CN113705708A - Intelligent classification and naming method for unmanned aerial vehicle inspection pictures of power transmission line - Google Patents
Intelligent classification and naming method for unmanned aerial vehicle inspection pictures of power transmission line Download PDFInfo
- Publication number
- CN113705708A CN113705708A CN202111027434.7A CN202111027434A CN113705708A CN 113705708 A CN113705708 A CN 113705708A CN 202111027434 A CN202111027434 A CN 202111027434A CN 113705708 A CN113705708 A CN 113705708A
- Authority
- CN
- China
- Prior art keywords
- aerial vehicle
- unmanned aerial
- pictures
- naming
- power transmission
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 230000005540 biological transmission Effects 0.000 title claims abstract description 43
- 238000000034 method Methods 0.000 title claims abstract description 40
- 238000007689 inspection Methods 0.000 title claims abstract description 11
- 238000012423 maintenance Methods 0.000 claims abstract description 17
- 238000004364 calculation method Methods 0.000 claims abstract description 5
- 238000013528 artificial neural network Methods 0.000 claims description 10
- 238000010586 diagram Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000012212 insulator Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- 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
-
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a method for intelligently classifying and naming unmanned aerial vehicle inspection pictures of a power transmission line, wherein the intelligent classification method classifies the unmanned aerial vehicle inspection pictures by constructing an operation and maintenance line basic information base, wherein the operation and maintenance line basic information base stores pole numbers, pole tower datum point longitude and latitude and pole tower attribution lines, when the imported unmanned aerial vehicle inspection pictures are classified, the distance between a shooting point and a pole tower is calculated according to the pole tower datum point longitude and latitude and longitude coordinate information of the shooting point in the inspection pictures, and the inspection pictures are classified according to the pole tower attribution lines and the pole numbers according to the distance near-far threshold range of the calculation result; the intelligent naming method firstly regulates the patrol operation of the unmanned aerial vehicle, and then combines the patrol picture classification result to carry out subsequent intelligent identification naming on the pictures of the transmission equipment components in the patrol pictures; the invention can automatically classify and name the unmanned aerial vehicle tour pictures, thereby saving time and labor cost.
Description
Technical Field
The invention relates to the technical field of unmanned aerial vehicle data processing, in particular to a method for intelligently classifying and naming patrol pictures of an unmanned aerial vehicle of a power transmission line.
Background
The scheme of classifying and naming the prior unmanned aerial vehicle tour pictures mainly comprises the following steps:
1. and (4) manually distinguishing the pictures, and manually clicking and combining the pictures by utilizing the fixed field combination function in the auxiliary software. And the functions of naming and filing the pictures are realized. Comparatively effectual arrangement, file unmanned aerial vehicle picture.
2. The manual naming filing method is characterized in that a fixed field combination function in auxiliary software is utilized to carry out manual clicking combination. The working efficiency can be improved to a certain degree, the whole working time is shortened by about 20 percent, and the effect is not obvious.
However, when the number of pictures generated by the unmanned aerial vehicle patrol work is huge, a lot of time and labor are needed for identifying and processing the pictures.
Disclosure of Invention
The invention provides a method for intelligently classifying and naming the unmanned aerial vehicle patrol pictures of a power transmission line, which can automatically classify and name the unmanned aerial vehicle patrol pictures and save time and labor cost.
The invention adopts the following technical scheme.
A method for intelligently classifying and naming Unmanned Aerial Vehicle (UAV) patrol pictures of a power transmission line comprises an intelligent classification method and an intelligent naming method, wherein the UAV stores longitude and latitude coordinates of shooting points in picture attribute information when shooting the patrol pictures, the intelligent classification method classifies the UAV patrol pictures by constructing an operation and maintenance line basic information base, the operation and maintenance line basic information base stores pole numbers, pole tower datum point longitude and latitude and a pole tower attribution line, when classifying the imported UAV patrol pictures, the distance between the shooting points and the pole tower is calculated according to the pole tower datum point longitude and latitude and the shooting point longitude and latitude coordinate information in the patrol pictures, and the patrol pictures are classified according to the pole tower attribution line and the pole numbers according to the distance far and near threshold range of the calculation result;
the intelligent naming method firstly stipulates the patrol operation of the unmanned aerial vehicle, and then carries out subsequent intelligent identification naming on the pictures of the power transmission equipment components in the patrol pictures by combining the patrol picture classification results.
The intelligent naming method comprises the step of stipulating a patrol operation track of the unmanned aerial vehicle, and particularly the step of limiting a shooting path of the power transmission equipment by the unmanned aerial vehicle.
The limitation of the shooting path and the shooting sequence of the unmanned aerial vehicle on the power transmission equipment is specifically to limit the unmanned aerial vehicle to shoot from the small-size side of the tower to the large-size side of the tower when shooting the power transmission equipment, shoot from the left side to the right side of the power transmission equipment and shoot from the lower part to the upper part of the power transmission equipment.
The intelligent naming method is characterized in that pictures shot by the unmanned aerial vehicle according to shooting paths are identified and read through a neural network intelligent identification algorithm so as to identify power transmission equipment components in the pictures, and the identified and read power transmission equipment component images are named one by one in combination with picture shooting sequence, tower model and hardware string assembly mode.
The tower information in the operation and maintenance line basic information base comprises longitude and latitude, tower shape, hardware assembly string type, loop attribute and double-loop relative position of the same tower; the loop attribute is either a double loop or a single loop.
The intelligent naming method further comprises an unmanned aerial vehicle navigation picture typical image library, a naming software execution frame of a neural network intelligent recognition algorithm is determined according to the pole tower type, the hardware string assembly mode and the specified unmanned aerial vehicle shooting sequence in the operation and maintenance line basic information library in combination with the unmanned aerial vehicle navigation picture typical image library, and intelligent naming of the detailed shooting components is carried out on the classified navigation pictures through naming software.
The neural network intelligent recognition algorithm is trained by pictures in an unmanned aerial vehicle navigation picture typical picture library.
Compared with the prior art, the invention has the advantages that:
1. the efficiency is improved, and the standardization of picture management is realized. The whole working time is shortened by about 40 percent.
2. The manpower is liberated, and the artificial intelligent operation is realized.
Drawings
The invention is described in further detail below with reference to the following figures and detailed description:
FIG. 1 is a schematic flow diagram of the present invention.
Detailed Description
As shown in the figure, the method for intelligently classifying and naming the unmanned aerial vehicle patrol pictures of the power transmission line comprises an intelligent classification method and an intelligent naming method, wherein the unmanned aerial vehicle stores longitude and latitude coordinates of shooting points in picture attribute information when shooting the patrol pictures, the intelligent classification method classifies the unmanned aerial vehicle patrol pictures by constructing an operation and maintenance line basic information base, the operation and maintenance line basic information base stores pole numbers, pole tower datum point longitude and latitude and pole tower attribution lines, when classifying the imported unmanned aerial vehicle patrol pictures, the distance between the shooting points and the pole towers is calculated according to the pole tower datum point longitude and latitude and longitude coordinate information of the shooting points in the patrol pictures, and the patrol pictures are classified according to the pole tower attribution lines and the pole numbers according to the distance near and far threshold range of the calculation result;
the intelligent naming method firstly stipulates the patrol operation of the unmanned aerial vehicle, and then carries out subsequent intelligent identification naming on the pictures of the power transmission equipment components in the patrol pictures by combining the patrol picture classification results.
The intelligent naming method comprises the step of stipulating a patrol operation track of the unmanned aerial vehicle, and particularly the step of limiting a shooting path of the power transmission equipment by the unmanned aerial vehicle.
The limitation of the shooting path and the shooting sequence of the unmanned aerial vehicle on the power transmission equipment is specifically to limit the unmanned aerial vehicle to shoot from the small-size side of the tower to the large-size side of the tower when shooting the power transmission equipment, shoot from the left side to the right side of the power transmission equipment and shoot from the lower part to the upper part of the power transmission equipment.
The intelligent naming method is characterized in that pictures shot by the unmanned aerial vehicle according to shooting paths are identified and read through a neural network intelligent identification algorithm so as to identify power transmission equipment components in the pictures, and the identified and read power transmission equipment component images are named one by one in combination with picture shooting sequence, tower model and hardware string assembly mode.
The tower information in the operation and maintenance line basic information base comprises longitude and latitude, tower shape, hardware assembly string type, loop attribute and double-loop relative position of the same tower; the loop attribute is either a double loop or a single loop.
The intelligent naming method further comprises an unmanned aerial vehicle navigation picture typical image library, a naming software execution frame of a neural network intelligent recognition algorithm is determined according to the pole tower type, the hardware string assembly mode and the specified unmanned aerial vehicle shooting sequence in the operation and maintenance line basic information library in combination with the unmanned aerial vehicle navigation picture typical image library, and intelligent naming of the detailed shooting components is carried out on the classified navigation pictures through naming software.
In the embodiment, the image data is classified and named by using an artificial intelligent neural network algorithm, attributes such as image coordinate information and the like are extracted, the operation and maintenance line coordinates are matched, and the accuracy of the artificial intelligent recognition system is improved according to an auxiliary scheme of data such as the model of a tower, the assembly mode of a hardware string, a specified shooting sequence and the like.
In the implementation of the embodiment, firstly, an unmanned aerial vehicle navigation patrol picture typical image library and an operation and maintenance line basic information library are constructed, and relevant data for classification and naming, such as tower basic information parameters, including longitude and latitude, tower shape, hardware assembly string type, double-circuit (single-circuit) and same-tower double-circuit relative positions, are stored.
When pictures are classified, unmanned aerial vehicle navigation pictures are imported, picture coordinate information is extracted to be matched and calculated with the reference coordinate information of the photographed pole tower, the relative distance between the daily unmanned aerial vehicle photographing position and the pole tower reference point is determined in the same coordinate system, and the navigation pictures photographed within the distance threshold range can be classified and belong to lines and pole numbers corresponding to the basic coordinates. The calculation is used as an algorithm for judging the corresponding line and pole number of the navigation patrol picture. And ensuring that the pictures are correctly classified.
When the pictures are named, a software execution frame is determined by utilizing a typical picture library of a navigation patrol picture according to the model of a tower, the assembly mode of a hardware string, a specified shooting sequence and the like. Intelligent naming of the detailed shooting parts is carried out on the classified pictures:
because some components in the structure of the power transmission equipment have strong symmetry, such as insulators on power transmission towers, the symmetric components are difficult to intelligently name simply according to an artificial intelligence recognition diagram. Even if the learning time of the intelligent algorithm is sufficient, the error rate is high. Therefore, before the naming method is implemented, the shooting route and the shooting sequence of the unmanned aerial vehicle need to be defined in a solidified mode, for example: when the unmanned aerial vehicle shoots the power transmission equipment, the unmanned aerial vehicle shoots the power transmission equipment from the small-size side to the large-size side, from left to right, from bottom to top and the like in sequence,
when the unmanned aerial vehicle carries out tour shooting according to the set shooting route and the set shooting sequence and provides corresponding pictures, parts in the pictures can be identified by using a neural network picture intelligent identification algorithm, and the tour pictures are named one by combining a classification result, an unmanned aerial vehicle tour picture typical picture library and an operation and maintenance line basic information library.
Claims (7)
1. The utility model provides a method of transmission line unmanned aerial vehicle tour picture intelligent classification, naming, includes intelligent classification method and intelligent naming method, unmanned aerial vehicle stores the shooting point longitude and latitude coordinate in picture attribute information when shooing the tour picture, its characterized in that: the intelligent classification method classifies the unmanned aerial vehicle inspection pictures by constructing an operation and maintenance line basic information base, wherein the operation and maintenance line basic information base stores pole numbers, pole tower datum point longitude and latitude and pole tower attribution lines, when the imported unmanned aerial vehicle inspection pictures are classified, the distance between a shooting point and a pole tower is calculated according to the pole tower datum point longitude and latitude and the shooting point longitude and latitude coordinate information in the inspection pictures, and the inspection pictures are classified according to the pole tower attribution lines and the pole numbers according to the distance near-far threshold range of the calculation result;
the intelligent naming method firstly stipulates the patrol operation of the unmanned aerial vehicle, and then carries out subsequent intelligent identification naming on the pictures of the power transmission equipment components in the patrol pictures by combining the patrol picture classification results.
2. The method for intelligently classifying and naming the unmanned aerial vehicle patrol pictures of the power transmission line according to claim 1, which is characterized in that: the intelligent naming method comprises the step of stipulating a patrol operation track of the unmanned aerial vehicle, and particularly the step of limiting a shooting path of the power transmission equipment by the unmanned aerial vehicle.
3. The method for intelligently classifying and naming the unmanned aerial vehicle patrol pictures of the power transmission line according to claim 2, which is characterized in that: the limitation of the shooting path and the shooting sequence of the unmanned aerial vehicle on the power transmission equipment is specifically to limit the unmanned aerial vehicle to shoot from the small-size side of the tower to the large-size side of the tower when shooting the power transmission equipment, shoot from the left side to the right side of the power transmission equipment and shoot from the lower part to the upper part of the power transmission equipment.
4. The method for intelligently classifying and naming the patrol pictures of the power transmission line unmanned aerial vehicle according to claim 3, which is characterized in that: the intelligent naming method is characterized in that pictures shot by the unmanned aerial vehicle according to shooting paths are identified and read through a neural network intelligent identification algorithm so as to identify power transmission equipment components in the pictures, and the identified and read power transmission equipment component images are named one by one in combination with picture shooting sequence, tower model and hardware string assembly mode.
5. The method for intelligently classifying and naming the unmanned aerial vehicle patrol pictures of the power transmission line according to claim 4, which is characterized in that: the tower information in the operation and maintenance line basic information base comprises longitude and latitude, tower shape, hardware assembly string type, loop attribute and double-loop relative position of the same tower; the loop attribute is either a double loop or a single loop.
6. The method for intelligently classifying and naming the patrol pictures of the power transmission line unmanned aerial vehicle according to claim 5, wherein the method comprises the following steps: the intelligent naming method further comprises an unmanned aerial vehicle navigation picture typical image library, a naming software execution frame of a neural network intelligent recognition algorithm is determined according to the pole tower type, the hardware string assembly mode and the specified unmanned aerial vehicle shooting sequence in the operation and maintenance line basic information library in combination with the unmanned aerial vehicle navigation picture typical image library, and intelligent naming of the detailed shooting components is carried out on the classified navigation pictures through naming software.
7. The method for intelligently classifying and naming the unmanned aerial vehicle patrol pictures of the power transmission line according to claim 6, which is characterized in that: the neural network intelligent recognition algorithm is trained by pictures in an unmanned aerial vehicle navigation picture typical picture library.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111027434.7A CN113705708A (en) | 2021-09-02 | 2021-09-02 | Intelligent classification and naming method for unmanned aerial vehicle inspection pictures of power transmission line |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111027434.7A CN113705708A (en) | 2021-09-02 | 2021-09-02 | Intelligent classification and naming method for unmanned aerial vehicle inspection pictures of power transmission line |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113705708A true CN113705708A (en) | 2021-11-26 |
Family
ID=78657460
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111027434.7A Pending CN113705708A (en) | 2021-09-02 | 2021-09-02 | Intelligent classification and naming method for unmanned aerial vehicle inspection pictures of power transmission line |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113705708A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20140077755A (en) * | 2012-12-14 | 2014-06-24 | 에이큐 주식회사 | Image photographing device and method for auto-naming image data |
| US20180211406A1 (en) * | 2017-01-23 | 2018-07-26 | Shanghai Hang Seng Electronic Technology Co., Ltd | Image processing method and device for unmanned aerial vehicle |
| CN111709361A (en) * | 2020-06-16 | 2020-09-25 | 广东电网有限责任公司 | Unmanned aerial vehicle inspection data processing method for power transmission line |
| CN112256060A (en) * | 2020-10-29 | 2021-01-22 | 广东电网有限责任公司 | Method for automatically naming pictures for automatic inspection of power transmission line unmanned aerial vehicle in real time |
| CN112445765A (en) * | 2020-12-01 | 2021-03-05 | 国网福建省电力有限公司电力科学研究院 | Aerial line unmanned aerial vehicle inspection picture sorting and naming method based on smart phone APP |
| CN112506221A (en) * | 2020-12-04 | 2021-03-16 | 国网湖北省电力有限公司检修公司 | Unmanned aerial vehicle route planning processing method based on laser point cloud |
-
2021
- 2021-09-02 CN CN202111027434.7A patent/CN113705708A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20140077755A (en) * | 2012-12-14 | 2014-06-24 | 에이큐 주식회사 | Image photographing device and method for auto-naming image data |
| US20180211406A1 (en) * | 2017-01-23 | 2018-07-26 | Shanghai Hang Seng Electronic Technology Co., Ltd | Image processing method and device for unmanned aerial vehicle |
| CN111709361A (en) * | 2020-06-16 | 2020-09-25 | 广东电网有限责任公司 | Unmanned aerial vehicle inspection data processing method for power transmission line |
| CN112256060A (en) * | 2020-10-29 | 2021-01-22 | 广东电网有限责任公司 | Method for automatically naming pictures for automatic inspection of power transmission line unmanned aerial vehicle in real time |
| CN112445765A (en) * | 2020-12-01 | 2021-03-05 | 国网福建省电力有限公司电力科学研究院 | Aerial line unmanned aerial vehicle inspection picture sorting and naming method based on smart phone APP |
| CN112506221A (en) * | 2020-12-04 | 2021-03-16 | 国网湖北省电力有限公司检修公司 | Unmanned aerial vehicle route planning processing method based on laser point cloud |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109145759B (en) | Vehicle attribute identification method, device, server and storage medium | |
| CN110660222B (en) | Intelligent environment-friendly electronic snapshot system for black-smoke road vehicle | |
| CN111914813A (en) | Power transmission line inspection image naming method and system based on image classification | |
| CN110348505B (en) | Vehicle color classification model training method and device and vehicle color identification method | |
| CN113516105B (en) | Lane detection method and device and computer readable storage medium | |
| CN113239764B (en) | Unmanned aerial vehicle inspection image preprocessing method for power transmission line | |
| CN113515655A (en) | Fault identification method and device based on image classification | |
| CN116052222A (en) | Cattle face recognition method for naturally collecting cattle face image | |
| CN116385958A (en) | Edge intelligent detection method for power grid inspection and monitoring | |
| CN111476314B (en) | Fuzzy video detection method integrating optical flow algorithm and deep learning | |
| CN111127520A (en) | Vehicle tracking method and system based on video analysis | |
| Xu et al. | Convolutional neural network based traffic sign recognition system | |
| CN115825984A (en) | Power transmission line inspection system and inspection method based on laser point cloud | |
| CN116846059A (en) | Edge detection system for power grid inspection and monitoring | |
| CN115423850A (en) | Anti-interference high-altitude parabolic capturing method capable of automatically filtering shaking target area | |
| CN112687023B (en) | Method for inspecting road facilities based on geo-fences | |
| CN113887272A (en) | Violent behavior intelligent safety detection system based on edge calculation | |
| CN113807309A (en) | Orchard machine walking route planning method based on deep learning | |
| CN117423157A (en) | Mine abnormal video action understanding method combining migration learning and regional invasion | |
| CN113705708A (en) | Intelligent classification and naming method for unmanned aerial vehicle inspection pictures of power transmission line | |
| CN113628251B (en) | Smart hotel terminal monitoring method | |
| CN115527270A (en) | Method for identifying specific behaviors in intensive crowd environment | |
| CN114299012A (en) | Object surface defect detection method and system based on convolutional neural network | |
| CN111353509B (en) | Key point extractor generation method of visual SLAM system | |
| CN113609317A (en) | Image library construction method and device and electronic equipment |
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 |