CN112944105A - Intelligent pipeline defect detection method and system - Google Patents
Intelligent pipeline defect detection method and system Download PDFInfo
- Publication number
- CN112944105A CN112944105A CN202110116396.6A CN202110116396A CN112944105A CN 112944105 A CN112944105 A CN 112944105A CN 202110116396 A CN202110116396 A CN 202110116396A CN 112944105 A CN112944105 A CN 112944105A
- Authority
- CN
- China
- Prior art keywords
- pipeline
- intelligent
- defect detection
- pipe wall
- processor
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 54
- 230000007547 defect Effects 0.000 title claims abstract description 39
- 238000000034 method Methods 0.000 claims abstract description 17
- 230000007246 mechanism Effects 0.000 claims abstract description 13
- 238000004590 computer program Methods 0.000 claims description 6
- 238000003062 neural network model Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 abstract description 4
- 238000007689 inspection Methods 0.000 description 3
- 238000003384 imaging method Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000007781 pre-processing Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F16—ENGINEERING ELEMENTS AND UNITS; GENERAL MEASURES FOR PRODUCING AND MAINTAINING EFFECTIVE FUNCTIONING OF MACHINES OR INSTALLATIONS; THERMAL INSULATION IN GENERAL
- F16L—PIPES; JOINTS OR FITTINGS FOR PIPES; SUPPORTS FOR PIPES, CABLES OR PROTECTIVE TUBING; MEANS FOR THERMAL INSULATION IN GENERAL
- F16L55/00—Devices or appurtenances for use in, or in connection with, pipes or pipe systems
- F16L55/26—Pigs or moles, i.e. devices movable in a pipe or conduit with or without self-contained propulsion means
- F16L55/28—Constructional aspects
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F16—ENGINEERING ELEMENTS AND UNITS; GENERAL MEASURES FOR PRODUCING AND MAINTAINING EFFECTIVE FUNCTIONING OF MACHINES OR INSTALLATIONS; THERMAL INSULATION IN GENERAL
- F16L—PIPES; JOINTS OR FITTINGS FOR PIPES; SUPPORTS FOR PIPES, CABLES OR PROTECTIVE TUBING; MEANS FOR THERMAL INSULATION IN GENERAL
- F16L55/00—Devices or appurtenances for use in, or in connection with, pipes or pipe systems
- F16L55/26—Pigs or moles, i.e. devices movable in a pipe or conduit with or without self-contained propulsion means
- F16L55/28—Constructional aspects
- F16L55/40—Constructional aspects of the body
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T17/00—Three dimensional [3D] modelling, e.g. data description of 3D objects
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F16—ENGINEERING ELEMENTS AND UNITS; GENERAL MEASURES FOR PRODUCING AND MAINTAINING EFFECTIVE FUNCTIONING OF MACHINES OR INSTALLATIONS; THERMAL INSULATION IN GENERAL
- F16L—PIPES; JOINTS OR FITTINGS FOR PIPES; SUPPORTS FOR PIPES, CABLES OR PROTECTIVE TUBING; MEANS FOR THERMAL INSULATION IN GENERAL
- F16L2101/00—Uses or applications of pigs or moles
- F16L2101/30—Inspecting, measuring or testing
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Computing Systems (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Artificial Intelligence (AREA)
- Mechanical Engineering (AREA)
- Evolutionary Computation (AREA)
- Data Mining & Analysis (AREA)
- Geometry (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Computer Graphics (AREA)
- Multimedia (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses an intelligent pipeline defect detection method and system, wherein the intelligent pipeline defect detection method comprises the following steps: when the pipeline detection device moves in the pipeline, the camera shooting mechanism periodically shoots the pipe wall to obtain the pipe wall pictures of the pipeline; establishing a three-dimensional model of the pipeline according to the acquired pipe wall picture, and generating a sectional view of the pipeline according to the three-dimensional model; and importing the profile into an identification model, and identifying the profile through the identification model to obtain the defect information of the pipeline. The invention provides an intelligent pipeline defect detection method and system, which do not need operators to look at continuously in the pipeline detection process.
Description
Technical Field
The invention relates to the field of pipeline defect detection. More particularly, the invention relates to an intelligent pipeline defect detection method and system.
Background
In the existing drainage pipeline and box culvert detection, according to relevant regulation regulations, in the process that a detection robot advances in a pipeline, video information is observed by field workers in real time, when the field workers find the pipeline defect, the detection robot can be stopped and look around the pipeline defect part at the same time, and the video and image information of the pipeline defect part are obtained. At present, the pipeline detection mainly depends on manual judgment, the whole-course observation is carried out through manual work, the detection efficiency is low, and the condition of missed detection is easy to occur.
