CN110865654A - Power grid unmanned aerial vehicle inspection defect processing method - Google Patents
Power grid unmanned aerial vehicle inspection defect processing method Download PDFInfo
- Publication number
- CN110865654A CN110865654A CN201911241462.1A CN201911241462A CN110865654A CN 110865654 A CN110865654 A CN 110865654A CN 201911241462 A CN201911241462 A CN 201911241462A CN 110865654 A CN110865654 A CN 110865654A
- Authority
- CN
- China
- Prior art keywords
- information
- image
- defect
- labeling
- images
- 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
- 230000007547 defect Effects 0.000 title claims abstract description 96
- 238000007689 inspection Methods 0.000 title claims abstract description 27
- 238000003672 processing method Methods 0.000 title claims abstract description 14
- 238000000034 method Methods 0.000 claims abstract description 36
- 238000002372 labelling Methods 0.000 claims abstract description 31
- 230000008569 process Effects 0.000 claims abstract description 24
- 239000003086 colorant Substances 0.000 claims abstract description 7
- 238000012545 processing Methods 0.000 claims abstract description 6
- 238000000586 desensitisation Methods 0.000 claims description 6
- 230000005540 biological transmission Effects 0.000 claims description 5
- 238000012550 audit Methods 0.000 claims description 3
- 239000003550 marker Substances 0.000 claims description 3
- 238000012552 review Methods 0.000 abstract description 11
- 238000012795 verification Methods 0.000 description 4
- 230000002776 aggregation Effects 0.000 description 3
- 238000004220 aggregation Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000005286 illumination Methods 0.000 description 2
- 239000012212 insulator Substances 0.000 description 2
- RZVHIXYEVGDQDX-UHFFFAOYSA-N 9,10-anthraquinone Chemical compound C1=CC=C2C(=O)C3=CC=CC=C3C(=O)C2=C1 RZVHIXYEVGDQDX-UHFFFAOYSA-N 0.000 description 1
- 206010035148 Plague Diseases 0.000 description 1
- 241000607479 Yersinia pestis Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000010365 information processing Effects 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000011179 visual inspection Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/10—Simultaneous control of position or course in three dimensions
- G05D1/101—Simultaneous control of position or course in three dimensions specially adapted for aircraft
Landscapes
- Engineering & Computer Science (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Automation & Control Theory (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a power grid unmanned aerial vehicle inspection defect processing method, which is used for improving the accuracy and efficiency of power grid unmanned aerial vehicle inspection defect processing, and the method comprises the steps of recording information such as GPS coordinates, elevations, a holder, a camera, sizes, photographing positions, photographers, photographing time and the like in the process of acquiring images by an unmanned aerial vehicle in an inspection manner, collecting the information after uploading the information to a network, collecting the images and the image information of the same tower into a class, collecting the images and the image information of the same part of different towers into a class, labeling the defects by a labeling person after removing sensitive information, wherein the labeling person does not need to confirm the photographing position of the images and the part positioned on the towers again, and only needs to label the defects; the boxes are uniformly used during marking, the defect grades are represented by different box colors, and the defects with marking rate exceeding 40% are transferred to a review staff for review, so that the review efficiency is improved; and a defect standard library is established for the defects, so that the defects are favorably sorted and analyzed.
Description
Technical Field
The invention belongs to the technical field of power grid unmanned aerial vehicle inspection, and particularly relates to a power grid unmanned aerial vehicle inspection defect processing method.
Background
For a long time, the inspection work of the power transmission line network with huge power grid in China mainly depends on a manual inspection mode, the timeliness, the safety and the accuracy of inspection results are difficult problems which plague the power grid operation and maintenance department for a long time in the inspection era, in recent years, an unmanned aerial vehicle is rapidly popularized and applied in the power grid industry as a high-tech inspection sharp device, a flight control hand flies along a line by operating the unmanned aerial vehicle and synchronously takes pictures or scans by laser, hidden danger defects in the line can be rapidly and accurately discovered, and along with the continuous improvement of the number of unmanned aerial vehicles, the number of flying hands and the skill level in the power grid industry in China, the coming inspection machine of the power grid can be considered to be comprehensive in the inspection era.
In the prior art, a large number of aerial images are judged by visual inspection, the mode is greatly influenced by subjective and objective factors, and the brightness and the resolution of the acquired images cannot be guaranteed because the illumination intensity and the angle of the unmanned aerial vehicle images change along with the change of illumination conditions; in addition, due to the influence of noise and motion blur in the image acquisition process, the image is seriously degraded and degraded, so that an auditor needs to extract, identify and detect a target image in an unmanned aerial vehicle image of the power equipment in a complex scene, the auditor firstly extracts the image, confirms the shooting position of the image and the position of a tower, because the image is seriously degraded and degraded, a large amount of time is consumed in the process and errors are easy to occur, then the auditor identifies and marks the defects, the marking process is not standard, and misunderstanding can be caused when the image with serious defects is reviewed by an expert, so that the process is low in accuracy and lower in efficiency.
Disclosure of Invention
The invention aims to provide a power grid unmanned aerial vehicle inspection defect processing method which is used for improving the accuracy and efficiency of power grid unmanned aerial vehicle inspection defect processing.
The technical scheme for solving the technical problems of the invention is as follows: a power grid unmanned aerial vehicle inspection defect processing method comprises
Step 1: the unmanned aerial vehicle patrols and shoots images of the power transmission line;
step 2: uploading the image shot in the step 1 to a network;
and step 3: collecting the images, collecting the images and the image information of the same tower into a class, and collecting the images and the image information of the same part of different towers into a class;
and 4, step 4: desensitizing the collected images to obtain an image with sensitive information removed;
and 5: distributing the image without the sensitive information to a labeling person for labeling, labeling each image by a plurality of persons, and submitting the labeled image to a server;
step 6: the server processes the images, and transfers the images with the marking rate exceeding 40% to a reviewer;
and 7: the image is audited by the reviewer;
and 8: submitting an auditing result;
and step 9: and establishing a defect standard library to store the checking result.
The information for image aggregation in step 3 includes: GPS coordinates, elevation information, holder information, camera information, dimension information, photographing position information, photographing person information and photographing time information.
And 3, renaming the images when the images are collected in the step 3, wherein the naming mode is that the positions of the towers and the towers are named.
In the desensitization process of the image in the step 4, a pyexiv2 module is used for reading image attribute information, and the removed sensitive information packet comprises a GPS coordinate, elevation information, holder information, camera information and a photo name, and the information is formatted and then stored in a MySQL data layer to generate a desensitization log.
The distribution in the step 5 is divided into automatic distribution and manual distribution, a marking person uses a marking tool manufactured based on opencv to frame the defect in a rectangular frame after finding the defect, simultaneously records the defect id, the left vertex coordinate, the right bottom point coordinate and the rectangular length and width information of the frame and stores the information in a MySQL database, simultaneously associates the marking information with the image, uniformly uses the square frame during marking, uses different square frame colors to represent the defect grade, selects the defect type after marking, inputs or selects preset remark information to describe the defect, adopts a mode of writing EXIF information and renaming the image or adding a photo watermark, can enlarge and reduce the image during marking, can find the position of the marking frame during enlarging and reducing, renames the image in a mode of adding a suffix, marks one image by multiple persons, and can adjust the number of the marked image, recording the personal identity information of the label and the time information of the label.
And 6, the server processes the image, namely restoring the erased sensitive information, and meanwhile adding information of a marker and defect description information, wherein the marking rate of more than 40% is passed, and the image with the marking rate of more than 40% is transferred to a reviewer.
And 7, the process of auditing the image by the reviewer in the step 7 comprises the steps of auditing the defect by the reviewer according to the defect type and the defect position, judging the marked content by effective marking, ineffective marking and error marking, recording the judgment result, submitting the auditing result after all audits are finished, and modifying the marked content in the auditing process.
The defect standard library established in step 9 includes a line name, a tower position, shooting time, and file names, exif information, labeling information, and labeling person identity information after the image is labeled.
The invention has the beneficial effects that: the method comprises the steps that information such as GPS coordinates, elevation information, holder information, camera information, dimension information, photographing position information, photographing person information and photographing time information is recorded in the process of image acquisition in routing inspection of an unmanned aerial vehicle, the information is collected after being uploaded to a network, images and image information of the same pole tower are collected into a class, images and image information of the same part of different pole towers are collected into a class, sensitive information is removed, and then a marking person marks defects, does not need to confirm the photographing positions of the images and the parts located on the pole towers again, and only needs to mark the defects; the method has the advantages that the boxes are uniformly used during marking, the defect grades are represented by different box colors, the defect types are input after marking, and defects with marking rate exceeding 40% are transferred to a review staff for review, so that review efficiency is improved; and a defect standard library is established for the defects, so that the defects are favorably sorted and analyzed.
Drawings
FIG. 1 is a flow chart of the present invention.
FIG. 2 is a flow chart of image aggregation in accordance with the present invention.
FIG. 3 is a flow chart of the sensitive information processing of the present invention.
Fig. 4 is a flow chart of picture distribution and labeling according to the present invention.
FIG. 5 is a flow chart of the server analysis of the present invention.
FIG. 6 is a flow chart of the manual review of the present invention.
FIG. 7 is a flow chart of the invention for creating a defect criteria library.
Detailed Description
The technical solution in 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. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
As shown in the figure I, the invention comprises
Step 1: the unmanned aerial vehicle patrols and shoots images of the power transmission line;
step 2: uploading the image shot in the step 1 to a network;
and step 3: collecting the images, collecting the images and the image information of the same tower into a class, and collecting the images and the image information of the same part of different towers into a class;
and 4, step 4: desensitizing the collected images to obtain an image with sensitive information removed;
and 5: distributing the image without the sensitive information to a labeling person for labeling, labeling each image by a plurality of persons, and submitting the labeled image to a server;
step 6: the server processes the images, and transfers the images with the marking rate exceeding 40% to a reviewer;
and 7: the image is audited by the reviewer;
and 8: submitting an auditing result;
and step 9: and establishing a defect standard library to store the checking result.
The information for image aggregation in step 3 includes: GPS coordinates, elevation information, holder information, camera information, dimension information, photographing position information, photographing person information and photographing time information.
And 3, renaming the images when the images are collected in the step 3, wherein the naming mode is that the positions of the towers and the towers are named.
In the desensitization process of the image in the step 4, a pyexiv2 module is used for reading image attribute information, and the removed sensitive information packet comprises a GPS coordinate, elevation information, holder information, camera information and a photo name, and the information is formatted and then stored in a MySQL data layer to generate a desensitization log.
The distribution in the step 5 is divided into automatic distribution and manual distribution, a marking person uses a marking tool manufactured based on opencv to frame the defect in a rectangular frame after finding the defect, simultaneously records the defect id, the left vertex coordinate, the right bottom point coordinate and the rectangular length and width information of the frame and stores the information in a MySQL database, simultaneously associates the marking information with the image, uniformly uses the square frame during marking, uses different square frame colors to represent the defect grade, selects the defect type after marking, inputs or selects preset remark information to describe the defect, adopts a mode of writing EXIF information and renaming the image or adding a photo watermark, can enlarge and reduce the image during marking, can find the position of the marking frame during enlarging and reducing, renames the image in a mode of adding a suffix, marks one image by multiple persons, and can adjust the number of the marked image, recording the personal identity information of the label and the time information of the label.
And 6, the server processes the image, namely restoring the erased sensitive information, and meanwhile adding information of a marker and defect description information, wherein the marking rate of more than 40% is passed, and the image with the marking rate of more than 40% is transferred to a reviewer.
And 7, the process of auditing the image by the reviewer in the step 7 comprises the steps of auditing the defect by the reviewer according to the defect type and the defect position, judging the marked content by effective marking, ineffective marking and error marking, recording the judgment result, submitting the auditing result after all audits are finished, and modifying the marked content in the auditing process.
The defect standard library established in step 9 includes a line name, a tower position, shooting time, and file names, exif information, labeling information, and labeling person identity information after the image is labeled.
Taking 500 KV Yangdong 1 line 35# and an upper-phase insulator large-size side image as an example, when images are collected, image data comprise a GPS coordinate and a WGS84 coordinate system of an unmanned aerial vehicle, elevation information, holder information, camera information, position marking, a shooting person and shooting time, the size of the images is 1-8M, the position marking is performed by two methods, the first method is marking according to a shooting sequence, namely shooting and marking are sequentially performed on different positions of a tower according to the sequence, and the second method is manually marking; the tower information requirements comprise a GPS coordinate and a WGS84 coordinate system of the tower, tower foundation information and tower detailed list information; uploading the images and information to a network or importing the images and the information through a data card, renaming the photos, wherein the format is that the position of a tower and a tower is arranged, the position is the large-size side of an upper insulator on a 500 KV Yangdong 1 line 35#, the tower is determined to be automatically generated through position comparison, the GPS coordinate and the WGS84 coordinate system of the unmanned aerial vehicle are compared with the GPS coordinate and the WGS84 coordinate system of the tower, the shot image is determined to be the image of the tower within a certain range, the naming of the position of the tower is generated through two methods of position marking, the method I is to mark according to a shooting sequence, namely, different positions of the tower are shot and marked in sequence, the marking is used as the position name, the method II is to mark manually, and the manually marked position name is used for naming.
When the image is desensitized, the sensitive information comprises GPS, elevation information, holder information, camera information and photo names (names after renaming), and the rules of the original photo data, the sensitive information and the original photo are backed up and the sensitive information is erased.
When distributing and marking images, distributing the images to designated personnel according to a preset user designated rule, one image needs to be sent to a plurality of designated personnel, marking is carried out by the plurality of designated personnel, marking is carried out manually, on the distributed pictures, marking is carried out by using a square frame, the square frame is used uniformly when marking, the defect grade is represented by using different square frame colors, according to the actual situation, an arrow and a circle are added for marking, the defect type is selected after marking, preset remark information is input or selected for defect description, the standard of the defect description is a power transmission equipment primary defect library, the defect description mode is carried out by writing EXIF information, renaming the pictures (adding defect suffixes) or adding picture watermarks, the marking personnel identity information is added according to the user designated rule, and effective identification time records are recorded, finally, a document is formed, and two methods are used for recording the effective identification time, namely the time spent for writing the EXIF information and the time spent for forming the document, and finally, the formed document is uploaded to a server, and the marking of the image can be carried out on an android platform.
Establishing a suspected defect library in the server for the uploaded document, wherein the establishment standard of the suspected defect library is that 40% or more of artificial marks are regarded as suspected defects, storing the suspected defects in a database, restoring sensitive information, capturing the name of the marked image, namely the suffix renamed after marking (adding a defect suffix), and storing the name into a corresponding document; and the manual efficiency is counted, including the processing quantity, the processing efficiency, the processing quality and the attention points.
And (3) carrying out manual review on a PC environment, carrying out suspected defect judgment on the documents in the suspected defect library by an expert, carrying out effective labeling, ineffective labeling and error labeling judgment on the labeled contents, recording the judgment result, submitting the verification result after all verification is finished, and modifying the labeled contents in the verification process.
And finally establishing a defect standard library according to the submitted verification result, inputting complete information and counting functions (counting functions with defects).
The method comprises the steps that information such as GPS coordinates, elevation information, holder information, camera information, dimension information, photographing position information, photographing person information and photographing time information is recorded in the process of image acquisition in routing inspection of an unmanned aerial vehicle, the information is collected after being uploaded to a network, images and image information of the same pole tower are collected into a class, images and image information of the same part of different pole towers are collected into a class, sensitive information is removed, and then a marking person marks defects, does not need to confirm the photographing positions of the images and the parts located on the pole towers again, and only needs to mark the defects; the method has the advantages that the boxes are uniformly used during marking, the defect grades are represented by different box colors, the defect types are input after marking, and defects with marking rate exceeding 40% are transferred to a review staff for review, so that review efficiency is improved; and a defect standard library is established for the defects, so that the defects are favorably sorted and analyzed.
Claims (8)
1. A power grid unmanned aerial vehicle inspection defect processing method is characterized by comprising the following steps,
step 1: the unmanned aerial vehicle patrols and shoots images of the power transmission line;
step 2: uploading the image shot in the step 1 to a network;
and step 3: collecting the images, collecting the images and the image information of the same tower into a class, and collecting the images and the image information of the same part of different towers into a class;
and 4, step 4: desensitizing the collected images to obtain an image with sensitive information removed;
and 5: distributing the image without the sensitive information to a labeling person for labeling, labeling each image by a plurality of persons, and submitting the labeled image to a server;
step 6: the server processes the images, and transfers the images with the marking rate exceeding 40% to a reviewer;
and 7: the image is audited by the reviewer;
and 8: submitting an auditing result;
and step 9: and establishing a defect standard library to store the checking result.
2. The power grid unmanned aerial vehicle inspection defect processing method according to claim 1, wherein the information for image collection in the step 3 comprises: GPS coordinates, elevation information, holder information, camera information, dimension information, photographing position information, photographing person information and photographing time information.
3. The power grid unmanned aerial vehicle inspection defect processing method according to claim 2, wherein the step 3 of collecting the images further comprises renaming the images, and the naming mode is that the positions of the towers and the towers are named.
4. The power grid unmanned aerial vehicle inspection defect processing method according to claim 3, wherein in the desensitization process of the image in the step 4, a pyexiv2 module is used for reading image attribute information, the removed sensitive information package comprises GPS coordinates, elevation information, pan-tilt information, camera information and photo names, the information is formatted and then stored in a MySQL data layer, and a desensitization log is generated.
5. The power grid unmanned aerial vehicle inspection defect processing method according to claim 4, wherein the distribution in the step 5 is divided into automatic distribution and manual distribution, after finding the defect, a labeling person uses a labeling tool manufactured based on opencv to frame the defect in a rectangular frame, records frame defect id, left vertex coordinates, right bottom point coordinates, rectangular length and width information and stores the frame defect id, the left vertex coordinates and the right bottom point coordinates in a MySQL database, associates labeling information and an image, uniformly uses a square frame during labeling, represents the defect level by using different square frame colors, selects the defect type after labeling, inputs or selects preset remark information for defect description, adopts a mode of writing EXIF information and renaming or adding a photo watermark to the photo during labeling, can amplify and reduce the image during the labeling process, and can find the position of the labeling frame during the amplifying and reducing process, renaming the image by adding a suffix, marking a picture by a plurality of people, adjusting the number of people marked on the picture, recording and marking the personal identity information of the person and marking the time information.
6. The power grid unmanned aerial vehicle inspection defect processing method according to claim 5, wherein the step 6 of processing the image by the server comprises restoring erased sensitive information and adding information of a marker, wherein the defect description information indicates that more than 40% of marking rate is passed, and the image with the marking rate exceeding 40% is transferred to a reviewer.
7. The power grid unmanned aerial vehicle inspection defect processing method according to claim 6, wherein the process of auditing the image by the reviewer in the step 7 includes the steps of auditing the defect by the reviewer according to the defect type and the defect position, judging the marked content by effective marking, ineffective marking and error marking, recording the judgment result, submitting the auditing result after all audits are completed, and modifying the marked content in the auditing process.
8. The power grid unmanned aerial vehicle inspection defect processing method according to claim 7, wherein the defect standard library established in the step 9 includes a line name, a tower position, shooting time, and a file name, exif information, labeling information, and labeling person identity information after labeling a picture.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911241462.1A CN110865654A (en) | 2019-12-06 | 2019-12-06 | Power grid unmanned aerial vehicle inspection defect processing method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911241462.1A CN110865654A (en) | 2019-12-06 | 2019-12-06 | Power grid unmanned aerial vehicle inspection defect processing method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110865654A true CN110865654A (en) | 2020-03-06 |
Family
ID=69658070
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911241462.1A Pending CN110865654A (en) | 2019-12-06 | 2019-12-06 | Power grid unmanned aerial vehicle inspection defect processing method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110865654A (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111797332A (en) * | 2020-07-31 | 2020-10-20 | 国网北京市电力公司 | Image display method, device and system |
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 |
CN113065462A (en) * | 2021-03-31 | 2021-07-02 | 广东电网有限责任公司 | Monitoring method, device, equipment and storage medium for power grid overhead line |
CN113867406A (en) * | 2021-11-10 | 2021-12-31 | 广东电网能源发展有限公司 | Unmanned aerial vehicle-based line inspection method and system, intelligent equipment and storage medium |
CN114047779A (en) * | 2021-10-22 | 2022-02-15 | 贵州电网有限责任公司 | Defect tracking method and system based on unmanned aerial vehicle inspection |
CN114219501A (en) * | 2022-02-22 | 2022-03-22 | 杭州衡泰技术股份有限公司 | Sample labeling resource allocation method, device and application |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104101332A (en) * | 2014-07-19 | 2014-10-15 | 国家电网公司 | Automatic matching method for inspection photos of transmission lines |
WO2015131462A1 (en) * | 2014-03-07 | 2015-09-11 | 国家电网公司 | Centralized monitoring system and monitoring method for unmanned aerial vehicle to patrol power transmission line |
US9592912B1 (en) * | 2016-03-08 | 2017-03-14 | Unmanned Innovation, Inc. | Ground control point assignment and determination system |
CN107239666A (en) * | 2017-06-09 | 2017-10-10 | 孟群 | A kind of method and system that medical imaging data are carried out with desensitization process |
CN107316353A (en) * | 2017-07-03 | 2017-11-03 | 国网冀北电力有限公司承德供电公司 | A kind of unmanned plane inspection approaches to IM, system and server |
CN107357313A (en) * | 2017-08-15 | 2017-11-17 | 成都优艾维智能科技有限责任公司 | A kind of transmission line malfunction maintenance system and method based on unmanned plane inspection image |
CN109472847A (en) * | 2018-10-16 | 2019-03-15 | 平安普惠企业管理有限公司 | A kind of image processing method, system and terminal device |
CN109872284A (en) * | 2019-01-18 | 2019-06-11 | 平安普惠企业管理有限公司 | Image information desensitization method, device, computer equipment and storage medium |
CN110378145A (en) * | 2019-06-10 | 2019-10-25 | 华为技术有限公司 | A kind of method and electronic equipment of sharing contents |
CN110414680A (en) * | 2019-07-23 | 2019-11-05 | 国家计算机网络与信息安全管理中心 | Knowledge system of processing based on crowdsourcing mark |
-
2019
- 2019-12-06 CN CN201911241462.1A patent/CN110865654A/en active Pending
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
WO2015131462A1 (en) * | 2014-03-07 | 2015-09-11 | 国家电网公司 | Centralized monitoring system and monitoring method for unmanned aerial vehicle to patrol power transmission line |
CN104101332A (en) * | 2014-07-19 | 2014-10-15 | 国家电网公司 | Automatic matching method for inspection photos of transmission lines |
US9592912B1 (en) * | 2016-03-08 | 2017-03-14 | Unmanned Innovation, Inc. | Ground control point assignment and determination system |
CN107239666A (en) * | 2017-06-09 | 2017-10-10 | 孟群 | A kind of method and system that medical imaging data are carried out with desensitization process |
CN107316353A (en) * | 2017-07-03 | 2017-11-03 | 国网冀北电力有限公司承德供电公司 | A kind of unmanned plane inspection approaches to IM, system and server |
CN107357313A (en) * | 2017-08-15 | 2017-11-17 | 成都优艾维智能科技有限责任公司 | A kind of transmission line malfunction maintenance system and method based on unmanned plane inspection image |
CN109472847A (en) * | 2018-10-16 | 2019-03-15 | 平安普惠企业管理有限公司 | A kind of image processing method, system and terminal device |
CN109872284A (en) * | 2019-01-18 | 2019-06-11 | 平安普惠企业管理有限公司 | Image information desensitization method, device, computer equipment and storage medium |
CN110378145A (en) * | 2019-06-10 | 2019-10-25 | 华为技术有限公司 | A kind of method and electronic equipment of sharing contents |
CN110414680A (en) * | 2019-07-23 | 2019-11-05 | 国家计算机网络与信息安全管理中心 | Knowledge system of processing based on crowdsourcing mark |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111797332A (en) * | 2020-07-31 | 2020-10-20 | 国网北京市电力公司 | Image display method, device and system |
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 |
CN112445765B (en) * | 2020-12-01 | 2022-06-07 | 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 |
CN113065462A (en) * | 2021-03-31 | 2021-07-02 | 广东电网有限责任公司 | Monitoring method, device, equipment and storage medium for power grid overhead line |
CN114047779A (en) * | 2021-10-22 | 2022-02-15 | 贵州电网有限责任公司 | Defect tracking method and system based on unmanned aerial vehicle inspection |
CN113867406A (en) * | 2021-11-10 | 2021-12-31 | 广东电网能源发展有限公司 | Unmanned aerial vehicle-based line inspection method and system, intelligent equipment and storage medium |
CN114219501A (en) * | 2022-02-22 | 2022-03-22 | 杭州衡泰技术股份有限公司 | Sample labeling resource allocation method, device and application |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110865654A (en) | Power grid unmanned aerial vehicle inspection defect processing method | |
CN111949809B (en) | Intelligent processing method for infrared inspection data of power transmission line | |
CN112633535A (en) | Photovoltaic power station intelligent inspection method and system based on unmanned aerial vehicle image | |
CN110455822A (en) | A kind of detection method of pcb board defect | |
CN105141889A (en) | Power transmission line intelligent patrol system based on image vision | |
CN108109437A (en) | It is a kind of that generation method is extracted from main shipping track based on the unmanned plane of map feature | |
CN111709361B (en) | Method for processing inspection data of unmanned aerial vehicle of power transmission line | |
WO2016169499A1 (en) | Random anti-counterfeiting marker-based anti-counterfeiting system, and anti-counterfeiting method therefor | |
CN111695486A (en) | High-precision direction signboard target extraction method based on point cloud | |
CN102637258A (en) | Method for creating online surface quality detection system defect library | |
CN112508343A (en) | Implementation method of visual construction management and control system for construction quality management | |
CN111178845A (en) | Data annotation system and method based on network service platform | |
CN111178282A (en) | Road traffic speed limit sign positioning and identifying method and device | |
CN114078218A (en) | Self-adaptive fusion forest smoke and fire identification data augmentation method | |
CN115689928A (en) | Method and system for removing duplicate of transmission tower inspection image under visible light | |
CN111723656A (en) | Smoke detection method and device based on YOLO v3 and self-optimization | |
CN110728269A (en) | High-speed rail contact net support pole number plate identification method | |
CN113378754A (en) | Construction site bare soil monitoring method | |
CN108921185A (en) | A kind of shelf sales promotion information recognition methods based on image recognition, device and system | |
CN113408630A (en) | Transformer substation indicator lamp state identification method | |
CN115841353B (en) | Advertisement putting photo acquisition and auditing method and device and terminal equipment | |
CN111680184A (en) | Orthographic file preprocessing system for aerial photo screening | |
CN108345895A (en) | Advertising image recognition methods and advertising image identifying system | |
CN106204343A (en) | A kind of construction quality control system and method based on mobile terminal | |
CN114863274A (en) | Surface green net thatch cover extraction method based on deep learning |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200306 |