CN111522355B - Unmanned aerial vehicle inspection system based on edge calculation and inspection method thereof - Google Patents
Unmanned aerial vehicle inspection system based on edge calculation and inspection method thereof Download PDFInfo
- Publication number
- CN111522355B CN111522355B CN202010197746.1A CN202010197746A CN111522355B CN 111522355 B CN111522355 B CN 111522355B CN 202010197746 A CN202010197746 A CN 202010197746A CN 111522355 B CN111522355 B CN 111522355B
- Authority
- CN
- China
- Prior art keywords
- aerial vehicle
- unmanned aerial
- server
- picture
- edge calculation
- 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.)
- Active
Links
- 238000007689 inspection Methods 0.000 title claims abstract description 48
- 238000004364 calculation method Methods 0.000 title claims abstract description 18
- 238000000034 method Methods 0.000 title claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 40
- 230000005540 biological transmission Effects 0.000 claims abstract description 26
- 238000013500 data storage Methods 0.000 claims abstract description 8
- 230000000694 effects Effects 0.000 claims description 8
- 238000005516 engineering process Methods 0.000 claims description 5
- 230000008569 process Effects 0.000 claims description 5
- 238000003331 infrared imaging Methods 0.000 claims description 3
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 description 4
- 230000006870 function Effects 0.000 description 4
- 238000001931 thermography Methods 0.000 description 4
- 238000012423 maintenance Methods 0.000 description 3
- 238000010248 power generation Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000012946 outsourcing Methods 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000009429 distress Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C11/00—Photogrammetry or videogrammetry, e.g. stereogrammetry; Photographic surveying
- G01C11/02—Picture taking arrangements specially adapted for photogrammetry or photographic surveying, e.g. controlling overlapping of pictures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/46—Multiprogramming arrangements
- G06F9/50—Allocation of resources, e.g. of the central processing unit [CPU]
- G06F9/5061—Partitioning or combining of resources
- G06F9/5072—Grid computing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
- G06T17/05—Geographic models
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N7/00—Television systems
- H04N7/18—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast
- H04N7/181—Closed-circuit television [CCTV] systems, i.e. systems in which the video signal is not broadcast for receiving images from a plurality of remote sources
-
- 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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02E—REDUCTION OF GREENHOUSE GAS [GHG] EMISSIONS, RELATED TO ENERGY GENERATION, TRANSMISSION OR DISTRIBUTION
- Y02E10/00—Energy generation through renewable energy sources
- Y02E10/50—Photovoltaic [PV] energy
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Remote Sensing (AREA)
- Multimedia (AREA)
- Geometry (AREA)
- Radar, Positioning & Navigation (AREA)
- Quality & Reliability (AREA)
- Automation & Control Theory (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Aviation & Aerospace Engineering (AREA)
- Astronomy & Astrophysics (AREA)
- Computer Graphics (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Signal Processing (AREA)
- Traffic Control Systems (AREA)
- Image Processing (AREA)
Abstract
The invention discloses an unmanned aerial vehicle inspection system based on edge calculation and an inspection method thereof, and relates to the technical field of photovoltaic power station inspection. The invention comprises an unmanned aerial vehicle, a camera, a ground station and a server, wherein the ground station is electrically connected with the server, the unmanned aerial vehicle is connected with the ground station in real time through a real-time transmission system, a miniature image processing device is fixed at the bottom of the unmanned aerial vehicle, the camera is fixed at the bottom of the unmanned aerial vehicle and is electrically connected with a control system of the unmanned aerial vehicle, the miniature image processing device comprises a shell, and a GPU (graphic processing unit) image processor and a data storage module are arranged in the shell. According to the invention, the unmanned aerial vehicle carrying the miniature image processing equipment can reduce time loss caused by wireless transmission of pictures, the pressure of ground station image processing can be reduced through pre-recognition of picture faults by the GPU image processor, normal solar photovoltaic panel images do not need to be transmitted to a ground service station, and the problems of overlarge frequency and long time consumption of picture transmission of the existing unmanned aerial vehicle inspection system are solved.
