CN112270267B - Camera shooting identification system capable of automatically capturing line faults - Google Patents
Camera shooting identification system capable of automatically capturing line faults Download PDFInfo
- Publication number
- CN112270267B CN112270267B CN202011180197.3A CN202011180197A CN112270267B CN 112270267 B CN112270267 B CN 112270267B CN 202011180197 A CN202011180197 A CN 202011180197A CN 112270267 B CN112270267 B CN 112270267B
- Authority
- CN
- China
- Prior art keywords
- recognition
- image
- recognition system
- line
- information
- 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
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
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/40—Scenes; Scene-specific elements in video content
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/02—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP]
- H04L67/025—Protocols based on web technology, e.g. hypertext transfer protocol [HTTP] for remote control or remote monitoring of applications
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/01—Protocols
- H04L67/12—Protocols specially adapted for proprietary or special-purpose networking environments, e.g. medical networks, sensor networks, networks in vehicles or remote metering networks
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L67/00—Network arrangements or protocols for supporting network services or applications
- H04L67/50—Network services
- H04L67/52—Network services specially adapted for the location of the user terminal
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/66—Remote control of cameras or camera parts, e.g. by remote control devices
- H04N23/661—Transmitting camera control signals through networks, e.g. control via the Internet
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04N—PICTORIAL COMMUNICATION, e.g. TELEVISION
- H04N23/00—Cameras or camera modules comprising electronic image sensors; Control thereof
- H04N23/60—Control of cameras or camera modules
- H04N23/695—Control of camera direction for changing a field of view, e.g. pan, tilt or based on tracking of objects
-
- 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
- Y04S10/52—Outage or fault management, e.g. fault detection or location
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Multimedia (AREA)
- Data Mining & Analysis (AREA)
- Computer Networks & Wireless Communication (AREA)
- Software Systems (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Traffic Control Systems (AREA)
- Studio Devices (AREA)
Abstract
The invention discloses a camera shooting identification system capable of automatically capturing line faults, which belongs to the field of electric power systems and comprises an air identification system and a ground identification system, wherein the air identification system and the ground identification system both comprise an identification unit, a storage unit, a control unit and a wireless device, the control unit controls the identification unit to identify information, when the identified information belongs to alarm information, the storage unit stores the information and transmits data to a cloud server through the wireless device, the cloud server is connected with a cloud control end, the cloud control end carries out secondary identification on the alarm information, and after targets meeting characteristics are screened, a map is drawn on the track of the targets according to time and place, so that people can conveniently find and track. The circuit fault and other fault problems can be effectively identified.
Description
Technical Field
The invention relates to the field of power systems, in particular to a shooting identification system capable of automatically shooting line faults.
Background
With the development of the power grid, dense lines are often easily entangled by kites or plastic bags, etc., which carries a certain risk to the lines, which often causes problems due to untimely handling. Traditional manual power line inspection methods are difficult in condition and low in efficiency, and first-line power inspection workers occasionally encounter the risks of being "dog-kept" and "snake-bitten".
Disclosure of Invention
The invention aims to solve the problem of providing a camera shooting identification system capable of automatically capturing line faults, which can effectively identify the line faults and other fault problems.
In order to solve the technical problems, the invention provides a camera shooting recognition system capable of automatically capturing line faults, which comprises an air recognition system and a ground recognition system, wherein the air recognition system and the ground recognition system both comprise a recognition unit, a storage unit, a control unit and a wireless device, the control unit controls the unit to carry out image analysis recognition on line images, when recognized image information belongs to alarm information, the storage unit stores the information and transmits data to a cloud server through the wireless device, the cloud server is connected with a cloud control end, the cloud control end carries out secondary recognition on the alarm information, after a target conforming to characteristics is screened, the target is positioned according to time and place, a map is drawn according to the coordinate positions of the target and a patrol personnel, yellow points are marked, and the patrol personnel can conveniently search and track; the aerial recognition system performs large-range line recognition to find out an alarm point and transmits the alarm point to the cloud control end, the cloud control end transmits information to a user after secondary recognition and confirmation, the user performs supplementary recognition on the alarm point by using the ground recognition system, the information is transmitted to the cloud control end after supplementary recognition and confirmation, the cloud control end modifies the yellow point into the black point, and the warning fault is to be eliminated.
