CN110672632A - Tunnel disease identification method - Google Patents
Tunnel disease identification method Download PDFInfo
- Publication number
- CN110672632A CN110672632A CN201910906269.9A CN201910906269A CN110672632A CN 110672632 A CN110672632 A CN 110672632A CN 201910906269 A CN201910906269 A CN 201910906269A CN 110672632 A CN110672632 A CN 110672632A
- Authority
- CN
- China
- Prior art keywords
- tunnel
- space grid
- grid map
- disease
- points
- 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
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/9515—Objects of complex shape, e.g. examined with use of a surface follower device
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/9515—Objects of complex shape, e.g. examined with use of a surface follower device
- G01N2021/9518—Objects of complex shape, e.g. examined with use of a surface follower device using a surface follower, e.g. robot
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30132—Masonry; Concrete
Landscapes
- Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Immunology (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Pathology (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Theoretical Computer Science (AREA)
- Signal Processing (AREA)
- Multimedia (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a tunnel defect identification method, which comprises the following steps: the method comprises the following steps that 3D data of the wall surface of a tunnel are collected by a 3D camera when a detection vehicle runs through the tunnel, the 3D data are subjected to network division, and a space grid graph is formed according to space point coordinates; scanning the tunnel in a nondestructive state by the detection vehicle in an initial state to obtain a space grid diagram in the initial state; scanning and detecting the tunnel by using a detection vehicle to obtain a detection space grid map; carrying out characteristic comparison analysis on the obtained detection space grid map and the initial state space grid map to obtain disease identification information; the disease identification information includes a disease location and a disease category. According to the invention, through omnibearing detection and three-dimensional network type point location detection on the interior of the tunnel, the state information of the inner wall of the tunnel can be efficiently and accurately acquired, the position, the type and the like of a disease appearing on the surface of the tunnel can be accurately identified, so that maintenance personnel can quickly repair the tunnel, and the safe operation of the tunnel is ensured.
Description
Technical Field
The invention belongs to the technical field of tunnel maintenance, and particularly relates to a tunnel defect identification method.
Background
In the tunnel construction and operation process, due to the influences of geological conditions, climatic conditions and various factors in the operation process, the defects of water leakage, crack damage, tunnel freeze injury, corrosion and the like are easy to occur on the surface of the tunnel. The appearance of disease not only can reduce the intensity of concrete, causes the damage to the tunnel surface, influences structural safety, still can reduce tunnel service life, causes huge potential safety hazard to rail transit's operation, and these diseases have influenced the security in tunnel, threaten the normal operation in tunnel to a certain extent more.
Traditionally, for tunnel structure disease inspection, data are collected by means of manual inspection, manual recording, picture shooting and the like, and then indoor analysis is carried out to give an evaluation result. In the existing tunnel disease detection process, the positioning calculation of the diseases is linear calculation, so that a conclusion cannot be quickly obtained in the calculation process, and the efficiency of the positioning calculation of the diseases is influenced.
Disclosure of Invention
In order to solve the problems, the invention provides a tunnel disease identification method, which can efficiently and accurately acquire the state information of the inner wall of a tunnel by performing omnibearing detection and three-dimensional network type point location detection on the inside of the tunnel, can accurately identify the position, the type and the like of the disease appearing on the surface of the tunnel, enables maintenance personnel to quickly repair the tunnel, and ensures the safe operation of the tunnel.
In order to achieve the purpose, the invention adopts the technical scheme that: a tunnel defect identification method is characterized in that a detection vehicle runs through a tunnel to acquire tunnel wall data so as to analyze the data and identify tunnel defects, and a 3D camera is arranged on the detection vehicle; the tunnel disease identification method comprises the following steps:
data acquisition: the method comprises the following steps that 3D data of the wall surface of a tunnel are collected by a 3D camera when a detection vehicle runs through the tunnel, the 3D data are subjected to network division, and a space grid graph is formed according to space point coordinates;
initial data acquisition: scanning the tunnel in a nondestructive state by the detection vehicle in an initial state to obtain a space grid diagram in the initial state;
acquiring tunnel data, namely scanning and detecting the tunnel by using a detection vehicle to acquire a detection space grid map;
and (3) real-time disease identification: carrying out characteristic comparison analysis on the obtained detection space grid map and the initial state space grid map to obtain disease identification information; the disease identification information includes a disease location and a disease category.