Description
Technical Field
The invention belongs to the technical field of photovoltaic power station inspection, and particularly relates to an unmanned aerial vehicle inspection system based on edge calculation and an inspection method thereof.
Background
The solar photovoltaic power generation system is mainly diversity type and distributed, the centralized power station is generally wide in occupied area, most of the centralized power station is built in northwest parts and some remote areas of China, natural environments are severe, the distributed power station is generally built on roofs, greenhouses and large-area pools, however, a large amount of operation and maintenance pressure is brought after the photovoltaic power stations are connected in a grid mode, such as conventional equipment detection, photovoltaic panel inspection and the like.
The traditional operation and maintenance mode adopts manual inspection, has low efficiency, and most of the equipment faults are judged according to experience of operation and maintenance personnel, so that deviation is very easy to generate, and meanwhile, under the severe natural environment of a remote area, the inspection work of a photovoltaic power station is very difficult and dangerous, and the traditional manual inspection cannot meet the requirements for photovoltaic areas such as agricultural light complementation, fishing light complementation and roof power stations, and cannot realize the purpose of safe and efficient photovoltaic inspection.
Through using unmanned aerial vehicle, in the flight task, convenient and fast has carried out various inspection tasks such as photovoltaic board inspection by plane, transmission tower inspection by plane inspection, booster station equipment inspection by plane to provide clear reliable video and photo data, be used for user follow-up data processing and fault analysis.
Because the unmanned aerial vehicle inspection is compared with manual inspection, the inspection difficulty is small, the coverage area is large, the unmanned aerial vehicle inspection system becomes one of the important construction contents of the smart city and the smart park at present, in the photovoltaic power generation field, the existing unmanned aerial vehicle inspection system is generally provided with an infrared sensor camera and a visible light camera by an unmanned aerial vehicle, an image is transmitted to a ground service station in the flight process, a ground station server judges whether a solar power panel is abnormal such as missing and falling strings or not by using a machine vision algorithm, the judgment result is fed back to the unmanned aerial vehicle, and the unmanned aerial vehicle is controlled to carry out subsequent targeted inspection work.
However, due to the limitation of the size of the picture and the bandwidth of the wireless transmission technology, the time delay is large, the real-time performance and the accuracy of unmanned aerial vehicle control are difficult to achieve, for example, a common unmanned aerial vehicle picture, the size of the picture is 640 x 512 pixels, the storage space of the picture is about 1MB, the transmission per second is calculated according to 2.4G wireless close-range transmission, 8 seconds are required for completing the picture transmission, if the time is definitely longer according to a 4G transmission mode, the transmission stability cannot be guaranteed, and once a shielding is met, the closed environment is met, the signal quality is poor, and the image cannot be transmitted.
For machine vision, the quality of the image is also directly related to the accuracy of fault discrimination, the identification accuracy of the 2K pixel quality of the image based on MatLab processing is more than 10 times of that of 720P pixel quality, if the pixel is too high, more transmission time is consumed by the transmission from the unmanned aerial vehicle to the ground service station due to the speed limit of wireless transmission, the flight of the unmanned aerial vehicle is rapid, and a great time difference is necessarily generated between the identification fault and the linkage operation of the unmanned aerial vehicle.
Therefore, if higher accuracy and quicker response time are required, the time loss due to picture transmission must be solved.
Disclosure of Invention
The invention aims to provide an unmanned aerial vehicle inspection system based on edge calculation, which can reduce time loss caused by wireless transmission of pictures through an unmanned aerial vehicle carrying miniature image processing equipment, can reduce the pressure of ground station image processing through pre-recognition of picture faults by a GPU image processor, and solves the problems of overlarge frequency and long time consumption of picture transmission of the conventional unmanned aerial vehicle inspection system because normal solar photovoltaic panel images do not need to be transmitted to a ground service station.
