CN114166180A - Tunnel multi-section visual detection system and self-adaptive adjustment method - Google Patents
Tunnel multi-section visual detection system and self-adaptive adjustment method Download PDFInfo
- Publication number
- CN114166180A CN114166180A CN202111482530.0A CN202111482530A CN114166180A CN 114166180 A CN114166180 A CN 114166180A CN 202111482530 A CN202111482530 A CN 202111482530A CN 114166180 A CN114166180 A CN 114166180A
- Authority
- CN
- China
- Prior art keywords
- aperture
- industrial
- tunnel
- focal length
- recording
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 66
- 238000000034 method Methods 0.000 title claims abstract description 47
- 230000000007 visual effect Effects 0.000 title claims abstract description 39
- 238000003384 imaging method Methods 0.000 claims abstract description 56
- 230000001502 supplementing effect Effects 0.000 claims abstract description 10
- 230000008054 signal transmission Effects 0.000 claims abstract description 4
- 238000004364 calculation method Methods 0.000 claims description 12
- 230000003044 adaptive effect Effects 0.000 claims description 7
- 230000001360 synchronised effect Effects 0.000 claims description 6
- 230000000694 effects Effects 0.000 claims description 5
- 238000009434 installation Methods 0.000 claims description 4
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 230000003247 decreasing effect Effects 0.000 claims description 3
- 238000011179 visual inspection Methods 0.000 claims 6
- 238000007689 inspection Methods 0.000 description 5
- 241001270131 Agaricus moelleri Species 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000013589 supplement Substances 0.000 description 2
- 206010045178 Tunnel vision Diseases 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000013480 data collection Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01C—MEASURING DISTANCES, LEVELS OR BEARINGS; SURVEYING; NAVIGATION; GYROSCOPIC INSTRUMENTS; PHOTOGRAMMETRY OR VIDEOGRAMMETRY
- G01C7/00—Tracing profiles
- G01C7/06—Tracing profiles of cavities, e.g. tunnels
Landscapes
- Engineering & Computer Science (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Studio Devices (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The invention relates to a tunnel multi-section visual detection system and a self-adaptive adjustment method. The main technical problems that the existing tunnel detection equipment cannot adapt to different tunnel sections, has high technical requirement and is not intelligent in detection and the like are solved. The system comprises a visual detection device, a mobile platform and an automatic imaging range adjusting system, wherein the visual detection device is arranged at one end of the mobile platform and comprises an industrial camera, a light supplementing device, a laser scanner and a visual acquisition frame, and the industrial camera, the light supplementing device and the laser scanner are arranged on the visual acquisition frame at intervals; the automatic imaging range adjusting system is respectively connected with the visual detection device and the laser scanner in a signal transmission mode, tunnel profile information acquired by the visual detection device and the laser scanner is acquired, focal lengths of different industrial cameras under the current profile are calculated, image gray scale is combined, exposure time and aperture are automatically adjusted, calculated data are stored, preset positions are set, and full-section detection rapid adjustment of different profiles is achieved.
Description
Technical Field
The invention relates to the field of tunnel section visual detection, in particular to a tunnel multi-section visual detection system and a self-adaptive adjusting method, which are applied to the field of tunnel structure detection.
Background
With the rapid development of domestic highway and subway tunnels, the operation scale of the tunnels is larger and larger. In the process of building and operating the tunnel, the tunnel is influenced by the load of the ground and surrounding buildings, the disturbance of soil body and the like, and the defects of cracks, water leakage, peeling, stripping and the like of the tunnel structure occur occasionally, so that the operation safety of the tunnel is influenced. Aiming at the problems of low manual detection efficiency, high cost and the like, a tunnel rapid detection system based on machine vision is developed and carried on a vehicle platform to rapidly collect apparent diseases of a tunnel structure.
The tunnel structure rapid detection based on machine vision is developed rapidly, and a plurality of methods exist in the market. Patent ZL 201721445535.5 discloses a tunnel vision detection system night, carries on the module including detecting car, CCD camera and equipment, has improved formation of image effect and detection device's detection efficiency. CN202110815077.4 discloses a new method of tunnel appearance influence data acquisition and analysis, installs 360 panorama camera in tunnel inspection car, through the wireless control tunnel inspection car at the uniform velocity go to carry out data collection to the tunnel inside, store in the industrial personal computer, carry out the preliminary treatment in the industrial personal computer, send to remote computer wirelessly. CN201720828598.2 discloses a tunnel intellectual detection system car, including fixed bearing system, vision collection system, speed of a motor vehicle measurement system, electric control system and safety warning system, can be under the circumstances of normal driving, the information on vehicle and tunnel lining surface is gathered in real time. The visual detection systems contained in the tunnel self-adaptive imaging system cannot realize self-adaptation to different tunnel profile types, and the problems of incomplete shooting and unclear imaging are likely to exist.
In summary, there is a need for a vision inspection system that is adaptive to automatic adjustment of various tunnel sections, imaging ranges and effects.
Disclosure of Invention
The invention aims to design a tunnel multi-section visual detection system and an adaptive adjustment method, and mainly solves the technical problems that the existing inspection equipment cannot automatically adapt to different tunnel sections, the focal length adjustment operation is complex, the requirement on personnel skills is high, and the like.
