CN112926488B - Electric power pole tower structure information-based operator violation identification method - Google Patents
Electric power pole tower structure information-based operator violation identification method Download PDFInfo
- Publication number
- CN112926488B CN112926488B CN202110287142.0A CN202110287142A CN112926488B CN 112926488 B CN112926488 B CN 112926488B CN 202110287142 A CN202110287142 A CN 202110287142A CN 112926488 B CN112926488 B CN 112926488B
- Authority
- CN
- China
- Prior art keywords
- power tower
- image
- electric power
- model
- image acquisition
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- 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
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Multimedia (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Psychiatry (AREA)
- Social Psychology (AREA)
- Human Computer Interaction (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a method for identifying violations of regulations of operators, in particular to a method for identifying violations of regulations of operators based on structural information of electric power towers, which is used for carrying out image acquisition on each electric power tower in an area, optimizing image acquisition points based on visual positioning of the electric power towers, carrying out image processing and analysis on acquired images of the same electric power tower, establishing corresponding three-dimensional models according to analysis results, storing the corresponding three-dimensional models in a model database, constructing identification models for identifying the behaviors of violations of regulations on various electric power towers, training the identification models, carrying out image acquisition on the electric power towers which are operating in the area, extracting human images from the acquired images according to the three-dimensional models corresponding to the electric power towers, analyzing the human images, and comprehensively considering the analysis identification results and the analysis results to identify the behaviors of violations of regulations; the technical scheme provided by the invention can effectively overcome the defect that the illegal operation behaviors of operators cannot be effectively identified in the prior art.
Description
Technical Field
The invention relates to a method for identifying violations of operators, in particular to a method for identifying violations of operators based on structural information of a power tower.
Background
With the rapid development of the economy in China, the capacity of the power system is continuously increased, the power grid scale is larger and larger, and the safety operation maintenance and monitoring work of the power grid are increasingly important. And the power grid operation equipment is widely distributed, most overhead power lines are positioned at fewer interpersonal places, and equipment such as power towers are arranged on complex terrains such as mountains, rivers and hills.
At present, the premise of the power grid operation is that the work responsible person and the work team member need to pass through a safety regulation examination, and qualified results are obtained, and personnel qualification is in an auditing period. When all personnel perform power equipment operations, relevant operation regulations must be strictly executed. Before operation, equipment operators make safety measures in advance, including power failure, electricity inspection, grounding, listing and the like, and work charge staff carries work tickets to carry out work starting permission, work is carried out on site by the tickets, a system of wearing safety helmets and wearing work clothes is strictly executed on a high-voltage site, and safety belts are tied to high-altitude operation exceeding 1.5 meters. For the work with higher operation risk level, the equipment manager needs to conduct safety supervision work on site. The safety supervision department performs sampling supervision on the work of the jurisdiction at irregular intervals, and the supervision content mainly comprises whether to wear safety helmets, wear working clothes, whether to tie safety belts for high-altitude operation with the height of more than 1.5 meters, whether safety measures meet the requirements, and the like.
The power tower is an important component of power transmission equipment and is responsible for supporting and mounting the power transmission line, and related operations should more strictly implement safety regulations. The supervision method of the operators for field operation mainly comprises a manual supervision method and a video monitoring method, however, both methods can not effectively identify the illegal operation behaviors of the operators, so that serious potential safety hazards exist on the operation field.
Disclosure of Invention
(one) solving the technical problems
Aiming at the defects existing in the prior art, the invention provides the method for identifying the violations of the operators based on the structural information of the power tower, which can effectively overcome the defect that the existing technology cannot effectively identify the violations of the operators.
(II) technical scheme
In order to achieve the above purpose, the invention is realized by the following technical scheme:
the method for identifying the violation of the operator based on the structural information of the power tower comprises the following steps:
s1, carrying out image acquisition on each power tower in an area, and optimizing image acquisition points based on visual positioning of the power towers;
s2, performing image processing and analysis on the acquired images of the same power tower, establishing a corresponding three-dimensional model according to an analysis result, and storing the model database;
s3, constructing an identification model for identifying the illegal operation behaviors on various types of power towers, and training the identification model;
s4, acquiring images of the power towers working in the area, and extracting human body images from the acquired images according to the three-dimensional model corresponding to the power towers;
s5, analyzing the human body image, inputting the human body image into the recognition model, and comprehensively considering the analysis recognition result and the analysis result to recognize the illegal operation behavior.
Preferably, in S1, image acquisition is performed on each power tower in the area, including:
the unmanned aerial vehicle is utilized to carry out regional inspection flight, environmental images in a region are continuously collected through the binocular vision camera, an electric power tower existing in the environmental images is identified by means of a neural network model, a first image collection point is set and flies to the image collection point according to the distance and the direction between the unmanned aerial vehicle and the electric power tower, and the collection visual angle of the binocular vision camera is adjusted to carry out image collection on the electric power tower.
Preferably, optimizing the image acquisition point in S1 based on the visual positioning of the power tower includes:
the depth of field information in the acquired image is read from the acquired image of the power tower, the position information of the object at the front end of the unmanned aerial vehicle is rebuilt based on the acquired view angle, the power tower is visually positioned by combining the position relation among the unmanned aerial vehicle and a plurality of parts in the power tower through a triangulation positioning method, and each image acquisition point is sequentially set based on the position of the first image acquisition point.
Preferably, when the unmanned aerial vehicle performs regional inspection and flying, the unmanned aerial vehicle continuously performs visual positioning on each power tower, acquires the position relationship between the unmanned aerial vehicle and each power tower, corrects the flying position and sets the position of an image acquisition point.
Preferably, in S2, image processing and analysis are performed on the collected images of the same power tower, and a corresponding three-dimensional model is built according to the analysis result and stored in a model database, including:
recording image acquisition points and acquisition visual angles corresponding to all acquired images of the same power tower, scaling pictures of all the acquired images to the same size according to the position relation between the image acquisition points and the power tower, analyzing all the processed acquired images, constructing a three-dimensional model corresponding to the power tower, simultaneously carrying out position identification on the power tower, and storing identification results and the three-dimensional model into a model database.
Preferably, in S3, an identification model for identifying the operation behavior of violations on various types of power towers is constructed, and the identification model is trained, including:
the method comprises the steps of collecting a training image set and a detection image set by manually simulating the illegal operation behaviors on various electric towers or performing network search by a crawler, inputting the training image set into an identification model for model training, judging the identification accuracy of the identification model by using the detection image set, and adjusting model parameters according to the identification accuracy.
Preferably, in S4, image acquisition is performed on the power tower operating in the area, including:
the operation personnel send the position information of operation electric power pole tower to unmanned aerial vehicle, and unmanned aerial vehicle retrieves the three-dimensional model that this electric power pole tower corresponds from the model database according to position information, flies to near this electric power pole tower simultaneously and carries out image acquisition.
Preferably, in S4, extracting a human body image from the acquired image according to the three-dimensional model corresponding to the power tower includes:
and removing a part containing the three-dimensional model of the power tower from the acquired image, analyzing and detecting a moving target by adopting a three-frame difference method, and then further screening a human body target according to contour pairing, wherein the characteristics of the human body target are matched according to space domain constraint, frequency domain characteristics and time domain characteristics.
Preferably, the analyzing the human body image in S5 includes:
marking all human bodies in the acquired images in sequence according to the human body target feature matching, wherein the same mark is adopted in the subsequent acquired images if the matching is successful, otherwise, a new mark is adopted;
the motion trail analysis result of the human body is obtained by connecting mass center coordinates in a time window quadruple to obtain a space-time discrete curve, calculating generalized curvature, space-time length and space-time inflection point number to represent scalar quantity of the space-time discrete curve, and extracting two vector characteristics of a space domain and a time domain on discrete points on the space-time discrete curve.
(III) beneficial effects
Compared with the prior art, the method for identifying the violations of the operators based on the structural information of the electric power towers can construct a three-dimensional model for each electric power tower in an area, and extract the human body image from the acquired image according to the three-dimensional model corresponding to the electric power towers, so that the extracted human body image is more accurate, the situation that the human body cannot be accurately identified due to the fact that the human body is partially overlapped with the electric power towers in the acquired image is prevented, the accuracy of identifying the violating operation behaviors of the operators can be further effectively improved, and potential safety hazards existing in an operation site are eliminated as much as possible.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It is evident that the drawings in the following description are only some embodiments of the present invention and that other drawings may be obtained from these drawings without inventive effort for a person of ordinary skill in the art.
FIG. 1 is a schematic flow chart of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention more clear, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. It will be apparent that the described embodiments are some, but not all, embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
The method for identifying the violations of the operators based on the structural information of the power towers is characterized in that as shown in fig. 1, the image acquisition is carried out on each power tower in the area, and the image acquisition points are optimized based on the visual positioning of the power towers.
Wherein, carry out image acquisition to each electric power shaft tower in the region, include:
the unmanned aerial vehicle is utilized to carry out regional inspection flight, environmental images in a region are continuously collected through the binocular vision camera, an electric power tower existing in the environmental images is identified by means of a neural network model, a first image collection point is set and flies to the image collection point according to the distance and the direction between the unmanned aerial vehicle and the electric power tower, and the collection visual angle of the binocular vision camera is adjusted to carry out image collection on the electric power tower.
Wherein, based on the visual localization to the electric power shaft tower, optimize image acquisition point, include:
the depth of field information in the acquired image is read from the acquired image of the power tower, the position information of the object at the front end of the unmanned aerial vehicle is rebuilt based on the acquired view angle, the power tower is visually positioned by combining the position relation among the unmanned aerial vehicle and a plurality of parts in the power tower through a triangulation positioning method, and each image acquisition point is sequentially set based on the position of the first image acquisition point.
In this application technical scheme, unmanned aerial vehicle carries out the region and patrols and examines when flying, constantly carries out visual localization to each electric power shaft tower, acquires the positional relationship of self and each electric power shaft tower, rectifies the position of flight and sets for the position of image acquisition point, ensures the quality of gathering the image.
Image processing and analysis are carried out on the acquired images of the same power tower, a corresponding three-dimensional model is established according to the analysis result, and the three-dimensional model is stored in a model database, and the method specifically comprises the following steps:
recording image acquisition points and acquisition visual angles corresponding to all acquired images of the same power tower, scaling pictures of all the acquired images to the same size according to the position relation between the image acquisition points and the power tower, analyzing all the processed acquired images, constructing a three-dimensional model corresponding to the power tower, simultaneously carrying out position identification on the power tower, and storing identification results and the three-dimensional model into a model database.
Constructing an identification model for identifying illegal operation behaviors on various types of power towers, and training the identification model, wherein the method specifically comprises the following steps of:
the method comprises the steps of collecting a training image set and a detection image set by manually simulating the illegal operation behaviors on various electric towers or performing network search by a crawler, inputting the training image set into an identification model for model training, judging the identification accuracy of the identification model by using the detection image set, and adjusting model parameters according to the identification accuracy.
And acquiring images of the power towers working in the area, and extracting human body images from the acquired images according to the three-dimensional model corresponding to the power towers.
The method for acquiring the image of the power tower in operation in the area comprises the following steps:
the operation personnel send the position information of operation electric power pole tower to unmanned aerial vehicle, and unmanned aerial vehicle retrieves the three-dimensional model that this electric power pole tower corresponds from the model database according to position information, flies to near this electric power pole tower simultaneously and carries out image acquisition.
The method for extracting the human body image from the acquired image according to the three-dimensional model corresponding to the electric power tower comprises the following steps:
and removing a part containing the three-dimensional model of the power tower from the acquired image, analyzing and detecting a moving target by adopting a three-frame difference method, and then further screening a human body target according to contour pairing, wherein the characteristics of the human body target are matched according to space domain constraint, frequency domain characteristics and time domain characteristics.
And analyzing the human body image, inputting the human body image into the recognition model, and comprehensively considering the analysis recognition result and the analysis result to recognize the illegal operation behavior.
Wherein, analyze human body image, include:
marking all human bodies in the acquired images in sequence according to the human body target feature matching, wherein the same mark is adopted in the subsequent acquired images if the matching is successful, otherwise, a new mark is adopted;
the motion trail analysis result of the human body is obtained by connecting mass center coordinates in a time window quadruple to obtain a space-time discrete curve, calculating generalized curvature, space-time length and space-time inflection point number to represent scalar quantity of the space-time discrete curve, and extracting two vector characteristics of a space domain and a time domain on discrete points on the space-time discrete curve.
In the technical scheme, on one hand, the recognition model of the illegal operation behavior is constructed to recognize the illegal operation behavior of the human body image with the three-dimensional model of the power tower removed; on the other hand, by analyzing the motion trail of the operator in the human body image, whether the illegal operation behavior exists or not is assisted and judged, and the accuracy of identifying the illegal operation behavior can be further improved. When the system recognizes that the illegal operation behaviors exist, the pictures of the illegal operation behaviors can be stored and recorded, and the pictures are stored in the operation memo corresponding to the operation tower for viewing.
The above embodiments are only for illustrating the technical solution of the present invention, and are not limiting; although the invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical scheme described in the foregoing embodiments can be modified or some technical features thereof can be replaced by equivalents; such modifications and substitutions do not depart from the spirit and scope of the technical solutions of the embodiments of the present invention.
Claims (9)
1. The utility model provides a method for identifying operators' violations based on electric power pole and tower structure information, which is characterized in that: the method comprises the following steps:
s1, carrying out image acquisition on each power tower in an area, and optimizing image acquisition points based on visual positioning of the power towers;
s2, performing image processing and analysis on the acquired images of the same power tower, establishing a corresponding three-dimensional model according to an analysis result, and storing the model database;
s3, constructing an identification model for identifying the illegal operation behaviors on various types of power towers, and training the identification model;
s4, acquiring images of the power towers working in the area, and extracting human body images from the acquired images according to the three-dimensional model corresponding to the power towers;
s5, analyzing the human body image, inputting the human body image into the recognition model, and comprehensively considering the analysis recognition result and the analysis result to recognize the illegal operation behavior.
2. The method for identifying operator violations based on power tower structure information according to claim 1, wherein the method comprises the following steps: in S1, image acquisition is carried out on each power tower in the area, and the method comprises the following steps:
the unmanned aerial vehicle is utilized to carry out regional inspection flight, environmental images in a region are continuously collected through the binocular vision camera, an electric power tower existing in the environmental images is identified by means of a neural network model, a first image collection point is set and flies to the image collection point according to the distance and the direction between the unmanned aerial vehicle and the electric power tower, and the collection visual angle of the binocular vision camera is adjusted to carry out image collection on the electric power tower.
3. The method for identifying the violation of the operator based on the structural information of the power tower according to claim 2, wherein the method comprises the following steps: in S1, optimizing an image acquisition point based on visual positioning of the power tower comprises:
the depth of field information in the acquired image is read from the acquired image of the power tower, the position information of the object at the front end of the unmanned aerial vehicle is rebuilt based on the acquired view angle, the power tower is visually positioned by combining the position relation among the unmanned aerial vehicle and a plurality of parts in the power tower through a triangulation positioning method, and each image acquisition point is sequentially set based on the position of the first image acquisition point.
4. The method for identifying operator violations based on power tower structure information according to claim 3, wherein the method comprises the steps of: when the unmanned aerial vehicle carries out regional inspection and flying, the unmanned aerial vehicle continuously carries out visual positioning on each power tower, acquires the position relation between the unmanned aerial vehicle and each power tower, corrects the flying position and sets the position of an image acquisition point.
5. The method for identifying operator violations based on power tower structure information according to claim 3, wherein the method comprises the steps of: s2, carrying out image processing and analysis on the acquired images of the same power tower, establishing a corresponding three-dimensional model according to an analysis result, and storing the three-dimensional model into a model database, wherein the method comprises the following steps:
recording image acquisition points and acquisition visual angles corresponding to all acquired images of the same power tower, scaling pictures of all the acquired images to the same size according to the position relation between the image acquisition points and the power tower, analyzing all the processed acquired images, constructing a three-dimensional model corresponding to the power tower, simultaneously carrying out position identification on the power tower, and storing identification results and the three-dimensional model into a model database.
6. The method for identifying operator violations based on power tower structure information according to claim 5, wherein the method comprises the following steps: s3, constructing an identification model for identifying illegal operation behaviors on various types of power towers, and training the identification model, wherein the method comprises the following steps:
the method comprises the steps of collecting a training image set and a detection image set by manually simulating the illegal operation behaviors on various electric towers or performing network search by a crawler, inputting the training image set into an identification model for model training, judging the identification accuracy of the identification model by using the detection image set, and adjusting model parameters according to the identification accuracy.
7. The method for identifying operator violations based on power tower structure information according to claim 6, wherein the method comprises the steps of: s4, performing image acquisition on the power towers working in the area, wherein the image acquisition comprises the following steps of:
the operation personnel send the position information of operation electric power pole tower to unmanned aerial vehicle, and unmanned aerial vehicle retrieves the three-dimensional model that this electric power pole tower corresponds from the model database according to position information, flies to near this electric power pole tower simultaneously and carries out image acquisition.
8. The method for identifying operator violations based on power tower structure information according to claim 7, wherein: and S4, extracting a human body image from the acquired image according to the three-dimensional model corresponding to the electric power tower, wherein the method comprises the following steps:
and removing a part containing the three-dimensional model of the power tower from the acquired image, analyzing and detecting a moving target by adopting a three-frame difference method, and then further screening a human body target according to contour pairing, wherein the characteristics of the human body target are matched according to space domain constraint, frequency domain characteristics and time domain characteristics.
9. The method for identifying operator violations based on power tower structure information according to claim 8, wherein the method comprises the steps of: in S5, analyzing the human body image, including:
marking all human bodies in the acquired images in sequence according to the human body target feature matching, wherein the same mark is adopted in the subsequent acquired images if the matching is successful, otherwise, a new mark is adopted;
the motion trail analysis result of the human body is obtained by connecting mass center coordinates in a time window quadruple to obtain a space-time discrete curve, calculating generalized curvature, space-time length and space-time inflection point number to represent scalar quantity of the space-time discrete curve, and extracting two vector characteristics of a space domain and a time domain on discrete points on the space-time discrete curve.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110287142.0A CN112926488B (en) | 2021-03-17 | 2021-03-17 | Electric power pole tower structure information-based operator violation identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110287142.0A CN112926488B (en) | 2021-03-17 | 2021-03-17 | Electric power pole tower structure information-based operator violation identification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112926488A CN112926488A (en) | 2021-06-08 |
| CN112926488B true CN112926488B (en) | 2023-05-30 |
Family
ID=76175814
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110287142.0A Active CN112926488B (en) | 2021-03-17 | 2021-03-17 | Electric power pole tower structure information-based operator violation identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112926488B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113824859B (en) * | 2021-08-17 | 2023-04-18 | 衢州光明电力投资集团有限公司赋腾科技分公司 | Construction hidden danger automatic identification and alarm device violating regulations |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006244140A (en) * | 2005-03-03 | 2006-09-14 | Hitachi Building Systems Co Ltd | Human behavior detecting and optimum responding system |
| KR20180060784A (en) * | 2016-11-29 | 2018-06-07 | 삼성전자주식회사 | Method and apparatus for determining abnormal object |
| CN110119656A (en) * | 2018-02-07 | 2019-08-13 | 中国石油化工股份有限公司 | Intelligent monitor system and the scene monitoring method violating the regulations of operation field personnel violating the regulations |
| WO2020154990A1 (en) * | 2019-01-30 | 2020-08-06 | 深圳市大疆创新科技有限公司 | Target object motion state detection method and device, and storage medium |
| CN111915725A (en) * | 2020-08-21 | 2020-11-10 | 青岛联合创智科技有限公司 | Human body measuring method based on motion reconstruction |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8615118B2 (en) * | 2010-05-28 | 2013-12-24 | The University Of Maryland, Baltimore | Techniques for tomographic image by background subtraction |
-
2021
- 2021-03-17 CN CN202110287142.0A patent/CN112926488B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2006244140A (en) * | 2005-03-03 | 2006-09-14 | Hitachi Building Systems Co Ltd | Human behavior detecting and optimum responding system |
| KR20180060784A (en) * | 2016-11-29 | 2018-06-07 | 삼성전자주식회사 | Method and apparatus for determining abnormal object |
| CN110119656A (en) * | 2018-02-07 | 2019-08-13 | 中国石油化工股份有限公司 | Intelligent monitor system and the scene monitoring method violating the regulations of operation field personnel violating the regulations |
| WO2020154990A1 (en) * | 2019-01-30 | 2020-08-06 | 深圳市大疆创新科技有限公司 | Target object motion state detection method and device, and storage medium |
| CN111915725A (en) * | 2020-08-21 | 2020-11-10 | 青岛联合创智科技有限公司 | Human body measuring method based on motion reconstruction |
Non-Patent Citations (1)
| Title |
|---|
| 人体异常行为识别在电力生产中的应用;张丽霞;;生物技术世界(第03期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112926488A (en) | 2021-06-08 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10269138B2 (en) | UAV inspection method for power line based on human visual system | |
| CN108537154B (en) | Power transmission line bird nest identification method based on HOG characteristics and machine learning | |
| CN112633535A (en) | Photovoltaic power station intelligent inspection method and system based on unmanned aerial vehicle image | |
| CN103996036B (en) | A kind of map data collecting method and device | |
| CN108280855A (en) | A kind of insulator breakdown detection method based on Fast R-CNN | |
| CN109829908B (en) | Binocular image-based method and device for detecting safety distance of ground object below power line | |
| CN107103437A (en) | A kind of electric operating behavior managing and control system based on image recognition | |
| CN111914813A (en) | Power transmission line inspection image naming method and system based on image classification | |
| CN112327906A (en) | Intelligent automatic inspection system based on unmanned aerial vehicle | |
| CN108846331A (en) | The video frequency identifying method whether a kind of EMU chassis screw fastener falls off | |
| CN112926488B (en) | Electric power pole tower structure information-based operator violation identification method | |
| CN109190545A (en) | Bird's Nest automatic recognition system and its methods and applications in transmission line of electricity | |
| CN114565845A (en) | Intelligent inspection system for underground tunnel | |
| CN111259855A (en) | Mobile safety helmet wearing detection method based on deep learning | |
| CN112455676A (en) | Intelligent monitoring and analyzing system and method for health state of photovoltaic panel | |
| CN112613449A (en) | Safety helmet wearing detection and identification method and system based on video face image | |
| CN114663672B (en) | Method and system for detecting corrosion of steel member of power transmission line tower | |
| CN112800950A (en) | Large security activity face searching method based on deep learning | |
| CN112037252A (en) | Eagle eye vision-based target tracking method and system | |
| CN114359712A (en) | Safety violation analysis system based on unmanned aerial vehicle inspection | |
| CN109712018A (en) | A kind of power transmission line comprehensive monitoring system | |
| CN114330477B (en) | Power equipment defect detection system and method based on mixed reality equipment | |
| CN106950996A (en) | One kind is based on unmanned plane railway high-tension bus-bar inspection obstacle avoidance system | |
| CN117498225B (en) | Unmanned aerial vehicle intelligent power line inspection system | |
| CN116071353B (en) | Bolt assembly detection 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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |