CN116778357A - Power line unmanned aerial vehicle inspection method and system utilizing visible light defect identification - Google Patents
Power line unmanned aerial vehicle inspection method and system utilizing visible light defect identification Download PDFInfo
- Publication number
- CN116778357A CN116778357A CN202310614549.9A CN202310614549A CN116778357A CN 116778357 A CN116778357 A CN 116778357A CN 202310614549 A CN202310614549 A CN 202310614549A CN 116778357 A CN116778357 A CN 116778357A
- Authority
- CN
- China
- Prior art keywords
- aerial vehicle
- unmanned aerial
- defect
- image
- inspection
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 89
- 238000007689 inspection Methods 0.000 title claims abstract description 63
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000000007 visual effect Effects 0.000 claims abstract description 46
- 238000001514 detection method Methods 0.000 claims abstract description 44
- 238000004891 communication Methods 0.000 claims description 10
- 239000012212 insulator Substances 0.000 claims description 10
- 229910052573 porcelain Inorganic materials 0.000 claims description 10
- 230000008859 change Effects 0.000 claims description 7
- 238000005286 illumination Methods 0.000 claims description 7
- 238000012216 screening Methods 0.000 claims description 6
- 238000004422 calculation algorithm Methods 0.000 claims description 5
- 238000013528 artificial neural network Methods 0.000 claims description 4
- JEIPFZHSYJVQDO-UHFFFAOYSA-N iron(III) oxide Inorganic materials O=[Fe]O[Fe]=O JEIPFZHSYJVQDO-UHFFFAOYSA-N 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 230000009467 reduction Effects 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 238000013527 convolutional neural network Methods 0.000 claims description 3
- 238000004020 luminiscence type Methods 0.000 claims description 3
- 238000007726 management method Methods 0.000 claims description 3
- 230000026676 system process Effects 0.000 claims description 3
- 230000007613 environmental effect Effects 0.000 abstract 2
- 238000010586 diagram Methods 0.000 description 10
- 230000006870 function Effects 0.000 description 6
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 235000005770 birds nest Nutrition 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 230000001276 controlling effect Effects 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000002349 favourable effect Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 239000000047 product Substances 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 230000001932 seasonal effect Effects 0.000 description 1
- 239000013589 supplement Substances 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
- 235000005765 wild carrot Nutrition 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/17—Terrestrial scenes taken from planes or by drones
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/20—Administration of product repair or maintenance
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/06—Electricity, gas or water supply
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- General Health & Medical Sciences (AREA)
- Marketing (AREA)
- Strategic Management (AREA)
- Water Supply & Treatment (AREA)
- Artificial Intelligence (AREA)
- Remote Sensing (AREA)
- Public Health (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Primary Health Care (AREA)
- Entrepreneurship & Innovation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Image Processing (AREA)
Abstract
The application relates to the technical field of power inspection, and discloses a power line unmanned aerial vehicle inspection method utilizing visible light defect identification; the unmanned aerial vehicle route calibration is utilized, the unmanned aerial vehicle route is optimized according to the weather, time and environmental changes, and the influence of environmental light on the image picture shot by the unmanned aerial vehicle is reduced as much as possible; the defect database is established, so that the detection accuracy and the recognition efficiency of the visual difference detection model are improved; through the visual difference detection model, the inspection pictures shot by the unmanned aerial vehicle are detected and compared by using the computing power of a computer, so that the workload of manual film reading is greatly reduced. The application also discloses a power line unmanned aerial vehicle inspection system utilizing the visible light defect identification, which is used for realizing the power line unmanned aerial vehicle inspection method utilizing the visible light defect identification.
Description
Technical Field
The application relates to the technical field of power inspection, in particular to a power line unmanned aerial vehicle inspection method and system utilizing visible light defect identification.
Background
At present, the Chinese patent with the bulletin number of CN102589524B discloses a power line inspection method, which specifically comprises the following steps: the unmanned aerial vehicle carrying the photographing device and the navigation system is utilized to automatically record image data of the real-time condition of the power line according to a preset route, and the information of the navigation point position data is fed back in real time; and determining suspected fault points in the power line according to the image data analysis result and the corresponding navigation point position data.