Disclosure of Invention
The invention aims to provide an intelligent pipeline defect detection method and system, which do not need operators to look at continuously in the pipeline detection process.
To achieve these objects and other advantages in accordance with the purpose of the invention, there is provided an intelligent pipeline defect detecting method, comprising the steps of:
when the pipeline detection device moves in the pipeline, the camera shooting mechanism periodically shoots the pipe wall to obtain the pipe wall pictures of the pipeline;
establishing a three-dimensional model of the pipeline according to the acquired pipe wall picture, and generating a sectional view of the pipeline according to the three-dimensional model;
and importing the profile into an identification model, and identifying the profile through the identification model to obtain the defect information of the pipeline.
Preferably, in the above intelligent method for detecting a defect in a pipeline, a sum of angles of view of cameras of an imaging mechanism of the pipeline detection apparatus is greater than 360 °.
Preferably, in the intelligent pipeline defect detection method, a three-dimensional model of the pipeline is established based on an SFM algorithm according to the acquired pipe wall picture.
Preferably, in the intelligent pipeline defect detection method, a three-dimensional model of the pipeline is established by adopting an MVSNet method according to the acquired picture of the pipe wall.
Preferably, in the method for detecting the defect of the intelligent pipeline, the recognition model is a trained neural network model.
Preferably, in the intelligent method for detecting the pipeline defect, the recognition model is a trained SVM classifier.
The invention also provides an intelligent pipeline defect detection system, which adopts any one of the intelligent pipeline defect detection methods, and comprises a pipeline detection device and a processor, wherein the pipeline detection device is provided with a camera mechanism, and the pipeline detection device is electrically connected with the processor.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the program to realize the steps of the intelligent pipeline defect detection method.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the intelligent pipeline defect detection method of any one of the above.
The invention has the beneficial effects that: in the pipeline detection process, an operator is not required to stare at the pipeline continuously, the pipeline detection device is only required to be controlled to move forwards, the pipeline detection device can automatically shoot an image of the inner wall of the pipeline and generate a 3D pipeline model in an image splicing mode, the pipeline defect position is not required to stop the detection equipment and look around, the detection efficiency is improved, and the missing detection risk is avoided.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention.
Detailed Description
The present invention is further described in detail below with reference to examples so that those skilled in the art can practice the invention with reference to the description.
The embodiment of the invention provides an intelligent pipeline defect detection method, which comprises the following steps:
when the pipeline detection device moves in the pipeline, the camera shooting mechanism periodically shoots the pipe wall to obtain the pipe wall pictures of the pipeline;
establishing a three-dimensional model of the pipeline according to the acquired pipe wall picture, and generating a sectional view of the pipeline according to the three-dimensional model;
and importing the profile into an identification model, and identifying the profile through the identification model to obtain the defect information of the pipeline.
In this embodiment, the pipeline inspection device uses an existing pipeline inspection robot, and a camera mechanism is provided thereon, and the camera mechanism generally comprises a plurality of cameras. In the pipeline detection, multiple cameras are used for periodically shooting the pipeline wall, the shot pipeline wall images are spliced to construct a 3D pipeline model, a sectional view of the inner wall of the pipeline is obtained according to the 3D model, the sectional view is identified, and defect information in the pipeline is obtained.
Preferably, as another embodiment of the present invention, a sum of angles of view of cameras of the imaging mechanism of the pipeline inspection device is greater than 360 °.
In the embodiment, the camera mechanism comprises a plurality of cameras, the sum of the field angles of all the cameras needs to be larger than 360 degrees, a panoramic image of the pipe wall can be obtained, and the accuracy of the established 3D model of the pipeline is ensured.
Preferably, as another embodiment of the present invention, a three-dimensional model of the pipeline is established based on an SFM algorithm according to the acquired picture of the pipe wall.
In this embodiment, sfm (structure from motion) is a three-dimensional reconstruction method, which is used to realize 3D reconstruction from motion. I.e. 3D information is derived from time-series 2D images. The input of SfM is a motion or a time series of 2D maps, and then the parameters of the camera can be deduced through matching between the 2D maps. In the application, a plurality of pipeline inner wall images are shot and then matched to obtain a 3D model of the pipeline, and then a pipeline internal section diagram is generated according to the 3D model of the pipeline.
Preferably, as another embodiment of the present invention, a three-dimensional model of the pipeline is established by using an MVSNet method according to the acquired picture of the pipe wall.
In this embodiment, MVSNet is a supervised learning method, which takes a reference image and a plurality of original images as input to obtain an end-to-end depth learning framework of a reference image depth map. The network firstly extracts the depth features of the image, then constructs a 3D cost body through differentiable projection transformation, outputs a 3D probability body through regularization, and then obtains a depth expectation along the depth direction through a soft argMin layer to obtain a depth map of a reference image.
Preferably, as another embodiment of the present invention, the recognition model is a trained neural network model or a trained SVM classifier.
In this embodiment, the recognition model is a machine learning model, which may be a trained neural network model for recognizing and classifying images, or a trained SVM classifier may be used, and for different types of machine learning models, only corresponding preprocessing needs to be performed on received images, and the input data pattern of the model is satisfied. The recognition model can be realized by adopting the prior art, and the description is not repeated here.
The invention also provides an intelligent pipeline defect detection system, which adopts any one of the intelligent pipeline defect detection methods, and comprises a pipeline detection device and a processor, wherein the pipeline detection device is provided with a camera mechanism, and the pipeline detection device is electrically connected with the processor.
The invention also provides an electronic device, which comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein the processor executes the program to realize the steps of the intelligent pipeline defect detection method.
The present invention also provides a non-transitory computer readable storage medium having stored thereon a computer program which, when executed by a processor, implements the steps of the intelligent pipeline defect detection method of any one of the above.
While embodiments of the invention have been described above, it is not limited to the applications set forth in the description and the embodiments, which are fully applicable to various fields of endeavor for which the invention may be embodied with additional modifications as would be readily apparent to those skilled in the art, and the invention is therefore not limited to the details given herein and to the embodiments shown and described without departing from the generic concept as defined by the claims and their equivalents.
Claims (9)
1. An intelligent pipeline defect detection method is characterized by comprising the following steps:
when the pipeline detection device moves in the pipeline, the camera shooting mechanism periodically shoots the pipe wall to obtain the pipe wall pictures of the pipeline;
establishing a three-dimensional model of the pipeline according to the acquired pipe wall picture, and generating a sectional view of the pipeline according to the three-dimensional model;
and importing the profile into an identification model, and identifying the profile through the identification model to obtain the defect information of the pipeline.
2. The intelligent pipeline defect detecting method as claimed in claim 1, wherein the sum of the field angles of the cameras of the camera mechanism of the pipeline detecting device is greater than 360 °.
3. The intelligent pipeline defect detection method of claim 1, wherein a three-dimensional model of the pipeline is established based on an SFM algorithm according to the acquired picture of the pipe wall.
4. The intelligent pipeline defect detection method of claim 1, wherein a three-dimensional model of the pipeline is established by an MVSNet method according to the acquired picture of the pipe wall.
5. The intelligent pipeline defect detection method of any one of claims 1-4, wherein the recognition model is a trained neural network model.
6. An intelligent pipeline defect detection method as claimed in any one of claims 1-4, wherein said recognition model is a trained SVM classifier.
7. An intelligent pipeline defect detection system adopting the method as claimed in any one of claims 1 to 7, characterized by comprising a pipeline detection device and a processor, wherein the pipeline detection device is provided with a camera mechanism, and the pipeline detection device is electrically connected with the processor.
8. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the steps of the method according to any of claims 1 to 6 are implemented when the processor executes the program.
9. A non-transitory computer-readable storage medium, on which a computer program is stored, which, when being executed by a processor, carries out the steps of the method according to any one of claims 1 to 6.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110116396.6A CN112944105A (en) | 2021-01-28 | 2021-01-28 | Intelligent pipeline defect detection method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110116396.6A CN112944105A (en) | 2021-01-28 | 2021-01-28 | Intelligent pipeline defect detection method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112944105A true CN112944105A (en) | 2021-06-11 |
Family
ID=76238522
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110116396.6A Pending CN112944105A (en) | 2021-01-28 | 2021-01-28 | Intelligent pipeline defect detection method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112944105A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113345082A (en) * | 2021-06-24 | 2021-09-03 | 云南大学 | Characteristic pyramid multi-view three-dimensional reconstruction method and system |
| CN116866723A (en) * | 2023-09-04 | 2023-10-10 | 广东力创信息技术有限公司 | Pipeline safety real-time monitoring and early warning system |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2500615A1 (en) * | 2011-03-18 | 2012-09-19 | SPERING micro-systems | Method for determining a tube diameter |
| CN109027514A (en) * | 2018-08-17 | 2018-12-18 | 江苏火禾信息技术有限公司 | A kind of underground piping detection device and method |
| CN110634140A (en) * | 2019-09-30 | 2019-12-31 | 南京工业大学 | Large-diameter tubular object positioning and inner wall defect detection method based on machine vision |
| CN210601076U (en) * | 2019-08-19 | 2020-05-22 | 福州市勘测院 | Quick detection device of pipeline structure situation |
| CN111412342A (en) * | 2019-01-08 | 2020-07-14 | 深圳市重器科技有限公司 | Pipeline detection robot and pipeline detection method |
| CN112255238A (en) * | 2020-10-14 | 2021-01-22 | 浙江浙能技术研究院有限公司 | Automatic identification and intelligent evaluation method for corrosion and pit defects of outer surface of oil-gas pipeline based on three-dimensional laser scanning |
-
2021
- 2021-01-28 CN CN202110116396.6A patent/CN112944105A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP2500615A1 (en) * | 2011-03-18 | 2012-09-19 | SPERING micro-systems | Method for determining a tube diameter |
| CN109027514A (en) * | 2018-08-17 | 2018-12-18 | 江苏火禾信息技术有限公司 | A kind of underground piping detection device and method |
| CN111412342A (en) * | 2019-01-08 | 2020-07-14 | 深圳市重器科技有限公司 | Pipeline detection robot and pipeline detection method |
| CN210601076U (en) * | 2019-08-19 | 2020-05-22 | 福州市勘测院 | Quick detection device of pipeline structure situation |
| CN110634140A (en) * | 2019-09-30 | 2019-12-31 | 南京工业大学 | Large-diameter tubular object positioning and inner wall defect detection method based on machine vision |
| CN112255238A (en) * | 2020-10-14 | 2021-01-22 | 浙江浙能技术研究院有限公司 | Automatic identification and intelligent evaluation method for corrosion and pit defects of outer surface of oil-gas pipeline based on three-dimensional laser scanning |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113345082A (en) * | 2021-06-24 | 2021-09-03 | 云南大学 | Characteristic pyramid multi-view three-dimensional reconstruction method and system |
| CN116866723A (en) * | 2023-09-04 | 2023-10-10 | 广东力创信息技术有限公司 | Pipeline safety real-time monitoring and early warning system |
| CN116866723B (en) * | 2023-09-04 | 2023-12-26 | 广东力创信息技术有限公司 | Pipeline safety real-time monitoring and early warning system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11270148B2 (en) | Visual SLAM method and apparatus based on point and line features | |
| Vidanapathirana et al. | LoGG3D-Net: Locally guided global descriptor learning for 3D place recognition | |
| Huletski et al. | Evaluation of the modern visual SLAM methods | |
| CN112944105A (en) | Intelligent pipeline defect detection method and system | |
| CN111209832B (en) | Auxiliary obstacle avoidance training method, equipment and medium for substation inspection robot | |
| Zhang et al. | Building a partial 3D line-based map using a monocular SLAM | |
| CN109444146A (en) | A kind of defect inspection method, device and the equipment of industrial processes product | |
| EP4116462A3 (en) | Method and apparatus of processing image, electronic device, storage medium and program product | |
| Wang et al. | Closed-loop tracking-by-detection for ROV-based multiple fish tracking | |
| EP3740907A1 (en) | Localising a vehicle | |
| GB2612029A (en) | Lifted semantic graph embedding for omnidirectional place recognition | |
| CN111179330A (en) | Binocular vision scene depth estimation method based on convolutional neural network | |
| Zhao et al. | Palletizing robot positioning bolt detection based on improved YOLO-V3 | |
| Gulde et al. | RoPose: CNN-based 2D pose estimation of industrial robots | |
| Sadrfaridpour et al. | Detecting and counting oysters | |
| KR101715781B1 (en) | Object recognition system and method the same | |
| CN117036417A (en) | Multi-scale transducer target tracking method based on space-time template updating | |
| Zhang et al. | Sof-slam: Segments-on-floor-based monocular slam | |
| CN114419102B (en) | Multi-target tracking detection method based on frame difference time sequence motion information | |
| US11551379B2 (en) | Learning template representation libraries | |
| US20240104774A1 (en) | Multi-dimensional Object Pose Estimation and Refinement | |
| Suzui et al. | Toward 6 dof object pose estimation with minimum dataset | |
| Li et al. | Workpiece intelligent identification and positioning system based on binocular machine vision | |
| Grigorescu et al. | Controlling Depth Estimation for Robust Robotic Perception | |
| Lee et al. | Bobby2: Buffer based robust high-speed object tracking |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20210611 |