Preferably, the aerial recognition system comprises a visible light image recognition device, an invisible light image recognition device, a positioning module, a wireless module, a flight control system and a ground controller, wherein the aerial wireless module is connected with the flight control system, the ground controller is internally provided with the ground wireless module, the aerial wireless module is in wireless connection with the ground wireless module, the flight control system drives the aerial recognition system to drive the visible light image recognition device and the invisible light image recognition device to recognize along a specified route, and the visible light image recognition device and the invisible light image respectively recognize equipment in the image and equipment temperature.
Preferably, the ground recognition system comprises a solar power supply module, a recognition module, a positioning module and a wireless transmission module, wherein the solar power supply module supplies power to the recognition system, the recognition module and the positioning module transmit information to the control unit in real time through the wireless transmission module, and the recognition module recognizes equipment in a video.
Preferably, the acquired images or videos of the aerial or terrestrial identification systems have geographic location markers and time markers.
The camera shooting identification method capable of automatically capturing line faults comprises the following steps:
(1) The air recognition system performs daily inspection and recognizes the power grid line in a large range;
(2) When the air recognition system recognizes a fault line, positioning is sent to the cloud server;
(3) The cloud controller performs secondary identification on the fault line, then sends and positions the fault line to a patrol personnel, and the patrol personnel arrive at an alarm point according to the map information, performs supplementary identification on the alarm point by using a ground identification system, and performs fault confirmation uploading or overhaul;
(4) And after the supplementary identification confirmation, transmitting information to a cloud control end, wherein the cloud control end modifies the yellow points into black points, and warns that the fault is to be removed.
Preferably, the method further comprises the following steps:
(1) The method comprises the steps that an air recognition system and a ground recognition system respectively acquire video information by utilizing a self recognition system, recognize each frame of video image in the video information, acquire a line image contained in the video information, and store the image into a storage module;
(2) The processor reads the information of the storage module to match the shot line image with the image information of the normal line, and a detection result is generated; judging whether the similarity is lower than a preset threshold value or not; if the similarity is lower than a preset threshold, judging that the line image contains an abnormal image, and determining that the detection result does not accord with the standard. And if the similarity is greater than or equal to a preset threshold value, judging that the circuit image does not contain abnormal information.
(3) The network communication module acquires a detection result, reads mobile data of data corresponding to the detection result which does not meet the standard, and uploads the mobile data to the cloud server;
(4) After the uploading is successful, the network communication module deletes relevant data from the local equipment;
(5) If the network is abnormal, the network communication module stores the result queue and waits until the network is uploaded again normally.
Preferably, the step (1) specifically includes:
the processor extracts frames of video information of the camera module, intercepts images of different time points according to the self-defined frequency, and stores the images into the storage module or stores directly acquired image information into the storage module to form a line image set.
Preferably, each frame of video image described in the step (1) specifically includes:
(1) The control end acquires a power grid line image to be detected; extracting a feature map of the power grid line image to be detected;
(2) Determining an area image corresponding to the feature map according to a preset candidate detection frame;
(3) Pooling the feature map and the region image to obtain feature vectors;
(4) Inputting the feature vector into a trained width learning network model to obtain the similarity between the power grid line image to be detected and each fault class and the candidate frame coordinates of the power grid line image to be detected;
(5) And selecting the fault category with the highest similarity as a line fault result of the power grid line image to be detected.
Preferably, the air recognition system specifically comprises the following operation methods:
1) The GPS positioning module I acquires and records the initial unmanned aerial vehicle position when the aerial recognition system takes off;
2): the visible light intelligent recognition device is used for collecting, processing and intelligently recognizing visible light images, and then data can be transmitted to the flight control system;
3): the invisible light intelligent recognition device is used for collecting, processing and intelligently recognizing invisible light images, then data can be transmitted to the flight control system, and the flight control system is used for carrying out auxiliary judgment on visible light data combined by the flight control system;
4): the flight control system controls the aerial recognition system to fly along the line direction.
Preferably, a cradle head is arranged in the ground recognition system, when the solar battery is used, the cradle head rotates at set angles at intervals, and the recognition system performs video acquisition and recognition.