The purpose of the invention can be realized by the following technical scheme: a tunnel multi-section visual detection system,
the system comprises a vision detection device, a mobile platform, an automatic imaging range adjusting system and an electric cabinet, wherein the electric cabinet is arranged in the middle of the mobile platform, the vision detection device is arranged at the end part of the mobile platform and comprises a plurality of industrial cameras, a plurality of light supplementing devices, a laser scanner and a vision acquisition frame, the industrial cameras and the light supplementing devices are arranged on the vision acquisition frame at intervals and used for acquiring apparent images of tunnel structures with different profile sections, and the laser scanner is arranged at the other side of the mobile platform; the detection speed of the system can reach more than 80 km/h. The industrial camera is provided with a zoom lens, and the zoom lens is provided with an automatic lens adjusting device. The industrial camera is an industrial linear array camera or an industrial area array camera.
The automatic imaging range adjusting system is respectively connected with the visual detection device and the laser scanner in a signal transmission manner, tunnel profile information acquired by the visual detection device and the laser scanner is acquired, focal lengths of different cameras under the current profile are calculated, image gray scale is combined, exposure time and aperture are automatically adjusted, calculated data are stored, preset positions are set, and quick adjustment of full-section detection of different profiles is achieved.
The industrial camera is arranged on the visual acquisition frame and is parallel to the section of the tunnel, and multi-camera synchronous shooting is realized through the synchronous control unit; the automatic lens adjusting device is used for adjusting the focal length, the aperture and the exposure time; the light supplementing device and the industrial camera are arranged on the same plane and are alternately arranged; the laser scanner is arranged on the other side of the mobile platform, the scanning range of the laser scanner is not lower than 270 degrees, the scanning frequency is not lower than 50Hz, the system error is not more than 5mm, and the scanning range is not blocked.
The installation position of the visual detection device is set according to the standard tunnel detection index requirements, the starting point of the coverage range is marked as Mstr, the end point position is marked as Mend, the number of the industrial cameras covering the starting point position is set to be 1, the number of the industrial cameras at the end point position is set to be n, the number of the industrial cameras is marked as n, the focal length of the industrial cameras is marked as f, and f belongs to { f1, f2.. The distance between the image center and the camera imaging center is recorded as Dg, Dg belongs to { Dg1, Dg2.... Dgn }, the overlapping distance between adjacent industrial cameras is recorded as Dg, and the Dg is generally set as 30 mm; selecting a focal length range of the zoom lens as fminmm-fmaxmm; the aperture parameters of each industrial camera are recorded as F, and F belongs to { F1, F2... Fn }; at the kth time, each industrial camera acquires an image marked as Img, Img ∈ { Img { k,1}, Img { k, 2}.... Img { k, n } }.
A self-adaptive adjusting method of a tunnel multi-section visual detection system comprises an automatic focal length adjusting method and an automatic exposure time and aperture adjusting method, wherein the automatic focal length adjusting method is combined with laser scanning data to adjust focal length to ensure that the detected tunnel section can be covered; the automatic exposure time and aperture adjusting method is combined with the gray scale and definition of the shot image to adjust the exposure time and the aperture and ensure the best imaging effect.
The automatic focus adjusting method comprises the following 5 steps:
(1) acquiring laser scanning data of the current tunnel profile, removing abnormal point data, and recording as S;
(2) converting the position of the industrial camera into a laser scanning coordinate system, calculating the circumferential imaging range of each industrial camera, recording the circumferential imaging range as Li, recording the circumferential imaging range between the imaging ranges of each industrial camera as Pi, recording the imaging overlapping distance Di of adjacent industrial cameras, recording the distance between the image center and the imaging center of the industrial camera as Di, and recording the farthest imaging distance as Dmaxi, closest imaging distance is recorded as Dmini, wherein i ∈ {1, 2.. n };
(3) when the start position Mstr is not contained within P1 or the end position Mend is not contained within Pn, the focal length f1 or fn is decreased by a step size of dftmm until Mstr is contained within P1 and Mend is contained within Pn, where dft is typically set to 1 mm; when the focal lengths of the industrial camera 1 and the industrial camera n are determined, keeping the focal lengths fixed;
(4) adjusting the focal lengths of other industrial cameras, specifically comprising the following steps:
(a) according to the imaging principle, the focal distance fci at the distance Di is calculated, and in order to keep a certain setting fi ═ fci + q, q is generally set to 5, the calculation is disclosed as follows:
di is the distance from the center of the industrial camera to the center of the imaging range, ui is the length of the imaging chip of the current industrial camera, and Hi is the imaging range. Generally, the imaging range of the industrial camera is divided into length and width directions, and the directions of ui and Hi are kept consistent.
