CN112461122A - Tunnel surface feature detection device and method - Google Patents

Tunnel surface feature detection device and method Download PDF

Info

Publication number
CN112461122A
CN112461122A CN202010996039.9A CN202010996039A CN112461122A CN 112461122 A CN112461122 A CN 112461122A CN 202010996039 A CN202010996039 A CN 202010996039A CN 112461122 A CN112461122 A CN 112461122A
Authority
CN
China
Prior art keywords
tunnel
image
distance
binocular
detection platform
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Granted
Application number
CN202010996039.9A
Other languages
Chinese (zh)
Other versions
CN112461122B (en
Inventor
王振宇
陈皓
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.)
Zhejiang University ZJU
Original Assignee
Zhejiang University ZJU
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 Zhejiang University ZJU filed Critical Zhejiang University ZJU
Priority to CN202010996039.9A priority Critical patent/CN112461122B/en
Publication of CN112461122A publication Critical patent/CN112461122A/en
Application granted granted Critical
Publication of CN112461122B publication Critical patent/CN112461122B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • 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
    • G01B11/002—Measuring arrangements characterised by the use of optical techniques for measuring two or more coordinates
    • 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
    • G01B11/02—Measuring arrangements characterised by the use of optical techniques for measuring length, width or thickness
    • 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
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration

Landscapes

  • General Physics & Mathematics (AREA)
  • Physics & Mathematics (AREA)
  • Engineering & Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Chemical & Material Sciences (AREA)
  • Analytical Chemistry (AREA)
  • Biochemistry (AREA)
  • General Health & Medical Sciences (AREA)
  • Immunology (AREA)
  • Pathology (AREA)
  • Theoretical Computer Science (AREA)
  • Signal Processing (AREA)
  • Length Measuring Devices By Optical Means (AREA)

Abstract

The invention discloses a tunnel surface feature detection device and a method, comprising the following steps: the mobile detection platform is used for providing motion along the tunnel direction; the annular array system is arranged at the upper part of the mobile detection platform and is used for acquiring a tunnel surface image and first distance data from the tunnel surface; the positioning system is arranged at the bottom of the mobile detection platform and is used for acquiring a track image and second distance data from the track; the tunnel marker is used for assisting in correcting the mileage and acquiring a tunnel convergence deformation value; the terminal is used for controlling the mobile detection platform, the annular array system and the positioning system; calculating the position relation between the mobile detection platform and the center of the track and the mileage of the mobile detection platform entering the tunnel; correcting mileage, and associating the space coordinates of the tunnel marker with the tunnel marker; and identifying and positioning the surface characteristics of the tunnel.