In order to solve the technical problems, the invention is realized by the following technical scheme:
the invention relates to an unmanned aerial vehicle inspection system based on edge calculation, which comprises an unmanned aerial vehicle, a camera, a ground station and a server, wherein the ground station is electrically connected with the server, the unmanned aerial vehicle is connected with the ground station in real time through a real-time transmission system, a miniature image processing device is fixed at the bottom of the unmanned aerial vehicle, the camera is fixed at the bottom of the unmanned aerial vehicle and is electrically connected with a control system of the unmanned aerial vehicle, the miniature image processing device comprises a shell, a GPU (graphics processing unit) image processor and a data storage module are arranged in the shell, the data storage module and the GPU image processor are electrically connected with the control system of the unmanned aerial vehicle, and the GPU image processor outputs a Json format text and is connected with the ground station through the unmanned aerial vehicle control system and the real-time transmission system.
Further, the text in Json format is as follows:
wherein, { } the framed area is the output content, () is the fixed content of a certain field, [ ] is the possible value range of the field, 2 is the row number in 2 x 102, and 102 is the vertical column number of the image.
Further, the system also comprises a plurality of GPS coordinates, wherein the GPS coordinates are electrically connected with the ground station, the GPS coordinates are arranged in the area to be detected, and the GPS coordinates form a cruising path.
Further, a GIS platform is arranged in the system part of the server, a modeling module is arranged in the GIS platform, the modeling module comprises image modeling and GIS map modeling, and the server generates a GIS model of the region to be detected through the image modeling and the GIS map modeling.
Further, a picture recognition subsystem and an image processing subsystem are arranged in a system part of the server.
Further, a Web display foreground is arranged in a system part of the server, and the server displays GIS model information on a display module of the server through the Web display foreground.
Further, the server is connected with a mobile phone APP through a data uploading module and a data downloading module.
Further, the unmanned aerial vehicle is provided with a GNSS positioning system, and the camera is an infrared and visible binocular camera.
Further, an unmanned aerial vehicle inspection method based on edge calculation comprises the following steps:
SS01 unmanned aerial vehicle cruises: the unmanned aerial vehicle is operated to fly along a cruising path set by a program at a set height and a set speed;
SS02 unmanned aerial vehicle photographed: when the unmanned aerial vehicle is above the photovoltaic module, a photo is taken through a camera according to a set frequency (time period or distance);
SS03 photo pretreatment: the GPU image processor captures an infrared imaging picture shot by the unmanned aerial vehicle, performs fault recognition on the picture through an image processing technology, and recognizes whether hot spots and strings fall on the solar photovoltaic panel;
when the conditions of hot spots and strings falling are not recognized on the solar photovoltaic panel, the unmanned aerial vehicle is not processed and is controlled to continue flying;
when the conditions of hot spots and strings falling are identified on the solar photovoltaic panel, the unmanned aerial vehicle transmits an original image with a coordinate signal and the identified fault point offset to a server;
SS04 image processing: after receiving the picture with the coordinate signal, the server processes the image, judges whether the battery board has a hot spot effect, and gives an alarm signal to the battery board with the hot spot effect;
SS05 GIS icon: the GIS model is displayed on a display module through a Web display foreground, a processing result in SS04 is led into the GIS platform, and when hot spots are found, the hot spots are displayed at the corresponding positions on the GIS model for warning;
the SS06 transmits the processing result detected by the SS04 to the mobile phone APP at the same time, and the processing result is used for warning;
the SS07 feeds the judging result in the SS04 back to the unmanned aerial vehicle at the same time, and controls the unmanned aerial vehicle to carry out subsequent targeted inspection work;
and after the unmanned aerial vehicle flies to the tail end of the cruising path, the SS08 indicates that the inspection is finished, and controls the unmanned aerial vehicle to fly back to fall at the starting point.