The invention has the beneficial effects that:
according to the invention, through the mode of combining an air system and a ground system, the large-data camera is utilized for identification, and the screening process of the large-data is placed at the front end, so that excessive pressure on a server is avoided, the problem can be effectively solved, the data can be effectively screened, and the fault can be simulated and judged by using countless cameras.
Drawings
Fig. 1: the system of the invention is connected with a schematic diagram;
fig. 2: the invention relates to an aerial recognition system connection schematic diagram;
fig. 3: the ground identification system is connected with a schematic diagram;
fig. 4: the working flow diagram of the invention;
fig. 5: the present invention identifies a flowchart.
Detailed Description
Example 1:
as shown in the figure, the camera shooting identification system capable of automatically capturing line faults comprises an air identification system and a ground identification system, wherein the air identification system and the ground identification system both comprise an identification unit, a storage unit, a control unit and a wireless device, the control unit controls the identification unit to carry out image analysis and identification on line images, when the identified image information belongs to alarm information, the storage unit stores the information and transmits data to a cloud server through the wireless device, the cloud server is connected with a cloud control end, the cloud control end carries out secondary identification on the alarm information, and an acquired image or video of the air identification system or the ground identification system has a geographic position mark and a time mark. After the targets meeting the characteristics are screened out, positioning the targets according to time and place, drawing a map according to the coordinate positions of the targets and the patrol personnel, and marking yellow points, so that the patrol personnel can conveniently search and track; the aerial recognition system performs large-range line recognition to find out an alarm point and transmits the alarm point to the cloud control end, the cloud control end transmits information to a user after secondary recognition and confirmation, the user performs supplementary recognition on the alarm point by using the ground recognition system, the information is transmitted to the cloud control end after supplementary recognition and confirmation, the cloud control end modifies the yellow point into the black point, and the warning fault is to be eliminated.
The aerial recognition system comprises a visible light image recognition device, an invisible light image recognition device, a positioning module, a wireless module, a flight control system and a ground controller, wherein the aerial wireless module is connected with the flight control system, the ground controller is internally provided with the ground wireless module, the aerial wireless module is in wireless connection with the ground wireless module, the flight control system drives the aerial recognition system to drive the visible light image recognition device and the invisible light image recognition device to recognize along a specified route, and the visible light image recognition device and the invisible light image respectively recognize equipment and equipment temperature in the image.
The ground recognition system comprises a solar power supply module, a recognition module and a positioning module, wherein the solar power supply module supplies power to the recognition system, the recognition module and the positioning module transmit information to the control unit in real time through the wireless transmission module, and the recognition module recognizes equipment in a video.
The camera shooting identification method capable of automatically capturing line faults comprises the following steps:
(1) The air recognition system performs daily inspection and recognizes the power grid line in a large range; the control end acquires a power grid line image to be detected; extracting a feature map of the power grid line image to be detected; determining an area image corresponding to the feature map according to a preset candidate detection frame; pooling the feature map and the region image to obtain feature vectors; inputting the feature vector into a trained width learning network model to obtain the similarity between the power grid line image to be detected and each fault class and the candidate frame coordinates of the power grid line image to be detected; and selecting the fault category with the highest similarity as a line fault result of the power grid line image to be detected.
(2) When the air recognition system recognizes a fault line, positioning is sent to the cloud server;
(3) The cloud controller performs secondary identification on the fault line, then sends and positions the fault line to a patrol personnel, and the patrol personnel arrive at an alarm point according to the map information, performs supplementary identification on the alarm point by using a ground identification system, and performs fault confirmation uploading or overhaul;
(4) The aerial recognition system and the ground recognition system respectively acquire video information by utilizing the self recognition system and recognize each frame of video image in the video information, specifically, the processor performs frame extraction on the video information of the camera module, intercepts images at different time points according to the self-defined frequency, and stores the images into the storage module or stores the directly acquired image information into the storage module to form a line image set.
(5) The processor reads the information of the storage module to match the shot line image with the image information of the normal line, and a detection result is generated; judging whether the similarity is lower than a preset threshold value or not; if the similarity is lower than a preset threshold, judging that the line image contains an abnormal image, wherein the detection result is not in accordance with the standard; and if the similarity is greater than or equal to a preset threshold value, judging that the circuit image does not contain abnormal information.
(6) The network communication module acquires a detection result, reads mobile data of data corresponding to the detection result which does not meet the standard, and uploads the mobile data to the cloud server;
(7) After the uploading is successful, the network communication module deletes relevant data from the local equipment;
(8) If the network is abnormal, the network communication module stores the result queue and waits until the network is uploaded again normally.
(9) And after the supplementary identification confirmation, transmitting information to a cloud control end, wherein the cloud control end modifies the yellow points into black points, and warns that the fault is to be removed.
The specific operation method of the air recognition system comprises the following steps:
1) The GPS positioning module I acquires and records the initial unmanned aerial vehicle position when the aerial recognition system takes off;
2): the visible light intelligent recognition device is used for collecting, processing and intelligently recognizing visible light images, and then data can be transmitted to the flight control system;
3): the invisible light intelligent recognition device is used for collecting, processing and intelligently recognizing invisible light images, then data can be transmitted to the flight control system, and the flight control system is used for carrying out auxiliary judgment on visible light data combined by the flight control system;
4): the flight control system controls the aerial recognition system to fly along the line direction.
The ground recognition system is internally provided with a cradle head, when the solar battery is used, the cradle head rotates at set angles at intervals, and the recognition system performs video acquisition and recognition.
Example 2:
the method utilizes popularity of the mobile video terminals of the unmanned aerial vehicle recorder and the unmanned aerial vehicle, obtains matching information of a target object at a server side by utilizing the mobile video terminal, matches the stored image data in the mobile video terminal according to the matching information, and when the image data associated with the target object is matched, sends the image data associated with the target object to the server side to determine a final matching result, exerts a monitoring coverage surface to the greatest extent, intelligently identifies a power line, an insulator and other devices through a visible light device, and assists in identifying the power line through an infrared thermal imager, then transmits the identified line information to the unmanned aerial vehicle, and a flight control system in the unmanned aerial vehicle can control the aircraft to fly along the line direction. The ground-based intelligent air-crash monitoring system is little in geographic influence, strong in mobility and flexibility, and free of risk of casualties due to the fact that patrol personnel operate on the ground. The defect type can be identified, the inspection effect is good, the inspection type is multiple, and the tower body, the insulator and the like are realized. The personnel utilization rate is high. An unmanned aerial vehicle can be controlled by only 1 person, can fly along a power line through image recognition, and automatically return to the voyage when flying to a certain distance or power is insufficient.
It will be appreciated by those skilled in the art that embodiments of the present application may be provided as a method, system, or computer program product. Accordingly, the present application may take the form of an entirely hardware embodiment, an entirely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present application 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, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
The present application is described with reference to flowchart illustrations and/or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each flow and/or block of the flowchart illustrations and/or block diagrams, and combinations of flows and/or blocks in the flowchart illustrations 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.
Claims (10)
1. The camera shooting recognition system is characterized by comprising an aerial recognition system and a ground recognition system, wherein the aerial recognition system and the ground recognition system both comprise a recognition unit, a storage unit, a control unit and a wireless device, the control unit controls the recognition unit to carry out image analysis recognition on a line image, when recognized image information belongs to alarm information, the storage unit stores the information and transmits data to a cloud server through the wireless device, the cloud server is connected with a cloud control end, the cloud control end carries out secondary recognition on the alarm information, and after targets meeting characteristics are screened, the targets are positioned according to time and place, a map is drawn according to coordinate positions of the targets and patrol personnel, yellow points are marked, and the patrol personnel can conveniently search and track; the aerial recognition system performs large-range line recognition to find out an alarm point and transmits the alarm point to the cloud control end, the cloud control end transmits information to a user after secondary recognition and confirmation, the user performs supplementary recognition on the alarm point by using the ground recognition system, the information is transmitted to the cloud control end after supplementary recognition and confirmation, the cloud control end modifies the yellow point into the black point, and the warning fault is to be eliminated.
2. The camera recognition system capable of automatically capturing line faults according to claim 1, wherein the aerial recognition system comprises a visible light image recognition device, an invisible light image recognition device, a positioning module, a wireless module, a flight control system and a ground controller, the aerial wireless module is connected with the flight control system, the ground controller is internally provided with the ground wireless module, the aerial wireless module is in wireless connection with the ground wireless module, the flight control system drives the aerial recognition system to drive the visible light image recognition device and the invisible light image recognition device to recognize along a specified line, and the visible light image recognition device and the invisible light image recognize equipment in the image and equipment temperature respectively.
3. The camera shooting recognition system capable of automatically capturing line faults according to claim 1, wherein the ground recognition system comprises a solar power supply module, a recognition module and a positioning module, the solar power supply module supplies power to the recognition system, the recognition module and the positioning module transmit information to a control unit in real time through the wireless transmission module, and the recognition module recognizes equipment in a video.
4. A camera recognition system for automatically taking a snap-shot line fault as claimed in claim 1, wherein the captured image or video of the aerial recognition system or the ground recognition system has a geographical location mark and a time mark.
5. A camera recognition system for automatically capturing line faults as claimed in any of claims 1 to 4, wherein the recognition process comprises the steps of:
(1) The air recognition system performs daily inspection and recognizes the power grid line in a large range;
(2) When the air recognition system recognizes a fault line, positioning is sent to the cloud server;
(3) The cloud controller performs secondary identification on the fault line, then sends and positions the fault line to a patrol personnel, and the patrol personnel arrive at an alarm point according to the map information, performs supplementary identification on the alarm point by using a ground identification system, and performs fault confirmation uploading or overhaul;
(4) And after the supplementary identification confirmation, transmitting information to a cloud control end, wherein the cloud control end modifies the yellow points into black points, and warns that the fault is to be removed.
6. The camera recognition system for automatically capturing line faults of claim 5, wherein the recognition process further comprises the steps of:
(1) The method comprises the steps that an air recognition system and a ground recognition system respectively acquire video information by utilizing a self recognition system, recognize each frame of video image in the video information, acquire a line image contained in the video information, and store the image into a storage module;
(2) The processor reads the information of the storage module to match the shot line image with the image information of the normal line, and a detection result is generated; judging whether the similarity is lower than a preset threshold value or not; if the similarity is lower than a preset threshold, judging that the line image contains an abnormal image, wherein the detection result is not in accordance with the standard; if the similarity is greater than or equal to a preset threshold value, judging that the circuit image does not contain abnormal information;
(3) The network communication module acquires a detection result, reads mobile data of data corresponding to the detection result which does not meet the standard, and uploads the mobile data to the cloud server;
(4) After the uploading is successful, the network communication module deletes relevant data from the local equipment;
(5) If the network is abnormal, the network communication module stores the result queue and waits until the network is uploaded again normally.
7. The system for automatically capturing line faults as claimed in claim 6, wherein each frame of video image in step (1) specifically comprises:
the processor extracts frames of video information of the camera module, intercepts images of different time points according to the self-defined frequency, and stores the images into the storage module or stores directly acquired image information into the storage module to form a line image set.
8. The system for automatically capturing line faults as claimed in claim 6, wherein the identifying in step (1) specifically comprises:
(1) The control end acquires a power grid line image to be detected; extracting a feature map of the power grid line image to be detected;
(2) Determining an area image corresponding to the feature map according to a preset candidate detection frame;
(3) Pooling the feature map and the region image to obtain feature vectors;
(4) Inputting the feature vector into a trained width learning network model to obtain the similarity between the power grid line image to be detected and each fault class and the candidate frame coordinates of the power grid line image to be detected;
(5) And selecting the fault category with the highest similarity as a line fault result of the power grid line image to be detected.
9. The camera recognition system capable of automatically capturing line faults as claimed in claim 5, wherein the air recognition system specifically comprises the following operation methods:
1) The GPS positioning module I acquires and records the initial unmanned aerial vehicle position when the aerial recognition system takes off;
2) The visible light intelligent recognition device is used for collecting, processing and intelligently recognizing visible light images, and then data can be transmitted to the flight control system;
3) The invisible light intelligent recognition device is used for collecting, processing and intelligently recognizing invisible light images, then data can be transmitted to the flight control system, and the flight control system is used for carrying out auxiliary judgment on visible light data combined by the flight control system;
4) The flight control system controls the aerial recognition system to fly along the line direction.
10. The system for automatically capturing and identifying line faults as claimed in claim 5, wherein a cradle head is arranged in the ground identification system, and rotates at set angles at intervals when a solar cell is used, and the identification system performs video acquisition and identification.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011180197.3A CN112270267B (en) | 2020-10-29 | 2020-10-29 | Camera shooting identification system capable of automatically capturing line faults |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011180197.3A CN112270267B (en) | 2020-10-29 | 2020-10-29 | Camera shooting identification system capable of automatically capturing line faults |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112270267A CN112270267A (en) | 2021-01-26 |
| CN112270267B true CN112270267B (en) | 2023-08-08 |
Family
ID=74344896
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011180197.3A Active CN112270267B (en) | 2020-10-29 | 2020-10-29 | Camera shooting identification system capable of automatically capturing line faults |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112270267B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113301142B (en) * | 2021-05-21 | 2022-05-31 | 广州科技贸易职业学院 | Network security monitoring method and system based on Internet of things |
| CN113515655A (en) * | 2021-06-24 | 2021-10-19 | 国网山东省电力公司邹城市供电公司 | Fault identification method and device based on image classification |
| CN113591574B (en) * | 2021-06-29 | 2024-02-27 | 山东信通电子股份有限公司 | Power transmission line inspection method and device based on laser radar |
| CN113743324B (en) * | 2021-09-07 | 2022-10-18 | 易科捷(武汉)生态科技有限公司成都分公司 | Automatic updating type fish identification system based on Internet of things |
| CN113542698B (en) * | 2021-09-16 | 2022-01-28 | 广州洛克韦陀安防科技有限公司 | Security protection real-time monitoring system based on 5G communication network |
| CN117351381A (en) * | 2023-12-05 | 2024-01-05 | 国网山东省电力公司淄博供电公司 | GCN-based inspection image foreign matter identification method, GCN-based inspection image foreign matter identification system, terminal and storage medium |
| CN117612047B (en) * | 2024-01-23 | 2024-04-12 | 国网湖北省电力有限公司信息通信公司 | Unmanned aerial vehicle inspection image recognition method for power grid based on AI large model |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105100728A (en) * | 2015-08-18 | 2015-11-25 | 零度智控（北京）智能科技有限公司 | Unmanned aerial vehicle video tracking shooting system and method |
| CN106504362A (en) * | 2016-10-18 | 2017-03-15 | 国网湖北省电力公司检修公司 | Power transmission and transformation system method for inspecting based on unmanned plane |
| CN106598064A (en) * | 2016-10-19 | 2017-04-26 | 广东容祺智能科技有限公司 | Unmanned aerial vehicle circuit line intelligent identification device and method |
| CN107148777A (en) * | 2016-10-26 | 2017-09-08 | 深圳前海达闼云端智能科技有限公司 | Intelligent patrol device, cloud control device, patrol method, control method, robot, controller, and non-transitory computer-readable storage medium |
| CN108776491A (en) * | 2018-05-23 | 2018-11-09 | 广东容祺智能科技有限公司 | Unmanned plane multiple target monitoring system and monitoring method based on dynamic image identification |
| CN109270958A (en) * | 2018-11-20 | 2019-01-25 | 国网四川省电力公司广安供电公司 | A kind of transmission line malfunction quickly positions UAV system automatically |
| CN109447048A (en) * | 2018-12-25 | 2019-03-08 | 苏州闪驰数控系统集成有限公司 | A kind of artificial intelligence early warning system |
| CN110633629A (en) * | 2019-08-02 | 2019-12-31 | 广东电网有限责任公司清远供电局 | Power grid inspection method, device, equipment and storage medium based on artificial intelligence |
| CN111784026A (en) * | 2020-05-28 | 2020-10-16 | 国网信通亿力科技有限责任公司 | Cloud-side cooperative sensing-based all-dimensional physical examination system for electrical equipment of transformer substation |
-
2020
- 2020-10-29 CN CN202011180197.3A patent/CN112270267B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105100728A (en) * | 2015-08-18 | 2015-11-25 | 零度智控（北京）智能科技有限公司 | Unmanned aerial vehicle video tracking shooting system and method |
| CN106504362A (en) * | 2016-10-18 | 2017-03-15 | 国网湖北省电力公司检修公司 | Power transmission and transformation system method for inspecting based on unmanned plane |
| CN106598064A (en) * | 2016-10-19 | 2017-04-26 | 广东容祺智能科技有限公司 | Unmanned aerial vehicle circuit line intelligent identification device and method |
| CN107148777A (en) * | 2016-10-26 | 2017-09-08 | 深圳前海达闼云端智能科技有限公司 | Intelligent patrol device, cloud control device, patrol method, control method, robot, controller, and non-transitory computer-readable storage medium |
| WO2018076191A1 (en) * | 2016-10-26 | 2018-05-03 | 深圳前海达闼云端智能科技有限公司 | Smart patrol device, cloud control device, patrol method, control method, robot, controller, and non-transient computer readable storage medium |
| CN108776491A (en) * | 2018-05-23 | 2018-11-09 | 广东容祺智能科技有限公司 | Unmanned plane multiple target monitoring system and monitoring method based on dynamic image identification |
| CN109270958A (en) * | 2018-11-20 | 2019-01-25 | 国网四川省电力公司广安供电公司 | A kind of transmission line malfunction quickly positions UAV system automatically |
| CN109447048A (en) * | 2018-12-25 | 2019-03-08 | 苏州闪驰数控系统集成有限公司 | A kind of artificial intelligence early warning system |
| CN110633629A (en) * | 2019-08-02 | 2019-12-31 | 广东电网有限责任公司清远供电局 | Power grid inspection method, device, equipment and storage medium based on artificial intelligence |
| CN111784026A (en) * | 2020-05-28 | 2020-10-16 | 国网信通亿力科技有限责任公司 | Cloud-side cooperative sensing-based all-dimensional physical examination system for electrical equipment of transformer substation |
Non-Patent Citations (1)
| Title |
|---|
| 基于无人机平台的复合绝缘子检测方法;张德钦 等;《仪器仪表与检测技术》;20180331;第37卷(第3期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112270267A (en) | 2021-01-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112270267B (en) | Camera shooting identification system capable of automatically capturing line faults | |
| CN111311597B (en) | Unmanned aerial vehicle inspection method and system for defective insulator | |
| CN103941746B (en) | Image processing system and method is patrolled and examined without man-machine | |
| CN205450784U (en) | Unmanned aerial vehicle electric power patrols linear system all | |
| CN112633535A (en) | Photovoltaic power station intelligent inspection method and system based on unmanned aerial vehicle image | |
| CN106547814A (en) | A kind of power transmission line unmanned machine patrols and examines the structuring automatic archiving method of image | |
| CN104834920A (en) | Intelligent forest fire recognition method and device based on multispectral image of unmanned plane | |
| CN105651780A (en) | Method, apparatus and system for detecting state of blower blade through unmanned plane | |
| CN112101088B (en) | Unmanned aerial vehicle electric power automatic inspection method, device and system | |
| CN205375192U (en) | Unmanned aerial vehicle distribution network system of patrolling and examining based on infrared image technique | |
| CN106355805A (en) | Big data substation monitoring system based on unmanned aerial vehicle and detection method thereof | |
| CN107014827A (en) | Transmission line of electricity defect analysis method based on image processing, device and system | |
| CN109063532B (en) | Unmanned aerial vehicle-based method for searching field offline personnel | |
| CN106162089A (en) | A kind of power-line patrolling image automatic identification analyzes system and the method for analysis thereof | |
| CN207268846U (en) | Electric inspection process robot | |
| CN109035665A (en) | A kind of novel forest fire early-warning system and fire alarm method | |
| CN110570536A (en) | intelligent line patrol system for extra-high voltage transmission line | |
| CN110647170A (en) | Navigation mark inspection device and method based on unmanned aerial vehicle | |
| CN107451527A (en) | A kind of large-scale public place hunting system based on unmanned plane | |
| CN107069859A (en) | A kind of wireless charging system and method based on unmanned plane base station | |
| CN210835732U (en) | Beacon inspection device based on unmanned aerial vehicle | |
| CN110457987A (en) | Face identification method based on unmanned plane | |
| CN115649501A (en) | Night driving illumination system and method for unmanned aerial vehicle | |
| CN106598064A (en) | Unmanned aerial vehicle circuit line intelligent identification device and method | |
| CN207924513U (en) | A kind of unmanned plane of achievable power line automatic detecting |
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 |