Description

Tunnel surface feature detection device and method
Technical Field
The invention belongs to the field of nondestructive testing, and particularly relates to a tunnel surface feature testing device and method.
Background
The tunnel is an important transportation facility, and the quality of the state of the tunnel directly affects the safety and efficiency of transportation. The total number and the total mileage of the tunnels in China are large in scale, and the tunnels are different in construction age, different in materials and various in structure. A large number of tunnels constructed in early stages are damaged in different degrees and tend to deteriorate year by year. In order to avoid accidents, the tunnel needs to be periodically detected and maintained in time.
The current tunnel lining surface state detection technical means mainly comprise a manual visual detection method, a manual instrument detection method, a geological radar detection method and the like. The manual detection consumes manpower, the efficiency is low, the crack is judged mainly by the experience of workers, the subjectivity is large, the objectivity of a detection result is difficult to ensure, the running of passing vehicles must be suspended in the detection process, and the detection personnel also have certain danger by means of lifting equipment such as a lift truck and the like; manual instrument detection requires workers to operate the instrument to focus, read data and record data in a short distance, the detection means consumes manpower and is low in efficiency, and errors are easy to occur in the data read manually; geological radar detection, while capable of accurately detecting cracks, does not have the versatility of image acquisition systems.
Disclosure of Invention
The invention aims to provide a tunnel surface feature detection device and method to solve the problems of labor consumption, low detection efficiency, poor safety and single function in the related technology.
In order to achieve the above purpose, the technical solution adopted by the embodiment of the present invention is as follows:
in a first aspect, an embodiment of the present invention provides a tunnel surface feature detection apparatus, including:
the mobile detection platform is used for providing motion along the tunnel direction;
the annular array system is arranged on the upper part of the mobile detection platform and consists of a plurality of first image distance acquisition units, each first image distance acquisition unit consists of a first binocular camera and a first laser ranging sensor, the first binocular camera is used for acquiring images on the surface of the tunnel, and the first laser ranging sensor is used for acquiring first distance data from the first laser ranging sensor to the surface of the tunnel;
the positioning system is arranged at the bottom of the mobile detection platform and consists of a second image distance acquisition unit, the second image distance acquisition unit consists of a second binocular camera and a second laser ranging sensor, the second binocular camera is used for acquiring track images, and the second laser ranging sensor is used for acquiring second distance data from the second laser ranging sensor to a track;
the tunnel marker consists of a light reflecting sheet and an electronic identifier, is arranged on the lining surface near the vault, the arch shoulder and the arch foot of the tunnel, and is used for assisting in correcting mileage and acquiring a convergence deformation value of the tunnel;
the terminal is used for acquiring the relative position relation between the cameras in the annular array system and the positioning system and the laser ranging sensor; performing parameter correction on all binocular cameras in the annular array system and the positioning system to obtain correction parameters in the depth direction, drawing a relation curve of the correction parameters and the distance, and fitting a relation between the correction parameters and the distance; controlling the mobile detection platform to enter the tunnel, controlling the annular array system and the positioning system to synchronously acquire images, and receiving a tunnel surface image, first distance data, a track image and second distance data; calculating the position relation between the mobile detection platform and the track center and the mileage of the mobile detection platform entering the tunnel according to the track image and the second distance data; acquiring and identifying tunnel markers according to the tunnel surface image and the first distance data, acquiring the position and mileage information associated with the electronic markers, correcting the mileage, calculating the space coordinate of each tunnel marker, and associating the space coordinate with the electronic markers; and comparing and calculating the space coordinate information associated with the same tunnel marker under different measurement times to obtain a tunnel convergence deformation value, and identifying and positioning the surface characteristics of the tunnel.
In a second aspect, an embodiment of the present invention provides a method for detecting a surface feature of a tunnel, where the method is implemented in a device for detecting a surface feature of a tunnel according to the first aspect, and the method includes:
s1, acquiring a relative position relation between a camera and a laser ranging sensor in an annular array system and a positioning system;
s2, performing parameter correction on all binocular cameras in the annular array system and the positioning system to obtain correction parameters in the depth direction, drawing a relation curve of the correction parameters and the distance, and fitting a relation between the correction parameters and the distance;
s3, controlling the mobile detection platform to enter the tunnel, controlling the annular array system and the positioning system to synchronously acquire images, and receiving a tunnel surface image, first distance data, a track image and second distance data;
s4, calculating and correcting the position relation between the mobile detection platform and the track center and the mileage of the mobile detection platform entering the tunnel according to the track image and the second distance data by combining the correction parameter and the distance relational expression obtained in the step S2;
s5, acquiring and identifying the tunnel markers according to the tunnel surface image, acquiring the position and mileage information associated with the electronic markers, correcting the mileage in the step S4, calculating and correcting the space coordinates of each tunnel marker according to the binocular distance measurement principle and the first distance data by combining the correction parameter and distance relation obtained in the step S2, and associating the space coordinates with the electronic markers; comparing and calculating the space coordinate information associated with the same tunnel marker under different measurement times to obtain a tunnel convergence deformation value;
and S6, according to the tunnel surface image and the first distance data, combining the relational expression of the correction parameters and the distance obtained in the step S2, and identifying and positioning the tunnel surface features by adopting an image identification technology, an image splicing technology and a binocular distance measuring principle to finish the detection of the tunnel surface features.
According to the technical scheme, the reconstruction of the three-dimensional model of the tunnel surface can be realized through the tunnel surface image acquired by the annular array system and the distance data from the first image distance acquisition unit to the tunnel surface, and the tunnel surface characteristics are marked and presented on the three-dimensional model; the position relation between the mobile detection platform and the center of the track and the mileage of the mobile detection platform entering the tunnel can be determined through the track image acquired by the positioning system and the distance data between the second image distance acquisition unit and the track; the method can assist in correcting the mileage and acquiring the convergence deformation value of the tunnel through the tunnel marker. Through a whole set of device, can liberate the manpower, realize the automation that tunnel surface characteristic detected, have advantages such as high efficiency, accurate, convenient.
Description of the drawings:
the accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention. In the drawings:
fig. 1 is a schematic diagram of a tunnel surface feature detection apparatus in this embodiment;
FIG. 2 is a schematic diagram illustrating a first image distance acquisition unit in the present embodiment;
FIG. 3 is a schematic diagram illustrating a second image distance acquisition unit in the present embodiment;
FIG. 4 is a schematic view of a manual calibration plate according to the present embodiment;
fig. 5 is a flowchart of a tunnel surface feature detection method according to the present embodiment;
in the figure: moving the detection platform 1; a circular array system 2; a positioning system 3; a first camera 4; a first laser ranging sensor 5; a second camera 6; a second laser ranging sensor 7; the plate 8 is calibrated manually.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
On the contrary, the invention is intended to cover alternatives, modifications, equivalents and alternatives which may be included within the spirit and scope of the invention as defined by the appended claims. Furthermore, in the following detailed description of the present invention, certain specific details are set forth in order to provide a better understanding of the present invention.
Example 1:
referring to fig. 1 to 4, the present embodiment provides a tunnel surface feature detection apparatus, including:
the mobile detection platform 1 is used for providing motion along the tunnel direction;
the annular array system 2 is arranged on the upper part of the mobile detection platform and consists of a plurality of first image distance acquisition units, each first image distance acquisition unit consists of a first binocular camera 4 and a first laser ranging sensor 5, the first binocular camera 4 is used for acquiring images on the surface of the tunnel, and the first laser ranging sensor 5 is used for acquiring distance data from the first laser ranging sensor to the surface of the tunnel;
the positioning system 3 is installed at the bottom of the mobile detection platform and consists of a second image distance acquisition unit, the second image distance acquisition unit consists of a second binocular camera 6 and a second laser ranging sensor 7, the second binocular camera 6 is used for acquiring track images, and the second laser ranging sensor 7 is used for acquiring distance data from the second laser ranging sensor to a track;
the tunnel marker consists of a light reflecting sheet and an electronic identifier, is arranged on the lining surface near the vault, the arch shoulder and the arch foot of the tunnel, and is used for assisting in correcting mileage and acquiring a convergence deformation value of the tunnel;
the terminal is used for acquiring the relative position relation between the cameras in the annular array system and the positioning system and the laser ranging sensor; performing parameter correction on all binocular cameras in the annular array system and the positioning system to obtain correction parameters in the depth direction, drawing a relation curve of the correction parameters and the distance, and fitting a relation between the correction parameters and the distance; controlling the mobile detection platform to enter the tunnel, controlling the annular array system and the positioning system to synchronously acquire images, and receiving a tunnel surface image, first distance data, a track image and second distance data; calculating the position relation between the mobile detection platform and the track center and the mileage of the mobile detection platform entering the tunnel according to the track image and the second distance data; acquiring and identifying tunnel markers according to the tunnel surface image and the first distance data, acquiring the position and mileage information associated with the electronic markers, correcting the mileage, calculating the space coordinate of each tunnel marker, and associating the space coordinate with the electronic markers; and comparing and calculating the space coordinate information associated with the same tunnel marker under different measurement times to obtain a tunnel convergence deformation value, and identifying and positioning the surface characteristics of the tunnel.
Example 2:
referring to fig. 5, the method for detecting a surface feature of a tunnel according to this embodiment includes the following steps:
s1, acquiring a relative position relation between a camera and a laser ranging sensor in an annular array system and a positioning system;
specifically, the relative positional relationship described in step S1 includes: the relative position relationship between each group of binocular cameras in the annular array system and the positioning system and the relative position relationship between each group of binocular cameras and the corresponding laser ranging sensors. The relative positional relationship described in step S1 is obtained by camera calibration. According to a Zhang-Zhengyou method, binocular calibration is carried out on each group of binocular cameras in the annular array system 2 and the positioning system 3, the relative positions of each group of binocular cameras relative to the binocular positioning system are calibrated, and the relative positions of each group of binocular cameras and the corresponding laser ranging sensors are calibrated by utilizing a structured light calibration method. In the embodiment, the matlab camera calibration tool box is adopted to complete the calibration work, and the method has the advantages of convenience in operation, high precision and the like.
S2, performing parameter correction on all binocular cameras in the annular array system and the positioning system to obtain correction parameters in the depth direction, drawing a relation curve of the correction parameters and the distance, and fitting a relation between the correction parameters and the distance; the method specifically comprises the following substeps:
step 2.1, the manual calibration plate 8 is arranged at a preset distance from the binocular camera, so that the laser beam emitted by the laser ranging sensor is positioned on the manual calibration plate 8, the binocular camera can acquire the image of the manual calibration plate, the distance data L of the laser ranging sensor is read, the image is acquired, and the images acquired by the binocular camera are respectively providedTaking the pixel coordinate (u) of the laser spot1，v1) And (u)2，v2) (ii) a In this embodiment, the pixel coordinates where the laser spot is located are extracted by using a feature point extraction algorithm based on conventional vision or a feature point extraction algorithm based on deep learning. The characteristic point extraction algorithm based on the traditional vision has the advantages of high algorithm efficiency, good portability, high precision and the like, and the characteristic point extraction algorithm based on the deep learning has the advantages of high precision, good robustness and the like.
Step 2.2, according to the binocular ranging principle, the following formula is obtained:
Figure BDA0002692642710000051
in the formula (x)c1，yc1，zc1) Represents the space coordinate of the laser spot under the coordinate system of the binocular camera left target, (x)c2，yc2，zc2) The space coordinate of the laser spot in the coordinate system of the binocular camera right target is shown, and the (x) is obtained by solving the equation systemc1，yc1，zc1)；
And 2.3, obtaining the following data according to the position relation between the left eye of the binocular camera and the laser ranging sensor and the distance data L of the laser ranging sensor:
Figure BDA0002692642710000052
in the formula (x)c1′，yc1′，zc1') denotes the spatial coordinates of the laser spot in the camera coordinate system of the binocular camera left eye, (x)0，y0，z0) The space coordinates of the laser ranging sensor under the coordinate system of the binocular camera left target are represented, and (i, j, k) the unit direction vector of the light beam emitted by the laser ranging sensor under the coordinate system of the binocular camera left target is represented; influenced by practical factors, solved by binocular principlesc1，yc1，zc1) Has large errorAnd the error is mainly caused by z in the depth directionc1Caused by z, which is indirectly derived from the range data L of the laser range sensorc1Is relatively accurate, so introducing correction parameters
Figure BDA0002692642710000053
Figure BDA0002692642710000054
Step 2.4, according to the actual engineering requirement, placing the manual calibration plate at different distances from the binocular camera, and repeating the steps 2.1-2.4 to obtain different zc1Correction factor in case of value
Figure BDA0002692642710000055
And plotting the values of
Figure BDA0002692642710000056
The relation curve graph is subjected to curve fitting to obtain
Figure BDA0002692642710000057
The fitting relation of (1). In this example, the difference method is used for drawing
Figure BDA0002692642710000058
The relation graph can be realized by means of matlab, mathematics and other software, and the method can effectively estimate the unknown zc1Correction factor under value
Figure BDA0002692642710000061
The value of (c).
S3, controlling the mobile detection platform to enter the tunnel, controlling the annular array system and the positioning system to synchronously acquire images, and receiving a tunnel surface image, first distance data, a track image and second distance data;
s4, calculating and correcting the position relation between the mobile detection platform and the track center and the mileage of the mobile detection platform entering the tunnel according to the track image and the second distance data by combining the correction parameter and the distance relational expression obtained in the step S2; the method specifically comprises the following substeps:
step 4.1, calculating the position relation between the mobile detection platform and the track center:
extracting pixel points of the track central point in the track image acquired by the positioning system, and calculating the space coordinate (x) of the track central point under the coordinate system of the binocular camera left target camera according to the binocular range finding principlec，yc，zc) Substituting the corresponding second distance data into the relation between the correction parameter and the distance obtained in step S2 to obtain the correction parameter
Figure BDA0002692642710000062
And calculating corrected space coordinates
Figure BDA0002692642710000063
In this embodiment, a graph segmentation algorithm based on conventional vision or a graph segmentation algorithm based on deep learning is used to extract the pixel coordinates where the track center point is located. The graph segmentation algorithm based on the traditional vision has the advantages of high algorithm efficiency, good portability, high precision and the like, and the graph segmentation algorithm based on the deep learning has the advantages of high precision, good robustness and the like.
Step 4.2, calculating the mileage of the mobile detection platform entering the tunnel:
along with the movement of the mobile detection platform, the setting system collects an image pair p at the position where the mobile detection platform moves to the position iiExtracting the image pair pi+1And piRespectively calculating the space coordinates (x) of the repeated point under the coordinate system of the left target camera of the binocular camera when the mobile detection platform moves to the position i +1 and the position i according to the principle of binocular range findingi+1，yi+1，zi+1) And (x)i，yi，zi) Substituting the corresponding second distance data into the relation between the correction parameter and the distance obtained in step S2 to obtain the correction parameter
Figure BDA0002692642710000064
And
Figure BDA0002692642710000065
obtaining corrected space coordinates
Figure BDA0002692642710000066
And
Figure BDA0002692642710000067
and further the determination of the moving mileage of the mobile detection platform is realized. In this embodiment, an image feature point matching algorithm is used to extract an image pair pi+1And piThe method has the advantages of high matching efficiency, high precision, good robustness and the like.
S5, acquiring and identifying the tunnel markers according to the tunnel surface image, acquiring the position and mileage information associated with the electronic markers, correcting the mileage in the step S4, calculating and correcting the space coordinates of each tunnel marker according to the binocular distance measurement principle and the first distance data by combining the correction parameter and distance relation obtained in the step S2, and associating the space coordinates with the electronic markers; comparing and calculating the space coordinate information associated with the same tunnel marker under different measurement times to obtain a tunnel convergence deformation value; the method specifically comprises the following substeps:
step 5.1, pasting tunnel markers on the lining surfaces near the tunnel vault, the arch shoulder and the arch foot of the important road section of the tunnel, and recording position and mileage information in the electronic identification; in the embodiment, the electronic identification adopts the two-dimensional code, and has the advantages of easy identification, good universality, low cost and the like
Step 5.2, when the images collected by the annular array system on the mobile detection platform contain the tunnel marker, scanning the electronic marker, reading the position and the mileage information, and calibrating the mileage calculated in the step S4;
step 5.3, identifying and extracting the positions of the reflectors in the tunnel marker on the image, combining the relative position relationship among each group of binocular cameras in the annular array system according to a binocular distance measurement principle, substituting the corresponding first distance data into the relational expression between the correction parameters and the distances obtained in the step S2 to obtain correction parameters, further calculating the space coordinates of each reflector after correction, and associating the space coordinates with the corresponding electronic identification information;
and 5.4, comparing and calculating the space coordinate information associated with the same tunnel marker under different measurement times to obtain a tunnel convergence deformation value.
And S6, according to the tunnel surface image and the first distance data, combining the relational expression of the correction parameters and the distance obtained in the step S2, and identifying and positioning the tunnel surface features by adopting an image identification technology, an image splicing technology and a binocular distance measuring principle to finish the detection of the tunnel surface features. The method specifically comprises the following substeps:
step 6.1, extracting pixel points of the tunnel surface features in the tunnel surface image, calculating space coordinates of the tunnel surface features in a coordinate system of a left target camera of a binocular camera according to a binocular ranging principle, substituting corresponding first distance data into the relational expression of the correction parameters and the distances obtained in the step S2 to obtain correction parameters, and calculating the corrected space coordinates; in the embodiment, the image recognition technology is adopted to extract the tunnel surface characteristics such as cracks and water leakage, and the method has the advantages of high efficiency, high precision and the like.
6.2, restoring the spatial three-dimensional information of the surface characteristics of the tunnel according to the corrected spatial coordinates in the step 6.1;
and 6.3, sequentially splicing the tunnel surface images by using an image splicing technology, and marking the tunnel surface characteristics on the spliced tunnel surface images by combining an image recognition technology according to the spatial three-dimensional information in the step 6.2.
In the embodiment, according to the corrected space coordinates, the image splicing technology and the image recognition technology are combined, the tunnel three-dimensional model can be reconstructed, the method has the advantage of intuition, the positions of the tunnel surface features such as cracks and water leakage can be further positioned, the geometrical information such as the sizes of the cracks and the areas of the water leakage can be calculated, and the method can be used for rapidly and effectively assisting detection personnel in positioning and recognizing the tunnel surface features.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like that fall within the spirit and principle of the present invention are intended to be included therein.

Claims (8)

1. A tunnel surface feature detection device, comprising:
the mobile detection platform is used for providing motion along the tunnel direction;
the annular array system is arranged on the upper part of the mobile detection platform and consists of a plurality of first image distance acquisition units, each first image distance acquisition unit consists of a first binocular camera and a first laser ranging sensor, the first binocular camera is used for acquiring images on the surface of the tunnel, and the first laser ranging sensor is used for acquiring first distance data from the first laser ranging sensor to the surface of the tunnel;
the positioning system is arranged at the bottom of the mobile detection platform and consists of a second image distance acquisition unit, the second image distance acquisition unit consists of a second binocular camera and a second laser ranging sensor, the second binocular camera is used for acquiring track images, and the second laser ranging sensor is used for acquiring second distance data from the second laser ranging sensor to a track;
the tunnel marker consists of a light reflecting sheet and an electronic identifier, is arranged on the lining surface near the vault, the arch shoulder and the arch foot of the tunnel, and is used for assisting in correcting mileage and acquiring a convergence deformation value of the tunnel;
the terminal is used for acquiring the relative position relation between the cameras in the annular array system and the positioning system and the laser ranging sensor; performing parameter correction on all binocular cameras in the annular array system and the positioning system to obtain correction parameters in the depth direction, drawing a relation curve of the correction parameters and the distance, and fitting a relation between the correction parameters and the distance; controlling the mobile detection platform to enter the tunnel, controlling the annular array system and the positioning system to synchronously acquire images, and receiving a tunnel surface image, first distance data, a track image and second distance data; calculating the position relation between the mobile detection platform and the track center and the mileage of the mobile detection platform entering the tunnel according to the track image and the second distance data; acquiring and identifying tunnel markers according to the tunnel surface image and the first distance data, acquiring the position and mileage information associated with the electronic markers, correcting the mileage, calculating the space coordinate of each tunnel marker, and associating the space coordinate with the electronic markers; and comparing and calculating the space coordinate information associated with the same tunnel marker under different measurement times to obtain a tunnel convergence deformation value, and identifying and positioning the surface characteristics of the tunnel.
2. A tunnel surface feature detection method implemented in the tunnel surface feature detection device of claim 1, the method comprising:
s1, acquiring a relative position relation between a camera and a laser ranging sensor in an annular array system and a positioning system;
s2, performing parameter correction on all binocular cameras in the annular array system and the positioning system to obtain correction parameters in the depth direction, drawing a relation curve of the correction parameters and the distance, and fitting a relation between the correction parameters and the distance;
s3, controlling the mobile detection platform to enter the tunnel, controlling the annular array system and the positioning system to synchronously acquire images, and receiving a tunnel surface image, first distance data, a track image and second distance data;
s4, calculating and correcting the position relation between the mobile detection platform and the track center and the mileage of the mobile detection platform entering the tunnel according to the track image and the second distance data by combining the correction parameter and the distance relational expression obtained in the step S2;
s5, acquiring and identifying the tunnel markers according to the tunnel surface image, acquiring the position and mileage information associated with the electronic markers, correcting the mileage in the step S4, calculating and correcting the space coordinates of each tunnel marker according to the binocular distance measurement principle and the first distance data by combining the correction parameter and distance relation obtained in the step S2, and associating the space coordinates with the electronic markers; comparing and calculating the space coordinate information associated with the same tunnel marker under different measurement times to obtain a tunnel convergence deformation value;
and S6, according to the tunnel surface image and the first distance data, combining the relational expression of the correction parameters and the distance obtained in the step S2, and identifying and positioning the tunnel surface features by adopting an image identification technology, an image splicing technology and a binocular distance measuring principle to finish the detection of the tunnel surface features.
3. The method according to claim 2, wherein the relative position relationship in step S1 includes: the relative position relationship between each group of binocular cameras in the annular array system and the positioning system and the relative position relationship between each group of binocular cameras and the corresponding laser ranging sensors.
4. The method according to claim 2, wherein the relative position relationship in step S1 is obtained by camera calibration.
5. The method according to claim 2, wherein the step S2 specifically includes:
step 2.1, the manual calibration plate is arranged at a preset distance from the binocular camera, so that the laser beams emitted by the laser ranging sensor are positioned on the manual calibration plate, the binocular camera can collect images of the manual calibration plate, the distance data L of the laser ranging sensor is read, the images are collected, and the pixel coordinates (u) where the laser spots are located are respectively extracted from the images collected by the binocular camera1，v1) And (u)2，v2)；
Step 2.2, according to the binocular ranging principle, the following formula is obtained:
Figure FDA0002692642700000021
in the formula (x)c1，yc1，zc1) Represents the space coordinate of the laser spot under the coordinate system of the binocular camera left target, (x)c2，yc2，zc2) The space coordinate of the laser spot in the coordinate system of the binocular camera right target is shown, and the (x) is obtained by solving the equation systemc1，yc1，zc1)；
And 2.3, obtaining the following data according to the position relation between the left eye of the binocular camera and the laser ranging sensor and the distance data L of the laser ranging sensor:
Figure FDA0002692642700000031
in the formula (x)c1′，yc1′，zc1') denotes the spatial coordinates of the laser spot in the camera coordinate system of the binocular camera left eye, (x)0，y0，z0) The space coordinates of the laser ranging sensor under the coordinate system of the binocular camera left target are represented, and (i, j, k) the unit direction vector of the light beam emitted by the laser ranging sensor under the coordinate system of the binocular camera left target is represented;
introducing correction parameters
Figure FDA0002692642700000032
Figure FDA0002692642700000033
Step 2.4, according to the actual engineering requirement, placing the manual calibration plate at different distances from the binocular camera, and repeating the steps 2.1-2.4 to obtain different zc1Correction factor in case of value
Figure FDA0002692642700000034
And plotting the values of
Figure FDA0002692642700000035
The relation curve graph is subjected to curve fitting to obtain
Figure FDA0002692642700000036
The fitting relation of (1).
6. The method according to claim 2, wherein the step S4 specifically includes:
step 4.1, calculating the position relation between the mobile detection platform and the track center:
extracting pixel points of the track central point in the track image acquired by the positioning system, and calculating the space coordinate (x) of the track central point under the coordinate system of the binocular camera left target camera according to the binocular range finding principlec，yc，zc) Substituting the corresponding second distance data into the relation between the correction parameter and the distance obtained in step S2 to obtain the correction parameter
Figure FDA0002692642700000037
And calculating corrected space coordinates
Figure FDA0002692642700000038
Step 4.2, calculating the mileage of the mobile detection platform entering the tunnel:
along with the movement of the mobile detection platform, the setting system collects an image pair p at the position where the mobile detection platform moves to the position iiExtracting the image pair pi+1And piRespectively calculating the space coordinates (x) of the repeated point under the coordinate system of the left target camera of the binocular camera when the mobile detection platform moves to the position i +1 and the position i according to the principle of binocular range findingi+1，yi+1，zi+1) And (x)i，yi，zi) Substituting the corresponding second distance data into the relation between the correction parameter and the distance obtained in step S2 to obtain the correction parameter
Figure FDA0002692642700000039
And
Figure FDA00026926427000000310
obtaining corrected space coordinates
Figure FDA00026926427000000311
And
Figure FDA00026926427000000312
and further the determination of the moving mileage of the mobile detection platform is realized.
7. The method according to claim 2, wherein the step S5 specifically includes:
step 5.1, pasting tunnel markers on the lining surfaces near the tunnel vault, the arch shoulder and the arch foot of the important road section of the tunnel, and recording position and mileage information in the electronic identification;
step 5.2, when the images collected by the annular array system on the mobile detection platform contain the tunnel marker, scanning the electronic marker, reading the position and the mileage information, and calibrating the mileage calculated in the step S4;
step 5.3, identifying and extracting the positions of the reflectors in the tunnel marker on the image, combining the relative position relationship among each group of binocular cameras in the annular array system according to a binocular distance measurement principle, substituting the corresponding first distance data into the relational expression between the correction parameters and the distances obtained in the step S2 to obtain correction parameters, further calculating the space coordinates of each reflector after correction, and associating the space coordinates with the corresponding electronic identification information;
and 5.4, comparing and calculating the space coordinate information associated with the same tunnel marker under different measurement times to obtain a tunnel convergence deformation value.
8. The method according to claim 2, wherein the step S6 specifically includes:
step 6.1, extracting pixel points of the tunnel surface features in the tunnel surface image, calculating space coordinates of the tunnel surface features in a coordinate system of a left target camera of a binocular camera according to a binocular ranging principle, substituting corresponding first distance data into the relational expression of the correction parameters and the distances obtained in the step S2 to obtain correction parameters, and calculating the corrected space coordinates;
6.2, restoring the spatial three-dimensional information of the surface characteristics of the tunnel according to the corrected spatial coordinates in the step 6.1;
and 6.3, sequentially splicing the tunnel surface images by using an image splicing technology, and marking the tunnel surface characteristics on the spliced tunnel surface images by combining an image recognition technology according to the spatial three-dimensional information in the step 6.2.
CN202010996039.9A 2020-09-21 2020-09-21 Tunnel surface feature detection device and method Active CN112461122B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202010996039.9A CN112461122B (en) 2020-09-21 2020-09-21 Tunnel surface feature detection device and method

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202010996039.9A CN112461122B (en) 2020-09-21 2020-09-21 Tunnel surface feature detection device and method

Publications (2)

Publication Number Publication Date
CN112461122A true CN112461122A (en) 2021-03-09
CN112461122B CN112461122B (en) 2022-04-19

Family

ID=74833702

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202010996039.9A Active CN112461122B (en) 2020-09-21 2020-09-21 Tunnel surface feature detection device and method

Country Status (1)

Country Link
CN (1) CN112461122B (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN115035060A (en) * 2022-06-07 2022-09-09 贵州聚原数技术开发有限公司 Tunnel wall deformation detection method based on computer image recognition
CN115127516A (en) * 2022-06-27 2022-09-30 长安大学 Multifunctional tunnel detection vehicle based on passenger car chassis
WO2023178837A1 (en) * 2022-03-25 2023-09-28 贵州省交通规划勘察设计研究院股份有限公司 Automatic tunnel monitoring and measuring device and method based on fixed-point itinerant measurement

Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080027591A1 (en) * 2006-07-14 2008-01-31 Scott Lenser Method and system for controlling a remote vehicle
CN102175251A (en) * 2011-03-25 2011-09-07 江南大学 Binocular intelligent navigation system
CN103697966A (en) * 2013-11-27 2014-04-02 浙江大学 Device and method for measuring height of micro-amplitude liquid surface wave in real time
US20140125801A1 (en) * 2012-03-16 2014-05-08 Tongji University On-line tunnel deformation monitoring system based on image analysis and its application
CN105841687A (en) * 2015-01-14 2016-08-10 上海智乘网络科技有限公司 Indoor location method and indoor location system
CN106152950A (en) * 2016-07-29 2016-11-23 上海岩土工程勘察设计研究院有限公司 A kind of based on lining section geometric properties motion scan data mileage localization method
CN205898143U (en) * 2016-07-20 2017-01-18 山东鲁能智能技术有限公司 Robot navigation system based on machine vision and laser sensor fuse
CN206291859U (en) * 2016-12-12 2017-06-30 浙江大学 A kind of laser ranging railway tunnel based on gyroscope positioning detects car
CN108267096A (en) * 2017-12-25 2018-07-10 中铁科学技术开发公司 Railway tunnel lining surface disease rapid detection system
CN110487195A (en) * 2019-08-06 2019-11-22 广州市奥特创通测控技术有限公司 Vehicle-mounted tunnel detection method and device based on direction linear array technology
CN110568447A (en) * 2019-07-29 2019-12-13 广东星舆科技有限公司 Visual positioning method, device and computer readable medium

Patent Citations (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20080027591A1 (en) * 2006-07-14 2008-01-31 Scott Lenser Method and system for controlling a remote vehicle
CN102175251A (en) * 2011-03-25 2011-09-07 江南大学 Binocular intelligent navigation system
US20140125801A1 (en) * 2012-03-16 2014-05-08 Tongji University On-line tunnel deformation monitoring system based on image analysis and its application
CN103697966A (en) * 2013-11-27 2014-04-02 浙江大学 Device and method for measuring height of micro-amplitude liquid surface wave in real time
CN105841687A (en) * 2015-01-14 2016-08-10 上海智乘网络科技有限公司 Indoor location method and indoor location system
CN205898143U (en) * 2016-07-20 2017-01-18 山东鲁能智能技术有限公司 Robot navigation system based on machine vision and laser sensor fuse
CN106152950A (en) * 2016-07-29 2016-11-23 上海岩土工程勘察设计研究院有限公司 A kind of based on lining section geometric properties motion scan data mileage localization method
CN206291859U (en) * 2016-12-12 2017-06-30 浙江大学 A kind of laser ranging railway tunnel based on gyroscope positioning detects car
CN108267096A (en) * 2017-12-25 2018-07-10 中铁科学技术开发公司 Railway tunnel lining surface disease rapid detection system
CN110568447A (en) * 2019-07-29 2019-12-13 广东星舆科技有限公司 Visual positioning method, device and computer readable medium
CN110487195A (en) * 2019-08-06 2019-11-22 广州市奥特创通测控技术有限公司 Vehicle-mounted tunnel detection method and device based on direction linear array technology

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
WANG J.: "The New Austrian Tunnelling Method", 《SPRING BERLIN HEIDELBERG》 *
李华: "基于双目视觉及激光测距的隧道变形监测系统", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *

Cited By (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023178837A1 (en) * 2022-03-25 2023-09-28 贵州省交通规划勘察设计研究院股份有限公司 Automatic tunnel monitoring and measuring device and method based on fixed-point itinerant measurement
CN115035060A (en) * 2022-06-07 2022-09-09 贵州聚原数技术开发有限公司 Tunnel wall deformation detection method based on computer image recognition
CN115127516A (en) * 2022-06-27 2022-09-30 长安大学 Multifunctional tunnel detection vehicle based on passenger car chassis
CN115127516B (en) * 2022-06-27 2024-02-02 长安大学 Multifunctional tunnel detection vehicle based on chassis of passenger car

Also Published As

Publication number Publication date
CN112461122B (en) 2022-04-19

Similar Documents

Publication Publication Date Title
CN112461122B (en) Tunnel surface feature detection device and method
US11551341B2 (en) Method and device for automatically drawing structural cracks and precisely measuring widths thereof
CN111505606B (en) Method and device for calibrating relative pose of multi-camera and laser radar system
CN111931565B (en) Autonomous inspection and hot spot identification method and system based on photovoltaic power station UAV
CN109655040B (en) Side slope displacement monitoring method based on unmanned aerial vehicle targeting technology
CN110031829B (en) Target accurate distance measurement method based on monocular vision
CN108562250B (en) Keyboard keycap flatness rapid measurement method and device based on structured light imaging
CN112906694A (en) Reading correction system and method for inclined pointer instrument image of transformer substation
CN103186892B (en) Aerial Images is utilized to generate the method and system of equal proportion outdoor scene scene photo
JP2008014940A (en) Camera calibration method for camera measurement of planar subject and measuring device applying same
KR20130004746A (en) Method for field survey of digital mapping road layers using vehicle mobile mapping system
CN114460093B (en) Aeroengine defect detection method and system
CN110849368B (en) High-precision rapid positioning device and method in tunnel
CN113592961B (en) Point cloud splicing method based on precision control field and point cloud feature similarity
CN115575407B (en) Detection method applied to track and tunnel
CN114511620B (en) Structure displacement monitoring method based on Mask R-CNN
CN114782342B (en) Urban hardware facility defect detection method and device
CN115205397A (en) Vehicle space-time information identification method based on computer vision and pose estimation
CN115389516A (en) Pavement disease de-weighting method based on high-precision positioning and deep neural network
CN115409691A (en) Bimodal learning slope risk detection method integrating laser ranging and monitoring image
US20210233276A1 (en) Imaging system
CN113989513A (en) Method for recognizing reading of square pointer type instrument
CN112325791A (en) Road surface structure depth testing device based on photogrammetry technology and testing method thereof
US11953310B2 (en) Method for measuring gap and flush of vehicle parts and measuring tunnel
CN116481460B (en) Apparent pit defect size detection method based on three-dimensional reconstruction model

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant