CN108564125A - A kind of insulator image classification method and system - Google Patents
A kind of insulator image classification method and system Download PDFInfo
- Publication number
- CN108564125A CN108564125A CN201810338505.7A CN201810338505A CN108564125A CN 108564125 A CN108564125 A CN 108564125A CN 201810338505 A CN201810338505 A CN 201810338505A CN 108564125 A CN108564125 A CN 108564125A
- Authority
- CN
- China
- Prior art keywords
- insulator
- aerial images
- analog image
- neural network
- electricity
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of insulator image classification method and systems.This method includes：Prepare analog image；The analog image is the simulation Aerial Images of transmission line of electricity, and the analog image includes insulation subgraph and Background；Obtain the history Aerial Images of transmission line of electricity；By the analog image and the history Aerial Images, neural network model is trained, disaggregated model is obtained；Transmission line of electricity is shot, the current Aerial Images of transmission line of electricity are obtained；Classified to the current Aerial Images according to the disaggregated model, obtains insulation subgraph.It can expand training sample by this method or system, improve the accuracy of disaggregated model.
Description
Technical field
The present invention relates to image classification fields, more particularly to a kind of insulator image classification method and system.
Background technology
Insulator is electric insulation and mechanical support member important in transmission line of electricity, while being also the multiple component of failure,
Accident quantity has occupied the umber one of transmission line of electricity accident quantity because of caused by insulator breakdown.If inspection finds insulation not in time
Security risk existing for son can cause heavy losses.In recent years, in intelligent grid construction, multi-rotor unmanned aerial vehicle starts gradually
The patrol task for undertaking transmission line of electricity tries hard to the inefficiencies for overcoming manual inspection and danger.But the boat of flying robot's acquisition
It claps in image, background is complicated and changeable and there are many interference, and target identification is difficult, and artificial observation is required in many cases,
Carefully identification can be found.Therefore, it is to realize the pass of the autonomous detection function of unmanned plane to study the target identification under complex background
Key.
Currently, deep learning algorithm big main bottleneck of practical application in isolator detecting is exactly that training sample is asked
Topic：(1) training sample is incomplete：Targeted species, length, angle are different, take photo by plane visual angle and sighting distance variation very greatly, sample collection is not
Comprehensively.(2) training sample quality is not high：The natural environment and landforms in transmission of electricity corridor with seasonal variations, clap from up to down by unmanned plane
It takes the photograph, Aerial Images background is complicated and changeable；Insulation sub-goal and fault zone are not prominent enough in the picture, and disturbed condition is serious.
Invention content
Sufficient, classification that in response to the problems existing in the prior art, the purpose of the present invention is to provide a kind of training samples is accurately
Insulator image classification method and system.
To achieve the above object, the present invention provides following schemes：
A kind of insulator image classification method, the method includes：
Prepare analog image；The analog image is the simulation Aerial Images of transmission line of electricity, and the analog image includes exhausted
Edge subgraph and Background；
Obtain the history Aerial Images of transmission line of electricity；
By the analog image and the history Aerial Images, neural network model is trained, is classified
Model；
Transmission line of electricity is shot, the current Aerial Images of transmission line of electricity are obtained；
Classified to the current Aerial Images according to the disaggregated model, obtains insulation subgraph.
Optionally, described to prepare analog image, it specifically includes：
According to the size and shape of insulator, insulator part is drawn, the insulator part includes metal termination, umbrella disk
And stick core；
The material parameters of insulator all parts are set；
All parts are combined, insulator is obtained；
Environment rendering is carried out to the insulator, obtains analog image.
Optionally, described by the analog image and the history Aerial Images, neural network model is instructed
Practice, obtains disaggregated model, specifically include：
Classified to the analog image and the history Aerial Images by the neural network model, is carried on the back
Scape figure output data and insulation subgraph output data；
Judge the Background output data and insulation sub-image data whether within the scope of error threshold；
It is no to be, it is determined that the neural network model is disaggregated model；
If it is not, then adjusting the parameter of the neural network model, make the Background output data and insulation subgraph
Data obtain disaggregated model within the scope of error threshold.
Optionally, the neural network model includes 3 convolutional layers, 3 down-sampling layers and 1 full articulamentum.