Along with the continuous upgrading of the electric power inspection technology, the unmanned aerial vehicle has been widely accepted and comprehensively popularized in the electric power inspection field by virtue of the advantages of small limit of the topography, good inspection effect of the tower head, low cost, simple operation, high inspection efficiency and the like, and the characteristics of effective supplement of manual inspection and helicopter inspection in the inspection range, content and frequency.
In the process of implementing the embodiments of the present disclosure, it is found that at least the following problems exist in the related art:
1. massive unmanned aerial vehicle inspection image data are generated, a manual film reading mode is often adopted, but the traditional manual film reading mode cannot meet the requirements;
2. due to the interference of shooting visual angles, illumination, seasonal changes, weather and the like on images, the quality of the images shot by the unmanned aerial vehicle is difficult to meet the requirements.
Disclosure of Invention
The following presents a simplified summary in order to provide a basic understanding of some aspects of the disclosed embodiments. This summary is not an extensive overview, and is intended to neither identify key/critical elements nor delineate the scope of such embodiments, but is intended as a prelude to the more detailed description that follows.
The embodiment of the disclosure provides a power line unmanned aerial vehicle inspection method and system utilizing visible light defect recognition, which are used for solving the technical problems that the image data of an unmanned aerial vehicle inspection power line is difficult to meet the requirement and massive image data are difficult to screen.
In some embodiments, the method for inspecting the power line unmanned aerial vehicle by using visible light defect identification specifically includes the following steps:
planning a preliminary route of the unmanned aerial vehicle according to weather, seasons and environments of an area where a route to be patrolled and examined is located;
positioning the position of the unmanned aerial vehicle by using satellites and a differential station;
calibrating the unmanned aerial vehicle route, wherein the unmanned aerial vehicle shoots an easily identifiable object as a reference object, the picture of the reference object is uploaded to a system, and the system adjusts the route of the unmanned aerial vehicle according to the angle, brightness and integrity of the reference object in the picture;
when the picture of the reference object meets the system preset, the unmanned aerial vehicle operates according to the adjusted route, and a patrol chart is shot;
the unmanned aerial vehicle binds the coordinate information with the inspection chart and then uploads the coordinate information to the system, and the system processes the inspection chart into an intermediate image;
classifying the image data of the intermediate image and the patrol image according to the part image database and the twin neural network algorithm;
performing visual difference detection on the classified images by using a visual difference detection model to obtain detection results;
screening out images with defects, and extracting coordinate information bound with the images.
Further, when the picture of the reference object does not meet the preset, repeating unmanned aerial vehicle route calibration;
setting a threshold value of the number of times of unmanned aerial vehicle route calibration, and manually intervening if the number of times of calibration exceeds the threshold value and still cannot obtain clear images.
Further, after the unmanned aerial vehicle runs for a preset unit time according to the adjusted route, the unmanned aerial vehicle route calibration is performed again.
It will be appreciated that the one unit time may be dynamically set based on line changes, changes in illumination caused by time changes and/or weather changes, rather than a fixed time.
Further, the specific steps of the system for processing the inspection chart into the intermediate image include:
noise reduction treatment is carried out on the inspection chart, and contrast ratio is adjusted;
eliminating the influence of brightness change, shadow and emitted light according to a luminescence model method;
and dividing each part of elements in the inspection chart by using the natural scene database and the part model database.
Further, the visual difference detection model is constructed by the following steps:
inputting normal part images as specifications, and establishing a specification image library;
inputting part images under the illumination influence of different weather and different time periods as an additional image library;
inputting the image with the defect, comparing the image with the defect with a standard image library and an additional image library by using a convolutional neural network, and outputting a visual difference result;
manually auditing and correcting the visual difference result, and marking the defect type;
inputting a plurality of known defect images into a visual difference detection model, and training the visual difference detection model;
a final visual difference detection model is obtained.