Further, the detection space grid map and the initial state space grid map both include positioning feature points and coordinate feature points, the positioning feature points are position identification points of the grid map including boundary points or center points, and the coordinate feature points are coordinates of each space point distributed on the grid map. The grid map can be quickly and accurately positioned by positioning the characteristic points, the coordinate characteristic points can accurately acquire the characteristic information and the coordinate position of each point in the grid map, and the detection speed is provided while the detection precision is ensured.
Further, in order to efficiently and accurately acquire the position and the characteristics of the disease, the method for performing characteristic comparison analysis on the detection space grid map and the initial state space grid map comprises the following steps:
nesting and overlapping the detection space grid map and the initial state space grid map according to the positioning characteristic points of the detection space grid map and the initial state space grid map to realize the positioning of the detection space grid map;
after positioning, each grid point in the detection space grid graph and the initial state space grid graph corresponds to each other;
comparing each corresponding coordinate feature point in the detection space grid map and the initial state space grid map, and extracting the grid point positions with differences;
performing area division according to the positions of the different grid points to form an area block diagram;
after image recognition is carried out on the shape of the area block diagram, disease categories are obtained;
and acquiring the position of the disease according to the coordinate information of the area block diagram.
Further, comparing each corresponding coordinate feature point in the detection space grid map and the initial state space grid map, and extracting the positions of grid points with differences, comprising the following steps:
respectively extracting for n timesDetecting two coordinate feature points of the same grid position m in the spatial grid map An and the initial state space grid map A0: an (x)m,ym,zm) And a0 (x)0,y0,z0);
Calculating the deviation distance between two coordinate characteristic points according to the two coordinate characteristic points at the same grid position, namely
And if the deviation distance H is larger than or equal to H, and H is a deviation error threshold parameter, determining that the tunnel wall surface at the grid position m is damaged and is a grid point with difference.
Further, the dividing of the regions according to the grid point positions to form the region block diagram includes the steps of:
clustering and dividing all the obtained grid points with differences, and dividing grid points adjacent to grid positions into the same region, so that grid points which are not adjacent to grid positions in all the grid points with differences are divided into different sub-regions to form a plurality of abnormal regions;
and extracting a boundary of each abnormal area, and framing the abnormal area according to the boundary position to form an area block diagram.
Further, the image recognition is carried out on the shape of the block diagram of the area to obtain the disease category, and the method comprises the following steps:
inputting the regional block diagram into a well-established disease image identification model established by a deep learning neural network;
and outputting the disease type through the disease type in the identification area block diagram of the disease image identification model.
Furthermore, segmented positioning points are arranged in the tunnel in an equal-span mode, and the segmented positioning points are identified by a 3D camera as one of the positioning feature points when the detection vehicle runs through the tunnel; segmenting the network graph data through segmented positioning points, dividing the network graph into a multi-segment sub-network graph by the segmented positioning points, and performing feature comparison analysis on the detection space grid graph and the initial state space grid graph under the corresponding segmented positioning points. Through the segmentation processing, the network map in each segment is processed independently, the operation speed can be improved, the disease position can be found out more efficiently, and the method is particularly suitable for being used in a tunnel with a long length.
Further, after the diseases are identified and repaired, the tunnel is scanned again in the initial state by the detection vehicle to obtain a new initial state space grid map, and the new initial state space grid map replaces the old initial state space grid map for the comparative analysis of the subsequent detection space grid map. Along with the long-term use of the tunnel, the accuracy of tunnel disease identification is improved through continuous updating of the initial state space grid map, and the method is suitable for the characteristic of long-term use of the tunnel.
