aerial image executed by the processor, the deep learning model and the classical image processing are used in a cascade mode, respective advantages are exerted, the difficulty in small target detection when an insulator defect area is detected directly can be overcome, and good real-time performance can be obtained.
As will be appreciated by one skilled in the art, embodiments of the present invention may be provided as a method, system, or computer program product. Accordingly, the present invention may take the form of a hardware embodiment, a software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, optical storage, and the like) having computer-usable program code embodied therein.
The present invention is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing apparatus to cause a series of operational steps to be performed on the computer or other programmable apparatus to produce a computer implemented process such that the instructions which execute on the computer or other programmable apparatus provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
It will be understood by those skilled in the art that all or part of the processes of the methods of the embodiments described above can be implemented by a computer program, which can be stored in a computer-readable storage medium, and when executed, can include the processes of the embodiments of the methods described above. The storage medium may be a magnetic disk, an optical disk, a read-only memory or a random access memory.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. An insulator defect detection method based on line patrol aerial images is characterized by comprising the following steps: the method comprises the following steps:
acquiring a line patrol aerial image, and acquiring and preprocessing an image of an area where an insulator is located in the line patrol aerial image based on a trained deep learning model;
acquiring edge information of the insulators in the image based on the preprocessed image of the region where the insulators are located, and obtaining a curve image which takes the axis of the insulator string as a reference and takes an insulator edge coordinate set as an output through integral projection curve calculation, wherein the region where the variation of the insulator edge coordinate in the image exceeds a set range is the identified defective insulator;
and marking the area where the defective insulator is located, and determining the position of the defective insulator in the image.
2. The inspection method for insulator defects based on line patrol aerial images according to claim 1, characterized in that: the training process of the deep learning model comprises the steps of constructing a training set and a testing set by utilizing the inspection aerial images with the insulator defects.
3. The inspection method for insulator defects based on line patrol aerial images according to claim 2, characterized in that: the training process of the deep learning model further comprises normalizing the image sizes in the training set.
4. The inspection method for insulator defects based on line patrol aerial images according to claim 3, characterized in that: the training process of the deep learning model further comprises the step of inputting the improved YOLOv3 deep model into the training set after normalization processing to obtain the trained deep learning model.
5. The inspection method for insulator defects based on line patrol aerial images according to claim 4, characterized in that: the improved YOLOv3 depth model introduces the shallow information of the Backbone network of the Backbone into a PANet path aggregation module through a branch F4; after down-sampling, an aggregation is formed with the features of the branches F1, F2, and F3 in the original network, and finally the new aggregated features are input to the attention module.
6. The inspection method for insulator defects based on line patrol aerial images according to claim 1, characterized in that: the preprocessing process comprises the steps of carrying out image segmentation after enhancing the image of the region where the insulator is located, and obtaining an image after binary segmentation.
7. The inspection method for insulator defects based on line patrol aerial images according to claim 1, characterized in that: and after the position of the insulator defect area is obtained, outputting a rectangular window according to the insulator boundary coordinates to realize detection result marking.
8. Insulator defect detecting system based on patrol line image of taking photo by plane, its characterized in that: the method comprises the following steps:
an insulator region detection module configured to: acquiring a line patrol aerial image, and acquiring and preprocessing an image of an area where an insulator is located in the line patrol aerial image based on a trained deep learning model;
an insulator defect detection module configured to: acquiring edge information of the insulators in the image based on the preprocessed image of the region where the insulators are located, and obtaining a curve image which takes the axis of the insulator string as a reference and takes an insulator edge coordinate set as an output through integral projection curve calculation, wherein the region where the variation of the insulator edge coordinate in the image exceeds a set range is the identified defective insulator; and marking the area where the defective insulator is located, and determining the position of the defective insulator in the image.
9. A computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method for inspecting an insulator defect based on an aerial image of a line patrol according to any one of claims 1 to 7.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program implements the steps in the method for inspecting insulator defects based on aerial images of line patrol according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210544889.4A CN114841980A (en) | 2022-05-19 | 2022-05-19 | Insulator defect detection method and system based on line patrol aerial image |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210544889.4A CN114841980A (en) | 2022-05-19 | 2022-05-19 | Insulator defect detection method and system based on line patrol aerial image |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114841980A true CN114841980A (en) | 2022-08-02 |
Family
ID=82571043
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210544889.4A Pending CN114841980A (en) | 2022-05-19 | 2022-05-19 | Insulator defect detection method and system based on line patrol aerial image |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114841980A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116228778A (en) * | 2023-05-10 | 2023-06-06 | 国网山东省电力公司菏泽供电公司 | Insulator rupture detection method and system based on multi-mode information fusion |
-
2022
- 2022-05-19 CN CN202210544889.4A patent/CN114841980A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116228778A (en) * | 2023-05-10 | 2023-06-06 | 国网山东省电力公司菏泽供电公司 | Insulator rupture detection method and system based on multi-mode information fusion |
| CN116228778B (en) * | 2023-05-10 | 2023-09-08 | 国网山东省电力公司菏泽供电公司 | Insulator rupture detection method and system based on multi-mode information fusion |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112115895B (en) | Pointer type instrument reading identification method, pointer type instrument reading identification device, computer equipment and storage medium | |
| CN113239930B (en) | Glass paper defect identification method, system, device and storage medium | |
| CN113646801A (en) | Defect detection method and device for defect image and computer readable storage medium | |
| CN110837839B (en) | High-precision unmanned aerial vehicle orthographic image manufacturing and data acquisition method | |
| CN110175519B (en) | Method and device for identifying separation and combination identification instrument of transformer substation and storage medium | |
| CN112419268A (en) | Method, device, equipment and medium for detecting image defects of power transmission line | |
| CN115661160B (en) | Panel defect detection method, system, device and medium | |
| CN110599453A (en) | Panel defect detection method and device based on image fusion and equipment terminal | |
| CN118134923B (en) | High-speed article visual detection method based on artificial intelligence | |
| CN111539924A (en) | Defect detection method, device and equipment for suspension clamp and storage medium | |
| CN116052094A (en) | Ship detection method, system and computer storage medium | |
| CN115797314A (en) | Part surface defect detection method, system, equipment and storage medium | |
| CN114841980A (en) | Insulator defect detection method and system based on line patrol aerial image | |
| CN109934151B (en) | Face detection method based on movidius computing chip and Yolo face | |
| CN113705564B (en) | Pointer type instrument identification reading method | |
| CN113902793A (en) | End-to-end building height prediction method and system based on single vision remote sensing image and electronic equipment | |
| CN110728229B (en) | Image processing method, device, equipment and storage medium | |
| CN116843665A (en) | Camera module gluing condition judging method, device, equipment and storage medium | |
| CN113487550B (en) | Target detection method and device based on improved activation function | |
| CN109448012A (en) | A kind of method for detecting image edge and device | |
| CN115546666A (en) | Power equipment bolt detection method and system based on unmanned aerial vehicle inspection | |
| CN115082650A (en) | Implementation method of automatic pipeline defect labeling tool based on convolutional neural network | |
| CN113920450A (en) | Method and device for identifying insulator RTV coating based on intrinsic image decomposition | |
| CN113902890A (en) | Self-supervision data enhancement method, system and equipment for visual concept detection | |
| CN111931920A (en) | Target detection method, device and storage medium based on cascade neural network |
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 |