Further, images with defects are screened, and meanwhile, specific defect types and defect areas are judged:
specific defect types include foreign object adhesion, defects, cracks, and rust.
Further, the part image library includes:
white porcelain insulator, reddish brown porcelain insulator, heavy hammer and part image library of connecting hardware fitting;
classifying the image data of the intermediate image and the inspection image according to the four part image libraries;
the visual difference detection model is provided with four, and corresponds to the four part images one by one.
Further, the defect management system is set up, and the specific steps include:
after screening out the image with the defects, outputting a report comprising the types of the parts, the types of the defects and the areas of the defects;
establishing a defect database, and inputting the report and the image into the defect database;
and visually displaying the defect database.
In some embodiments, the power line unmanned aerial vehicle inspection system using visible light defect identification includes:
the unmanned aerial vehicle is provided with high-definition camera equipment and a satellite navigation system, and is provided with an RTK module, a spiral antenna and a 5G communication module;
the differential station is arranged on the ground and is communicated with the navigation satellite and the unmanned aerial vehicle, and the unmanned aerial vehicle performs high-precision positioning;
a storage module for storing the reference picture, the inspection picture, the intermediate image and the coordinate information taken by the unmanned aerial vehicle according to claim 1, and the program of image data classification and visual difference detection;
a server for planning the unmanned aerial vehicle route of claim 1, and performing a program of image data classification and visual difference detection;
and the base station communication module is connected with the server and is communicated with the unmanned aerial vehicle.
Further, the unmanned aerial vehicle is an electrically driven unmanned rotorcraft.
The power line unmanned aerial vehicle inspection method and system utilizing visible light defect identification provided by the embodiment of the disclosure can realize the following technical effects:
1. the inspection pictures shot by the unmanned aerial vehicle can be detected and compared by using the calculation power of a computer through the visual difference detection model, so that the workload of manual film reading is greatly reduced;
2. by establishing a defect database, the detection accuracy and the recognition efficiency of the visual difference detection model can be improved;
3. utilize unmanned aerial vehicle route calibration, can be better optimize unmanned aerial vehicle route according to the change of weather, time and environment, reduce the influence of ambient light to unmanned aerial vehicle shooting image picture as far as possible.
The foregoing general description and the following description are exemplary and explanatory only and are not restrictive of the application.
Drawings
One or more embodiments are illustrated by way of example and not limitation in the figures of the accompanying drawings, in which like references indicate similar elements, and in which like reference numerals refer to similar elements, and in which:
fig. 1 is a schematic diagram of a power line unmanned aerial vehicle inspection method using visible light defect recognition according to an embodiment of the present disclosure;
FIG. 2 is a schematic diagram of a method for constructing a visual disparity detection model according to an embodiment of the present disclosure;
fig. 3 is a schematic diagram of another inspection method of a power line unmanned aerial vehicle using visible light defect recognition according to an embodiment of the present disclosure;
fig. 4 is a schematic diagram of a power line unmanned aerial vehicle inspection system device using visible light defect recognition according to an embodiment of the present disclosure;
fig. 5 is a schematic diagram of a server, a storage module and a base station communication module of an unmanned power line inspection system using visible light defect recognition according to an embodiment of the present disclosure.
Reference numerals: 1. unmanned plane; 2. an RTK module; 3. a helical antenna; 5. a differential station; 6. a storage module; 7. a server; 8. and the base station communication module.
Detailed Description
So that the manner in which the features and techniques of the disclosed embodiments can be understood in more detail, a more particular description of the embodiments of the disclosure, briefly summarized below, may be had by reference to the appended drawings, which are not intended to be limiting of the embodiments of the disclosure. In the following description of the technology, for purposes of explanation, numerous details are set forth in order to provide a thorough understanding of the disclosed embodiments. However, one or more embodiments may still be practiced without these details. In other instances, well-known structures and devices may be shown simplified in order to simplify the drawing.