The beneficial effects of the technical scheme are as follows:
the method comprises the steps of detecting the interior of a tunnel in an omnibearing manner through a 3D camera, acquiring 3D data of the wall surface of the tunnel by a detection vehicle running through the tunnel, analyzing the data, identifying tunnel defects, and establishing space point coordinates through network division to form a space grid map; and comparing and analyzing the characteristics of the acquired detection space grid map and the initial state space grid map to acquire the disease identification information. The position and the characteristics of each point location can be accurately obtained by simulating the three-dimensional grid diagram of the tunnel inner wall, the state information of the tunnel inner wall can be efficiently and accurately obtained by identifying the change state of each point location and the change state of the point locations around the point location and by establishing a neural network model to identify the image characteristics of a pathological area, and the position, the type and the like of diseases on the surface of the tunnel can be accurately identified.
According to the method, the defects on the inner wall of the tunnel are quickly and accurately positioned and identified, so that maintenance personnel can quickly repair the defects, the manual labor force is greatly reduced, and the service life of the tunnel is prolonged; the safe operation of the tunnel is ensured, and the operation potential safety hazard of rail transit is effectively avoided.
Drawings
Fig. 1 is a schematic flow chart of a tunnel defect identification method of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is further described with reference to the accompanying drawings.
In this embodiment, referring to fig. 1, the invention provides a tunnel defect identification method, in which a detection vehicle runs through a tunnel to obtain tunnel wall data, so as to analyze the data and identify a tunnel defect, and the detection vehicle is provided with a 3D camera; the tunnel disease identification method comprises the following steps:
data acquisition: the method comprises the following steps that 3D data of the wall surface of a tunnel are collected by a 3D camera when a detection vehicle runs through the tunnel, the 3D data are subjected to network division, and a space grid graph is formed according to space point coordinates;
initial data acquisition: scanning the tunnel in a nondestructive state by the detection vehicle in an initial state to obtain a space grid diagram in the initial state;
acquiring tunnel data, namely scanning and detecting the tunnel by using a detection vehicle to acquire a detection space grid map;
and (3) real-time disease identification: carrying out characteristic comparison analysis on the obtained detection space grid map and the initial state space grid map to obtain disease identification information; the disease identification information includes a disease location and a disease category.
As an optimization scheme of the above embodiment, the detection space grid map and the initial state space grid map both include positioning feature points and coordinate feature points, the positioning feature points are position identification points of the grid map including boundary points or center points, and the coordinate feature points are coordinates of each space point distributed on the grid map. The grid map can be quickly and accurately positioned by positioning the characteristic points, the coordinate characteristic points can accurately acquire the characteristic information and the coordinate position of each point in the grid map, and the detection speed is provided while the detection precision is ensured.
In order to efficiently and accurately acquire the positions and the characteristics of the diseases, the method for performing characteristic comparison analysis on the detection space grid map and the initial state space grid map comprises the following steps:
nesting and overlapping the detection space grid map and the initial state space grid map according to the positioning characteristic points of the detection space grid map and the initial state space grid map to realize the positioning of the detection space grid map;
after positioning, each grid point in the detection space grid graph and the initial state space grid graph corresponds to each other;
comparing each corresponding coordinate feature point in the detection space grid map and the initial state space grid map, and extracting the grid point positions with differences;
performing area division according to the positions of the different grid points to form an area block diagram;
after image recognition is carried out on the shape of the area block diagram, disease categories are obtained;
and acquiring the position of the disease according to the coordinate information of the area block diagram.
The method comprises the following steps of comparing each corresponding coordinate feature point in a detection space grid map and an initial state space grid map, and extracting grid point positions with differences, wherein the method comprises the following steps:
respectively extracting two coordinate feature points of the same grid position m in the nth detection space grid map An and the initial state space grid map A0: an (x)m,ym,zm) And a0 (x)0,y0,z0);
Calculating the deviation distance between two coordinate characteristic points according to the two coordinate characteristic points at the same grid position, namely
And if the deviation distance H is larger than or equal to H, and H is a deviation error threshold parameter, determining that the tunnel wall surface at the grid position m is damaged and is a grid point with difference.
As an optimization scheme of the above embodiment, the dividing regions according to grid point positions to form a region block diagram includes:
clustering and dividing all the obtained grid points with differences, and dividing grid points adjacent to grid positions into the same region, so that grid points which are not adjacent to grid positions in all the grid points with differences are divided into different sub-regions to form a plurality of abnormal regions;
and extracting a boundary of each abnormal area, and framing the abnormal area according to the boundary position to form an area block diagram.
And carrying out image recognition on the shape of the block diagram of the area to obtain a disease category, wherein the method comprises the following steps:
inputting the regional block diagram into a well-established disease image identification model established by a deep learning neural network;
and outputting the disease type through the disease type in the identification area block diagram of the disease image identification model.
As an optimization scheme of the embodiment, segmented positioning points are arranged in the tunnel at equal span, and the segmented positioning points are identified by a 3D camera as one of the positioning feature points when the detection vehicle runs through the tunnel; segmenting the network graph data through segmented positioning points, dividing the network graph into a multi-segment sub-network graph by the segmented positioning points, and performing feature comparison analysis on the detection space grid graph and the initial state space grid graph under the corresponding segmented positioning points. Through the segmentation processing, the network map in each segment is processed independently, the operation speed can be improved, the disease position can be found out more efficiently, and the method is particularly suitable for being used in a tunnel with a long length.
As an optimization scheme of the embodiment, after the disease is identified and repaired, the tunnel is scanned again in the initial state by the detection vehicle to obtain a new initial state space grid map, and the new initial state space grid map replaces the old initial state space grid map for the comparative analysis of the subsequent detection space grid map. Along with the long-term use of the tunnel, the accuracy of tunnel disease identification is improved through continuous updating of the initial state space grid map, and the method is suitable for the characteristic of long-term use of the tunnel.
The foregoing shows and describes the general principles and broad features of the present invention and advantages thereof. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, which are described in the specification and illustrated only to illustrate the principle of the present invention, but that various changes and modifications may be made therein without departing from the spirit and scope of the present invention, which fall within the scope of the invention as claimed. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (8)
1. A tunnel defect identification method is characterized in that a detection vehicle runs through a tunnel to obtain tunnel wall data so as to analyze the data and identify tunnel defects, and a 3D camera is arranged on the detection vehicle; the tunnel disease identification method comprises the following steps:
data acquisition: the method comprises the following steps that 3D data of the wall surface of a tunnel are collected by a 3D camera when a detection vehicle runs through the tunnel, the 3D data are subjected to network division, and a space grid graph is formed according to space point coordinates;
initial data acquisition: scanning the tunnel in a nondestructive state by the detection vehicle in an initial state to obtain a space grid diagram in the initial state;
acquiring tunnel data, namely scanning and detecting the tunnel by using a detection vehicle to acquire a detection space grid map;
and (3) real-time disease identification: carrying out characteristic comparison analysis on the obtained detection space grid map and the initial state space grid map to obtain disease identification information; the disease identification information includes a disease location and a disease category.
2. The tunnel defect identification method according to claim 1, wherein the detection space grid map and the initial state space grid map both include positioning feature points and coordinate feature points, the positioning feature points are position identification points of the grid map including boundary points or center points, and the coordinate feature points are coordinates of each space point distributed on the grid map.
3. The tunnel disease identification method according to claim 2, wherein the process of performing feature comparison analysis on the detection space grid map and the initial state space grid map comprises the steps of:
nesting and overlapping the detection space grid map and the initial state space grid map according to the positioning characteristic points of the detection space grid map and the initial state space grid map to realize the positioning of the detection space grid map;
after positioning, each grid point in the detection space grid graph and the initial state space grid graph corresponds to each other;
comparing each corresponding coordinate feature point in the detection space grid map and the initial state space grid map, and extracting the grid point positions with differences;
performing area division according to the positions of the different grid points to form an area block diagram;
after image recognition is carried out on the shape of the area block diagram, disease categories are obtained;
and acquiring the position of the disease according to the coordinate information of the area block diagram.
4. The tunnel defect identification method according to claim 3, wherein each corresponding coordinate feature point in the detection space grid map and the initial state space grid map is compared, and the position of the grid point with the difference is extracted, comprising the steps of:
respectively extracting two coordinate feature points of the same grid position m in the nth detection space grid map An and the initial state space grid map A0: an (x)m,ym,zm) And a0 (x)0,y0,z0);
Calculating the deviation distance between two coordinate characteristic points according to the two coordinate characteristic points at the same grid position, namely
And if the deviation distance H is larger than or equal to H, and H is a deviation error threshold parameter, determining that the tunnel wall surface at the grid position m is damaged and is a grid point with difference.
5. The tunnel defect identification method according to claim 4, wherein the area division is performed according to the grid point positions to form an area block diagram, comprising the steps of:
clustering and dividing all the obtained grid points with differences, and dividing grid points adjacent to grid positions into the same region, so that grid points which are not adjacent to grid positions in all the grid points with differences are divided into different sub-regions to form a plurality of abnormal regions;
and extracting a boundary of each abnormal area, and framing the abnormal area according to the boundary position to form an area block diagram.
6. The tunnel defect identification method according to claim 5, wherein the image identification of the shape of the block diagram of the area to obtain the defect type comprises the steps of:
inputting the regional block diagram into a well-established disease image identification model established by a deep learning neural network;
and outputting the disease type through the disease type in the identification area block diagram of the disease image identification model.
7. The tunnel disease identification method according to any one of claims 2-6, wherein segmented positioning points are arranged in the tunnel at equal spans, and a 3D camera identifies the segmented positioning points as one of the positioning feature points when a detection vehicle runs through the tunnel; segmenting the network graph data through segmented positioning points, dividing the network graph into a multi-segment sub-network graph by the segmented positioning points, and performing feature comparison analysis on the detection space grid graph and the initial state space grid graph under the corresponding segmented positioning points.
8. The tunnel disease identification method according to claim 1, wherein after the disease is identified and repaired, the tunnel is scanned again in the initial state by the detection vehicle to obtain a new initial state space grid map, and the new initial state space grid map replaces the old initial state space grid map for the comparative analysis of the subsequent detection space grid map.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910906269.9A CN110672632A (en) | 2019-09-24 | 2019-09-24 | Tunnel disease identification method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201910906269.9A CN110672632A (en) | 2019-09-24 | 2019-09-24 | Tunnel disease identification method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN110672632A true CN110672632A (en) | 2020-01-10 |
Family
ID=69078627
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201910906269.9A Pending CN110672632A (en) | 2019-09-24 | 2019-09-24 | Tunnel disease identification method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110672632A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111551562A (en) * | 2020-01-20 | 2020-08-18 | 深圳大学 | Bridge pavement structure damage identification method and system |
CN113361869A (en) * | 2021-05-19 | 2021-09-07 | 上海天麦能源科技有限公司 | Artificial intelligence anomaly detection method and system for gas pipe network |
CN114821514A (en) * | 2022-06-30 | 2022-07-29 | 交通运输部公路科学研究所 | A remove detecting system for detecting tunnel road surface wet and slippery state |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004037419A (en) * | 2002-07-08 | 2004-02-05 | Nakata Sokuryo:Kk | Tunnel control chart and its system |
CN106841216A (en) * | 2017-02-28 | 2017-06-13 | 浙江工业大学 | Tunnel defect automatic identification equipment based on panoramic picture CNN |
CN109060821A (en) * | 2018-07-10 | 2018-12-21 | 深圳大学 | Tunnel defect detection method and tunnel defect detection device based on laser detection |
CN109087291A (en) * | 2018-07-26 | 2018-12-25 | 杭州国翌科技有限公司 | Tunnel location information library method for building up and tunnel defect localization method |
CN109242828A (en) * | 2018-08-13 | 2019-01-18 | 浙江大学 | 3D printing product 3 D defects detection method based on optical grating projection multistep phase shift method |
CN110220909A (en) * | 2019-04-28 | 2019-09-10 | 浙江大学 | A kind of Shield-bored tunnels Defect inspection method based on deep learning |
-
2019
- 2019-09-24 CN CN201910906269.9A patent/CN110672632A/en active Pending
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2004037419A (en) * | 2002-07-08 | 2004-02-05 | Nakata Sokuryo:Kk | Tunnel control chart and its system |
CN106841216A (en) * | 2017-02-28 | 2017-06-13 | 浙江工业大学 | Tunnel defect automatic identification equipment based on panoramic picture CNN |
CN109060821A (en) * | 2018-07-10 | 2018-12-21 | 深圳大学 | Tunnel defect detection method and tunnel defect detection device based on laser detection |
CN109087291A (en) * | 2018-07-26 | 2018-12-25 | 杭州国翌科技有限公司 | Tunnel location information library method for building up and tunnel defect localization method |
CN109242828A (en) * | 2018-08-13 | 2019-01-18 | 浙江大学 | 3D printing product 3 D defects detection method based on optical grating projection multistep phase shift method |
CN110220909A (en) * | 2019-04-28 | 2019-09-10 | 浙江大学 | A kind of Shield-bored tunnels Defect inspection method based on deep learning |
Non-Patent Citations (2)
Title |
---|
李明博等: "BIM技术在运营隧道病害检测结果三维可视化中的应用", 《中外公路》 * |
李聪波等: "基于改进ICP算法的损伤零部件精确配准方法", 《计算机集成制造系统》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111551562A (en) * | 2020-01-20 | 2020-08-18 | 深圳大学 | Bridge pavement structure damage identification method and system |
CN113361869A (en) * | 2021-05-19 | 2021-09-07 | 上海天麦能源科技有限公司 | Artificial intelligence anomaly detection method and system for gas pipe network |
CN113361869B (en) * | 2021-05-19 | 2023-11-24 | 上海天麦能源科技有限公司 | Artificial intelligence anomaly detection method and system for gas pipe network |
CN114821514A (en) * | 2022-06-30 | 2022-07-29 | 交通运输部公路科学研究所 | A remove detecting system for detecting tunnel road surface wet and slippery state |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN111322985B (en) | Tunnel clearance analysis method, device and system based on laser point cloud | |
CN108898085B (en) | Intelligent road disease detection method based on mobile phone video | |
CN108230344B (en) | Automatic identification method for tunnel water leakage diseases | |
CN111899288B (en) | Tunnel leakage water area detection and identification method based on infrared and visible light image fusion | |
CN110672632A (en) | Tunnel disease identification method | |
CN106290388A (en) | A kind of insulator breakdown automatic testing method | |
CN110009633B (en) | Steel rail surface defect detection method based on reverse Gaussian difference | |
CN110232682B (en) | Image-based track foreign matter detection method | |
CN111507971A (en) | Tunnel surface defect detection method | |
CN109870458B (en) | Pavement crack detection and classification method based on three-dimensional laser sensor and bounding box | |
CN104992429A (en) | Mountain crack detection method based on image local reinforcement | |
CN114581764B (en) | Underground structure crack disease discriminating method based on deep learning algorithm | |
CN112085699B (en) | Pavement crack extraction method based on two-dimensional image | |
CN111524154B (en) | Image-based tunnel segment automatic segmentation method | |
CN113436157A (en) | Vehicle-mounted image identification method for pantograph fault | |
Dang et al. | Deep learning-based masonry crack segmentation and real-life crack length measurement | |
CN110567680A (en) | Track fastener looseness detection method based on angle comparison | |
Wu et al. | Concrete spalling detection for metro tunnel from point cloud based on roughness descriptor | |
CN111724358A (en) | Concrete quality detection method and system based on image and convolutional neural network | |
CN112508911A (en) | Rail joint touch net suspension support component crack detection system based on inspection robot and detection method thereof | |
CN117314921B (en) | RFID-based starting point detection and treatment method for track inspection equipment | |
CN111723793B (en) | Real-time rigid contact net positioning point identification method | |
CN113781436B (en) | High-voltage switch state monitoring method based on camera and angle measurement | |
CN116183622A (en) | Subway seepage water detection method based on point cloud information | |
CN108805843B (en) | Tunnel concrete lining seam removing method based on translation and extension of straight line segment |
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: 20200110 |
|
RJ01 | Rejection of invention patent application after publication |