CN111325747B - Disease detection method and device for rectangular tunnel - Google Patents

Disease detection method and device for rectangular tunnel Download PDF

Info

Publication number
CN111325747B
CN111325747B CN202010195598.XA CN202010195598A CN111325747B CN 111325747 B CN111325747 B CN 111325747B CN 202010195598 A CN202010195598 A CN 202010195598A CN 111325747 B CN111325747 B CN 111325747B
Authority
CN
China
Prior art keywords
point
point cloud
distance
rectangular tunnel
data
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.)
Active
Application number
CN202010195598.XA
Other languages
Chinese (zh)
Other versions
CN111325747A (en
Inventor
唐超
马海志
李梓豪
王思锴
王勇
王晓静
于淼
杨晓飞
朱霞
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Urban Construction Exploration and Surveying Design Research Institute Co Ltd
Original Assignee
Beijing Urban Construction Exploration and Surveying Design Research Institute Co Ltd
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Beijing Urban Construction Exploration and Surveying Design Research Institute Co Ltd filed Critical Beijing Urban Construction Exploration and Surveying Design Research Institute Co Ltd
Priority to CN202010195598.XA priority Critical patent/CN111325747B/en
Publication of CN111325747A publication Critical patent/CN111325747A/en
Application granted granted Critical
Publication of CN111325747B publication Critical patent/CN111325747B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/0002—Inspection of images, e.g. flaw detection
    • G06T7/0004—Industrial image inspection
    • G—PHYSICS
    • G01—MEASURING; TESTING
    • G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
    • G01B11/00—Measuring arrangements characterised by the use of optical techniques
    • G01B11/16—Measuring arrangements characterised by the use of optical techniques for measuring the deformation in a solid, e.g. optical strain gauge
    • 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
    • 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
    • G06T3/04—
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T3/00—Geometric image transformation in the plane of the image
    • G06T3/60—Rotation of a whole image or part thereof
    • 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
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/10—Image acquisition modality
    • G06T2207/10004—Still image; Photographic image
    • 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

Abstract

According to the defect detection method and device for the rectangular tunnel, the original data comprising the coordinate data of the point cloud collected on the inner surface of the rectangular tunnel and the intensity data of the point cloud are obtained, the point cloud is determined to be mapped to the position of the pixel in the gray level image by the coordinate data, the intensity data are converted into the gray level data of the pixel, the original data are converted into the gray level image, and the water seepage area of the rectangular tunnel is detected by carrying out image processing of a preset type on the gray level image. Compared with a manual detection mode, the method has higher efficiency and accuracy.

Description

Disease detection method and device for rectangular tunnel
Technical Field
The application relates to the field of electronic information, in particular to a disease detection method and device for a rectangular tunnel.
Background
The defect detection of the tunnel can comprise water leakage detection of the tunnel wall and deformation detection of the tunnel wall. Currently, a manual inspection mode is generally used for detecting the tunnel defect. Therefore, it is easy to miss and has low efficiency.
Therefore, how to improve the efficiency and accuracy of defect detection of rectangular tunnels becomes a current urgent problem to be solved.
Disclosure of Invention
The application provides a defect detection method and device for a rectangular tunnel, and aims to solve the problem of how to improve the defect detection efficiency and accuracy of the rectangular tunnel.
In order to achieve the above object, the present application provides the following technical solutions:
a defect detection method for a rectangular tunnel comprises the following steps:
obtaining raw data, the raw data comprising: coordinate data of point clouds and intensity data of the point clouds acquired on the inner surface of the rectangular tunnel;
converting the original data into a gray image, wherein the coordinate data determines the position of the point cloud mapped to a pixel in the gray image, and the intensity data is converted into gray data of the pixel;
and detecting the water seepage area of the rectangular tunnel by carrying out image processing of a preset type on the gray level image.
Optionally, the raw data further includes: mileage data of the point cloud, wherein the mileage data is used for indicating mileage of the point cloud;
the converting the original data into a gray scale image includes:
dividing the point cloud into left and right sides by taking a vertical line where the central point of the rectangular tunnel is located as a dividing line;
dividing the left side point cloud into an upper left point cloud, a left waist point cloud and a lower left point cloud according to coordinates of an upper left vertex and a lower left vertex of the rectangular tunnel;
dividing the right side point cloud into an upper right point cloud, a lower right waist point cloud and a lower right point cloud according to coordinates of an upper right vertex and a lower right vertex of the rectangular tunnel;
rotating the left lower point cloud and the left waist point cloud by 90 degrees clockwise around the left lower vertex and projecting the left lower point cloud and the left waist point cloud to a left inner wall plane of the rectangular tunnel, and rotating the point cloud projected into the left inner wall plane by 90 degrees clockwise around the left upper vertex;
rotating the right lower point cloud and the right waist point cloud by 90 degrees anticlockwise around the right lower vertex and projecting the right lower point cloud and the right waist point cloud to a right inner wall plane of the rectangular tunnel, and rotating the point cloud projected into the right inner wall plane by 90 degrees anticlockwise around the right upper vertex;
dividing the rotated point cloud into a left side and a right side along the central point, setting grids with preset scales along the left-right direction from the central point, and dividing the rotated point cloud into the grids;
and converting the point cloud intensity data of the point cloud in the grid into gray values.
Optionally, before said converting the point cloud intensity data of the point cloud within the grid into a gray value, the method further comprises:
for any one of the grids comprising a plurality of point cloud frames with the same mileage, only reserving the point cloud frame with one mileage within the range of the grid as the point cloud in the grid;
if there is no point cloud in any one of the grids, the point cloud in the previous frame of the point cloud frame which has a mileage greater than the range of the grid and is closest to the range of the grid is used as the point cloud in the grid
Optionally, the determining of the preset scale of the grid includes:
setting the length and width of the gray level image; the ratio of the length to the width is the same as a reference ratio, and the reference ratio is the ratio of the width of the rectangular tunnel to the perimeter of the section;
the method comprises the steps of determining the dimension of a grid in the length direction by using the length of the gray image and the number of grids preset in the length direction, and determining the dimension of the grid in the width direction by using the width of the gray image and the number of grids preset in the width direction.
Optionally, the preset type of image processing includes:
contrast enhancement, binarization, erosion, saturation adjustment and edge extraction.
Optionally, the method further comprises:
and detecting deformation of the rectangular tunnel by analyzing horizontal distance and vertical distance of the rectangular tunnel, wherein the horizontal distance and the vertical distance are obtained according to the coordinate data.
Optionally, the process of obtaining the horizontal distance includes:
acquiring position data of a target point in the point cloud; wherein the target point is a point in a point pair comprising: any position point of a preset height from the ground on any side wall of the rectangular tunnel and a relative point on the opposite side wall;
for any one of the target points, if the difference between the first distance and the second distance is within a preset difference range, taking twice of the second distance as the horizontal distance of the target point, otherwise, taking twice of the first distance as the horizontal distance of the target point, wherein the first distance is the horizontal distance from the target point to the central point, the second distance is the distance from a straight line to the central point, and the straight line is the straight line that the perpendicularity formed by the target point and the adjacent target point meets a preset perpendicularity threshold value;
the vertical distance acquisition process comprises the following steps:
calculating a third distance, wherein the third distance is the distance from a target top point to the center of the track, and the target top point is any top point;
and if the levelness of the straight line formed by the target top point and the adjacent top point meets a preset levelness threshold, taking twice of a fourth distance as the vertical distance, otherwise taking twice of the third distance as the vertical distance, wherein the fourth distance is the distance from the straight line to the center of the track.
A defect detection device for a rectangular tunnel, comprising:
the acquisition module is used for acquiring original data, wherein the original data comprises: coordinate data of point clouds and intensity data of the point clouds acquired on the inner surface of the rectangular tunnel;
the conversion module is used for converting the original data into a gray image, wherein the coordinate data determine the position of the point cloud mapped into pixels in the gray image, and the intensity data are converted into gray data of the pixels;
and the detection module is used for detecting the water seepage area of the rectangular tunnel by carrying out image processing of a preset type on the gray level image.
A defect detection device for a rectangular tunnel, comprising:
a memory and a processor;
the memory is used for storing a program, and the processor is used for running the program so as to realize the disease detection method for the rectangular tunnel.
A computer readable storage medium having stored thereon a computer program which, when run on a computer, implements the above-described disease detection method for rectangular tunnels.
According to the defect detection method and device for the rectangular tunnel, the original data comprising the coordinate data of the point cloud and the intensity data of the point cloud acquired on the inner surface of the rectangular tunnel are acquired, the coordinate data are used for determining the position of the point cloud to be mapped into the pixel in the gray level image, the intensity data are converted into the gray level data of the pixel, the original data are converted into the gray level image, and the water seepage area of the rectangular tunnel is detected through the preset type image processing of the gray level image. Compared with a manual detection mode, the method has higher efficiency and accuracy.
Drawings
In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required in the embodiments or the description of the prior art will be briefly described below, it being obvious that the drawings in the following description are only some embodiments of the present application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
Fig. 1 is a flowchart of a disease detection method for a rectangular tunnel according to the disclosure of the embodiment of the present application;
FIG. 2 is a flowchart of converting point cloud data into a gray scale map according to an embodiment of the present disclosure;
FIG. 3 is a flow chart of detecting deformation using horizontal and vertical distances as disclosed in an embodiment of the present application;
fig. 4 is a schematic structural diagram of a defect detection device for a rectangular tunnel according to an embodiment of the present application.
Detailed Description
The technical scheme of the embodiment of the application can be applied to, but is not limited to, rectangular tunnels in the field of rail transit. Further, the method can be applied to defect detection of the subway rectangular tunnel.
The following description of the embodiments of the present application will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are only some, but not all, of the embodiments of the present application. All other embodiments, which can be made by one of ordinary skill in the art without undue burden from the present disclosure, are within the scope of the present disclosure.
Fig. 1 is a diagram of a disease detection method for a rectangular tunnel according to an embodiment of the present application, including the following steps:
s101: raw data is acquired.
In this embodiment, the point cloud data is acquired by scanning the inner wall of the rectangular tunnel using a laser scanner. Specifically, a track type three-dimensional laser scanner is adopted to scan the inside of a rectangular tunnel, a laser probe is arranged in the three-dimensional laser scanner, the section of the tunnel is scanned in a mode of rotating and emitting laser beams at high frequency, and the laser beams return to a laser radar after contacting the surface of the tunnel to obtain tunnel surface information.
Further, the laser scanner travels in the tunnel direction at preset intervals, and at each position point, the laser probe rotates at high frequency to emit a laser beam, and feedback radar data of the laser beam emitted by 360 degrees of rotation is used as one frame of point cloud data. At each location, at least one frame of point cloud data can be acquired.
Wherein, the original data comprises: point cloud data (including coordinate data), inertial navigation data, mileage data, and intensity data (representing the intensity of the fed back radar data) for points on the inner surface of the tunnel.
S102: the raw data is converted into a gray scale image.
That is, three-dimensional point clouds are converted into two-dimensional images, coordinate data of the point clouds determine positions of the point clouds mapped to pixels in the gray-scale image, and intensity data of the point clouds are converted into gray-scale data of the pixels. Because the point cloud data includes mileage data, pixel points corresponding to each frame of point cloud in the gray scale image may also correspond to mileage data.
The specific implementation of S102 will be described in detail in the flow shown in fig. 2.
S103: and detecting the water seepage area of the rectangular tunnel by carrying out image processing of a preset type on the gray level image.
Wherein the preset type of image processing includes, but is not limited to: contrast enhancement, binarization, erosion, saturation adjustment and edge extraction.
Since the area of the water penetration region is large in the gray image and is often represented in black, a closed region having a gray value of 0 (in practice, not limited to 0, but a threshold value may be set according to an empirical value) may be extracted from the gray image as the water penetration region. Binarization and edge extraction in preset type image processing can realize extraction of black closed areas.
However, the applicant found in the course of the study that the background in the grey-scale map was similar to the grey-scale value of the water-permeable region, and therefore, in order to improve the accuracy of recognition, a contrast enhancement process was performed prior to binarization to increase the difference in the grey-scale values of the pixels in the background and the wading region.
After binarization, etching treatment and saturation adjustment are performed, with the aim of removing noise to improve the accuracy of edge extraction. Specifically, edge extraction may use a Canny operator edge extraction algorithm.
It should be noted that, for the specific implementation manner of the above image processing, reference may be made to the prior art, and details are not repeated here. The above image processing modes can adopt a full-automatic mode or a mode of combining manual and automatic modes, for example, contrast increasing processing can be adopted, contrast parameters can be set manually, and repeated debugging can be carried out, so that the contrast with the best enhancement effect is obtained.
It will be appreciated that if there is a closed region in the processed image, then it is determined that a water penetration region is detected, otherwise it is determined that no water penetration region is detected. Furthermore, based on the closed area, the area of the water seepage area can be obtained, and the position of the water seepage area can be accurately positioned by combining mileage information.
S104: and detecting the deformation of the rectangular tunnel by analyzing the horizontal distance and the vertical distance of the rectangular tunnel.
In the actual space, the horizontal distance is the distance between any one position point on any side wall of a rectangular tunnel, which is at a height (for example, 1.5 meters) from the center of a track (the center line of the track laid in the tunnel), and the opposite point on the opposite side wall. The relative point of any one of the position points is a position point which is at the same height from the center of the track and whose line connecting to the position point is a horizontal line.
In this embodiment, a specific implementation manner of calculating the horizontal distance by using the point cloud will be described in detail in the flow shown in fig. 3.
Based on the definition of the horizontal distance, it can be understood that if the relation between the horizontal distance and the preset horizontal distance threshold value meets the preset condition, it is determined that deformation of the rectangular tunnel is detected, otherwise, it is determined that the rectangular tunnel is not deformed.
The vertical distance is the vertical distance from the center of the track at any point on the top of the rectangular tunnel. It is understood that if the relation between the vertical distance and the preset vertical distance threshold value meets the preset condition, it is determined that deformation of the rectangular tunnel is detected, otherwise, it is determined that the rectangular tunnel is not deformed. The specific implementation of calculating the vertical distance by the point cloud will be described in detail in the flow shown in fig. 3.
The flow shown in fig. 1 obtains a gray image of the inner surface of the rectangular tunnel through the point cloud data of the inner surface of the rectangular tunnel, so as to detect the water seepage area in the rectangular tunnel based on the gray image. And detecting the deformation of the rectangular tunnel through the point cloud data of the inner surface of the rectangular tunnel. Compared with manual inspection, on one hand, the inspection efficiency can be improved, the inspection cost is greatly reduced, and on the other hand, the point cloud data obtained through laser scanning can fully cover the inner surface of the tunnel and is small in granularity, so that the accuracy of the detection result obtained based on the point cloud data is higher.
Experiments prove that compared with the manual detection, the efficiency of the method disclosed by the embodiment is improved by more than 5 times.
Fig. 2 is a flow of converting original data into a gray scale image according to an embodiment of the present application, including the following steps:
s201: coordinates of four vertices (upper left, lower left, upper right, lower right) of an end of a rectangular tunnel (entrance or exit of the tunnel) and coordinates of a center point of the rectangular tunnel are acquired.
S202: the scale of the grid within the gray scale image is acquired.
In the present embodiment, a grid is provided as a sampling unit of a point cloud within a grayscale image. The length direction and width method both divide the grid.
Specifically, the dimension of the grid is determined in the following manner: the length and width of the gray image are set, and the ratio of the length and width of the gray image is the same as the ratio of the width of the rectangular tunnel to the perimeter of the section (which can be used as a reference ratio). And determining the dimension of the grids in the length direction by using the length of the gray image and the number of the preset grids in the length direction in the gray image. For example, if the preset number of grids in the length direction of the gray image is 1000 and the length of the gray image is 1000 cm, the scale of the grids in the length direction of the gray image is 1 cm. The dimension of the grid in the width direction is determined using the width of the gradation image and the number of grids preset in the width direction in the gradation image.
It is understood that the grid may also correspond to mileage data based on the above-described grid division method and mileage data of the rectangular tunnel. The specific corresponding manner can be referred to in the prior art, and will not be described herein.
S203: the point cloud of the rectangular tunnel is divided into left and right sides by taking the vertical line where the center point of the rectangular tunnel (the coordinates of the center point are acquired in S201) is located as a dividing line.
S204: for any one of the point clouds, taking the left point cloud as an example, the left point cloud is divided into an upper left point cloud, a left waist point cloud and a lower left point cloud according to the coordinates of the upper left vertex and the lower left vertex (acquired in S201).
S205: the lower left point cloud is rotated 90 degrees clockwise around the lower left vertex and projected to the left inner wall plane (plane defined in the vertical direction and in the forward direction of the upper left vertex), the lower left point cloud is also projected to the left inner wall plane, and the point cloud projected into the left inner wall plane is rotated 90 degrees clockwise around the upper left vertex.
And similarly processing the right point cloud: dividing the right side point cloud into an upper right point cloud, a lower right waist point cloud and a lower right point cloud according to coordinates of an upper right vertex and a lower right vertex of the rectangular tunnel, rotating the lower right point cloud and the lower right waist point cloud by 90 degrees anticlockwise around the lower right vertex and projecting the lower right point cloud to a right side inner wall plane of the rectangular tunnel, and rotating the point cloud projected into the right side inner wall plane by 90 degrees anticlockwise around the upper right vertex.
S206: dividing the rotated point cloud into left and right sides along the center point, arranging grids along the left and right directions from the center point, and dividing the rotated point cloud into the grids.
The set scale of the grid is the scale acquired in S202.
For any one grid, the point cloud with the mileage within the range of the grid is divided into the point cloud in the grid. The mileage of any point in the point cloud is represented by mileage data in the point cloud data of the point cloud.
S207: for any one grid including a plurality of point cloud frames of the same mileage, only one point cloud frame of the mileage within the range of the grid is reserved as the point cloud within the grid.
It should be noted that, since the laser scanning head may be at one position and the laser head rotates a plurality of times, the position corresponds to a plurality of point cloud frames, and therefore, there may be a plurality of point cloud frames having a mileage within the range of the grid, in this case, only one point cloud frame having a mileage within the range of the grid may be reserved as the point cloud within the grid.
S208: if no point cloud exists in any grid, the point cloud in the previous frame of the point cloud frame which has the mileage greater than the range of the grid and is closest to the range of the grid is taken as the point cloud in the grid.
It can be appreciated that in S206-S207, all grids are filled into the point cloud, so that sampling of the point cloud data is completed, and the sampled point cloud is obtained.
S209: and performing intensity smoothing and intensity filling treatment on the point cloud in the grid.
S209 is an optional step, with the aim of making the quality of the generated gray-scale image higher.
S210: and converting the point cloud intensity data of the point cloud in the grid into gray values, and converting the point cloud data into gray images.
Further, mileage information of the point cloud in the grid can be recorded.
The flow shown in fig. 2 converts the point cloud data into a gray image according to the structural characteristics of the rectangular tunnel (S203-S206), and lays a foundation for detecting the water seepage area based on the image.
Fig. 3 is a flow of calculating a horizontal distance by a point cloud and detecting deformation according to an embodiment of the present application, including the following steps:
s301: position data of a target point in a point cloud is acquired.
Wherein the target point is a point in a point pair. The point pairs include: any one point on any one side wall of the rectangular tunnel at a preset height (for example, 1.5 meters) from the ground, and an opposite point on the opposite side wall.
Specifically, the position data of the target point can be determined according to the coordinates in the point cloud data and the coordinates of the end and the center point of the rectangular tunnel. The specific manner may be found in the prior art and will not be described in detail here.
Further, in order to reduce the calculation amount, equally spaced target points on the side wall of the rectangular tunnel may be taken.
S302: the horizontal distance, i.e. the first distance, of any one target point to the center point is calculated.
S303: whether the perpendicularity of the straight line formed by the target point and the adjacent target point meets a preset perpendicularity threshold (for example, 90 degrees with the ground) is judged, if yes, S304 is executed, and if not, S306 is executed.
S304: a straight line is calculated, the distance to the center point, i.e. the second distance.
S305: whether the difference between the first distance and the second distance is within the preset difference range is determined, if yes, S307 is executed, and if no, S306 is executed.
S306: and taking twice the second distance as the horizontal distance of the target point.
S307: twice the first distance is taken as the horizontal distance of the target point.
S308: and judging the difference value between the horizontal distance and the horizontal distance threshold value, if the difference value is within the allowable range of the design value, determining that the rectangular tunnel is not deformed, otherwise, determining that the horizontal tunnel is deformed.
S309: the vertical distance, i.e. the third distance, of any top point in the point cloud to the center of the track is calculated.
S310: it is determined whether the levelness of the straight line formed by the top point and the adjacent top point satisfies a preset levelness threshold (for example, 0 degrees), if so, S311 is executed, and if not, S314 is executed.
S311: the distance of the straight line to the center of the track, i.e. the fourth distance, is calculated.
S312: whether the difference between the third distance and the fourth distance is within the preset difference range is determined, if yes, S314 is executed, and if no, S313 is executed.
S313: twice the fourth distance is taken as the vertical distance of the top point.
S314: twice the third distance is taken as the vertical distance of the top point.
S315: and judging the difference value between the vertical distance and the vertical distance threshold value, if the difference value is within the allowable range of the design value, determining that the rectangular tunnel is not deformed, otherwise, determining that the rectangular tunnel is deformed.
As can be seen from the flow chart of fig. 3, in this embodiment, the horizontal distance and the vertical distance are obtained based on the point cloud, and the deformation is detected according to the horizontal distance and the vertical distance, because the point cloud can be regarded as uniform sampling of the points on the inner surface of the tunnel, the accuracy of the deformation detection result is high, and compared with the manual measurement, the deformation detection result has higher efficiency and lower cost.
Fig. 4 is a disease detection device for a rectangular tunnel, which is disclosed in an embodiment of the present application, including: the device comprises an acquisition module, a conversion module and a detection module.
The acquisition module is used for acquiring original data, wherein the original data comprises: coordinate data of the point cloud and intensity data of the point cloud acquired on the inner surface of the rectangular tunnel. The conversion module is used for converting the original data into a gray image, wherein the coordinate data determines the position of the point cloud to be mapped into the position of the pixel in the gray image, and the intensity data is converted into the gray data of the pixel. The detection module is used for detecting the water seepage area of the rectangular tunnel by carrying out image processing of a preset type on the gray level image. Optionally, the detection module is further configured to detect deformation of the rectangular tunnel by analyzing a horizontal distance and a vertical distance of the rectangular tunnel, where the horizontal distance and the vertical distance are obtained according to the coordinate data.
Specifically, the raw data further includes: mileage data of the point cloud, wherein the mileage data is used for indicating mileage of the point cloud. The specific implementation mode of converting the original data into the gray image by the conversion module is as follows: and dividing the point cloud into left and right sides by taking the vertical line where the central point of the rectangular tunnel is located as a dividing line. And dividing the left point cloud into an upper left point cloud, a left waist point cloud and a lower left point cloud according to the coordinates of the upper left vertex and the lower left vertex of the rectangular tunnel. Dividing the right side point cloud into an upper right point cloud, a lower right waist point cloud and a lower right point cloud according to coordinates of an upper right vertex and a lower right vertex of the rectangular tunnel, rotating the lower left point cloud and the lower left waist point cloud by 90 degrees clockwise around the lower left vertex and projecting the lower left point cloud to a left inner wall plane of the rectangular tunnel, and rotating the point cloud projected into the left inner wall plane by 90 degrees clockwise around the upper left vertex. And rotating the right lower point cloud and the right waist point cloud by 90 degrees anticlockwise around the right lower vertex and projecting the right lower point cloud and the right waist point cloud to the right inner wall plane of the rectangular tunnel, and rotating the point cloud projected to the right inner wall plane by 90 degrees anticlockwise around the right upper vertex. Dividing the rotated point cloud into a grid with a preset scale along the left side and the right side of the center point and setting the grid with the preset scale along the left-right direction from the center point, dividing the rotated point cloud into the grids, and converting the point cloud intensity data of the point cloud in the grid column into gray values.
Further, the conversion module is further configured to: before the point cloud intensity data of the point clouds in the grid are converted into gray values, only reserving a point cloud frame with one mileage within the range of the grid as the point cloud in the grid for any one grid comprising a plurality of point cloud frames with the same mileage; if any one of the grids does not have the point cloud, the point cloud in the frame above the point cloud frame which has the mileage greater than the range of the grid and is closest to the range of the grid is taken as the point cloud in the grid.
Further, the determining process of the preset scale of the grid includes: setting the length and width of the gray level image; the ratio of the length to the width is the same as a reference ratio, and the reference ratio is the ratio of the width of the rectangular tunnel to the perimeter of the section; the method comprises the steps of determining the dimension of a grid in the length direction by using the length of a gray image and the number of grids preset in the length direction, and determining the dimension of the grid in the width direction by using the width of the gray image and the number of grids preset in the width direction.
Specifically, the preset type of image processing includes: contrast enhancement, binarization, erosion, saturation adjustment and edge extraction.
Specifically, the process for obtaining the horizontal distance comprises the following steps: acquiring position data of a target point in the point cloud; wherein the target point is a point in a point pair comprising: any position point of any side wall of the rectangular tunnel with preset height from the ground and the opposite point on the opposite side wall; for any one target point, if the difference between the first distance and the second distance is within a preset difference range, taking twice of the second distance as the horizontal distance of the target point, otherwise, taking twice of the first distance as the horizontal distance of the target point, wherein the first distance is the horizontal distance from the target point to the central point, the second distance is the distance from the straight line to the central point, and the straight line is the straight line that the perpendicularity formed by the target point and the adjacent target point meets a preset perpendicularity threshold value.
The vertical distance acquisition process comprises the following steps:
and calculating a third distance, wherein the third distance is the distance from the top point of the target to the center of the track, and the top point of the target is any one top point. And if the levelness of the straight line formed by the target top point and the adjacent top point meets a preset levelness threshold, taking twice of a fourth distance as the vertical distance, otherwise taking twice of the third distance as the vertical distance, wherein the fourth distance is the distance from the straight line to the center of the track.
The device shown in fig. 4 can convert the point cloud data of the inner surface of the rectangular tunnel into a gray image, detect the water seepage area based on the gray image, and detect deformation based on the point cloud data, so that the defect detection of the rectangular tunnel according to the point cloud data is realized, and the efficiency and the accuracy are higher.
The embodiment of the application also discloses disease detection equipment for rectangular tunnel, including: memory and a processor. The memory is used for storing a program, and the processor is used for running the program to realize the defect detection method for the rectangular tunnel according to the embodiment.
A computer-readable storage medium having stored thereon a computer program which, when run on a computer, implements the disease detection method for a rectangular tunnel described in the above embodiment.
The functions described in the methods of the present application, if implemented in the form of software functional units and sold or used as a stand-alone product, may be stored in a computing device readable storage medium. Based on such understanding, a portion of the embodiments of the present application that contributes to the prior art or a portion of the technical solution may be embodied in the form of a software product stored in a storage medium, comprising several instructions for causing a computing device (which may be a personal computer, a server, a mobile computing device or a network device, etc.) to perform all or part of the steps of the methods described in the embodiments of the present application. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a random access Memory (RAM, random Access Memory), a magnetic disk, or an optical disk, or other various media capable of storing program codes.
In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, so that the same or similar parts between the embodiments are referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present application. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the application. Thus, the present application is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.

Claims (8)

1. The defect detection method for the rectangular tunnel is characterized by comprising the following steps of:
obtaining raw data, the raw data comprising: coordinate data of point clouds and intensity data of the point clouds acquired on the inner surface of the rectangular tunnel;
converting the original data into a gray image, wherein the coordinate data determines the position of the point cloud mapped to a pixel in the gray image, and the intensity data is converted into gray data of the pixel;
detecting the water seepage area of the rectangular tunnel by carrying out image processing of a preset type on the gray level image;
detecting deformation of the rectangular tunnel by analyzing horizontal distance and vertical distance of the rectangular tunnel, wherein the horizontal distance and the vertical distance are obtained according to the coordinate data;
the horizontal distance obtaining process comprises the following steps:
acquiring position data of a target point in the point cloud; wherein the target point is a point in a point pair comprising: any position point of a preset height from the ground on any side wall of the rectangular tunnel and a relative point on the opposite side wall;
for any one of the target points, if the difference between the first distance and the second distance is within a preset difference range, taking twice of the second distance as the horizontal distance of the target point, otherwise, taking twice of the first distance as the horizontal distance of the target point, wherein the first distance is the horizontal distance from the target point to a central point, the second distance is the distance from a straight line to the central point, and the straight line is the straight line that the perpendicularity formed by the target point and the adjacent target point meets a preset perpendicularity threshold value;
the vertical distance acquisition process comprises the following steps:
calculating a third distance, wherein the third distance is the distance from a target top point to the center of the track, and the target top point is any top point;
and if the levelness of the straight line formed by the target top point and the adjacent top point meets a preset levelness threshold, taking twice of a fourth distance as the vertical distance, otherwise taking twice of the third distance as the vertical distance, wherein the fourth distance is the distance from the straight line to the center of the track.
2. The method of claim 1, wherein the raw data further comprises: mileage data of the point cloud, wherein the mileage data is used for indicating mileage of the point cloud;
the converting the original data into a gray scale image includes:
dividing the point cloud into left and right sides by taking a vertical line where the central point of the rectangular tunnel is located as a dividing line;
dividing the left side point cloud into an upper left point cloud, a left waist point cloud and a lower left point cloud according to coordinates of an upper left vertex and a lower left vertex of the rectangular tunnel;
dividing the right side point cloud into an upper right point cloud, a lower right waist point cloud and a lower right point cloud according to coordinates of an upper right vertex and a lower right vertex of the rectangular tunnel;
rotating the left lower point cloud and the left waist point cloud by 90 degrees clockwise around the left lower vertex and projecting the left lower point cloud and the left waist point cloud to a left inner wall plane of the rectangular tunnel, and rotating the point cloud projected into the left inner wall plane by 90 degrees clockwise around the left upper vertex;
rotating the right lower point cloud and the right waist point cloud by 90 degrees anticlockwise around the right lower vertex and projecting the right lower point cloud and the right waist point cloud to a right inner wall plane of the rectangular tunnel, and rotating the point cloud projected into the right inner wall plane by 90 degrees anticlockwise around the right upper vertex;
dividing the rotated point cloud into a left side and a right side along the central point, setting grids with preset scales along the left-right direction from the central point, and dividing the rotated point cloud into the grids;
and converting the point cloud intensity data of the point cloud in the grid into gray values.
3. The method of claim 2, further comprising, prior to said converting said point cloud intensity data of a point cloud within said grid to gray values:
for any one of the grids comprising a plurality of point cloud frames with the same mileage, only reserving the point cloud frame with one mileage within the range of the grid as the point cloud in the grid;
if any one of the grids does not have the point cloud, the point cloud in the frame above the point cloud frame which has the mileage greater than the range of the grid and is closest to the range of the grid is taken as the point cloud in the grid.
4. A method according to claim 3, wherein the determining of the preset dimensions of the grid comprises:
setting the length and width of the gray level image; the ratio of the length to the width is the same as a reference ratio, and the reference ratio is the ratio of the width of the rectangular tunnel to the perimeter of the section;
the method comprises the steps of determining the dimension of a grid in the length direction by using the length of the gray image and the number of grids preset in the length direction, and determining the dimension of the grid in the width direction by using the width of the gray image and the number of grids preset in the width direction.
5. The method of claim 1, wherein the preset type of image processing comprises:
contrast enhancement, binarization, erosion, saturation adjustment and edge extraction.
6. A defect detection device for a rectangular tunnel, comprising:
the acquisition module is used for acquiring original data, wherein the original data comprises: coordinate data of point clouds and intensity data of the point clouds acquired on the inner surface of the rectangular tunnel;
the conversion module is used for converting the original data into a gray image, wherein the coordinate data determine the position of the point cloud mapped into pixels in the gray image, and the intensity data are converted into gray data of the pixels;
the detection module is used for detecting the water seepage area of the rectangular tunnel by carrying out image processing of a preset type on the gray level image;
the detection module is also used for detecting the deformation of the rectangular tunnel by analyzing the horizontal distance and the vertical distance of the rectangular tunnel, and the horizontal distance and the vertical distance are obtained according to the coordinate data;
the horizontal distance obtaining process comprises the following steps:
acquiring position data of a target point in the point cloud; wherein the target point is a point in a point pair comprising: any position point of a preset height from the ground on any side wall of the rectangular tunnel and a relative point on the opposite side wall;
for any one of the target points, if the difference between the first distance and the second distance is within a preset difference range, taking twice of the second distance as the horizontal distance of the target point, otherwise, taking twice of the first distance as the horizontal distance of the target point, wherein the first distance is the horizontal distance from the target point to a central point, the second distance is the distance from a straight line to the central point, and the straight line is the straight line that the perpendicularity formed by the target point and the adjacent target point meets a preset perpendicularity threshold value;
the vertical distance acquisition process comprises the following steps:
calculating a third distance, wherein the third distance is the distance from a target top point to the center of the track, and the target top point is any top point;
and if the levelness of the straight line formed by the target top point and the adjacent top point meets a preset levelness threshold, taking twice of a fourth distance as the vertical distance, otherwise taking twice of the third distance as the vertical distance, wherein the fourth distance is the distance from the straight line to the center of the track.
7. A defect detection apparatus for a rectangular tunnel, comprising:
a memory and a processor;
the memory is used for storing a program, and the processor is used for running the program to realize the defect detection method for the rectangular tunnel according to any one of claims 1 to 5.
8. A computer readable storage medium having stored thereon a computer program, characterized in that the computer program, when run on a computer, implements the method for detecting a defect for a rectangular tunnel according to any one of claims 1 to 5.
CN202010195598.XA 2020-03-19 2020-03-19 Disease detection method and device for rectangular tunnel Active CN111325747B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010195598.XA CN111325747B (en) 2020-03-19 2020-03-19 Disease detection method and device for rectangular tunnel

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010195598.XA CN111325747B (en) 2020-03-19 2020-03-19 Disease detection method and device for rectangular tunnel

Publications (2)

Publication Number Publication Date
CN111325747A CN111325747A (en) 2020-06-23
CN111325747B true CN111325747B (en) 2023-07-11

Family

ID=71171590

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010195598.XA Active CN111325747B (en) 2020-03-19 2020-03-19 Disease detection method and device for rectangular tunnel

Country Status (1)

Country Link
CN (1) CN111325747B (en)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN113837996B (en) * 2021-08-17 2023-09-29 北京工商大学 Automatic subway tunnel defect detection method supporting manual verification

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2014098704A (en) * 2013-12-16 2014-05-29 Kajima Corp Inner space displacement measuring method and inner space displacement measuring system
WO2018008808A1 (en) * 2016-07-07 2018-01-11 한국철도기술연구원 Tunnel inspection system comprising individually driven rail-guided vehicle and inertia navigation system
CN109615653A (en) * 2018-12-19 2019-04-12 上海大学 Percolating water area detecting and recognition methods based on deep learning and visual field projection model
CN110221277A (en) * 2019-06-21 2019-09-10 北京航空航天大学 A kind of tunnel surface infiltration method for extracting region based on laser radar scanning
CN110322428A (en) * 2019-05-07 2019-10-11 武汉汉宁轨道交通技术有限公司 Detect the method, apparatus and electronic equipment of tunnel defect

Family Cites Families (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100300006A1 (en) * 2009-05-29 2010-12-02 Cecil Magpuri Virtual reality dome theater
DE102012211515A1 (en) * 2012-07-03 2014-05-22 Bayerische Motoren Werke Aktiengesellschaft Method for monitoring distribution property e.g. particle size, of airflow transported precipitation of snow generated in wind tunnel, involves observing cut surface by camera directed toward cut surface
GB201320521D0 (en) * 2013-11-20 2014-01-01 Pilkington Group Ltd Coating apparatus
CN104359459B (en) * 2014-12-04 2017-02-22 上海岩土工程勘察设计研究院有限公司 Method for scanning reflectivity information to generate tunnel lining image by virtue of three-dimensional laser
US9945668B2 (en) * 2016-03-29 2018-04-17 Queen's University At Kingston Tunnel convergence detection apparatus and method
CN110411361B (en) * 2019-05-15 2021-08-17 首都师范大学 Laser detection data processing method for mobile tunnel

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2014098704A (en) * 2013-12-16 2014-05-29 Kajima Corp Inner space displacement measuring method and inner space displacement measuring system
WO2018008808A1 (en) * 2016-07-07 2018-01-11 한국철도기술연구원 Tunnel inspection system comprising individually driven rail-guided vehicle and inertia navigation system
CN109615653A (en) * 2018-12-19 2019-04-12 上海大学 Percolating water area detecting and recognition methods based on deep learning and visual field projection model
CN110322428A (en) * 2019-05-07 2019-10-11 武汉汉宁轨道交通技术有限公司 Detect the method, apparatus and electronic equipment of tunnel defect
CN110221277A (en) * 2019-06-21 2019-09-10 北京航空航天大学 A kind of tunnel surface infiltration method for extracting region based on laser radar scanning

Also Published As

Publication number Publication date
CN111325747A (en) 2020-06-23

Similar Documents

Publication Publication Date Title
CN107014294B (en) Contact net geometric parameter detection method and system based on infrared image
CN109635816B (en) Lane line generation method, apparatus, device, and storage medium
CN111102935B (en) Tunnel structure detection method and device and electronic equipment
CN110322428B (en) Method and device for detecting tunnel diseases and electronic equipment
CN112240772B (en) Lane line generation method and device
CN115170669A (en) Identification and positioning method and system based on edge feature point set registration and storage medium
CN111220235B (en) Water level monitoring method and device
CN111325747B (en) Disease detection method and device for rectangular tunnel
CN109446485B (en) Seasonal lake bottom terrain generation method based on multi-source data fusion
CN104574312A (en) Method and device of calculating center of circle for target image
CN110660094A (en) Subway tunnel mobile scanning point cloud fine division method based on image recognition
JP2015059768A (en) Level difference measuring device, level difference measuring method and program
CN113223176B (en) Method and device for acquiring multi-dimensional pipeline characteristic parameters
CN114549751A (en) Template monitoring system and method for box girder production
CN114387408A (en) Method and device for generating digital elevation model and computer readable storage medium
CN116399302B (en) Method for monitoring dynamic compaction settlement in real time based on binocular vision and neural network model
CN109101892A (en) Laser radar target object detecting method based on grid and density clustering algorithm
CN111415344B (en) Disease detection method and device for horseshoe-shaped tunnel
JP3749726B1 (en) Low contrast defect inspection method under periodic noise, low contrast defect inspection method under repeated pattern
CN112001907B (en) Method for measuring roughness of surrounding rock in tunnel construction site
CN103440486A (en) Method and system for detecting dimension of label in image
CN114842166A (en) Negative obstacle detection method, system, medium, and apparatus applied to structured road
CN110779450A (en) Abrasion detection method and device for power supply three-rail
CN113658037B (en) Method and device for converting depth image into gray level image
CN104599278B (en) Shallow sea sand wave information extraction method based on remote sensing image

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