The terms first, second and the like in the description and in the claims of the embodiments of the disclosure and in the above-described figures are used for distinguishing between similar objects and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used may be interchanged where appropriate in order to describe embodiments of the present disclosure. Furthermore, the terms "comprise" and "have," as well as any variations thereof, are intended to cover a non-exclusive inclusion.
The term "plurality" means two or more, unless otherwise indicated.
Referring to fig. 1, fig. 2, and fig. 3, an embodiment of the disclosure provides a method for inspecting an electric power line unmanned aerial vehicle using visible light defect identification, including:
s01, planning a preliminary route of the unmanned aerial vehicle according to weather, seasons and environments of an area where a route to be inspected is located; the analysis of weather, seasons and environments is mainly used for obtaining the illumination condition of the patrol land so as to reduce the influence of the external illumination environment on the shooting of the power line as much as possible by optimizing the route of the unmanned aerial vehicle; parameters of real-time change such as wind power, wind direction, cloud layer thickness and the like are often difficult to accurately obtain in advance and are regulated by the coordination capacity of the unmanned aerial vehicle;
s02, positioning the position of the unmanned aerial vehicle by using satellites and a differential station;
s03, calibrating the unmanned aerial vehicle route, wherein the unmanned aerial vehicle shoots an easily identifiable object as a reference object, the picture of the reference object is uploaded to a system, and the system adjusts the route of the unmanned aerial vehicle according to the angle, brightness and integrity of the reference object in the picture;
s04, when the picture of the reference object meets the system preset, the unmanned aerial vehicle operates according to the adjusted route, and a patrol chart is shot;
s05, the unmanned aerial vehicle binds the coordinate information with the inspection image and then uploads the coordinate information to a system, and the system processes the inspection image into an intermediate image;
s06, classifying the image data of the intermediate image and the patrol image according to the part image database and the twin neural network algorithm;
s07, performing visual difference detection on the classified images by using a visual difference detection model to obtain detection results;
s08, screening out images with defects, and extracting coordinate information bound with the images.
By adopting the power line unmanned aerial vehicle inspection method utilizing visible light defect identification, which is provided by the embodiment of the application, the centimeter-level positioning of the unmanned aerial vehicle can be realized through the cooperation of the navigation system of the satellite and the differential station, so that the unmanned aerial vehicle can be controlled to accurately shoot the power line; by utilizing the visual difference detection model, the content in the inspection drawing can be better analyzed, the investment of manual film reading is better reduced, and the film reading efficiency is improved.
Optionally, repeating the unmanned aerial vehicle route calibration when the picture of the reference object does not meet the preset value during the unmanned aerial vehicle route calibration;
setting a threshold value of the number of times of unmanned aerial vehicle route calibration, and manually intervening if the number of times of calibration exceeds the threshold value and still cannot obtain clear images.
Therefore, long-time route calibration of the unmanned aerial vehicle can be avoided, and the efficiency of route calibration of the unmanned aerial vehicle is improved.
Optionally, after the unmanned aerial vehicle runs for a preset unit time according to the adjusted route, the unmanned aerial vehicle route calibration is performed again.
Because wind power and wind direction change in the moment, the thickness of cloud layer also is constantly changing, through the continuous calibration and the feedback of route, can further reduce the influence that ambient light was shot to unmanned aerial vehicle that send.
Optionally, the specific step of processing the inspection chart into the intermediate image by the system includes:
noise reduction treatment is carried out on the inspection chart, and contrast ratio is adjusted;
eliminating the influence of brightness change, shadow and emitted light according to a luminescence model method;
and dividing each part of elements in the inspection chart by using the natural scene database and the part model database.
The inspection chart after the noise reduction treatment can remove more fine variegates, reduce the workload of a subsequent visual difference detection module and improve the detection efficiency;
the method is used for eliminating the influence of external light environment on the inspection chart as much as possible by adjusting the contrast and eliminating the influence of brightness change, shadow and emitted light, so that the subsequent detection efficiency is further improved;
the power cable is usually located in a remote position, natural scenes in the environment are unified, such as forests, grasslands, water surfaces and the like, and image data of the natural scenes are input into a system to train an image visual recognition model;
meanwhile, part images of the power line, such as white porcelain insulators, reddish brown porcelain insulators, heavy hammers and part images of connecting hardware fittings, are input into a system, and an image visual recognition model is trained so as to divide natural scenes and parts by using the image visual recognition model; so as to further improve the subsequent detection efficiency.
