CN110990658A - Method for realizing image processing algorithm of power transmission line on embedded system - Google Patents
Method for realizing image processing algorithm of power transmission line on embedded system Download PDFInfo
- Publication number
- CN110990658A CN110990658A CN201911111078.XA CN201911111078A CN110990658A CN 110990658 A CN110990658 A CN 110990658A CN 201911111078 A CN201911111078 A CN 201911111078A CN 110990658 A CN110990658 A CN 110990658A
- Authority
- CN
- China
- Prior art keywords
- transmission line
- power transmission
- image
- image processing
- processing algorithm
- 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
- 230000005540 biological transmission Effects 0.000 title claims abstract description 69
- 238000012545 processing Methods 0.000 title claims abstract description 62
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000011161 development Methods 0.000 claims abstract description 6
- HPTJABJPZMULFH-UHFFFAOYSA-N 12-[(Cyclohexylcarbamoyl)amino]dodecanoic acid Chemical compound OC(=O)CCCCCCCCCCCNC(=O)NC1CCCCC1 HPTJABJPZMULFH-UHFFFAOYSA-N 0.000 claims abstract description 5
- 230000003213 activating effect Effects 0.000 claims abstract description 4
- 238000012360 testing method Methods 0.000 claims description 21
- 238000013527 convolutional neural network Methods 0.000 claims description 13
- 238000010276 construction Methods 0.000 claims description 8
- 239000000779 smoke Substances 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 239000000383 hazardous chemical Substances 0.000 claims description 3
- 238000012806 monitoring device Methods 0.000 abstract description 2
- 238000013135 deep learning Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 230000001629 suppression Effects 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 230000004913 activation Effects 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000011160 research Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/904—Browsing; Visualisation therefor
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
- Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Databases & Information Systems (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Public Health (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Water Supply & Treatment (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Image Analysis (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The utility model discloses a method for realizing image processing algorithm of power transmission line on an embedded system, which comprises the following steps: downloading a Linux operating system, programming the Linux operating system into an SD card, and activating a Jetson Nano development board; installing CUDA, OpenCV and CUDNN toolkits; downloading a PyTorch framework and installing the PyTorch framework through a Pip tool box; and transplanting the trained image processing algorithm of the power transmission line to an embedded system. According to the method and the device, the image processing algorithm of the power transmission line is deployed on the embedded equipment with low power consumption and applied to the actual online monitoring device of the power transmission line, so that the data processing time can be shortened, the timeliness of data processing is improved, and the cloud processing pressure is reduced.
Description
Technical Field
The disclosure belongs to the field of image processing, and particularly relates to a method for realizing an image processing algorithm of a power transmission line on an embedded system.
Background
The transmission line is easy to be damaged by the outside because the environment is complicated and changeable and is exposed outside all the year round. As an important component of electric energy transmission, the normal operation of the transmission line is the premise of ensuring the stability of the power grid, and with the continuous development of the power grid in China, the distribution of the transmission line is more and more intensive, the accuracy rate of detection and early warning by means of the traditional image processing technology is lower, and the intelligent construction of the power grid is severely restricted.
Compared with traditional manual inspection, the centralized processing is carried out after image acquisition by utilizing existing monitoring equipment, an unmanned aerial vehicle and the like, although the workload of workers is greatly reduced, the problems of low processing speed, poor timeliness and the like can occur when the acquired massive images and videos are all processed by a cloud end, therefore, the detection method is deployed to the embedded equipment to operate, and the intelligent processing is carried out on the embedded equipment, so that the method is a better practical mode.
The deep learning is taken as the latest research trend in the field of artificial intelligence at present, revolutionary changes are brought to the field of computer vision and image processing, the deep learning and image processing technology are combined and applied to the online monitoring of the power transmission line, and the power transmission line is deployed to an embedded device to run, so that the routing inspection process is more efficient, intelligent and accurate.
Disclosure of Invention
Aiming at the defects in the prior art, the disclosure aims to provide a method for realizing an image processing algorithm of a power transmission line on an embedded system.
In order to achieve the above purpose, the present disclosure provides the following technical solutions:
a method for realizing an image processing algorithm of a power transmission line on an embedded system comprises the following steps:
s100: downloading a Linux operating system, programming the Linux operating system into an SD card, and activating a Jetson Nano development board;
s200: installing CUDA, OpenCV and CUDNN toolkits;
s300: downloading a PyTorch framework and installing the PyTorch framework through a Pip tool box;
s400: and transplanting the trained image processing algorithm of the power transmission line to an embedded system.
Preferably, the power transmission line image processing algorithm is composed of a convolutional neural network, the convolutional neural network comprises a network configuration file, a weight file and a type file, and the network configuration file, the weight file and the type file are placed in the same file folder named in advance.
Preferably, the network configuration file is used for storing a network structure and training and testing parameters of the image processing algorithm of the power transmission line.
Preferably, the weight file is a binary file, and the weights of the convolutional neural network are stored in a sequence manner.
Preferably, the type file is used for storing the hidden danger types of the power transmission line, which can be detected by the power transmission line image processing algorithm.
Preferably, the hidden danger types of the power transmission line comprise any one or more of a crane, a tower crane, construction machinery, a wire foreign body and smoke.
Preferably, after the trained image processing algorithm of the power transmission line is transplanted to an embedded system, a test image needs to be placed in a folder which is the same as the network configuration file, the weight file and the type file, and the test image is input to the convolutional neural network for testing by running a test program.
Preferably, after the test image is tested, the acquired power transmission line image is placed in a folder where the test image is located to be detected in the same mode.
Preferably, before the test image is tested or the collected transmission line image is detected, a virtual memory needs to be added and an image interface needs to be closed.
The present disclosure also provides a method for processing an image of a power transmission line, including the following steps:
s11: collecting an image of the power transmission line through online monitoring equipment;
s12: constructing an image processing algorithm model according to the collected power transmission line image;
s13: implementing the image processing algorithm model into an embedded system using the implementation method of claim 1;
s14: and processing the image of the power transmission line by using the embedded system, and detecting the potential environmental hazards of the power transmission line, including a crane, a tower crane, construction machinery, foreign matters of a wire and smoke.
Compared with the prior art, the beneficial effect that this disclosure brought does: the image processing algorithm of the power transmission line is deployed on the embedded equipment with low power consumption and applied to the actual online monitoring device of the power transmission line, so that the data processing time can be shortened, the timeliness of data processing is improved, and the cloud processing pressure is reduced.
Drawings
Fig. 1 is a flowchart of a method for implementing an image processing algorithm for a power transmission line on an embedded system according to an embodiment of the present disclosure;
fig. 2 is a flowchart of a method for processing an image of a power transmission line according to another embodiment of the present disclosure.
Detailed Description
In the following description, numerous details are set forth to provide a more thorough explanation of embodiments of the present disclosure. It will be apparent, however, to one skilled in the art that embodiments of the invention may be practiced without these specific details. In other instances, well-known structures and devices are shown in block diagram form, rather than in detail, in order to avoid obscuring embodiments of the present disclosure. Furthermore, features of different embodiments described below may be combined with each other, unless specifically stated otherwise.
The terms "including" and "having," and any variations thereof, as used in this disclosure, are intended to cover and not be exhaustive. For example, a process, method, system, or article or apparatus that comprises a list of steps or elements is not limited to only those steps or elements but may alternatively include other steps or elements not expressly listed or inherent to such process, method, system, article, or apparatus.
Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the disclosure, and the embodiment described is a portion of but not all embodiments of the disclosure. The appearances of the phrase in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments. It will be appreciated by those skilled in the art that the embodiments described herein may be combined with other embodiments.
The technical solution of the present disclosure is described in detail below with reference to fig. 1 to 2 and the embodiments.
Referring to fig. 1, in an embodiment, the present disclosure provides a method for implementing a power transmission line image processing algorithm on an embedded system, including the following steps:
s100: downloading a Linux operating system, programming the Linux operating system into an SD card, and activating a Jetson Nano development board;
s200: installing CUDA, OpenCV and CUDNN toolkits;
s300: downloading a PyTorch framework and installing the PyTorch framework through a Pip tool box;
s400: and transplanting the trained image processing algorithm of the power transmission line to an embedded system.
By the method, the image processing algorithm of the power transmission line can be deployed on the embedded system with low power consumption, compared with the existing method, the data processing time can be shortened, the timeliness of data processing is improved, and therefore the problems of low processing speed and poor timeliness existing in the process of processing the image from the cloud end can be solved.
It should be noted that, in this embodiment, the internal memory of the development board Jetson Nano is 4GB, the downloaded Linux operating system is a Linux ubuntu18.04 system, and CUDA, OpenCV, and CUDNN respectively adopt CUDA10.0, opencv3.3.1, and CUDNN7.3.1.
In another embodiment, the image processing algorithm of the power transmission line is composed of a convolutional neural network, the convolutional neural network comprises a network configuration file, a weight file and a type file, and the network configuration file, the weight file and the type file are placed in the same pre-named folder.
In another embodiment, the network configuration file is used for storing a network structure and training and testing parameters of the image processing algorithm of the power transmission line.
In another embodiment, the weight file is a binary file, and the weights of the convolutional neural network are stored in a sequence manner.
In another embodiment, the type file is used for storing the hidden danger types of the power transmission line, which can be detected by the power transmission line image processing algorithm.
In another embodiment, the hidden danger types of the power transmission line comprise any one or more of a crane, a tower crane, construction machinery, a wire foreign body and smoke.
In another embodiment, after the trained image processing algorithm of the power transmission line is transplanted to an embedded system, a test image needs to be placed in a folder which is the same as the network configuration file, the weight file and the type file, and the test image is input to the convolutional neural network for testing by running a test program.
In another embodiment, after the test image is tested, the collected power transmission line image is placed in a folder where the test image is located to be detected in the same manner.
In another embodiment, because the original method has a memory overflow error, this embodiment proposes a new method written using a PyTorch frame, which is used to process the image of the power transmission line, as shown in fig. 2, and specifically includes the following steps:
s11: collecting an image of the power transmission line through online monitoring equipment;
s12: constructing an image processing algorithm model according to the collected power transmission line image;
in the step, the image processing algorithm model consists of a series of 1 × 1 and 3 × 3 convolutional layers, each convolutional layer is connected with a BN layer for standardization operation, then connected with a Leaky ReLU activation function, a total of 53 convolutional networks are used for carrying out feature extraction on the image of the power transmission line, and then a feature interaction layer is arranged. And carrying out non-maximum suppression algorithm processing on the plurality of predicted boundary boxes to obtain a final boundary box, and converting the final boundary box to an original image to obtain the category and the position of the hidden danger.
After the algorithm model is built, the collected power transmission line images are divided into 5 types including foreign matters of wires, construction machinery, a tower crane, a crane and smoke by using marking software, the collected images are trained by using a pre-trained convolutional neural network, and the network weight coefficient is updated by using a random gradient descent (SGD) method. The initial learning rate is set to 0.001, the momentum coefficient is set to 0.9, and the weighted attenuation coefficient is set to 0.0005. The number of images input by the network at a time is 8. The learning rate is updated by adopting an exponential decay method, the learning rate is multiplied by 0.9 every 5 training rounds, and the training is carried out for 80 times in total, so that the network weight finally used for evaluation is obtained.
S13: implementing the image processing algorithm model into an embedded system according to the steps shown in FIG. 1;
s14: and processing the image of the power transmission line by using the embedded system, and detecting the potential environmental hazards of the power transmission line, including a crane, a tower crane, construction machinery, foreign matters of a wire and smoke.
In the step, the processing of the power transmission line image is mainly realized through Jetson Nano, and the specific method comprises the following steps: performing feature extraction on the acquired power transmission line image by using a neural convolution network in a GPU (graphics processing Unit) acceleration reasoning mode and constructing a feature map; and predicting the boundary boxes of the feature map according to the feature map, and processing the plurality of predicted boundary boxes by using a non-maximum suppression algorithm to obtain the types and positions of the hidden dangers.
The intelligent processing method for the electric transmission line image, which is adopted by the invention, has strong robustness and high detection precision, can carry out detection in a complex environment, and is more convenient to analyze the state of the electric transmission line when being deployed on an embedded device.
The above embodiments are only used to help understanding the core idea of the present invention, and should not be taken as limiting the scope of the present invention; meanwhile, for a person skilled in the art, any changes made in the embodiments and the application range according to the idea of the present invention are considered to be within the protection scope of the present invention.
Claims (10)
1. A method for realizing an image processing algorithm of a power transmission line on an embedded system comprises the following steps:
s100: downloading a Linux operating system, programming the Linux operating system into an SD card, and activating a Jetson Nano development board;
s200: installing CUDA, OpenCV and CUDNN toolkits;
s300: downloading a PyTorch framework and installing the PyTorch framework through a Pip tool box;
s400: and transplanting the trained image processing algorithm of the power transmission line to an embedded system.
2. The method according to claim 1, wherein the image processing algorithm for the power transmission line is preferably composed of a convolutional neural network, the convolutional neural network comprises a network configuration file, a weight file and a type file, and the network configuration file, the weight file and the type file are placed in the same pre-named folder.
3. The method of claim 2, wherein the network profile is used to store network structure and training and testing parameters of the transmission line image processing algorithm.
4. The method of claim 2, wherein the weight file is a binary file, and wherein the weights of the convolutional neural network are stored in a sequence.
5. The method according to claim 2, wherein the type file is used for storing the hidden danger types of the power transmission line, which can be detected by the power transmission line image processing algorithm.
6. The method according to claim 5, wherein the power transmission line hidden danger types comprise any one or more of cranes, tower cranes, construction machinery, foreign wire objects and fireworks.
7. The method according to claim 2, wherein after the trained image processing algorithm for the power transmission line is transplanted to the embedded system, a test image needs to be placed in a folder which is the same as the network configuration file, the weight file and the type file, and the test image is input to the convolutional neural network for testing by running a test program.
8. The method according to claim 7, characterized in that after the test of the test image is completed, the acquired transmission line image is placed in a folder in which the test image is located to perform detection in the same manner.
9. The method according to claim 7 or 8, wherein a virtual memory needs to be added and an image interface needs to be closed before the test image is tested or the acquired transmission line image is detected.
10. A method for processing images of a power transmission line comprises the following steps:
s11: collecting an image of the power transmission line through online monitoring equipment;
s12: constructing an image processing algorithm model according to the collected power transmission line image;
s13: implementing the image processing algorithm model into an embedded system using the implementation method of claim 1;
s14: and processing the image of the power transmission line by using the embedded system, and detecting the potential environmental hazards of the power transmission line, including a crane, a tower crane, construction machinery, foreign matters of a wire and smoke.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911111078.XA CN110990658A (en) | 2019-11-15 | 2019-11-15 | Method for realizing image processing algorithm of power transmission line on embedded system |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911111078.XA CN110990658A (en) | 2019-11-15 | 2019-11-15 | Method for realizing image processing algorithm of power transmission line on embedded system |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110990658A true CN110990658A (en) | 2020-04-10 |
Family
ID=70084233
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911111078.XA Pending CN110990658A (en) | 2019-11-15 | 2019-11-15 | Method for realizing image processing algorithm of power transmission line on embedded system |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110990658A (en) |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112465794A (en) * | 2020-12-10 | 2021-03-09 | 无锡卡尔曼导航技术有限公司 | Golf ball detection method based on YOLOv4 and embedded platform |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108416755A (en) * | 2018-03-20 | 2018-08-17 | 南昌航空大学 | A kind of image de-noising method and system based on deep learning |
CN109034227A (en) * | 2018-07-16 | 2018-12-18 | 广东电网有限责任公司 | A kind of method that transmission line of electricity external force destroys intelligent recognition |
CN109657584A (en) * | 2018-12-10 | 2019-04-19 | 长安大学 | Assist the improvement LeNet-5 converged network traffic sign recognition method driven |
CN109816024A (en) * | 2019-01-29 | 2019-05-28 | 电子科技大学 | A kind of real-time automobile logo detection method based on multi-scale feature fusion and DCNN |
CN109961460A (en) * | 2018-12-26 | 2019-07-02 | 国网浙江省电力有限公司 | A kind of multiple target method for inspecting based on improvement YOLOv3 model |
CN109961003A (en) * | 2018-12-26 | 2019-07-02 | 安徽继远软件有限公司 | A kind of airborne auxiliary inspection device of embedded transmission line of electricity based on FPGA |
CN109977953A (en) * | 2019-03-29 | 2019-07-05 | 南京邮电大学 | Implementation method based on the algorithm of target detection of YOLOV3 on embedded device |
CN110210475A (en) * | 2019-05-06 | 2019-09-06 | 浙江大学 | A kind of characters on license plate image partition method of non-binaryzation and edge detection |
-
2019
- 2019-11-15 CN CN201911111078.XA patent/CN110990658A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108416755A (en) * | 2018-03-20 | 2018-08-17 | 南昌航空大学 | A kind of image de-noising method and system based on deep learning |
CN109034227A (en) * | 2018-07-16 | 2018-12-18 | 广东电网有限责任公司 | A kind of method that transmission line of electricity external force destroys intelligent recognition |
CN109657584A (en) * | 2018-12-10 | 2019-04-19 | 长安大学 | Assist the improvement LeNet-5 converged network traffic sign recognition method driven |
CN109961460A (en) * | 2018-12-26 | 2019-07-02 | 国网浙江省电力有限公司 | A kind of multiple target method for inspecting based on improvement YOLOv3 model |
CN109961003A (en) * | 2018-12-26 | 2019-07-02 | 安徽继远软件有限公司 | A kind of airborne auxiliary inspection device of embedded transmission line of electricity based on FPGA |
CN109816024A (en) * | 2019-01-29 | 2019-05-28 | 电子科技大学 | A kind of real-time automobile logo detection method based on multi-scale feature fusion and DCNN |
CN109977953A (en) * | 2019-03-29 | 2019-07-05 | 南京邮电大学 | Implementation method based on the algorithm of target detection of YOLOV3 on embedded device |
CN110210475A (en) * | 2019-05-06 | 2019-09-06 | 浙江大学 | A kind of characters on license plate image partition method of non-binaryzation and edge detection |
Non-Patent Citations (1)
Title |
---|
宿延吉: "神经网络理论及应用", 东北林业大学出版社 * |
Cited By (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112465794A (en) * | 2020-12-10 | 2021-03-09 | 无锡卡尔曼导航技术有限公司 | Golf ball detection method based on YOLOv4 and embedded platform |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111178206B (en) | Building embedded part detection method and system based on improved YOLO | |
CN109255288A (en) | A kind of road surface breakage detection method, device and terminal device | |
CN107563431A (en) | A kind of image abnormity detection method of combination CNN transfer learnings and SVDD | |
CN108764456B (en) | Airborne target identification model construction platform, airborne target identification method and equipment | |
CN105824249A (en) | Testing method and testing system for aircraft parameter display results | |
CN112036463A (en) | Power equipment defect detection and identification method based on deep learning | |
CN110910440B (en) | Power transmission line length determination method and system based on power image data | |
CN115294476B (en) | Edge computing intelligent detection method and device for unmanned aerial vehicle power inspection | |
CN113252701B (en) | Cloud edge cooperation-based power transmission line insulator self-explosion defect detection system and method | |
CN108733893A (en) | The public building burst pollution of coupling depth learning method is traced to the source | |
CN110990658A (en) | Method for realizing image processing algorithm of power transmission line on embedded system | |
CN113359829B (en) | Unmanned aerial vehicle power plant intelligent inspection method based on big data | |
CN116227586A (en) | Meta learning fault diagnosis method and device based on depth residual error shrinkage prototype network | |
CN115082813A (en) | Detection method, unmanned aerial vehicle, detection system and medium | |
WO2022014586A1 (en) | Inspection method | |
CN114018219A (en) | Transmission tower vibration monitoring method, device, equipment and storage medium | |
CN111596157A (en) | Power system fault condition prediction method, device, system and storage medium | |
CN116225070A (en) | Environment monitoring method and system based on unmanned aerial vehicle automatic patrol | |
CN115100592B (en) | Method and device for identifying hidden danger of external damage of power transmission channel and storage medium | |
CN115754600A (en) | Overhead ground wire strand breakage identification method and device, terminal device and storage medium | |
Li et al. | Non-destructive testing research on the surface damage faced by the Shanhaiguan Great Wall based on machine learning | |
CN113076672B (en) | Composite insulator bird pecking defect risk level assessment method based on improved SSD | |
CN114241045A (en) | Power transmission line forest fire distance measuring method and device, computer equipment and storage medium | |
CN111950343A (en) | Automatic transmission tower identification method and system based on satellite remote sensing technology | |
CN113570264A (en) | Offshore land-source pollutant emission management system |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200410 |