A kind of insulator image classification system, including：
Module is prepared, analog image is used to prepare；The analog image is the simulation Aerial Images of transmission line of electricity, the mould
Quasi- image includes insulation subgraph and Background；
Acquisition module, the history Aerial Images for obtaining transmission line of electricity；
Training module, for by the analog image and the history Aerial Images, being carried out to neural network model
Training, obtains disaggregated model；
Taking module obtains the current Aerial Images of transmission line of electricity for being shot to transmission line of electricity；
Sort module obtains insulation subgraph for classifying to the current Aerial Images according to the disaggregated model
Picture.
Optionally, the preparation module includes：
Drawing unit draws insulator part for the size and shape according to insulator, and the insulator part includes
Metal termination, umbrella disk and stick core；
Setting unit, the material parameters for insulator all parts to be arranged；
Assembled unit obtains insulator for being combined all parts；
Rendering unit obtains analog image for carrying out environment rendering to the insulator.
Optionally, the training module includes：
Taxon classifies to the analog image for passing through the neural network model, it is defeated to obtain Background
Go out data and insulation subgraph output data；
Judging unit, for judging the Background output data and insulation sub-image data whether in error threshold model
In enclosing；
Determination unit is connect with the judgment module, for working as the Background output data and insulator picture number
When according within the scope of error threshold, determine that the neural network model is disaggregated model；And for being exported when the Background
When data and insulation sub-image data be not within the scope of error threshold, the parameter of the neural network model is adjusted, is made described
Background output data and insulation sub-image data obtain disaggregated model within the scope of error threshold.
Optionally, the neural network model includes 3 convolutional layers, 3 down-sampling layers and 1 full articulamentum.
Compared with prior art, the present invention has the following technical effects：The present invention expands instruction by preparing analog image
Practice sample, and neural network model be trained by training sample, can accurately and rapidly to insulation subgraph into
Row classification.
Description of the drawings
It in order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, below will be to institute in embodiment
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the present invention
Example, for those of ordinary skill in the art, without having to pay creative labor, can also be according to these attached drawings
Obtain other attached drawings.
Fig. 1 is the flow chart of insulator image classification method of the embodiment of the present invention；
Fig. 2 is the structure diagram of insulator image classification system of the embodiment of the present invention.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
Sufficient, classification that in response to the problems existing in the prior art, the purpose of the present invention is to provide a kind of training samples is accurately
Insulator image classification method and system.
In order to make the foregoing objectives, features and advantages of the present invention clearer and more comprehensible, below in conjunction with the accompanying drawings and specific real
Applying mode, the present invention is described in further detail.
Fig. 1 is the flow chart of insulator image classification method of the embodiment of the present invention.As shown in Figure 1, a kind of insulation subgraph
Sorting technique includes the following steps：
Step 101：Prepare analog image；The analog image is the simulation Aerial Images of transmission line of electricity, the simulation drawing
As including insulation subgraph and Background.
Specifically, according to standard GB/T/T 7253《Plate-shaped suspension type insulator chain component size and characteristic》And GB1001
《Cap and pin type suspension insulator technical conditions》Defined insulator sizes and technical conditions, using 3Dmax modeling softwares to insulation
Work is drawn and rendered to son.
The first step drawn and rendered is according to the size of insulator specified in national standard, on multiple views (front view, a left side
View, top view etc.) in carry out the drafting of metal termination, umbrella disk and stick core, second step is all parts to insulator respectively
The generation setting of material is carried out, third step is that all parts are combined into an insulator chain, is configured to rendering contexts, most
After start render insulation subsample finished product rendered, obtain the illustraton of model of insulator.Insulator is drawn according to stipulations,
Include the glass insulator of 3 kinds of different models, a kind of whiteware insulator and a kind of red ceramic insulator.And it is exhausted to each
Edge submodel carries out different angle, different size and different types of projection imaging.The simulation for generating pure gray background increases
Strong sample, in assorting process, weakening the background characteristics in positive sample, reinforced insulation subcharacter realizes that network class is accurate
The fast lifting of true rate.
Step 102：Obtain the history Aerial Images of transmission line of electricity.
Step 103：By the analog image and the history Aerial Images, neural network model is trained,
Obtain disaggregated model.
Specifically, using the convolutional neural networks model in deep learning network, by 3 convolutional layers, 3 down-sampling layers, 1
A full articulamentum composition, convolutional layer con1 by using 256 7*7 convolution kernel sliding processing 256*256*3 by altimetric image；
The receptive field size of down-sampling layer pool2 is 2*2, for removing redundant data；Convolutional layer con3 and con5 use 128 respectively
The convolution kernel of the convolution kernel of 6*6 and 64 3*3；The receptive field size of down-sampling layer pool4 and pool6 are all 3*3；Whole network
Training parameter number is 65280.Network obtains rational connection weight by carrying out minimum optimization to loss function value
Value.