Optionally, the visual difference detection model in S07, the constructing step includes:
s071 inputs normal part images as specifications, and establishes a specification image library;
s072, inputting part images under the illumination influence of different weather and different time periods as an additional image library;
s073, inputting an image with a defect, comparing the image with the defect with a standard image library and an additional image library by using a convolutional neural network, and outputting a visual difference result;
s074, manually auditing and correcting the visual difference result, and marking the defect type;
s075 inputting a plurality of known defect images into a visual difference detection model, and training the visual difference detection model;
s076 a final visual difference detection model is obtained.
By repeatedly training the visual difference detection model by using the normal part image and the part image having the defect, the recognition efficiency and accuracy of the model to the defect can be improved.
Optionally, S08 screens out images with defects and extracts coordinate information bound by the images; the following steps are added:
s09, judging specific defect types and defect areas:
s10, specific defect types include foreign object adhesion, defect, crack and rust;
optionally, specific defect types at S10 include foreign object adhesion, defects, cracks, and rust; then, setting up a defect management system, wherein the method comprises the following steps:
s11, after screening out images with defects, outputting reports comprising part types, defect types and defect areas;
s12, establishing a defect database, and inputting the report and the image into the defect database;
s13, visually displaying a defect database, and manufacturing defect data into a pie chart or a bar chart according to different types of parts and different defects of the parts, so that the defect type of the part is conveniently and rapidly analyzed, and the defect type of the part is relatively high, thereby being convenient for preventing and controlling the defect.
Optionally, S06 categorizes the image data of the intermediate image and the inspection map according to the part image database and the twin neural network algorithm; the part image library in this step includes:
white porcelain insulator, reddish brown porcelain insulator, heavy hammer and part image library of connecting hardware fitting;
classifying the image data of the intermediate image and the inspection image according to the four part image libraries;
the visual difference detection model is provided with four, and corresponds to the four part images one by one.
Defects that may occur in different parts are different, for example, the connection fitting may be corroded or hung with foreign matters (usually bird nest), the white porcelain insulator and the reddish brown porcelain insulator may be damaged, the heavy hammer may be broken or missing, etc.;
different visual difference detection models are established for different parts, so that the detection efficiency and accuracy can be further improved.
Referring to fig. 4 and 5, an embodiment of the disclosure provides a power line unmanned aerial vehicle inspection system device using visible light defect recognition, including:
the unmanned aerial vehicle 1 is provided with high-definition camera equipment and a satellite navigation system, and is provided with an RTK module 2, a spiral antenna 3 and a 5G communication module; the unmanned aerial vehicle 1 is an electrically driven unmanned rotorcraft;
the differential station 5 is arranged on the ground and is communicated with the navigation satellite and the unmanned aerial vehicle 1, and the unmanned aerial vehicle 1 performs high-precision positioning;
a storage module 6, configured to store the reference object picture, the inspection image, the intermediate image, and the coordinate information, and the program for classifying the image data and detecting the visual difference taken by the unmanned aerial vehicle 1 according to claim 1;
a server 7 for planning the route of the unmanned aerial vehicle 1 according to claim 1, and executing a program of image data classification and visual difference detection;
the base station communication module 8 is connected with the server 7 and is communicated with the unmanned aerial vehicle 1.
Unmanned aerial vehicle 1 has greatly improved unmanned aerial vehicle 1 flight through the cooperation of differential station 5 and navigation satellite, is favorable to more accurate clear acquisition to patrol and examine the image.
Embodiments of the present disclosure may be embodied in a software product stored on a storage medium, including one or more instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of a method according to embodiments of the present disclosure. And the aforementioned storage medium may be a non-transitory storage medium including: a plurality of media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or a transitory storage medium.
The above description and the drawings illustrate embodiments of the disclosure sufficiently to enable those skilled in the art to practice them. Other embodiments may involve structural, logical, electrical, process, and other changes. The embodiments represent only possible variations. Individual components and functions are optional unless explicitly required, and the sequence of operations may vary. Portions and features of some embodiments may be included in, or substituted for, those of others. Moreover, the terminology used in the present application is for the purpose of describing embodiments only and is not intended to limit the claims. As used in the description of the embodiments and the claims, the singular forms "a," "an," and "the" (the) are intended to include the plural forms as well, unless the context clearly indicates otherwise. Similarly, the term "and/or" as used in this disclosure is meant to encompass any and all possible combinations of one or more of the associated listed. Furthermore, when used in the present disclosure, the terms "comprises," "comprising," and/or variations thereof, mean that the recited features, integers, steps, operations, elements, and/or components are present, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof. Without further limitation, an element defined by the phrase "comprising one …" does not exclude the presence of other like elements in a process, method or apparatus comprising such elements. In this context, each embodiment may be described with emphasis on the differences from the other embodiments, and the same similar parts between the various embodiments may be referred to each other. For the methods, products, etc. disclosed in the embodiments, if they correspond to the method sections disclosed in the embodiments, the description of the method sections may be referred to for relevance.
Those of skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware, or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the solution. The skilled artisan may use different methods for each particular application to achieve the described functionality, but such implementation should not be considered to be beyond the scope of the embodiments of the present disclosure. It will be clearly understood by those skilled in the art that, for convenience and brevity of description, specific working procedures of the above-described systems, apparatuses and units may refer to corresponding procedures in the foregoing method embodiments, which are not repeated herein.
In the embodiments disclosed herein, the disclosed methods, articles of manufacture (including but not limited to devices, apparatuses, etc.) may be practiced in other ways. For example, the apparatus embodiments described above are merely illustrative, and for example, the division of the units may be merely a logical function division, and there may be additional divisions when actually implemented, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted, or not performed. In addition, the coupling or direct coupling or communication connection shown or discussed with each other may be through some interface, device or unit indirect coupling or communication connection, which may be in electrical, mechanical or other form. The units described as separate units may or may not be physically separate, and units shown 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 may be selected according to actual needs to implement the present embodiment. In addition, each functional unit in the embodiments of the present disclosure may be integrated in one processing unit, or each unit may exist alone physically, or two or more units may be integrated in one unit.
The flowcharts and block diagrams in the figures illustrate the architecture, functionality, and operation of possible implementations of systems, methods and computer program products according to embodiments of the present disclosure. In this regard, each block in the flowchart or block diagrams may represent a module, segment, or portion of code, which comprises one or more executable instructions for implementing the specified logical function(s). In some alternative implementations, the functions noted in the block may occur out of the order noted in the figures. For example, two blocks shown in succession may, in fact, be executed substantially concurrently, or the blocks may sometimes be executed in the reverse order, depending upon the functionality involved. In the description corresponding to the flowcharts and block diagrams in the figures, operations or steps corresponding to different blocks may also occur in different orders than that disclosed in the description, and sometimes no specific order exists between different operations or steps. For example, two consecutive operations or steps may actually be performed substantially in parallel, they may sometimes be performed in reverse order, which may be dependent on the functions involved. Each block of the block diagrams and/or flowchart illustration, and combinations of blocks in the block diagrams and/or flowchart illustration, can be implemented by special purpose hardware-based systems which perform the specified functions or acts, or combinations of special purpose hardware and computer instructions.
Claims (10)
1. The power line unmanned aerial vehicle inspection method utilizing visible light defect identification is characterized by comprising the following specific steps of:
planning a preliminary route of the unmanned aerial vehicle according to weather, seasons and environments of an area where a route to be patrolled and examined is located;
positioning the position of the unmanned aerial vehicle by using satellites and a differential station;
calibrating the unmanned aerial vehicle route, wherein the unmanned aerial vehicle shoots an easily identifiable object as a reference object, the picture of the reference object is uploaded to a system, and the system adjusts the route of the unmanned aerial vehicle according to the angle, brightness and integrity of the reference object in the picture;
when the picture of the reference object meets the system preset, the unmanned aerial vehicle operates according to the adjusted route, and a patrol chart is shot;
the unmanned aerial vehicle binds the coordinate information with the inspection chart and then uploads the coordinate information to the system, and the system processes the inspection chart into an intermediate image;
classifying the image data of the intermediate image and the patrol image according to the part image database and the twin neural network algorithm;
performing visual difference detection on the classified images by using a visual difference detection model to obtain detection results;
screening out images with defects, and extracting coordinate information bound with the images.
2. The inspection method of a power line unmanned aerial vehicle using visible light defect recognition according to claim 1, wherein when the picture of the reference object does not meet the preset, the unmanned aerial vehicle line calibration is repeated;
setting a threshold value of the number of times of unmanned aerial vehicle route calibration, and manually intervening if the number of times of calibration exceeds the threshold value and still cannot obtain clear images.
3. The inspection method of the power line unmanned aerial vehicle using visible light defect recognition according to claim 1, wherein the unmanned aerial vehicle performs unmanned aerial vehicle route calibration again after operating for a preset unit time according to the adjusted route.
4. The inspection method of a power line unmanned aerial vehicle using visible light defect recognition of claim 1, wherein the specific step of processing the inspection map into an intermediate image by the system comprises:
noise reduction treatment is carried out on the inspection chart, and contrast ratio is adjusted;
eliminating the influence of brightness change, shadow and emitted light according to a luminescence model method;
and dividing each part of elements in the inspection chart by using the natural scene database and the part model database.
5. The method according to any one of claims 1-4, wherein the visual difference detection model is constructed by:
inputting normal part images as specifications, and establishing a specification image library;
inputting part images under the illumination influence of different weather and different time periods as an additional image library;
inputting the image with the defect, comparing the image with the defect with a standard image library and an additional image library by using a convolutional neural network, and outputting a visual difference result;
manually auditing and correcting the visual difference result, and marking the defect type;
inputting a plurality of known defect images into a visual difference detection model, and training the visual difference detection model;
a final visual difference detection model is obtained.
6. The inspection method of a power line unmanned aerial vehicle using visible light defect recognition according to any one of claims 1 to 4, wherein images with defects are screened out, and meanwhile, specific defect types and defect areas are determined:
specific defect types include foreign object adhesion, defects, cracks, and rust.
7. The inspection method of a power line unmanned aerial vehicle using visible light defect recognition according to any one of claims 1 to 4, wherein,
the part image library includes:
white porcelain insulator, reddish brown porcelain insulator, heavy hammer and part image library of connecting hardware fitting;
classifying the image data of the intermediate image and the inspection image according to the four part image libraries;
the visual difference detection model is provided with four, and corresponds to the four part images one by one.
8. The inspection method of the power line unmanned aerial vehicle using visible light defect recognition according to claim 6, wherein the defect management system is provided, and the specific steps include:
after screening out the image with the defects, outputting a report comprising the types of the parts, the types of the defects and the areas of the defects;
establishing a defect database, and inputting the report and the image into the defect database;
and visually displaying the defect database.
9. The utility model provides an utilize power line unmanned aerial vehicle inspection system of visible light defect discernment which characterized in that includes:
the unmanned aerial vehicle is provided with high-definition camera equipment and a satellite navigation system, and is provided with an RTK module, a spiral antenna and a 5G communication module;
the differential station is arranged on the ground and is communicated with the navigation satellite and the unmanned aerial vehicle, and the unmanned aerial vehicle performs high-precision positioning;
a storage module for storing the reference picture, the inspection picture, the intermediate image and the coordinate information taken by the unmanned aerial vehicle according to claim 1, and the program of image data classification and visual difference detection;
a server for planning the unmanned aerial vehicle route of claim 1, and performing a program of image data classification and visual difference detection;
and the base station communication module is connected with the server and is communicated with the unmanned aerial vehicle.
10. The power line unmanned aerial vehicle inspection system utilizing visible light defect identification of claim 9, wherein the unmanned aerial vehicle is an electrically driven unmanned rotorcraft.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310614549.9A CN116778357A (en) | 2023-05-29 | 2023-05-29 | Power line unmanned aerial vehicle inspection method and system utilizing visible light defect identification |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310614549.9A CN116778357A (en) | 2023-05-29 | 2023-05-29 | Power line unmanned aerial vehicle inspection method and system utilizing visible light defect identification |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116778357A true CN116778357A (en) | 2023-09-19 |
Family
ID=88009087
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310614549.9A Pending CN116778357A (en) | 2023-05-29 | 2023-05-29 | Power line unmanned aerial vehicle inspection method and system utilizing visible light defect identification |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116778357A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117109598A (en) * | 2023-10-23 | 2023-11-24 | 中冶建筑研究总院（深圳）有限公司 | Ground-air collaborative multi-rotor unmanned aerial vehicle routing inspection path planning method and system |
-
2023
- 2023-05-29 CN CN202310614549.9A patent/CN116778357A/en active Pending
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117109598A (en) * | 2023-10-23 | 2023-11-24 | 中冶建筑研究总院（深圳）有限公司 | Ground-air collaborative multi-rotor unmanned aerial vehicle routing inspection path planning method and system |
| CN117109598B (en) * | 2023-10-23 | 2024-01-23 | 中冶建筑研究总院（深圳）有限公司 | Ground-air collaborative multi-rotor unmanned aerial vehicle routing inspection path planning method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107014827B (en) | Transmission line defect analysis method, device and system based on image processing | |
| Akagic et al. | Pothole detection: An efficient vision based method using rgb color space image segmentation | |
| KR102094341B1 (en) | System for analyzing pot hole data of road pavement using AI and for the same | |
| CN111784685A (en) | Power transmission line defect image identification method based on cloud edge cooperative detection | |
| CN108648169B (en) | Method and device for automatically identifying defects of high-voltage power transmission tower insulator | |
| US11361423B2 (en) | Artificial intelligence-based process and system for visual inspection of infrastructure | |
| EP3408828B1 (en) | Systems and methods for detecting imaged clouds | |
| CN110610483B (en) | Crack image acquisition and detection method, computer equipment and readable storage medium | |
| US8503761B2 (en) | Geospatial modeling system for classifying building and vegetation in a DSM and related methods | |
| JP2016223815A (en) | Deterioration diagnostic system and deterioration diagnostic method | |
| CN116778357A (en) | Power line unmanned aerial vehicle inspection method and system utilizing visible light defect identification | |
| CN108665468B (en) | Device and method for extracting tangent tower insulator string | |
| CN112884795A (en) | Power transmission line inspection foreground and background segmentation method based on multi-feature significance fusion | |
| CN113706472A (en) | Method, device and equipment for detecting road surface diseases and storage medium | |
| CN111523392B (en) | Deep learning sample preparation method and recognition method based on satellite orthographic image full gesture | |
| CN111325076B (en) | Aviation ground building extraction method based on fusion of U-net and Seg-net networks | |
| CN112613437A (en) | High-accuracy illegal building identification method | |
| CN117036756A (en) | Remote sensing image matching method and system based on variation automatic encoder | |
| AU2021106502A4 (en) | A Blasting Pile Measurement And Statistics Method For Open-pit Mines Based On UAV Technology | |
| CN114708190A (en) | Road crack detection and evaluation algorithm based on deep learning | |
| CN112991425A (en) | Water area water level extraction method and system and storage medium | |
| CN112287787A (en) | Crop lodging classification method based on gradient histogram features | |
| CN104915959A (en) | Aerial photography image quality evaluation method and system | |
| CN112017057A (en) | Insurance claim settlement processing method and device | |
| CN117670979B (en) | Bulk cargo volume measurement method based on fixed point position monocular camera |
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 |