(b) If Di is less than Dgi and Di is less than dg, the focal length fi is reduced according to the step length of 0.5mm until Di is more than or equal to dg, wherein i belongs to {2,3.. n-1 };
(b) if Di is more than Dgi and Di is more than dg, the focal length fi is increased according to the step length of 0.5mm, the focal length adjustment frequency is recorded as m, if the m-1 th Di is more than or equal to dg, and the m-1 th Di is less than dg, the focal length of the m-1 th is taken as the adjusted focal length f of the current industrial cameraEi;
(5) Calculating the imaging precision of each industrial camera, and recording the imaging precision as Ai, wherein i belongs to {2,3.... n-1}, the maximum value is Amax, the minimum value is Amin, the industrial cameras corresponding to the cameras are numbered as Am and An, and if Amax is greater than 2 xAmin, the Am is taken as a reference, and the focal length f is taken as a referenceAmIncreasing according to the step length of 0.5mm, sequentially adjusting the focal lengths of other industrial cameras according to the step (4) until Amax is less than or equal to 2 multiplied by Amin, and if the calculation cannot be converged, setting the calculation frequency as it, which is generally set as 20; adjusting the definition of the current image by automatically adjusting the depth-of-field adjusting device; record the current focal length as fE,fE∈{fE1,fE2......fEn}。
The automatic exposure time and aperture adjusting method comprises the following 3 steps:
(1) in the continuous acquisition process, for the ith industrial camera, acquiring the kth detection image Img { k, i }, and acquiring the gray level average value of the current image by a two-time gray level calculation method, wherein the method comprises the following steps:
(a) calculating the gray average value of the image Img { k, i } and recording as Gg;
(b) acquiring coordinate points with gray values higher than Gmin and lower than Gmax in the image Img { k, i } and corresponding gray values, calculating a gray average value of the coordinate points and recording the gray average value as Ge; wherein Gmin is Gg × 0.3, Gmax is Gg × 2, and if Gmax > 220, Gmax is 220; meanwhile, the average value of the gray scales of the image target is Gd, which is generally 100.
(2) Using the relationship between the image gray level mean Ge and the exposure time T, F, the values of a1 and a2 are calculated as shown in the following equation:
acquiring two groups of data Ge1, T1, F1, Ge2, T2 and F2, and acquiring values of a1 and a2, wherein a1 and a2 are related to the industrial camera, and the values are calibrated and stored once and can be directly used without calibration.
(3) In the continuous acquisition process, the exposure time and the aperture value are continuously adjusted according to the gray value of the acquired image, and the adjustment method comprises the following steps:
acquiring the exposure time Tg and the aperture Fg of the current industrial camera, wherein the maximum value which can be set by the exposure time is the time required by the visual detection system to move 2 pixels and is recorded as Tgmax, and the maximum value which can be adjusted by the aperture is recorded as Fgmax;
a. if Ge is larger than or equal to Gd, keeping the aperture unchanged, calculating the exposure time according to the formula in the step (2), and recording the exposure time as TEi(ii) a If TEiIf Tgmax is greater than T, then TEiSetting Tgmax, calculating the aperture value according to the formula in the step (2), and recording the aperture value as FEiAdjusting the aperture of the industrial camera; simultaneously recording the parameter of the light source controller as LEi。
b. If Ge is less than Gd, the aperture is preferentially adjusted, and the aperture value is calculated according to the formula in the step (2) and is recorded as FEiIf F isEiFgmax, then FEiSet to Fgmax; adjusting the exposure time according to the step a and recording the exposure time as T when the aperture is adjusted to the maximum and still does not meet the requirementEi(ii) a If the requirement is still not met, the power of the light source can be adjusted according to the system, and meanwhile, the parameter of the light source controller is recorded as LEi。
c. Recording the current focal length as TE,TE∈{TE1,TE2......TEn}。
And recording the adjusted focal length, exposure time and aperture according to the highway section, the tunnel name, the uplink and the downlink and the detection time, and facilitating the direct parameter calling and setting during the next detection.
The invention has the beneficial effects that:
(1) the invention relates to a tunnel multi-section visual detection system which can reduce manual intervention, reduce the requirements on personnel and realize full-automatic switching and detection of different types of sections;
(2) the method is based on visual detection and laser scanning data, and combines the relationship among image brightness information, brightness and exposure time to quickly calculate camera adjustment parameters under different tunnel profiles;
(3) the technical scheme of the invention fixes the adjusted parameters and the tunnel information, can ensure that the parameters are directly called when the next detection operation is carried out, and does not need to be adjusted for many times.
Drawings
FIG. 1 is a schematic diagram of the structural topology of an embodiment of the present invention;
FIG. 2 is a schematic diagram of an apparatus installation layout of an adaptive cross-sectional vision inspection system according to an embodiment of the present invention;
fig. 3 is a schematic view of a camera and a lens structure for automatically adjusting parameters according to an embodiment of the present invention.
In the figure: 1-an industrial linear array camera, 2-a zoom lens, 3-a lens automatic regulating device, 4-a light supplementing device, 5-a vision collecting frame, 6-an electric cabinet, 7-a laser scanner and 8-a moving platform.
Detailed Description
The invention is described in detail below with reference to the figures and the specific embodiments.
As shown in fig. 1, 2, and 3, a tunnel multi-section visual detection system is composed of a visual detection device, a mobile platform 8, and an electrical cabinet 6, wherein the electrical cabinet 6 (schneider APC AR3100 is selected and may be customized according to actual items) is installed in the middle of the mobile platform 8, the visual detection device is installed at an end of the mobile platform and includes a plurality of industrial line cameras 1, a plurality of light supplement devices 4, a laser scanner 7, and a visual collection frame 5, the industrial line cameras 1 and the light supplement devices 4 are installed on the visual collection frame 5 at intervals for obtaining tunnel structure apparent images of different profile sections, and the laser scanner 7 is installed at the other side of the mobile platform 8; the detection speed of the system can reach more than 80 km/h. The industrial linear array camera 1 is provided with a zoom lens 2, and the zoom lens 2 is provided with an automatic lens adjusting device 3.
The automatic imaging range adjusting system is respectively connected with the visual detection device and the laser scanner 7 in a signal transmission mode, tunnel profile information acquired by the visual detection device and the laser scanner is acquired, focal lengths of different cameras under the current profile are calculated, image gray scale is combined, exposure time and aperture are automatically adjusted, calculated data are stored, preset positions are set, and full-section detection rapid adjustment of different profiles is achieved.
A tunnel multi-section visual detection system, industrial line camera 1 chooses Teledyne DALSA line camera, the maximum line frequency can reach 280kHz, the resolution is 8192 x 4, its pixel size is 5 μm; the light supplementing device selects a 808nm portable laser light source with strong vision, the minimum laser line width covers the range of 2-12 mm, and the light source angle is 90 degrees.
The industrial linear array camera 1 is arranged on the visual acquisition frame 5, is parallel to the section of the tunnel, and realizes multi-camera synchronous shooting through a synchronous control unit; the automatic lens adjusting device 3 is used for adjusting focal length, aperture and exposure time; the light supplementing device 4 and the industrial linear array camera 1 are arranged on the same plane and are alternately arranged; the scanning range of the laser scanner 7 is not less than 270 degrees, the scanning frequency is not less than 50Hz, the system error is not more than 5mm, and the scanning range is not shielded. The laser scanner 7 can select Z + F PROFILER9012, the scanning range is 360 degrees, the scanning frequency is selectable from 50Hz, 100Hz and 200Hz, the ranging resolution is 0.1mm, and the type of the laser is 1 level.
The installation position of the visual detection device is set according to the standard tunnel detection index requirements, the starting point of the coverage range is marked as Mstr, the end point position is marked as Mend, the number of the industrial linear array cameras covering the starting point position is set to be 1, the number of the industrial linear array cameras at the end point position is set to be n, the number of the industrial linear array cameras is marked as n, the focal length of the industrial linear array cameras is marked as f, and f belongs to { f1, f2.. The distance between the image center and the camera imaging center is recorded as Dg, Dg belongs to { Dg1, Dg2.... Dgn }, the overlapping distance between adjacent industrial linear array cameras is recorded as Dg, and the Dg is generally set as 30 mm; selecting a focal length range of the zoom lens as fminmm-fmaxmm; the aperture parameter of each industrial linear array camera is recorded as F, and F belongs to { F1, F2... Fn }; at the kth time, an obtained image of each industrial linear array camera is recorded as Img, wherein the Img belongs to { Img { k,1}, and Img { k, 2}.... Img { k, n } }.
In the system shown in fig. 2, the number of the industrial line cameras is 6, the focal length range of the zoom lens is 16 mm-96 mm, and a subway shield tunnel with a diameter of 5.2 meters is taken as an example. In the implementation process, in order to ensure an imaging lens, each industrial linear array camera can be provided with a telescopic structure, so that the requirement of improving the precision to the maximum extent is met. Under the premise that the image acquisition precision is set to be 0.288mm, the focal lengths of different industrial linear cameras are 55mm, 55mm and 55mm, the distances between the image center and the camera imaging center are 2257.8mm, 2257.8mm, 2257.8mm, 2257.8mm, 2257.8mm and 2257.8mm respectively, the aperture parameters are F5.6, F5.6 and F5.6, and the overlapping areas between adjacent industrial linear cameras are 312mm, 402mm, 312mm and 312mm in sequence.
A self-adaptive adjusting method of a tunnel multi-section visual detection system comprises an automatic focal length adjusting method and an automatic exposure time and aperture adjusting method, wherein the automatic focal length adjusting method is combined with laser scanning data to adjust focal length to ensure that the detected tunnel section can be covered; the automatic exposure time and aperture adjusting method is combined with the gray scale and definition of the shot image to adjust the exposure time and the aperture and ensure the best imaging effect.
The automatic focus adjusting method comprises the following 5 steps:
(1) acquiring laser scanning data of the current tunnel profile, removing abnormal point data, and recording as S;
(2) converting the camera position to a laser scanning coordinate system, calculating the annular imaging range of each industrial linear array camera, recording the annular imaging range as Li, recording the annular imaging range between each industrial linear array camera as Pi, and recording the imaging overlapping distance d of adjacent industrial linear array camerasi, recording the distance between the image center and the imaging center of the industrial linear array camera as Di, and recording the farthest imaging distance as Dmaxi, closest imaging distance is recorded as Dmini, wherein i ∈ {1, 2.. n };
(3) when the start position Mstr is not contained within P1 or the end position Mend is not contained within Pn, the focal length f1 or fn is decreased by a step size of dftmm until Mstr is contained within P1 and Mend is contained within Pn, where dft is typically set to 1 mm; when the focal lengths of the industrial linear array camera 1 and the industrial linear array camera n are determined, keeping the focal lengths fixed;
(4) adjusting the focal lengths of other industrial linear array cameras, which comprises the following specific steps:
(a) according to the imaging principle, the focal distance fci at the distance Di is calculated, and in order to keep a certain setting fi ═ fci + q, q is generally set to 5, the calculation is disclosed as follows:
di is the distance from the center of the industrial linear array camera to the center of an imaging range, ui is the length of an imaging chip of the current industrial linear array camera, and Hi is the imaging range. Generally, the imaging range of an industrial line camera is divided into length and width directions, and the directions of ui and Hi are kept consistent.
(b) If Di is less than Dgi and Di is less than dg, the focal length fi is reduced according to the step length of 0.5mm until Di is more than or equal to dg, wherein i belongs to {2,3.. n-1 };
(b) if Di is more than Dgi and Di is more than dg, the focal length fi is increased according to the step length of 0.5mm, the focal length adjustment frequency is recorded as m, if the m-1 th Di is more than or equal to dg, and the m-1 th Di is less than dg, the focal length of the m-1 th is taken as the adjusted focal length f of the current industrial linear array cameraEi;
(5) Calculating the imaging precision of each industrial linear array camera, and recording the imaging precision as Ai, wherein i belongs to {2,3.... n-1}, the maximum value is Amax, the minimum value is Amin, the serial numbers of the corresponding industrial linear array cameras are Am and An, if Amax is more than 2 multiplied by Amin, the Am is taken as a reference, and the focal length f is taken as the referenceAmIncreasing according to the step length of 0.5mm, and sequentially adjusting other industries according to the step (4)The focal length of the linear array camera is set to 20 when Amax is less than or equal to 2 multiplied by Amin and the calculation times are Ite if the calculation can not be converged; adjusting the definition of the current image by automatically adjusting the depth-of-field adjusting device; record the current focal length as fE,fE∈{fE1,fE2......fEn}。
When the tunnel profile is changed into a horseshoe-shaped tunnel, the imaging precision is respectively 0.308mm, 0.309mm, 0.308mm and 0.308mm, the focal length is 58mm, 55mm, 56mm, 55mm and 58mm, the distance between the image center and the imaging center of the industrial linear array camera is 2559.1mm, 2429.7mm, 2469.4mm, 2469.5mm, 2429.7mm and 2559.1mm, the aperture parameters are F5.6, F2.8, F5.6 and F5.6, and the overlapping area between adjacent industrial linear array cameras is sequentially 64mm, 336mm, 421mm, 336mm and 64 mm.
The automatic exposure time and aperture adjusting method comprises the following 3 steps:
(1) in the continuous acquisition process, for the ith industrial linear array camera, acquiring the kth detection image Img { k, i }, and acquiring the gray level average value of the current image by a two-time gray level calculation method, wherein the method comprises the following steps:
(a) calculating the gray average value of the image Img { k, i } and recording as Gg;
(b) acquiring coordinate points with gray values higher than Gmin and lower than Gmax in the image Img { k, i } and corresponding gray values, calculating a gray average value of the coordinate points and recording the gray average value as Ge; wherein Gmin is Gg × 0.3, Gmax is Gg × 2, and if Gmax > 220, Gmax is 220; meanwhile, the average value of the gray scales of the image target is Gd, which is generally 100.
(2) Using the relationship between the image gray level mean Ge and the exposure time T, F, the values of a1 and a2 are calculated as shown in the following equation:
acquiring two groups of data Ge1, T1, F1, Ge2, T2 and F2, and acquiring values of a1 and a2, wherein a1 and a2 are related to the industrial linear array camera, and the values are calibrated and stored once and can be directly used without calibration subsequently.
(3) In the continuous acquisition process, the exposure time and the aperture value are continuously adjusted according to the gray value of the acquired image, and the adjustment method comprises the following steps:
acquiring the exposure time Tg and the aperture Fg of the current industrial linear array camera, wherein the maximum value which can be set by the exposure time is the time required by the visual detection system to move 2 pixels and is recorded as Tgmax, and the maximum value which can be adjusted by the aperture is recorded as Fgmax;
a. if Ge is larger than or equal to Gd, keeping the aperture unchanged, calculating the exposure time according to the formula in the step (2), and recording the exposure time as TEi(ii) a If TEiIf Tgmax is greater than T, then TEiSetting Tgmax, calculating the aperture value according to the formula in the step (2), and recording the aperture value as FEiAdjusting the aperture of the industrial linear array camera; simultaneously recording the parameter of the light source controller as LEi。
b. If Ge is less than Gd, the aperture is preferentially adjusted, and the aperture value is calculated according to the formula in the step (2) and is recorded as FEiIf F isEiFgmax, then FEiSet to Fgmax; adjusting the exposure time according to the step a and recording the exposure time as T when the aperture is adjusted to the maximum and still does not meet the requirementEi(ii) a If the requirement is still not met, the power of the light source can be adjusted according to the system, and meanwhile, the parameter of the light source controller is recorded as LEi。
c. Recording the current focal length as TE,TE∈{TE1,TE2......TEn}。
And recording the adjusted focal length, exposure time and aperture according to the highway section, the tunnel name, the uplink and the downlink and the detection time, and facilitating the direct parameter calling and setting during the next detection.
The foregoing detailed description of the preferred embodiments of the invention has been presented. It should be understood that numerous modifications and variations could be devised by those skilled in the art in light of the present teachings without departing from the inventive concepts. Therefore, the technical solutions that can be obtained by a person skilled in the art through logic analysis, reasoning or limited experiments based on the prior art according to the concept of the present invention should be within the protection scope of the present invention as claimed in the claims.
Claims (9)
1. The utility model provides a many sections of tunnel visual inspection system which characterized in that: the system comprises a vision detection device, a mobile platform, an automatic imaging range adjusting system and an electric cabinet, wherein the electric cabinet is arranged in the middle of the mobile platform, the vision detection device is arranged at the end part of the mobile platform and comprises a plurality of industrial cameras, a plurality of light supplementing devices, a laser scanner and a vision acquisition frame, the industrial cameras and the light supplementing devices are arranged on the vision acquisition frame at intervals and used for acquiring apparent images of tunnel structures with different profile sections, and the laser scanner is arranged at the other side of the mobile platform; the automatic imaging range adjusting system is respectively connected with the visual detection device and the laser scanner in a signal transmission mode, tunnel profile information acquired by the visual detection device and the laser scanner is acquired, focal lengths of different industrial cameras under the current profile are calculated, image gray scale is combined, exposure time and aperture are automatically adjusted, calculated data are stored, preset positions are set, and full-section detection rapid adjustment of different profiles is achieved.
2. The tunnel multi-section visual inspection system of claim 1, wherein: the industrial camera is provided with a zoom lens, and the zoom lens is provided with an automatic lens adjusting device.
3. The tunnel multi-section visual inspection system of claim 1, wherein: the industrial cameras are mounted on the visual collection frame and parallel to the cross section of the tunnel, and multi-camera synchronous shooting is achieved through the synchronous control unit.
4. The tunnel multi-section visual inspection system of claim 1, wherein: the automatic lens adjusting device is used for adjusting the focal length, the aperture and the exposure time.
5. The tunnel multi-section visual inspection system of claim 1, wherein: the installation position of the visual detection device is set according to the standard tunnel detection index requirements, the starting point of the coverage range is marked as Mstr, the end point position is marked as Mend, the number of industrial cameras covering the starting point position is set to be 1, the number of industrial cameras at the end point position is set to be n, the number of the industrial cameras is marked as n, the focal length of the industrial cameras is marked as f, and f belongs to { f1, f2.. The distance between the image center and the imaging center of the industrial camera is recorded as Dg, Dg belongs to { Dg1, Dg2.... Dgn }, and the overlapping distance between adjacent industrial cameras is recorded as Dg; selecting a focal length range of the zoom lens as fminmm-fmaxmm; the aperture parameters of each industrial camera are recorded as F, and F belongs to { F1, F2... Fn }; and recording the acquired image as Img by each industrial linear array camera at the kth time.
6. The adaptive adjustment method of the tunnel multi-section visual inspection system as recited in claim 1, wherein: the method comprises an automatic focal length adjusting method and an automatic exposure time and aperture adjusting method, wherein the automatic focal length adjusting method is combined with laser scanning data, and the focal length is adjusted to ensure that the detected tunnel section can be covered; the automatic exposure time and aperture adjusting method is combined with the gray scale and definition of the shot image to adjust the exposure time and the aperture and ensure the best imaging effect.
7. The adaptive adjustment method according to claim 6, wherein: the automatic focal length adjusting method comprises the following 5 steps:
(1) acquiring laser scanning data of the current tunnel profile, removing abnormal point data, and recording as S;
(2) converting the position of the industrial camera into a laser scanning coordinate system, calculating the circumferential imaging range of each industrial camera, recording the circumferential imaging range as Li, recording the circumferential imaging range between the imaging ranges of each industrial camera as Pi, recording the imaging overlapping distance Di of adjacent industrial cameras, recording the distance between the image center and the imaging center of the industrial camera as Di, and recording the farthest imaging distance as Dmaxi, closest imaging distance is recorded as Dmini, wherein i ∈ {1, 2.. n };
(3) when the start position Mstr is not contained within P1 or the end position Mend is not contained within Pn, the focal length f1 or fn is decreased by a step size of dftmm until Mstr is contained within P1 and Mend is contained within Pn; when the focal lengths of the industrial camera 1 and the industrial camera n are determined, keeping the focal lengths fixed;
(4) adjusting the focal lengths of other industrial cameras, specifically comprising the following steps:
(a) according to the imaging principle, the focal distance fci at the distance Di is calculated, and in order to keep a certain setting fi ═ fci + q, the calculation is disclosed as follows:
di is the distance from the center of the industrial camera to the center of an imaging range, ui is the length of an imaging chip of the current industrial camera, and Hi is the imaging range; the imaging range of the industrial camera is divided into length and width directions, and the ui and Hi directions are kept consistent;
(b) if Di is less than Dgi and Di is less than dg, the focal length fi is reduced according to the step length of 0.5mm until Di is more than or equal to dg, wherein i belongs to {2,3.. n-1 };
(b) if Di is more than Dgi and Di is more than dg, the focal length fi is increased according to the step length of 0.5mm, the focal length adjustment frequency is recorded as m, if the m-1 th Di is more than or equal to dg, and the m-1 th Di is less than dg, the focal length of the m-1 th is taken as the adjusted focal length f of the current industrial cameraEi;
(5) Calculating the imaging precision of each industrial camera, and recording the imaging precision as Ai, wherein i belongs to {2,3.... n-1}, the maximum value is Amax, the minimum value is Amin, the industrial cameras corresponding to the cameras are numbered as Am and An, and if Amax is greater than 2 xAmin, the Am is taken as a reference, and the focal length f is taken as a referenceAmIncreasing according to the step length of 0.5mm, sequentially adjusting the focal lengths of other industrial cameras according to the step (4) until Amax is less than or equal to 2 multiplied by Amin, and if the calculation cannot be converged, setting the calculation frequency as it, which is generally set as 20; adjusting the definition of the current image by automatically adjusting the depth-of-field adjusting device; record the current focal length as fE,fE∈{fE1,fE2......fEn}。
8. The adaptive adjustment method according to claim 6, wherein: the automatic exposure time and aperture adjusting method comprises the following 3 steps:
(1) in the continuous acquisition process, for the ith industrial camera, acquiring the kth detection image Img { k, i }, and acquiring the gray level average value of the current image by a two-time gray level calculation method, wherein the method comprises the following steps:
(a) calculating the gray average value of the image Img { k, i } and recording as Gg;
(b) acquiring coordinate points with gray values higher than Gmin and lower than Gmax in the image Img { k, i } and corresponding gray values, calculating a gray average value of the coordinate points and recording the gray average value as Ge; wherein Gmin is Gg × 0.3, Gmax is Gg × 2, and if Gmax > 220, Gmax is 220; simultaneously setting the average value of the image target gray level as Gd;
(2) using the relationship between the image gray level mean Ge and the exposure time T, F, the values of a1 and a2 are calculated as shown in the following equation:
acquiring two groups of data Ge1, T1, F1, Ge2, T2 and F2, and acquiring values of a1 and a2, wherein a1 and a2 are related to the industrial camera, are calibrated and stored once, and can be directly used without calibration subsequently;
(3) in the continuous acquisition process, the exposure time and the aperture value are continuously adjusted according to the gray value of the acquired image, and the adjustment method comprises the following steps:
acquiring the exposure time Tg and the aperture Fg of the current industrial camera, wherein the maximum value which can be set by the exposure time is the time required by the visual detection system to move 2 pixels and is recorded as Tgmax, and the maximum value which can be adjusted by the aperture is recorded as Fgmax;
a. if Ge is larger than or equal to Gd, keeping the aperture unchanged, calculating the exposure time according to the formula in the step (2), and recording the exposure time as TEi(ii) a If TEiIf Tgmax is greater than T, then TEiSetting Tgmax, calculating the aperture value according to the formula in the step (2), and recording the aperture value as FEiAdjusting the aperture of the industrial camera; simultaneously recording the parameter of the light source controller as LEi;
b. If Ge is less than Gd, the aperture is preferentially adjusted according to the step (2)The formula (2) calculates the aperture value, which is marked as FEiIf F isEiFgmax, then FEiSet to Fgmax; adjusting the exposure time according to the step a and recording the exposure time as T when the aperture is adjusted to the maximum and still does not meet the requirementEi(ii) a If the requirement is still not met, the power of the light source can be adjusted according to the system, and meanwhile, the parameter of the light source controller is recorded as LEi。
c. Recording the current focal length as TE,TE∈{TE1,TE2......TEn}。
9. The adaptive adjustment method according to claim 6, wherein: and recording the adjusted focal length, exposure time and aperture according to the highway section, the tunnel name, the uplink and the downlink and the detection time, and facilitating the direct parameter calling and setting during the next detection.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111482530.0A CN114166180B (en) | 2021-12-07 | 2021-12-07 | Tunnel multi-section visual detection system and self-adaptive adjustment method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202111482530.0A CN114166180B (en) | 2021-12-07 | 2021-12-07 | Tunnel multi-section visual detection system and self-adaptive adjustment method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN114166180A true CN114166180A (en) | 2022-03-11 |
CN114166180B CN114166180B (en) | 2024-07-23 |
Family
ID=80483689
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202111482530.0A Active CN114166180B (en) | 2021-12-07 | 2021-12-07 | Tunnel multi-section visual detection system and self-adaptive adjustment method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN114166180B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114910048A (en) * | 2022-05-25 | 2022-08-16 | 中国十七冶集团有限公司 | Tunnel under-excavation automatic detector and detection method |
CN116358492A (en) * | 2023-06-01 | 2023-06-30 | 辽宁省交通规划设计院有限责任公司 | Tunnel intelligent detection device and method |
CN116437212A (en) * | 2023-04-12 | 2023-07-14 | 中铁隧道局集团有限公司 | Automatic zooming device and method for track type tunnel structure health information acquisition system |
CN116534070A (en) * | 2023-04-12 | 2023-08-04 | 中铁隧道局集团有限公司 | Quick mounting and dismounting carrying device for tunnel health information acquisition |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20080103820A (en) * | 2007-05-25 | 2008-11-28 | 한국철도기술연구원 | Hybrid tunnel scanning instrument |
KR20110008402A (en) * | 2009-07-20 | 2011-01-27 | 김수언 | Method of inspecting tunnel inner part damage by vision sensor system |
CN108593654A (en) * | 2018-03-28 | 2018-09-28 | 北京交通大学 | Tunnel image capturing system and method |
CN110111412A (en) * | 2019-04-08 | 2019-08-09 | 浙江省交通规划设计研究院有限公司 | A kind of acquisition methods of tunnel excavation face country rock point cloud model |
CN110346807A (en) * | 2019-06-21 | 2019-10-18 | 北京交通大学 | Tunneling data acquires device and method |
CN113504242A (en) * | 2021-07-19 | 2021-10-15 | 北京洞微科技发展有限公司 | New method for acquiring and analyzing tunnel apparent image data |
-
2021
- 2021-12-07 CN CN202111482530.0A patent/CN114166180B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
KR20080103820A (en) * | 2007-05-25 | 2008-11-28 | 한국철도기술연구원 | Hybrid tunnel scanning instrument |
KR20110008402A (en) * | 2009-07-20 | 2011-01-27 | 김수언 | Method of inspecting tunnel inner part damage by vision sensor system |
CN108593654A (en) * | 2018-03-28 | 2018-09-28 | 北京交通大学 | Tunnel image capturing system and method |
CN110111412A (en) * | 2019-04-08 | 2019-08-09 | 浙江省交通规划设计研究院有限公司 | A kind of acquisition methods of tunnel excavation face country rock point cloud model |
CN110346807A (en) * | 2019-06-21 | 2019-10-18 | 北京交通大学 | Tunneling data acquires device and method |
CN113504242A (en) * | 2021-07-19 | 2021-10-15 | 北京洞微科技发展有限公司 | New method for acquiring and analyzing tunnel apparent image data |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114910048A (en) * | 2022-05-25 | 2022-08-16 | 中国十七冶集团有限公司 | Tunnel under-excavation automatic detector and detection method |
CN116437212A (en) * | 2023-04-12 | 2023-07-14 | 中铁隧道局集团有限公司 | Automatic zooming device and method for track type tunnel structure health information acquisition system |
CN116534070A (en) * | 2023-04-12 | 2023-08-04 | 中铁隧道局集团有限公司 | Quick mounting and dismounting carrying device for tunnel health information acquisition |
CN116358492A (en) * | 2023-06-01 | 2023-06-30 | 辽宁省交通规划设计院有限责任公司 | Tunnel intelligent detection device and method |
CN116358492B (en) * | 2023-06-01 | 2023-08-04 | 辽宁省交通规划设计院有限责任公司 | Tunnel intelligent detection device and method |
Also Published As
Publication number | Publication date |
---|---|
CN114166180B (en) | 2024-07-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN114166180A (en) | Tunnel multi-section visual detection system and self-adaptive adjustment method | |
CN110297498B (en) | Track inspection method and system based on wireless charging unmanned aerial vehicle | |
JP6608042B2 (en) | Apparatus and method for diagnosis of electric power equipment using thermal image camera | |
CN107786785B (en) | Illumination processing method and device | |
CN111255637B (en) | Real-time tower clearance monitoring system and method thereof | |
JP2017026316A (en) | Oil leakage detection system | |
JP7010330B2 (en) | Image processing system, image processing method, image processing device and program | |
CN106506953A (en) | The substation equipment image acquisition method of servo is focused on and is exposed based on designated area | |
CN108387517B (en) | Slice scanning method and system | |
KR101825725B1 (en) | Method and device for diagnosing deterioration of solar cell module | |
WO2024055788A1 (en) | Laser positioning method based on image informaton, and robot | |
CN102589808A (en) | Large-scale tunnel seepage point measuring method | |
CN110666814A (en) | Power distribution network inspection robot | |
JP2017175475A (en) | Monitoring system and monitoring method | |
CN111147764A (en) | Leaky coaxial cable image acquisition method and system based on real-time image recognition | |
CN205179442U (en) | Tunnel self -adaptation lighting device based on image processing | |
CN112326039B (en) | Photovoltaic power plant patrols and examines auxiliary system | |
CN112543272B (en) | Transformer substation inspection camera device with light regulation function and method | |
CN101527793A (en) | Dynamic image picturing method for preventing environmental light interference and system thereof | |
CN113155852A (en) | Transmission band detection method and device and electronic equipment | |
CN203190947U (en) | Transmission line image acquisition device and transmission line icing thickness detection system | |
CN105812677B (en) | A kind of image generating method and system | |
CN111367286A (en) | Laser vision positioning system and method for measuring position of docking equipment | |
CN114627119B (en) | Visual neural network-based appearance defect intelligent identification system and identification method | |
CN108366210B (en) | Unmanned aerial vehicle and unmanned aerial vehicle control method |
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 |