Classified to the analog image and the history Aerial Images by the neural network model, is carried on the back
Scape figure output data and insulation subgraph output data；
Judge the Background output data and insulation sub-image data whether within the scope of error threshold；
It is no to be, it is determined that the neural network model is disaggregated model；
If it is not, then adjusting the parameter of the neural network model, make the Background output data and insulation subgraph
Data obtain disaggregated model within the scope of error threshold.
Step 104：Transmission line of electricity is shot, the current Aerial Images of transmission line of electricity are obtained.
Step 105：Classified to the current Aerial Images according to the disaggregated model, obtains insulation subgraph.
According to specific embodiment provided by the invention, the invention discloses following technique effects：The present invention is by preparing mould
Quasi- image is trained neural network model by training sample to expand training sample, can be accurately and rapidly
Classify to insulation subgraph.
Fig. 2 is the structure diagram of insulator image classification system of the embodiment of the present invention.As shown in Fig. 2, a kind of insulation subgraph
As categorizing system, including：
Module 201 is prepared, analog image is used to prepare；The analog image is the simulation Aerial Images of transmission line of electricity, institute
It includes insulation subgraph and Background to state analog image.
The preparation module 201 specifically includes：
Drawing unit draws insulator part for the size and shape according to insulator, and the insulator part includes
Metal termination, umbrella disk and stick core；
Setting unit, the material parameters for insulator all parts to be arranged；
Assembled unit obtains insulator for being combined all parts；
Rendering unit obtains analog image for carrying out environment rendering to the insulator.
Acquisition module 202, the history Aerial Images for obtaining transmission line of electricity.
Training module 203 is trained neural network model for passing through the analog image, obtains disaggregated model.
The training module 203 specifically includes：
Taxon classifies to the analog image for passing through the neural network model, it is defeated to obtain Background
Go out data and insulation subgraph output data；
Judging unit, for judging the Background output data and insulation sub-image data whether in error threshold model
In enclosing；
Determination unit is connect with the judgment module, for working as the Background output data and insulator picture number
When according within the scope of error threshold, determine that the neural network model is disaggregated model；And for being exported when the Background
When data and insulation sub-image data be not within the scope of error threshold, the parameter of the neural network model is adjusted, is made described
Background output data and insulation sub-image data obtain disaggregated model within the scope of error threshold.
Taking module 204 obtains the current Aerial Images of transmission line of electricity for being shot to transmission line of electricity；
Sort module 205 obtains insulator for classifying to the current Aerial Images according to the disaggregated model
Image.
Each embodiment is described by the way of progressive in this specification, the highlights of each of the examples are with other
The difference of embodiment, just to refer each other for identical similar portion between each embodiment.For system disclosed in embodiment
For, since it is corresponded to the methods disclosed in the examples, so description is fairly simple, related place is said referring to method part
It is bright.
Principle and implementation of the present invention are described for specific case used herein, and above example is said
The bright method and its core concept for being merely used to help understand the present invention；Meanwhile for those of ordinary skill in the art, foundation
The thought of the present invention, there will be changes in the specific implementation manner and application range.In conclusion the content of the present specification is not
It is interpreted as limitation of the present invention.
Claims (8)
1. a kind of insulator image classification method, which is characterized in that the method includes：
Prepare analog image；The analog image is the simulation Aerial Images of transmission line of electricity, and the analog image includes insulator
Image and Background；
Obtain the history Aerial Images of transmission line of electricity；
By the analog image and the history Aerial Images, neural network model is trained, disaggregated model is obtained；
Transmission line of electricity is shot, the current Aerial Images of transmission line of electricity are obtained；
Classified to the current Aerial Images according to the disaggregated model, obtains insulation subgraph.
2. sorting technique according to claim 1, which is characterized in that it is described to prepare analog image, it specifically includes：
According to the size and shape of insulator, draw insulator part, the insulator part include metal termination, umbrella disk and
Stick core；
The material parameters of insulator all parts are set；
All parts are combined, insulator is obtained；
Environment rendering is carried out to the insulator, obtains analog image.
3. sorting technique according to claim 1, which is characterized in that described by the analog image and the history
Aerial Images are trained neural network model, obtain disaggregated model, specifically include：
Classified to the analog image and the history Aerial Images by the neural network model, obtains Background
Output data and insulation subgraph output data；
Judge the Background output data and insulation sub-image data whether within the scope of error threshold；
It is no to be, it is determined that the neural network model is disaggregated model；
If it is not, then adjusting the parameter of the neural network model, make the Background output data and insulation sub-image data
Within the scope of error threshold, disaggregated model is obtained.
4. sorting technique according to claim 1, which is characterized in that the neural network model includes 3 convolutional layers, 3
A down-sampling layer and 1 full articulamentum.
5. a kind of insulator image classification system, which is characterized in that the system comprises：
Module is prepared, analog image is used to prepare；The analog image is the simulation Aerial Images of transmission line of electricity, the simulation drawing
As including insulation subgraph and Background；
Acquisition module, the history Aerial Images for obtaining transmission line of electricity；
Training module, for by the analog image and the history Aerial Images, being trained to neural network model,
Obtain disaggregated model；
Taking module obtains the current Aerial Images of transmission line of electricity for being shot to transmission line of electricity；
Sort module obtains insulation subgraph for classifying to the current Aerial Images according to the disaggregated model.
6. system according to claim 5, which is characterized in that the preparation module includes：
Drawing unit draws insulator part, the insulator part includes metal for the size and shape according to insulator
End, umbrella disk and stick core；
Setting unit, the material parameters for insulator all parts to be arranged；
Assembled unit obtains insulator for being combined all parts；
Rendering unit obtains analog image for carrying out environment rendering to the insulator.
7. system according to claim 5, which is characterized in that the training module includes：
Taxon, for being divided the analog image and the history Aerial Images by the neural network model
Class obtains Background output data and insulation subgraph output data；
Judging unit, for judging the Background output data and insulation sub-image data whether in error threshold range
It is interior；
Determination unit is connect with the judgment module, for existing when the Background output data and insulation sub-image data
When within the scope of error threshold, determine that the neural network model is disaggregated model；And for working as the Background output data
And insulation sub-image data not within the scope of error threshold when, adjust the parameter of the neural network model, make the background
Figure output data and insulation sub-image data obtain disaggregated model within the scope of error threshold.
8. system according to claim 5, which is characterized in that the neural network model is including under 3 convolutional layers, 3
Sample level and 1 full articulamentum.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810338505.7A CN108564125A (en) | 2018-04-16 | 2018-04-16 | A kind of insulator image classification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810338505.7A CN108564125A (en) | 2018-04-16 | 2018-04-16 | A kind of insulator image classification method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108564125A true CN108564125A (en) | 2018-09-21 |
Family
ID=63535204
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810338505.7A Pending CN108564125A (en) | 2018-04-16 | 2018-04-16 | A kind of insulator image classification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108564125A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111799697A (en) * | 2020-07-08 | 2020-10-20 | 云南电网有限责任公司电力科学研究院 | Self-explosion simulation method and system for glass insulator of power transmission line |
| CN114820567A (en) * | 2022-05-17 | 2022-07-29 | 合肥工业大学 | Insulator detection method based on deep learning |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106877237A (en) * | 2017-03-16 | 2017-06-20 | 天津大学 | A kind of method of insulator missing in detection transmission line of electricity based on Aerial Images |
| CN106919932A (en) * | 2017-03-13 | 2017-07-04 | 华北电力大学（保定） | A kind of insulator of " simulation is true " parallel construction positions soft recognition methods |
| CN107145846A (en) * | 2017-04-26 | 2017-09-08 | 贵州电网有限责任公司输电运行检修分公司 | A kind of insulator recognition methods based on deep learning |
| CN107274451A (en) * | 2017-05-17 | 2017-10-20 | 北京工业大学 | Isolator detecting method and device based on shared convolutional neural networks |
| CN107680090A (en) * | 2017-10-11 | 2018-02-09 | 电子科技大学 | Based on the electric transmission line isolator state identification method for improving full convolutional neural networks |
| CN107808141A (en) * | 2017-11-08 | 2018-03-16 | 国家电网公司 | A kind of electric transmission line isolator explosion recognition methods based on deep learning |
-
2018
- 2018-04-16 CN CN201810338505.7A patent/CN108564125A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106919932A (en) * | 2017-03-13 | 2017-07-04 | 华北电力大学（保定） | A kind of insulator of " simulation is true " parallel construction positions soft recognition methods |
| CN106877237A (en) * | 2017-03-16 | 2017-06-20 | 天津大学 | A kind of method of insulator missing in detection transmission line of electricity based on Aerial Images |
| CN107145846A (en) * | 2017-04-26 | 2017-09-08 | 贵州电网有限责任公司输电运行检修分公司 | A kind of insulator recognition methods based on deep learning |
| CN107274451A (en) * | 2017-05-17 | 2017-10-20 | 北京工业大学 | Isolator detecting method and device based on shared convolutional neural networks |
| CN107680090A (en) * | 2017-10-11 | 2018-02-09 | 电子科技大学 | Based on the electric transmission line isolator state identification method for improving full convolutional neural networks |
| CN107808141A (en) * | 2017-11-08 | 2018-03-16 | 国家电网公司 | A kind of electric transmission line isolator explosion recognition methods based on deep learning |
Non-Patent Citations (5)
| Title |
|---|
| YONGJIE ZHAI等: "Fault detection of insulator based on saliency and adaptive morphology", 《MULTIMEDIA TOOLS AND APPLICATIONS》 * |
| YONGJIE ZHAI等: "Multi-Saliency Aggregation-Based Approach for Insulator Flashover Fault Detection Using Aerial Images", 《ENERGIES》 * |
| ZHENBING ZHAO等: "Multi-patch deep features for power line insulator status classification from aerial images", 《2016 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN)》 * |
| 伍洋: "基于机器学习的航拍图像绝缘子识别方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑（月刊）计算机软件及计算机应用》 * |
| 王磊: "基于图像特征和标签分布学习的航拍绝缘子识别定位方法研究", 《中国优秀硕士学位论文全文数据库 信息科技辑（月刊）计算机软件及计算机应用》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111799697A (en) * | 2020-07-08 | 2020-10-20 | 云南电网有限责任公司电力科学研究院 | Self-explosion simulation method and system for glass insulator of power transmission line |
| CN114820567A (en) * | 2022-05-17 | 2022-07-29 | 合肥工业大学 | Insulator detection method based on deep learning |
| CN114820567B (en) * | 2022-05-17 | 2024-02-13 | 合肥工业大学 | Insulator detection method based on deep learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107742093B (en) | Real-time detection method, server and system for infrared image power equipment components | |
| CN112380952B (en) | Power equipment infrared image real-time detection and identification method based on artificial intelligence | |
| CN110059694B (en) | Intelligent identification method for character data in complex scene of power industry | |
| CN111444821B (en) | Automatic identification method for urban road signs | |
| CN106356757B (en) | A kind of power circuit unmanned plane method for inspecting based on human-eye visual characteristic | |
| CN109376605B (en) | Electric power inspection image bird-stab-prevention fault detection method | |
| CN112183667B (en) | Insulator fault detection method in cooperation with deep learning | |
| CN109345547B (en) | Traffic lane line detection method and device based on deep learning multitask network | |
| CN112419401A (en) | Aircraft surface defect detection system based on cloud edge cooperation and deep learning | |
| CN109241902A (en) | A kind of landslide detection method based on multi-scale feature fusion | |
| CN108764082A (en) | A kind of Aircraft Targets detection method, electronic equipment, storage medium and system | |
| CN106851229B (en) | Security and protection intelligent decision method and system based on image recognition | |
| CN110807765B (en) | Suspension insulator string inclination detection method and system based on image processing | |
| CN109815800A (en) | Object detection method and system based on regression algorithm | |
| CN112381060A (en) | Building earthquake damage level classification method based on deep learning | |
| CN112229845A (en) | Unmanned aerial vehicle high-precision winding tower intelligent inspection method based on visual navigation technology | |
| CN109086803A (en) | A kind of haze visibility detection system and method based on deep learning and the personalized factor | |
| CN110992307A (en) | Insulator positioning and identifying method and device based on YOLO | |
| CN111898444A (en) | Aircraft landing gear state determination method based on image recognition | |
| CN113780132A (en) | Lane line detection method based on convolutional neural network | |
| CN113284144B (en) | Tunnel detection method and device based on unmanned aerial vehicle | |
| CN109785288A (en) | Transmission facility defect inspection method and system based on deep learning | |
| CN109978847A (en) | Drag-line housing disease automatic identifying method based on transfer learning Yu drag-line robot | |
| CN109815798A (en) | Unmanned plane image processing method and system | |
| CN108564125A (en) | A kind of insulator image classification method and 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 |
Application publication date: 20180921 |
|
| RJ01 | Rejection of invention patent application after publication |