The invention has the following beneficial effects:
1. according to the invention, the unmanned aerial vehicle carrying the miniature image processing equipment can reduce time loss caused by wireless transmission of the picture, the pressure of image processing of the ground station can be reduced through pre-identifying the picture faults by the GPU image processor, and the normal solar photovoltaic panel image does not need to be transmitted to the ground service station, so that the frequency of image transmission is greatly reduced, and the detection efficiency of the picture is greatly improved.
2. According to the invention, the information such as fault point offset and the like transmitted back by the unmanned aerial vehicle is identified and processed through the picture identification subsystem and the image processing subsystem which are arranged in the server, further matching processing can be performed, and more complex fault scenes such as cracks, breaks, pinholes and the like can be obtained through deep learning.
Of course, it is not necessary for any one product to practice the invention to achieve all of the advantages set forth above at the same time.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings that are needed for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
FIG. 1 is a system schematic block diagram of an unmanned aerial vehicle inspection system based on edge calculation;
FIG. 2 is a flow chart of the inspection method of the present invention;
fig. 3 is a flowchart of the processing of the image processing in the server of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, the invention discloses an unmanned aerial vehicle inspection system based on edge calculation, which comprises an unmanned aerial vehicle, a camera, a ground station and a server, wherein the ground station is electrically connected with the server, and the unmanned aerial vehicle is connected with the ground station in real time through a real-time transmission system;
the unmanned aerial vehicle is an outsourcing large-scale longitude and latitude M600 Pro unmanned aerial vehicle, the model continues the high load and excellent flight performance of the longitude and latitude M600, and the reliability is further improved by adopting a modularized design, so that the unmanned aerial vehicle is more convenient to use;
the camera is an outsourced Xinghan XT2 binocular camera, integrates an FLIR high-precision thermal imaging sensor and a 4K visible light sensor, and can record and transmit thermal imaging and visible light images simultaneously;
wherein the ground station is an outsourced Xinjiang PC ground station, and the ground station functions comprise the following functions: 1. an industrial-scale flight control algorithm; 2. a real-time flight instrument panel; 3. automatic return to voyage/one-key return to voyage in distress; 4. keyboard/custom rocker flight control; 5. a following function; 6. full-automatic flight control of beyond visual range; 7. fully autonomous takeoff/landing; 8. customizing the waypoints; 9. 6 preset route templates; 10. 3 waypoint turning modes are selectable; 11. controlling a self-defined steering engine channel; 12. setting a batch of route action tasks;
the bottom of the unmanned aerial vehicle is fixedly provided with a miniature image processing device, and the camera is fixed at the bottom of the unmanned aerial vehicle and is electrically connected with a control system of the unmanned aerial vehicle;
the miniature image processing device comprises a shell, wherein a GPU image processor and a data storage module are arranged in the shell, the data storage module and the GPU image processor are electrically connected with a control system of the unmanned aerial vehicle, and image information can be stored and reserved in the unmanned aerial vehicle through the data storage module;
and the GPU image processor outputs the text in the Json format and is connected with the ground station through the unmanned aerial vehicle control system and the real-time transmission system.
The text in the Json format is as follows:
wherein, { } the framed area is the output content, () is the fixed content of a certain field, [ ] is the possible value range of the field, 2 is the row number in 2 x 102, and 102 is the vertical column number of the image;
when the result of the judgment is normal, the binary byte stream of the picture and the fault offset are empty, so that the data transmission quantity can be greatly reduced, the transmission delay is reduced, after the ground station acquires the information, the picture with fault data can be overlapped through the binary byte stream of the picture and the fault offset, thereby further judging whether the picture is a hidden danger of crack, broken edge and the like, influencing the photovoltaic power generation, controlling the unmanned aerial vehicle to fly in low altitude and positioning the fault position in detail.
The system further comprises a plurality of GPS coordinates, wherein the GPS coordinates are electrically connected with the ground station, the GPS coordinates are arranged in the to-be-detected area, and the GPS coordinates form a cruising path.
The GIS model comprises a server and a GIS map, wherein a GIS platform is arranged in a system part of the server, a modeling module is arranged in the GIS platform, the modeling module comprises image modeling and GIS map modeling, and the server generates a GIS model of a region to be detected through the image modeling and the GIS map modeling.
The system part of the server is provided with a picture identification subsystem and an image processing subsystem, and the subsystem receives the thermal imaging picture with the GPS coordinate signal and processes the thermal imaging picture. The processed content comprises: 1. giving the average temperature of the battery plate; 2. judging whether the battery plate has a hot spot effect or not, and giving an alarm signal to the battery plate with the hot spot effect, wherein the alarm signal comprises the size of the hot spots, the number of the hot spots and the absolute temperature rise of the hot spots; 3. gps coordinates.
The system part of the server is provided with a Web display foreground, the server displays GIS model information on a display module of the server through the Web display foreground, the Web display foreground displays GIS graph information, and when faults are found, fault points are prompted and warned on the GIS graph.
The server is connected with a mobile phone APP through a data uploading module and a data downloading module.
The unmanned aerial vehicle is provided with a GNSS positioning system, the camera is an infrared and visible light binocular camera, the GNSS positioning system is an outsourcing GNSS positioning system of the type of the D-RTK in the Dajiang, the system is a high-precision navigation positioning system specially developed for an A3 series flight control system, three-dimensional positioning precision is improved to a centimeter level from a meter level through a real-time dynamic differential technology, positioning, height fixing and direction finding functions are integrated, the defects of a traditional GPS, a barometer and a compass are overcome, and an accurate and reliable system solution is provided for high-precision application requirements.
As shown in fig. 2, the unmanned aerial vehicle inspection method based on edge calculation includes the following steps:
SS01 unmanned aerial vehicle cruises: the unmanned aerial vehicle is operated to fly along a cruising path set by a program at a set height and a set speed;
SS02 unmanned aerial vehicle photographed: when the unmanned aerial vehicle is above the photovoltaic module, a photo is taken through a camera according to a set frequency (time period or distance);
SS03 photo pretreatment: the GPU image processor captures an infrared imaging picture shot by the unmanned aerial vehicle, performs fault recognition on the picture through an image processing technology, and recognizes whether hot spots and strings fall on the solar photovoltaic panel;
when the conditions of hot spots and strings falling are not recognized on the solar photovoltaic panel, the unmanned aerial vehicle is not processed and is controlled to continue flying;
when the conditions of hot spots and strings falling are identified on the solar photovoltaic panel, the unmanned aerial vehicle transmits an original image with a coordinate signal and the identified fault point offset to a server;
SS04 image processing: after receiving the picture with the coordinate signal, the server processes the image, judges whether the battery board has a hot spot effect, and gives an alarm signal to the battery board with the hot spot effect;
SS05 GIS icon: the GIS model is displayed on a display module through a Web display foreground, a processing result in SS04 is led into the GIS platform, and when hot spots are found, the hot spots are displayed at the corresponding positions on the GIS model for warning;
the SS06 transmits the processing result detected by the SS04 to the mobile phone APP at the same time, and the processing result is used for warning;
the SS07 feeds the judging result in the SS04 back to the unmanned aerial vehicle at the same time, and controls the unmanned aerial vehicle to carry out subsequent targeted inspection work;
and after the unmanned aerial vehicle flies to the tail end of the cruising path, the SS08 indicates that the inspection is finished, and controls the unmanned aerial vehicle to fly back to fall at the starting point.
In the description of the present specification, the descriptions of the terms "one embodiment," "example," "specific example," and the like, mean that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the present invention. In this specification, schematic representations of the above terms do not necessarily refer to the same embodiments or examples. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples.
The preferred embodiments of the invention disclosed above are intended only to assist in the explanation of the invention. The preferred embodiments are not exhaustive or to limit the invention to the precise form disclosed. Obviously, many modifications and variations are possible in light of the above teaching. The embodiments were chosen and described in order to best explain the principles of the invention and the practical application, to thereby enable others skilled in the art to best understand and utilize the invention. The invention is limited only by the claims and the full scope and equivalents thereof.
Claims (8)
1. Unmanned aerial vehicle system of patrolling and examining based on edge calculation, including unmanned aerial vehicle, camera, ground station and server electric connection, unmanned aerial vehicle passes through real-time transmission system and is connected its characterized in that with ground station in real time:
the bottom of the unmanned aerial vehicle is fixedly provided with a miniature image processing device, and the camera is fixed at the bottom of the unmanned aerial vehicle and is electrically connected with a control system of the unmanned aerial vehicle;
the miniature image processing device comprises a shell, wherein a GPU image processor and a data storage module are arranged in the shell, and the data storage module and the GPU image processor are electrically connected with a control system of the unmanned aerial vehicle;
the GPU image processor outputs a Json format text and is connected with the ground station through the unmanned aerial vehicle control system and the real-time transmission system;
the text in Json format is as follows:
{
picture position: (longitude, latitude);
pre-judging results: normal; [ Song/hot spot ]
Picture binary byte stream: {010100001010010100111000111111010101 … 010101};
fault offset: {4, 103, 104, 105, 106,2 x 102,2 x 103,2 x 104,2 x 105,2 x 106 … … x 103, 306 x 104}
}；
Wherein, { } the framed area is the output content, () is the fixed content of a certain field, [ ] is the possible value range of the field, 2 is the row number in 2 x 102, and 102 is the vertical column number of the image.
2. The unmanned aerial vehicle inspection system based on edge calculation of claim 1, further comprising a plurality of GPS coordinates, wherein the plurality of GPS coordinates are electrically connected with a ground station, the plurality of GPS coordinates are installed in an area to be inspected, and the plurality of GPS coordinates form a cruising path.
3. The unmanned aerial vehicle inspection system based on edge calculation according to claim 1, wherein a GIS platform is arranged in a system part of the server, a modeling module is arranged in the GIS platform, the modeling module comprises image modeling and GIS map modeling, and the server generates a GIS model of an area to be inspected through the image modeling and the GIS map modeling.
4. The unmanned aerial vehicle inspection system based on edge calculation of claim 1, wherein a picture recognition subsystem and an image processing subsystem are provided in the system portion of the server.
5. The unmanned aerial vehicle inspection system based on edge calculation according to claim 3, wherein a Web display foreground is arranged in a system part of the server, and the server displays GIS model information on a display module of the server through the Web display foreground.
6. The unmanned aerial vehicle inspection system based on edge calculation of claim 1, wherein the server is connected with a mobile phone APP through a data uploading module and a data downloading module.
7. The unmanned aerial vehicle inspection system based on edge calculation of claim 1, wherein the unmanned aerial vehicle is provided with a GNSS positioning system, and the camera is a binocular camera of infrared light and visible light.
8. The unmanned aerial vehicle inspection method based on edge calculation according to any one of claims 1 to 7, comprising the steps of:
SS01 unmanned aerial vehicle cruises: the unmanned aerial vehicle is operated to fly along a cruising path set by a program at a set height and a set speed;
SS02 unmanned aerial vehicle photographed: when the unmanned aerial vehicle is above the photovoltaic module, a photo is taken through a camera according to a set frequency (time period or distance);
SS03 photo pretreatment: the GPU image processor captures an infrared imaging picture shot by the unmanned aerial vehicle, performs fault recognition on the picture through an image processing technology, and recognizes whether hot spots and strings fall on the solar photovoltaic panel;
when the conditions of hot spots and strings falling are not recognized on the solar photovoltaic panel, the unmanned aerial vehicle is not processed and is controlled to continue flying;
when the conditions of hot spots and strings falling are identified on the solar photovoltaic panel, the unmanned aerial vehicle transmits an original image with a coordinate signal and the identified fault point offset to a server;
SS04 image processing: after receiving the picture with the coordinate signal, the server processes the image, judges whether the battery board has a hot spot effect, and gives an alarm signal to the battery board with the hot spot effect;
SS05 GIS icon: the GIS model is displayed on a display module through a Web display foreground, a processing result in SS04 is led into the GIS platform, and when hot spots are found, the hot spots are displayed at the corresponding positions on the GIS model for warning;
the SS06 transmits the processing result detected by the SS04 to the mobile phone APP at the same time, and the processing result is used for warning;
the SS07 feeds the judging result in the SS04 back to the unmanned aerial vehicle at the same time, and controls the unmanned aerial vehicle to carry out subsequent targeted inspection work;
and after the unmanned aerial vehicle flies to the tail end of the cruising path, the SS08 indicates that the inspection is finished, and controls the unmanned aerial vehicle to fly back to fall at the starting point.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010197746.1A CN111522355B (en) | 2020-03-19 | 2020-03-19 | Unmanned aerial vehicle inspection system based on edge calculation and inspection method thereof |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010197746.1A CN111522355B (en) | 2020-03-19 | 2020-03-19 | Unmanned aerial vehicle inspection system based on edge calculation and inspection method thereof |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111522355A CN111522355A (en) | 2020-08-11 |
| CN111522355B true CN111522355B (en) | 2023-06-13 |
Family
ID=71901932
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010197746.1A Active CN111522355B (en) | 2020-03-19 | 2020-03-19 | Unmanned aerial vehicle inspection system based on edge calculation and inspection method thereof |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111522355B (en) |
Families Citing this family (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI742864B (en) * | 2020-09-25 | 2021-10-11 | 向陽優能電力股份有限公司 | A solar panel detection management system |
| CN114667493A (en) * | 2020-10-22 | 2022-06-24 | 华为数字能源技术有限公司 | Power station patrol system and power station patrol method |
| CN112311872A (en) * | 2020-10-29 | 2021-02-02 | 山东翔迈智能科技有限公司 | Unmanned aerial vehicle nest autonomous cruise network system |
| CN112595936A (en) * | 2020-11-06 | 2021-04-02 | 广西电网有限责任公司崇左供电局 | Power transmission line composite insulator intelligent detection system based on unmanned aerial vehicle patrols and examines |
| CN112668847B (en) * | 2020-12-17 | 2023-11-24 | 国网山西省电力公司运城供电公司 | Autonomous inspection integrated management system for distribution network line unmanned aerial vehicle |
| CN112904890B (en) * | 2021-01-15 | 2023-06-30 | 北京国网富达科技发展有限责任公司 | Unmanned aerial vehicle automatic inspection system and method for power line |
| CN113852994B (en) * | 2021-11-18 | 2023-04-18 | 南京信息工程大学 | High-altitude base station cluster auxiliary edge calculation method used in emergency communication |
| CN114489121A (en) * | 2021-12-31 | 2022-05-13 | 新奥数能科技有限公司 | Inspection method and device for photovoltaic power station |
| CN114859964A (en) * | 2022-04-20 | 2022-08-05 | 贵州电网有限责任公司 | Anti-interference system suitable for transmission line patrols and examines unmanned aerial vehicle and uses |
| CN116225028B (en) * | 2023-05-04 | 2023-07-21 | 尚特杰电力科技有限公司 | Forward driving deviation correcting method and deviation correcting device for cleaning robot |
| CN117236936A (en) * | 2023-11-11 | 2023-12-15 | 中节能（新泰）太阳能科技有限公司 | Unmanned aerial vehicle-based photovoltaic power station obstacle positioning method |
| CN118170153A (en) * | 2024-05-09 | 2024-06-11 | 鹰驾科技（深圳）有限公司 | Unmanned aerial vehicle edge calculation processing method based on 360-degree looking around camera assistance |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015131462A1 (en) * | 2014-03-07 | 2015-09-11 | 国家电网公司 | Centralized monitoring system and monitoring method for unmanned aerial vehicle to patrol power transmission line |
| CN105929838A (en) * | 2016-05-20 | 2016-09-07 | 腾讯科技（深圳）有限公司 | Flight control method of aircraft, mobile terminal and flight control end |
| CN109187558A (en) * | 2018-10-10 | 2019-01-11 | 中南大学 | A kind of photovoltaic plant automatic tour inspection system based on unmanned plane |
-
2020
- 2020-03-19 CN CN202010197746.1A patent/CN111522355B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015131462A1 (en) * | 2014-03-07 | 2015-09-11 | 国家电网公司 | Centralized monitoring system and monitoring method for unmanned aerial vehicle to patrol power transmission line |
| CN105929838A (en) * | 2016-05-20 | 2016-09-07 | 腾讯科技（深圳）有限公司 | Flight control method of aircraft, mobile terminal and flight control end |
| CN109187558A (en) * | 2018-10-10 | 2019-01-11 | 中南大学 | A kind of photovoltaic plant automatic tour inspection system based on unmanned plane |
Non-Patent Citations (1)
| Title |
|---|
| 加鹤萍 ; .基于机翼变形的新型电力巡线固定翼无人机的研制.内蒙古电力技术.2013,(03),第33-37页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111522355A (en) | 2020-08-11 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111522355B (en) | Unmanned aerial vehicle inspection system based on edge calculation and inspection method thereof | |
| US11378458B2 (en) | Airborne inspection systems and methods | |
| CN101201248B (en) | Aviation close range photography displacement measurement system based on unmanned aerial vehicle as well as measurement method thereof | |
| US20220077820A1 (en) | Method and system for soar photovoltaic power station monitoring | |
| CN110244766B (en) | Planning method and system for unmanned aerial vehicle routing inspection route of photovoltaic power station | |
| US20220301302A1 (en) | Air and sea based fishing data collection and analysis systems and methods | |
| CN107589758A (en) | A kind of intelligent field unmanned plane rescue method and system based on double source video analysis | |
| CN202094531U (en) | Power transmission line inspection device suitable for unmanned aerial vehicle | |
| CN107144281B (en) | Unmanned aerial vehicle indoor positioning system and positioning method based on cooperative targets and monocular vision | |
| CN110127000B (en) | Intelligent navigation eye system for transport ship | |
| Xing et al. | Multi-UAV cooperative system for search and rescue based on YOLOv5 | |
| CN213302860U (en) | Three-dimensional visual obstacle avoidance system of unmanned aerial vehicle | |
| WO2018045354A2 (en) | Unmanned aerial system assisted navigational systems and methods | |
| CN201133815Y (en) | Aviation close shot displacement measuring device based on unmanned plane | |
| CN112286228A (en) | Unmanned aerial vehicle three-dimensional visual obstacle avoidance method and system | |
| CN206236228U (en) | A kind of forest fire monitoring early-warning system based on unmanned plane | |
| CN113867386A (en) | Unmanned aerial vehicle inspection method and system for pipe belt machine | |
| CN111652276B (en) | All-weather portable multifunctional bionic positioning and attitude-determining viewing system and method | |
| CN113063401A (en) | Unmanned aerial vehicle aerial survey system | |
| US20220221857A1 (en) | Information processing apparatus, information processing method, program, and information processing system | |
| CN116974298A (en) | Single-line laser radar-based transmission line simulated flight method and system | |
| CN115826596B (en) | Intelligent thermal power plant chimney inspection method and system based on multi-rotor unmanned aerial vehicle | |
| CN115355952B (en) | Intelligent inspection system for crude oil storage tank | |
| CN217879087U (en) | Unmanned aerial vehicle CO2 detection system and device | |
| Lin et al. | Application of multi-band networking and UAV in natural environment protection and disaster prevention |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |