CN109284739B - Power transmission line external damage prevention early warning method and system based on deep learning - Google Patents
Power transmission line external damage prevention early warning method and system based on deep learning Download PDFInfo
- Publication number
- CN109284739B CN109284739B CN201811254489.XA CN201811254489A CN109284739B CN 109284739 B CN109284739 B CN 109284739B CN 201811254489 A CN201811254489 A CN 201811254489A CN 109284739 B CN109284739 B CN 109284739B
- Authority
- CN
- China
- Prior art keywords
- transmission line
- power transmission
- unmanned aerial
- aerial vehicle
- deep learning
- 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
- 230000005540 biological transmission Effects 0.000 title claims abstract description 64
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000013135 deep learning Methods 0.000 title claims abstract description 25
- 230000002265 prevention Effects 0.000 title claims abstract description 18
- 238000007689 inspection Methods 0.000 claims abstract description 29
- 238000013528 artificial neural network Methods 0.000 claims abstract description 20
- 238000004891 communication Methods 0.000 claims abstract description 4
- 238000012549 training Methods 0.000 claims description 19
- 238000013527 convolutional neural network Methods 0.000 claims description 16
- 238000003062 neural network model Methods 0.000 claims description 10
- 238000012360 testing method Methods 0.000 claims description 6
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 239000004020 conductor Substances 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 210000002569 neuron Anatomy 0.000 claims description 3
- 230000001902 propagating effect Effects 0.000 claims description 3
- 238000001514 detection method Methods 0.000 description 7
- 238000010586 diagram Methods 0.000 description 3
- 230000011218 segmentation Effects 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
- G06V20/13—Satellite images
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Astronomy & Astrophysics (AREA)
- Remote Sensing (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
- Alarm Systems (AREA)
Abstract
The invention relates to a power transmission line external damage prevention early warning method and system based on deep learning, wherein a camera and a wireless communication module are carried on more than one unmanned aerial vehicle, each unmanned aerial vehicle patrols the power transmission line according to a preset route, height and shooting angle, and image data shot in a target area are transmitted to a server corresponding to a patrol station; then, a server of the inspection station builds a deep neural network by adopting a deep learning method on image data transmitted back by the unmanned aerial vehicle in real time, intelligently identifies a target, judges position coordinates with external force damage risks and transmits the position coordinates to a central console; and finally, the central console receives the early warning coordinate positions sent by the inspection stations so as to warn the workers. The unmanned aerial vehicle and the deep learning algorithm popularized in the market realize external damage prevention early warning of the power transmission line in a larger range.
Description
Technical Field
The invention relates to the field of power transmission line protection, in particular to a power transmission line external damage prevention early warning method and system based on deep learning.
Background
The transmission line in China bears the heavy burden of electric energy in a transmission area, so that the stable operation of the transmission line is guaranteed to be very important. Meanwhile, due to the fact that the modern construction speed is increased continuously, engineering construction frequently seriously threatens the safety of the power transmission line, external force damage becomes a main factor influencing the safety of the power transmission line, and prevention of the external force damage is urgent. Most of the existing methods for preventing external force damage rely on manual inspection and detection of an external force damage prevention system, but the manual inspection is not timely and low in efficiency, so that external force damage cannot be well prevented, and loss is reduced; the system for preventing external force from damaging has a complex structure, is inconvenient to operate and has a small prevention range.
Along with the gradual popularization of unmanned aerial vehicle application, the electric power inspection unmanned aerial vehicle receives wide attention and application of each large power grid company because of the characteristics of low risk, low cost and flexible operation of field operation. However, mass image data obtained by inspection still needs many professionals with abundant experience to consume days for carrying out boring image retrieval and analysis tasks, conditions of missed inspection and misjudgment are easy to occur in the process, the line inspection cost is increased, and the line inspection efficiency is reduced. In recent years, deep learning relies on good learning ability of the unmanned aerial vehicle, the unmanned aerial vehicle fault recognition method is widely applied to fault recognition of inspection images of the unmanned aerial vehicle, and good results are obtained.
Disclosure of Invention
In view of the above, the invention aims to provide an aerial image power transmission line external damage prevention early warning method and system based on deep learning, and the aerial image power transmission line external damage prevention early warning method and system based on deep learning are used for realizing external damage prevention early warning of a power transmission line in a larger range by using an unmanned aerial vehicle and a deep learning algorithm which are popularized in the market.
The invention is realized by adopting the following scheme: a power transmission line external damage prevention early warning method based on deep learning specifically comprises the following steps:
step S1: carrying a camera and a wireless communication module on more than one unmanned aerial vehicle, patrolling the power transmission line by each unmanned aerial vehicle according to a preset route, height and shooting angle, and transmitting image data shot in a target area to a server corresponding to a patrolling station;
step S2: a server of the inspection station builds a deep neural network by adopting a deep learning method on image data transmitted back by the unmanned aerial vehicle in real time, intelligently identifies a target, judges position coordinates with external force damage risks and transmits the position coordinates to a central console;
step S3: and the central console receives the early warning coordinate positions sent by the inspection stations so as to warn workers.
Further, in step S2, the deep neural network is built by using a Mask R-CNN neural network, edge pixel points of the power transmission line and the dangerous target are obtained through the Mask R-CNN neural network, individual edge pixel points of the power transmission line and the dangerous target are appropriately selected to calculate the distance between the dangerous target and the power transmission line, when the minimum value of the distances is smaller than a set threshold value, it is indicated that there is an external force damage risk, and at this time, an alarm is sent to the central console through the server.
Further, the step S2 specifically includes the following steps:
step S11: continuously collecting pictures shot by an unmanned aerial vehicle as a training sample set;
step S12: constructing a Mask R-CNN neural network model;
step S13: converting the data format of the training sample set, inputting the training sample set into the neural network model in the step S12 for training, storing the training model at regular intervals of training period, testing the performance of the current model by using the data of the test set, and calculating the average accuracy rate, the omission ratio and the false alarm ratio; when each parameter of the model reaches an expected value and tends to be stable, the model is stored and then solidified, and only constants including weight and bias of the forward propagating neurons are reserved;
step S14: inputting image data transmitted back by the unmanned aerial vehicle in real time into a trained Mask R-CNN neural network model to obtain edge pixel points of the power transmission line and the dangerous target, and properly selecting individual edge pixel points of the power transmission line and the dangerous target;
step S15: because the image is a pixel coordinate system, namely a direct coordinate system u-v taking the pixel as a unit is established by taking the upper left corner of the image as an original point, and the abscissa u and the ordinate v of the pixel are the number of columns and the number of rows in the image array respectively; therefore, when the unmanned aerial vehicle actually patrols the right side of the power transmission line, the dangerous target pixel point only needs to select two point coordinates (u1, v1) and (u2, v2) with the minimum u and the minimum v, and the pixel point of the power transmission line selects the point closest to the dangerous target;
step S16: converting the pixel coordinate into a world coordinate capable of representing the actual three-dimensional coordinate of the pixel point;
step S17: according to the world coordinate and a spatial distance formula, the actual spatial distance between the power transmission conductor and the dangerous target is obtained;
step S18: and (4) comparing the actual space distance obtained in the step (S17) with a preset threshold, and if the actual space distance is smaller than the preset threshold, proving that a dangerous target enters a safety protection area of the power transmission line and is dangerous to damage the dangerous target, and sending an alarm to a central console by the server.
Further, in step S16, the conversion between the world coordinates and the pixel coordinates adopts the following equation:
wherein u and v are respectively the horizontal and vertical coordinates of the pixel, the first and second matrix on the right side of the equal sign are the internal and external parameters of the camera, Xw、Yw、ZwIs the world coordinate of the point, ZcAre camera coordinates;
and (4) obtaining world coordinates corresponding to the pixel coordinates through inverse operation.
The invention also provides a system of the electric transmission line external damage prevention early warning method based on the deep learning, which comprises a central console, more than one inspection station and more than one unmanned aerial vehicle; one patrol station corresponds to a certain number of unmanned aerial vehicles according to the concrete conditions;
the unmanned aerial vehicle is provided with a high-definition camera and a wireless transmission module and is used for collecting the images of the power transmission line and transmitting the images to the corresponding inspection station;
a server is arranged in the patrol station and used for building a deep neural network for image data transmitted back by the unmanned aerial vehicle in real time by adopting a deep learning method, intelligently identifying a target, judging a position coordinate with external force damage risk and transmitting the position coordinate to a central console;
the central console can receive the alarms sent by the inspection stations and acquire the position coordinates of the alarm at the moment.
Further, the central console can inquire the patrol progress of each patrol station and the image data stored on the patrol station server in real time.
Compared with the prior art, the invention has the following beneficial effects: the invention replaces the manual inspection and the camera exploration method with the unmanned aerial vehicle inspection mode, thereby reducing the labor cost, improving the efficiency and greatly improving the inspection range. The invention simultaneously utilizes the Mask R-CNN neural network to carry out intelligent detection on the image data, sets the threshold value to judge whether the hidden danger of external force damage exists, improves the efficiency and guarantees the real-time requirement, and simultaneously reduces the false alarm rate.
Drawings
Fig. 1 is a schematic diagram of a system according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a neural network model training process according to an embodiment of the present invention.
Fig. 3 is a schematic flow chart illustrating a process of determining whether a dangerous object exists according to an embodiment of the present invention.
Fig. 4 is a schematic diagram of a conversion process of a pixel coordinate and a world coordinate according to an embodiment of the present invention.
Detailed Description
The invention is further explained below with reference to the drawings and the embodiments.
It should be noted that the following detailed description is exemplary and is intended to provide further explanation of the disclosure. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of example embodiments according to the present application. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
As shown in fig. 1, the embodiment provides a power transmission line external damage prevention early warning method based on deep learning, which specifically includes the following steps:
step S1: carrying a camera and a wireless communication module on more than one unmanned aerial vehicle, patrolling the power transmission line by each unmanned aerial vehicle according to a preset route, height and shooting angle, and transmitting image data shot in a target area to a server corresponding to a patrolling station;
step S2: a server of the inspection station builds a deep neural network by adopting a deep learning method on image data transmitted back by the unmanned aerial vehicle in real time, intelligently identifies a target, judges position coordinates with external force damage risks and transmits the position coordinates to a central console;
step S3: and the central console receives the early warning coordinate positions sent by the inspection stations so as to warn workers.
In this embodiment, in step S2, the deep neural network is built by using a Mask R-CNN neural network, edge pixel points of the power transmission line and the dangerous target are obtained through the Mask R-CNN neural network, individual edge pixel points of the power transmission line and the dangerous target are appropriately selected to calculate the distance between the dangerous target and the power transmission line, when the minimum value of the distances is smaller than a set threshold value, it is indicated that there is an external force damage risk, and at this time, an alarm is sent to the central console through the server.
In this embodiment, the step S2 specifically includes the following steps:
as shown in fig. 2, step S11: continuously collecting pictures shot by an unmanned aerial vehicle as a training sample set;
step S12: constructing a Mask R-CNN neural network model; the Mask R-CNN neural network is an Instance segmentation (Instance segmentation) algorithm, can be used for target detection, target Instance segmentation and target key point detection, and is compared with other R-CNN neural networks, and the Mask R-CNN is most critical in that feature point positioning is carried out at a pixel level so as to achieve the effect of determining the edge of each object;
step S13: converting the data format of the training sample set, inputting the training sample set into the neural network model in the step S12 for training, storing the training model at regular intervals of training period, testing the performance of the current model by using the data of the test set, and calculating the average accuracy rate, the omission ratio and the false alarm ratio; when each parameter of the model reaches an expected value and tends to be stable, the model is stored and then solidified, and only constants including weight and bias of the forward propagating neurons are reserved;
as shown in fig. 3, step S14: inputting image data transmitted back by the unmanned aerial vehicle in real time into a trained Mask R-CNN neural network model to obtain edge pixel points of the power transmission line and the dangerous target, and properly selecting individual edge pixel points of the power transmission line and the dangerous target;
step S15: because the image is a pixel coordinate system, namely a direct coordinate system u-v taking the pixel as a unit is established by taking the upper left corner of the image as an original point, and the abscissa u and the ordinate v of the pixel are the number of columns and the number of rows in the image array respectively; therefore, when the unmanned aerial vehicle actually patrols the right side of the power transmission line, the dangerous target pixel point only needs to select two point coordinates (u1, v1) and (u2, v2) with the minimum u and the minimum v, and the pixel point of the power transmission line selects the point closest to the dangerous target;
step S16: because the pixel coordinate cannot represent the actual coordinate of the point in the real three-dimensional space and the actual distance between the power transmission line and the dangerous target cannot be accurately calculated, the pixel coordinate needs to be converted into a world coordinate capable of representing the actual three-dimensional coordinate of the pixel point;
step S17: according to the world coordinate and a spatial distance formula, the actual spatial distance between the power transmission conductor and the dangerous target is obtained;
step S18: and (4) comparing the actual space distance obtained in the step (S17) with a preset threshold, and if the actual space distance is smaller than the preset threshold, proving that a dangerous target enters a safety protection area of the power transmission line and is dangerous to damage the dangerous target, and sending an alarm to a central console by the server.
As shown in fig. 4, in the present embodiment, in step S16, the conversion between the world coordinates and the pixel coordinates adopts the following equation:
wherein u and v are each asThe first and second matrix on the right side of the abscissa and ordinate of the pixel with equal sign are internal and external parameters of the camera, Xw、Yw、ZwIs the world coordinate of the point, ZcAre camera coordinates;
and (4) obtaining world coordinates corresponding to the pixel coordinates through inverse operation.
As shown in fig. 1, the embodiment further provides a system of the power transmission line external damage prevention early warning method based on the above deep learning, which includes a central console, more than one patrol station, and more than one unmanned aerial vehicle; one patrol station corresponds to a certain number of unmanned aerial vehicles according to the concrete conditions;
the unmanned aerial vehicle is provided with a high-definition camera and a wireless transmission module and is used for collecting the images of the power transmission line and transmitting the images to the corresponding inspection station;
a server is arranged in the patrol station and used for building a deep neural network for image data transmitted back by the unmanned aerial vehicle in real time by adopting a deep learning method, intelligently identifying a target, judging a position coordinate with external force damage risk and transmitting the position coordinate to a central console;
the central console can receive the alarms sent by the inspection stations and acquire the position coordinates of the alarm at the moment.
In this embodiment, the central console can inquire the patrol progress of each patrol station and the image data stored on the patrol station server in real time.
The fine, the high definition digtal camera of carrying on the unmanned aerial vehicle, resolution ratio is 1080P, unmanned aerial vehicle in addition can be according to the patrol route that plans in advance, a key automatic take-off is patrolled according to set height and set shooting angle. The patrol path is planned by a professional plane in advance and is led into an unmanned aerial vehicle configuration. Image data shot in the target area is uploaded to the patrol station through the unmanned aerial vehicle wireless transmission module (or the image transmission module of the unmanned aerial vehicle).
Preferably, the patrol station is composed of a server and at least one unmanned aerial vehicle in an area with the server as the circle center and 3 kilometers as the radius. On the upper partThe unmanned aerial vehicle patrols the area according to a preset trajectory and uploads image data to the server in real time. Further, a 3 x 3m is provided in the patrol station2The unmanned aerial vehicle start and stop district to and a staff, so that retrieve unmanned aerial vehicle and change the battery.
Preferably, the server comprises three modules of image storage, image identification and early warning information reporting. The image storage module can store image data transmitted back by the real-time image of the unmanned aerial vehicle in a set storage space, the image recognition module adopts a deep learning method to build a deep neural network to intelligently recognize a target, and the early warning information reporting module can upload position coordinates which are recognized by the image recognition module and have external force damage risks to a central console.
The image identification module is the core of the whole method and comprises an external force damage target detection module and a power transmission line and dangerous target distance judgment module. The external force damage target detection module needs to be trained and cured in advance and then loaded into a server of the inspection station, and the model performance can be continuously improved through image data continuously collected by the inspection station, so that higher accuracy is achieved. When the collected images pass through the target detection module to detect the power transmission line and the dangerous target, whether the dangerous target has external force damage hidden danger or not can be judged through the distance judgment module.
The above description is only a preferred embodiment of the present invention, and all equivalent changes and modifications made in accordance with the claims of the present invention should be covered by the present invention.
Claims (4)
1. A power transmission line external damage prevention early warning method based on deep learning is characterized by comprising the following steps: the method comprises the following steps:
step S1: carrying a camera and a wireless communication module on more than one unmanned aerial vehicle, patrolling the power transmission line by each unmanned aerial vehicle according to a preset route, height and shooting angle, and transmitting image data shot in a target area to a server corresponding to a patrolling station;
step S2: a server of the inspection station builds a deep neural network by adopting a deep learning method on image data transmitted back by the unmanned aerial vehicle in real time, intelligently identifies a target, judges position coordinates with external force damage risks and transmits the position coordinates to a central console;
step S3: the central console receives the early warning coordinate positions sent by the inspection stations and is used for warning workers;
in step S2, the deep neural network is built by using a Mask R-CNN neural network, edge pixel points of the power transmission line and the dangerous target are obtained through the Mask R-CNN neural network, individual edge pixel points of the power transmission line and the dangerous target are appropriately selected to calculate the distance between the dangerous target and the power transmission line, when the minimum value of the distances is smaller than a set threshold value, it is indicated that there is an external force damage risk, and an alarm is sent to the central console through the server at this time;
wherein, the step S2 specifically includes the following steps:
step S11: continuously collecting pictures shot by an unmanned aerial vehicle as a training sample set;
step S12: constructing a Mask R-CNN neural network model;
step S13: converting the data format of the training sample set, inputting the training sample set into the neural network model in the step S12 for training, storing the training model at regular intervals of training period, testing the performance of the current model by using the data of the test set, and calculating the average accuracy rate, the omission ratio and the false alarm ratio; when each parameter of the model reaches an expected value and tends to be stable, the model is stored and then solidified, and only constants including weight and bias of the forward propagating neurons are reserved;
step S14: inputting image data transmitted back by the unmanned aerial vehicle in real time into a trained Mask R-CNN neural network model to obtain edge pixel points of the power transmission line and the dangerous target, and properly selecting individual edge pixel points of the power transmission line and the dangerous target;
step S15: because the image is a pixel coordinate system, namely a direct coordinate system u-v taking the pixel as a unit is established by taking the upper left corner of the image as an original point, and the abscissa u and the ordinate v of the pixel are the number of columns and the number of rows in the image array respectively; therefore, when the unmanned aerial vehicle actually patrols the right side of the power transmission line, the dangerous target pixel point only needs to select two point coordinates (u1, v1) and (u2, v2) with the minimum u and the minimum v, and the pixel point of the power transmission line selects the point closest to the dangerous target;
step S16: converting the pixel coordinate into a world coordinate capable of representing the actual three-dimensional coordinate of the pixel point;
step S17: according to the world coordinate and a spatial distance formula, the actual spatial distance between the power transmission conductor and the dangerous target is obtained;
step S18: and (4) comparing the actual space distance obtained in the step (S17) with a preset threshold, and if the actual space distance is smaller than the preset threshold, proving that a dangerous target enters a safety protection area of the power transmission line and is dangerous to damage the dangerous target, and sending an alarm to a central console by the server.
2. The electric transmission line external damage prevention early warning method based on deep learning of claim 1, wherein: in step S16, the conversion between the world coordinates and the pixel coordinates is represented by the following equation:
wherein u and v are respectively the horizontal and vertical coordinates of the pixel, the first and second matrix on the right side of the equal sign are the internal and external parameters of the camera, Xw、Yw、ZwIs the world coordinate of the point, ZcAre camera coordinates;
and (4) obtaining world coordinates corresponding to the pixel coordinates through inverse operation.
3. The system of the early warning method for preventing external force damage of the power transmission line based on deep learning is characterized by comprising the following steps of: the system comprises a central control console, more than one inspection station and more than one unmanned aerial vehicle; one patrol station corresponds to a certain number of unmanned aerial vehicles according to the concrete conditions;
the unmanned aerial vehicle is provided with a high-definition camera and a wireless transmission module and is used for collecting the images of the power transmission line and transmitting the images to the corresponding inspection station;
a server is arranged in the patrol station and used for building a deep neural network for image data transmitted back by the unmanned aerial vehicle in real time by adopting a deep learning method, intelligently identifying a target, judging a position coordinate with external force damage risk and transmitting the position coordinate to a central console;
the central console can receive the alarms sent by the inspection stations and acquire the position coordinates of the alarm at the moment.
4. The electric transmission line external damage prevention early warning system based on deep learning of claim 3, wherein: the central console can inquire the patrol progress of each patrol station and the image data stored on the patrol station server in real time.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811254489.XA CN109284739B (en) | 2018-10-26 | 2018-10-26 | Power transmission line external damage prevention early warning method and system based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811254489.XA CN109284739B (en) | 2018-10-26 | 2018-10-26 | Power transmission line external damage prevention early warning method and system based on deep learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109284739A CN109284739A (en) | 2019-01-29 |
| CN109284739B true CN109284739B (en) | 2021-09-28 |
Family
ID=65178516
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811254489.XA Active CN109284739B (en) | 2018-10-26 | 2018-10-26 | Power transmission line external damage prevention early warning method and system based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109284739B (en) |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110321770B (en) * | 2019-03-25 | 2022-05-31 | 西安长城数字软件有限公司 | Pipeline monitoring method, device, equipment and storage medium |
| CN110008901A (en) * | 2019-04-04 | 2019-07-12 | 天津工业大学 | A method for insulator fault identification and location based on Mask R-CNN |
| CN110730327A (en) * | 2019-09-03 | 2020-01-24 | 华为技术有限公司 | A method and acquisition front-end for monitoring transmission lines |
| CN110766281B (en) * | 2019-09-20 | 2022-04-26 | 国网宁夏电力有限公司电力科学研究院 | Transmission conductor wind damage early warning method and terminal based on deep learning |
| CN110599538B (en) * | 2019-09-30 | 2020-09-22 | 山东信通电子股份有限公司 | Method and device for identifying icing thickness of transmission line conductor |
| CN110852320B (en) * | 2019-11-08 | 2022-06-24 | 积成电子股份有限公司 | Transmission channel foreign matter intrusion detection method based on deep learning |
| CN111401146A (en) * | 2020-02-26 | 2020-07-10 | 长江大学 | Unmanned aerial vehicle power inspection method, device and storage medium |
| CN111402247B (en) * | 2020-03-23 | 2023-04-18 | 华南理工大学 | Machine vision-based method for detecting defects of suspension clamp on power transmission line |
| CN111582192A (en) * | 2020-05-11 | 2020-08-25 | 智洋创新科技股份有限公司 | Suspicious sample identification method based on continuous alarm of power transmission line channel image |
| CN111862506A (en) * | 2020-07-29 | 2020-10-30 | 杭州巨骐信息科技股份有限公司 | Holographic sensing external force damage monitoring method |
| CN111862505A (en) * | 2020-07-29 | 2020-10-30 | 杭州巨骐信息科技股份有限公司 | Holographic perception external damage monitoring system |
| CN114093051B (en) * | 2020-08-05 | 2023-10-31 | 中国联合网络通信集团有限公司 | Communication line inspection method, equipment and system, computer-readable storage medium |
| CN112950504A (en) * | 2021-03-02 | 2021-06-11 | 山东鲁能软件技术有限公司智能电气分公司 | Power transmission line inspection haze weather monocular hidden danger object distance measurement method and system |
| CN114782314A (en) * | 2022-03-17 | 2022-07-22 | 云南电网有限责任公司电力科学研究院 | A method for prompting the risk of external breakage of power grid transmission lines |
| CN115267418B (en) * | 2022-04-22 | 2025-05-13 | 北京佳服信息科技有限公司 | Monitoring method, device, equipment and storage medium for compliance laying of transmission and distribution lines |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102446390A (en) * | 2011-03-16 | 2012-05-09 | 上海市电力公司 | A method and system for safety detection and early warning of monitoring areas near transmission lines |
| CN107909585A (en) * | 2017-11-14 | 2018-04-13 | 华南理工大学 | Inner membrance dividing method in a kind of blood vessel of intravascular ultrasound image |
| CN108037770A (en) * | 2017-11-22 | 2018-05-15 | 国网山东省电力公司济宁供电公司 | Unmanned plane power transmission line polling system and method based on artificial intelligence |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10078790B2 (en) * | 2017-02-16 | 2018-09-18 | Honda Motor Co., Ltd. | Systems for generating parking maps and methods thereof |
-
2018
- 2018-10-26 CN CN201811254489.XA patent/CN109284739B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102446390A (en) * | 2011-03-16 | 2012-05-09 | 上海市电力公司 | A method and system for safety detection and early warning of monitoring areas near transmission lines |
| CN107909585A (en) * | 2017-11-14 | 2018-04-13 | 华南理工大学 | Inner membrance dividing method in a kind of blood vessel of intravascular ultrasound image |
| CN108037770A (en) * | 2017-11-22 | 2018-05-15 | 国网山东省电力公司济宁供电公司 | Unmanned plane power transmission line polling system and method based on artificial intelligence |
Non-Patent Citations (2)
| Title |
|---|
| "Transmission line extraction and recognition from natural complex background";Wei-Guo Tong.et al;《IEEE》;20090825;全文 * |
| "基于高压输电线的防外力破坏预警技术研究";李忠魁等;《设计研究与应用》;20170430;第38卷(第4期);全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109284739A (en) | 2019-01-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109284739B (en) | Power transmission line external damage prevention early warning method and system based on deep learning | |
| CN114035614B (en) | Unmanned aerial vehicle autonomous inspection method and system based on prior information and storage medium | |
| CN110321853B (en) | Distributed cable external-damage-prevention system based on video intelligent detection | |
| CN110097787B (en) | A ship collision warning monitoring system and method based on monitoring beacon lights | |
| CN108445767B (en) | A visual field safety supervision and management system based on UAV | |
| CN111458721B (en) | Exposed garbage identification and positioning method, device and system | |
| CN115603466B (en) | Ship shore power system based on artificial intelligence visual identification | |
| CN110910440B (en) | Power transmission line length determination method and system based on power image data | |
| CN115797873B (en) | Crowd density detection method, system, equipment, storage medium and robot | |
| CN113313006B (en) | Urban illegal building supervision method, system and storage medium based on unmanned aerial vehicle | |
| CN104994347A (en) | Intelligent security video monitoring system and detection processing method thereof | |
| CN112332541A (en) | Monitoring system and method for transformer substation | |
| CN109977840A (en) | A kind of airport scene monitoring method based on deep learning | |
| CN116631158A (en) | Landslide early warning device based on image recognition and computer vision | |
| CN114723271A (en) | Power transmission project quality detection method and system based on image recognition | |
| CN115909240A (en) | Road congestion detection method based on lane line and vehicle identification | |
| CN116736891A (en) | Autonomous track planning system and method for multi-machine collaborative inspection power grid line | |
| CN112614130A (en) | Unmanned aerial vehicle power transmission line insulator fault detection method based on 5G transmission and YOLOv3 | |
| CN115617080B (en) | Unmanned aerial vehicle inspection system and method for transformer substation | |
| CN116647032B (en) | Real-time protection system and method for power transmission line of target construction vehicle | |
| CN112233270A (en) | Unmanned aerial vehicle is intelligence around tower system of patrolling and examining independently | |
| CN216647401U (en) | Safety helmet recognition device | |
| CN116026778A (en) | Sky-ground-based park carbon emission comprehensive monitoring system and method | |
| CN112702579A (en) | Automatic identification system based on unmanned aerial vehicle image of taking photo by plane | |
| CN218214363U (en) | Smart pile terminal equipment of smart multipurpose |
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 |