CN113688758A - Gas transmission pipeline high consequence district intelligent recognition system based on edge calculation - Google Patents
Gas transmission pipeline high consequence district intelligent recognition system based on edge calculation Download PDFInfo
- Publication number
- CN113688758A CN113688758A CN202111008419.8A CN202111008419A CN113688758A CN 113688758 A CN113688758 A CN 113688758A CN 202111008419 A CN202111008419 A CN 202111008419A CN 113688758 A CN113688758 A CN 113688758A
- Authority
- CN
- China
- Prior art keywords
- aerial vehicle
- unmanned aerial
- information
- gas transmission
- pipeline
- 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.)
- Granted
Links
Images
Classifications
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
Abstract
The invention provides an intelligent identification system for a high consequence area of a gas transmission pipeline based on edge calculation. Unmanned aerial vehicle follows appointed position along the pipeline with a take photo by plane at a certain height, reduces high multi-angle after discerning high back fruit district and shoots ground feature information. The intelligent system uses unmanned aerial vehicle equipment as a carrier and comprises three deep learning models of ground feature information identification, ground feature region classification and leakage disaster estimation. The unmanned aerial vehicle is firstly fused with a ground gas transmission pipeline sensor to obtain pipeline information, the shot ground feature information is identified by airborne Jetson NX and then estimated, and meanwhile, dynamic detection of the path to the periphery is judged through edge calculation by combining with airborne radar Kalman filtering. And displaying the result on the edge end server. And after the flight is finished and the flight falls down, the data is transmitted to a cloud server for training an intelligent system model and updating parameters. And after the weight is updated, the result is transmitted back to the unmanned aerial vehicle.
Description
Technical Field
The invention relates to the technical fields of image processing, deep learning, edge calculation and the like, in particular to an intelligent system of a gas transmission pipeline high-consequence area based on edge calculation.
Background
With the continuous development of economy, the urbanization level is continuously improved. Gas pipelines and the like play a very important role in providing energy, and if leakage occurs, the public safety is seriously harmed or great environmental damage is caused. The urbanization and natural resources around the gas transmission pipeline will also change. How to intelligently identify high consequence areas of a gas pipeline is a problem which needs to be solved urgently at present. The method aims at the problem that the monitoring is mainly completed by manual monitoring at present, but the pipeline has the problems of complex environment, long line and the like, and cannot be completed in real time, efficiently and at low cost.
To solve the above problem, edge calculation is performed as needed. The edge computing belongs to distributed computing, and collected data are processed nearby on an intelligent gateway at the edge side of a network without uploading a large amount of data to a remote core management platform.
Compared with cloud computing, edge computing utilizes existing data and computing capacity on a cloud server, response time of a recognition result is greatly shortened, and when the recognition result is returned, feature information of an image is sent to the cloud server to serve as a new training set.
Disclosure of Invention
The embodiment of the application provides an intelligent identification system for a high consequence area of a gas transmission pipeline based on edge calculation. The system mainly comprises unmanned aerial vehicle equipment, a gas transmission pipeline sensor, a high-consequence area intelligent system and a cloud server. The method aims to identify the high consequence area of the gas transmission pipeline, and realize surface feature information identification, surface feature area classification, leakage disaster estimation and the like of the high consequence area.
In order to achieve the purpose, the application adopts the following technical scheme:
s1: the unmanned aerial vehicle cruises and takes aerial photos from an appointed position along the pipeline at a certain height, and reduces the height after identifying a high back fruit area to take ground feature information and acquire image information at multiple angles; fusing with a ground gas pipeline sensor to obtain pipeline information;
s11: the method comprises the steps of improving the edge computing capability of the unmanned aerial vehicle, detecting in real time that certain parallel computing capability is needed, and integrating edge computing hardware Jetson Xavier NX on the unmanned aerial vehicle;
s12: improve gas transmission pipeline sensor, make it can send pipeline information, geographic information etc. to unmanned aerial vehicle. And analyzing the abnormal information of the pipeline by combining the images.
S2: the cloud server builds a neural network system and trains a weight according to the collected image;
s21: building ground feature information recognition based on a semantic segmentation network model, manually marking out building species information, road information, railway information, bridge information and the like, preprocessing an image data set, enhancing the image and training out an initial generation weight through a network;
s22: the method comprises the steps of realizing land feature region classification based on a VGG image classification network, manually classifying different remote sensing image data sets based on population gathering density information, factory park distribution density information, forest and lake landforms and other distribution density information, preprocessing the image data sets, enhancing the images and then training initial generation weights through the network;
s23: and obtaining a leakage disaster estimation model by combining the obtained information with the underground pipeline information accumulation weight.
S3: the airborne Jetson Xavier NX identifies and judges ground feature information shot in real time, and meanwhile, the dynamic peripheral automatic detection of the path is judged through edge calculation by combining with the airborne radar Kalman filtering;
s31: the unmanned aerial vehicle carries a binocular camera, a GPS (global positioning system) and a laser radar module, the unmanned aerial vehicle cruises and takes aerial photos along the specified position of the pipeline through GPS positioning, the Jetson Xavier NX module reduces the height to shoot a target object after identifying a high back fruit area, so that the ground feature information is shot at more accurate multiple angles, the precision is improved, the obtained observation data is optimally estimated by combining algorithms such as Kalman filtering, sensor fusion and ground feature information identification, and an algorithm for automatically addressing and acquiring image information around the gas transmission pipeline by the unmanned aerial vehicle is realized;
s4: the unmanned aerial vehicle transfers the detection result back to the cloud server in real time for a person to judge, and transmits newly acquired image data to the cloud server after the flight is finished and the flight falls for training an intelligent system model and updating parameters; after the weight is updated, the result is transmitted back to the unmanned aerial vehicle;
s41: the unmanned aerial vehicle transfers the detection result back to the cloud server in real time for judgment by personnel, and the personnel can operate the unmanned aerial vehicle in real time to identify the region of interest;
s42: the cloud server performs transfer learning on the newly acquired image data in combination with the previous weight and updates the new weight, and the result is transmitted back to the unmanned aerial vehicle after the weight is updated.
Drawings
FIG. 1 is a system flow diagram;
FIG. 2 is a system effect diagram;
FIG. 3 is an identification flow diagram;
Detailed Description
The embodiment of the application provides an intelligent system for a high consequence area based on edge calculation. The method has the advantages that the intelligent identification of the passing-region pairs after the gas transmission pipeline is high is realized in real time and efficiently at low cost. The system mainly comprises unmanned aerial vehicle equipment, a gas transmission pipeline sensor, a high-consequence area intelligent system and a cloud server.
And S1, the unmanned plane can take off from the maintenance point A of the gas transmission pipeline, land, charge and deliver the identification data to the maintenance point B after about 30 minutes of cruise identification, and continue to fly to the next point C after the charging is finished in the same way.
S2 unmanned aerial vehicle will shoot the top view on 1000 meters of pipeline at first, according to the semantic segmentation algorithm preliminary judge building kind and coordinate, road grade and coordinate, railway kind and coordinate, nature resource kind and coordinate etc.. And then the unmanned aerial vehicle automatically addresses the target objects and buildings with the reliability lower than the threshold value along the road to shoot the target objects and buildings at multiple angles. Further strengthen the discernment to object judgement and building floor. This process can be monitored by human assistance to prevent the drone from falling over an obstacle and injuring the person.
S3 defines the region grade to be four region grades according to the classification of the number of residents along the pipeline and the density of buildings according to GB 32167-2015 oil and gas transmission pipeline integrity management standard. The high-consequence distinction is divided into three types, and the potential influence radius of the gas transmission pipeline is determined by the following formula:
s4 is realized through semantic segmentation based on MASKRCNN according to the recognition of the feature information and the classification of the feature region, the pipeline position and the information are artificially marked in the map, and the influence range can be calculated through a formula. And judging whether the distance between the ground object target and the pipeline is satisfied or not. The information categories are:
road surface feature categories (such as expressways, provinces, national roads, railways and the like) are identified, and the flat-storey buildings are classified into first-level high back fruit areas.
The method comprises the steps of identifying natural resource ground object types (such as natural protection areas of wetlands, forests and the like), building height above one floor and below six floors, classifying the buildings, transportation hubs and flammable and explosive places into second-level high back fruit areas.
And identifying the natural resource land feature types (such as rivers, reservoirs, water sources and the like), and classifying the buildings higher than six floors into the fruit areas with the third-level height. The system automatically marks the land feature area and the high consequence area.
S5, estimating the leakage disaster according to the leakage disaster, wherein the estimation can be realized by image classification, and a large amount of environment aerial photographs near the normal gas transmission pipeline are collected firstly. Then, environmental aerial photographs with different degrees caused by gas pipeline leakage are collected. Thereby estimating the environment near the gas pipeline if leakage occurs.
Claims (5)
1. The utility model provides a gas transmission pipeline high consequence district intelligent recognition system based on edge calculation which characterized in that comprises unmanned aerial vehicle equipment, gas transmission pipeline sensor, high consequence district intelligent system, high in the clouds server, and the system includes following step:
s1: the unmanned aerial vehicle cruises and takes aerial photos from an appointed position along the pipeline at a certain height, reduces the height after identifying a high back fruit area and takes ground feature information at multiple angles to acquire image information, and fuses with the ground gas pipeline sensor to acquire pipeline information;
s2: the cloud server builds a neural network system and trains a weight according to the collected image;
s3: the airborne Jetson Xavier NX identifies and judges ground feature information shot in real time, and meanwhile, the dynamic peripheral automatic detection of the path is judged through edge calculation by combining with the airborne radar Kalman filtering;
s4: the unmanned aerial vehicle transfers the detection result back to the cloud server in real time for personnel to judge, transmits newly acquired image data to the cloud server after the flight is finished and falls for training of an intelligent system model and updating of parameters, and returns the result to the unmanned aerial vehicle after the weight updating is finished.
2. The intelligent identification system for the high consequence area of the gas transmission pipeline based on the edge calculation as claimed in claim 1, wherein: in the unmanned aerial vehicle in step S1, by improving the edge calculation capability of the unmanned aerial vehicle, the information of the duct sensor is improved so that the duct sensor can communicate with the unmanned aerial vehicle, and the specific steps are as follows:
s11: the method comprises the steps of improving the edge computing capability of the unmanned aerial vehicle, detecting in real time that certain parallel computing capability is needed, and integrating edge computing hardware Jetson Xavier NX on the unmanned aerial vehicle;
s12: the gas transmission pipeline sensor is improved, so that the gas transmission pipeline sensor can send pipeline information, geographic information and the like to the unmanned aerial vehicle, and the pipeline abnormal information is analyzed by combining images.
3. The intelligent identification system for the high consequence area of the gas transmission pipeline based on the edge calculation as claimed in claim 1, wherein: the neural network system described in step S2 identifies different ground object targets from the images captured by the unmanned aerial vehicle in step S21, classifies different ground object regions from the images captured by the unmanned aerial vehicle in step S22, and finally obtains a leakage disaster estimation model in step S23, which includes the following steps:
s21: building ground feature information recognition based on a semantic segmentation network model, manually marking out building species information, road information, railway information, bridge information and the like, preprocessing an image data set, enhancing the image and training out an initial generation weight through a network;
s22: the method comprises the steps of realizing land feature region classification based on a VGG image classification network, manually classifying different remote sensing image data sets based on population gathering density information, factory park distribution density information, forest and lake landforms and other distribution density information, preprocessing the image data sets, enhancing the images and then training initial generation weights through the network;
s23: and obtaining a leakage disaster estimation model by combining the obtained information with the underground pipeline information accumulation weight.
4. The intelligent identification system for the high consequence area of the gas transmission pipeline based on the edge calculation as claimed in claim 1, wherein: s3, the unmanned aerial vehicle carries more sensors to communicate with the ground sensors, and the specific steps are as follows:
unmanned aerial vehicle carries on binocular camera, GPS and laser radar module, unmanned aerial vehicle passes through GPS location and cruises along the pipeline assigned position and takes photo by plane, thereby it highly shoots the target object to reduce behind the high back fruit district behind the identification of Jetson Xavier NX module and shoots ground object information and improve the precision to more accurate multi-angle, combine Kalman filtering, sensor fusion, algorithm such as ground object information identification carry out optimal estimation to the observation data who acquires, realize unmanned aerial vehicle automatic addressing and gather gas transmission pipeline image information algorithm on every side.
5. The intelligent identification system for the high consequence area of the gas transmission pipeline based on the edge calculation as claimed in claim 1, wherein: the unmanned aerial vehicle in the step S4 enables personnel to operate in real time through the step S41, and obtains a more accurate result through the step S42 of migratory learning, and the specific steps are as follows:
s41: the unmanned aerial vehicle transfers the detection result back to the cloud server in real time for judgment by personnel, and the personnel can operate the unmanned aerial vehicle in real time to identify the region of interest;
s42: the cloud server performs transfer learning on the newly acquired image data in combination with the previous weight and updates the new weight, and the result is transmitted back to the unmanned aerial vehicle after the weight is updated.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111008419.8A CN113688758B (en) | 2021-08-31 | 2021-08-31 | Intelligent recognition system for high-consequence region of gas transmission pipeline based on edge calculation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111008419.8A CN113688758B (en) | 2021-08-31 | 2021-08-31 | Intelligent recognition system for high-consequence region of gas transmission pipeline based on edge calculation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113688758A true CN113688758A (en) | 2021-11-23 |
| CN113688758B CN113688758B (en) | 2023-05-30 |
Family
ID=78584155
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111008419.8A Active CN113688758B (en) | 2021-08-31 | 2021-08-31 | Intelligent recognition system for high-consequence region of gas transmission pipeline based on edge calculation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113688758B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112765389A (en) * | 2021-02-04 | 2021-05-07 | 中国石油天然气集团有限公司 | Method and system for identifying high consequence area of oil and gas transmission pipeline and storage medium |
| CN116434060A (en) * | 2023-03-13 | 2023-07-14 | 创辉达设计股份有限公司 | Automatic extraction method and system for collecting house information by unmanned aerial vehicle |
| CN116958907A (en) * | 2023-09-18 | 2023-10-27 | 四川泓宝润业工程技术有限公司 | Method and system for inspecting surrounding hidden danger targets of gas pipeline |
Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140280277A1 (en) * | 2013-03-15 | 2014-09-18 | Global Precision Solutions, Llp. | System and method for integration and correlation of gis data |
| CN108960049A (en) * | 2018-05-25 | 2018-12-07 | 中国石油天然气股份有限公司 | Recognition methods, device and the storage medium in the high consequence area of long-distance oil & gas pipeline |
| CN110070243A (en) * | 2018-01-23 | 2019-07-30 | 中国石油化工股份有限公司 | The high consequence area identification and evaluation system and method for oil pipeline |
| CN110782673A (en) * | 2019-10-26 | 2020-02-11 | 江苏看见云软件科技有限公司 | Vehicle violation identification and detection system based on unmanned aerial vehicle shooting cloud computing |
| US20200193609A1 (en) * | 2018-12-18 | 2020-06-18 | Qualcomm Incorporated | Motion-assisted image segmentation and object detection |
| WO2020124247A1 (en) * | 2018-12-21 | 2020-06-25 | Canscan Softwares And Technologies Inc. | Automated inspection system and associated method for assessing the condition of shipping containers |
| CN111536429A (en) * | 2020-07-08 | 2020-08-14 | 浙江浙能天然气运行有限公司 | Decision fusion-based oil and gas pipeline early warning system and method |
| CN111766214A (en) * | 2020-07-03 | 2020-10-13 | 昆明物理研究所 | Unmanned aerial vehicle-mounted spectral imaging data processing method and system based on edge calculation |
| CN111784737A (en) * | 2020-06-10 | 2020-10-16 | 中国人民解放军军事科学院国防科技创新研究院 | Automatic target tracking method and system based on unmanned aerial vehicle platform |
| CN112326686A (en) * | 2020-11-02 | 2021-02-05 | 坝道工程医院(平舆) | Unmanned aerial vehicle intelligent cruise pavement disease detection method, unmanned aerial vehicle and detection system |
| US20210064869A1 (en) * | 2019-08-28 | 2021-03-04 | Sheetal Reddy Arrabotu | Method and system for identification of landing sites for aerial vehicles |
| CN112529012A (en) * | 2020-12-11 | 2021-03-19 | 平安科技（深圳）有限公司 | Oil-gas pipeline inspection method, device, equipment and medium based on target matching |
| CN112765389A (en) * | 2021-02-04 | 2021-05-07 | 中国石油天然气集团有限公司 | Method and system for identifying high consequence area of oil and gas transmission pipeline and storage medium |
| CN113305858A (en) * | 2021-06-07 | 2021-08-27 | 仲恺农业工程学院 | Visual robot method and device for removing shellfish in raw water pipeline |
| CN113965241A (en) * | 2020-07-01 | 2022-01-21 | 深圳中科保泰科技有限公司 | Method and related device for endowing artificial intelligence to unmanned aerial vehicle patrolling, mining and patrolling |
-
2021
- 2021-08-31 CN CN202111008419.8A patent/CN113688758B/en active Active
Patent Citations (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140280277A1 (en) * | 2013-03-15 | 2014-09-18 | Global Precision Solutions, Llp. | System and method for integration and correlation of gis data |
| CN110070243A (en) * | 2018-01-23 | 2019-07-30 | 中国石油化工股份有限公司 | The high consequence area identification and evaluation system and method for oil pipeline |
| CN108960049A (en) * | 2018-05-25 | 2018-12-07 | 中国石油天然气股份有限公司 | Recognition methods, device and the storage medium in the high consequence area of long-distance oil & gas pipeline |
| US20200193609A1 (en) * | 2018-12-18 | 2020-06-18 | Qualcomm Incorporated | Motion-assisted image segmentation and object detection |
| WO2020124247A1 (en) * | 2018-12-21 | 2020-06-25 | Canscan Softwares And Technologies Inc. | Automated inspection system and associated method for assessing the condition of shipping containers |
| US20210064869A1 (en) * | 2019-08-28 | 2021-03-04 | Sheetal Reddy Arrabotu | Method and system for identification of landing sites for aerial vehicles |
| CN110782673A (en) * | 2019-10-26 | 2020-02-11 | 江苏看见云软件科技有限公司 | Vehicle violation identification and detection system based on unmanned aerial vehicle shooting cloud computing |
| CN111784737A (en) * | 2020-06-10 | 2020-10-16 | 中国人民解放军军事科学院国防科技创新研究院 | Automatic target tracking method and system based on unmanned aerial vehicle platform |
| CN113965241A (en) * | 2020-07-01 | 2022-01-21 | 深圳中科保泰科技有限公司 | Method and related device for endowing artificial intelligence to unmanned aerial vehicle patrolling, mining and patrolling |
| CN111766214A (en) * | 2020-07-03 | 2020-10-13 | 昆明物理研究所 | Unmanned aerial vehicle-mounted spectral imaging data processing method and system based on edge calculation |
| CN111536429A (en) * | 2020-07-08 | 2020-08-14 | 浙江浙能天然气运行有限公司 | Decision fusion-based oil and gas pipeline early warning system and method |
| CN112326686A (en) * | 2020-11-02 | 2021-02-05 | 坝道工程医院(平舆) | Unmanned aerial vehicle intelligent cruise pavement disease detection method, unmanned aerial vehicle and detection system |
| CN112529012A (en) * | 2020-12-11 | 2021-03-19 | 平安科技（深圳）有限公司 | Oil-gas pipeline inspection method, device, equipment and medium based on target matching |
| CN112765389A (en) * | 2021-02-04 | 2021-05-07 | 中国石油天然气集团有限公司 | Method and system for identifying high consequence area of oil and gas transmission pipeline and storage medium |
| CN113305858A (en) * | 2021-06-07 | 2021-08-27 | 仲恺农业工程学院 | Visual robot method and device for removing shellfish in raw water pipeline |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112765389A (en) * | 2021-02-04 | 2021-05-07 | 中国石油天然气集团有限公司 | Method and system for identifying high consequence area of oil and gas transmission pipeline and storage medium |
| CN116434060A (en) * | 2023-03-13 | 2023-07-14 | 创辉达设计股份有限公司 | Automatic extraction method and system for collecting house information by unmanned aerial vehicle |
| CN116434060B (en) * | 2023-03-13 | 2023-09-15 | 创辉达设计股份有限公司 | Automatic extraction method and system for collecting house information by unmanned aerial vehicle |
| CN116958907A (en) * | 2023-09-18 | 2023-10-27 | 四川泓宝润业工程技术有限公司 | Method and system for inspecting surrounding hidden danger targets of gas pipeline |
| CN116958907B (en) * | 2023-09-18 | 2023-12-26 | 四川泓宝润业工程技术有限公司 | Method and system for inspecting surrounding hidden danger targets of gas pipeline |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113688758B (en) | 2023-05-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111259809B (en) | Unmanned aerial vehicle coastline floating garbage inspection system based on DANet | |
| Varney et al. | DALES: A large-scale aerial LiDAR data set for semantic segmentation | |
| CN113688758B (en) | Intelligent recognition system for high-consequence region of gas transmission pipeline based on edge calculation | |
| CN106441233B (en) | Power channel corridor method for inspecting based on oblique photograph three-dimensional reconstruction | |
| KR101933216B1 (en) | River topography information generation method using drone and geospatial information | |
| CN109117749A (en) | A kind of abnormal object monitoring and managing method and system based on unmanned plane inspection image | |
| CN103176185B (en) | Method and system for detecting road barrier | |
| CN107392247B (en) | Real-time detection method for ground object safety distance below power line | |
| CN106525057A (en) | Generation system for high-precision road map | |
| CN110673628B (en) | Inspection method for oil-gas pipeline of composite wing unmanned aerial vehicle | |
| CN111458721B (en) | Exposed garbage identification and positioning method, device and system | |
| Chen et al. | Valid: A comprehensive virtual aerial image dataset | |
| US11657464B1 (en) | System for determining type of property inspection based on captured images | |
| CN111339826A (en) | Landslide unmanned aerial vehicle linear sensor network frame detection system | |
| CN108896021B (en) | Method for extracting artificial forest stand structure parameters based on aerial photogrammetry point cloud | |
| CN113239864A (en) | Route planning method of unmanned aerial vehicle suitable for agricultural investigation | |
| CN116486289A (en) | Gas pipeline high-consequence area identification method driven by multi-source data and knowledge | |
| CN110009054B (en) | Hierarchical airborne LiDAR point cloud classification method utilizing geometric and intensity features | |
| CN116958907A (en) | Method and system for inspecting surrounding hidden danger targets of gas pipeline | |
| CN112861737A (en) | Forest fire smoke detection method based on image dark channel and YoLov3 | |
| Kandoi et al. | Pothole detection using accelerometer and computer vision with automated complaint redressal | |
| JP2024514175A (en) | Bird detection and species determination | |
| CN112097743A (en) | Building earthquake-resistant characteristic analysis method based on unmanned aerial vehicle technology | |
| US20210200237A1 (en) | Feature coverage analysis | |
| Wang et al. | Bayberry tree recognition dataset based on the aerial photos and deep learning model |
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 |