CN111855664B - Adjustable three-dimensional tunnel defect detection system - Google Patents
Adjustable three-dimensional tunnel defect detection system Download PDFInfo
- Publication number
- CN111855664B CN111855664B CN202010537816.3A CN202010537816A CN111855664B CN 111855664 B CN111855664 B CN 111855664B CN 202010537816 A CN202010537816 A CN 202010537816A CN 111855664 B CN111855664 B CN 111855664B
- Authority
- CN
- China
- Prior art keywords
- dimensional
- image
- tunnel
- structured light
- disease
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
-
- 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
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B21/00—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant
- G01B21/02—Measuring arrangements or details thereof, where the measuring technique is not covered by the other groups of this subclass, unspecified or not relevant for measuring length, width, or thickness
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01S—RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- G01S19/00—Satellite radio beacon positioning systems; Determining position, velocity or attitude using signals transmitted by such systems
- G01S19/38—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system
- G01S19/39—Determining a navigation solution using signals transmitted by a satellite radio beacon positioning system the satellite radio beacon positioning system transmitting time-stamped messages, e.g. GPS [Global Positioning System], GLONASS [Global Orbiting Navigation Satellite System] or GALILEO
- G01S19/42—Determining position
Abstract
The invention discloses an adjustable tunnel disease three-dimensional detection system which comprises a junction tunnel apparent disease acquisition device, a mechanical body structure and a data storage and processing device. The tunnel apparent disease acquisition device consists of a structured light laser acquisition system and an image acquisition system, and completes the depth information acquisition of the tunnel apparent disease and the two-dimensional plane information acquisition of the tunnel apparent disease; the mechanical body structure is used for realizing the mechanical motion function of the detection system; the data storage and processing device carries out preprocessing, splicing, fusion and other processing on the acquired images and outputs the processed images. The invention realizes the three-dimensional detection of the apparent tunnel diseases by adopting a structured light and camera fusion mode, and solves the problem that the apparent tunnel diseases cannot reflect the disease depth in the prior art through signal processing technologies such as image preprocessing, image splicing correction, multi-source data fusion and the like.
Description
Technical Field
The invention belongs to the technical field of tunnel safety detection, and particularly relates to an adjustable tunnel defect three-dimensional detection system which mainly utilizes structured light and a digital camera to detect three-dimensional detection and data processing of apparent defects on the inner wall of a tunnel.
Background
Lining cracks can appear in the highway tunnel in the operation stage due to various factors, and the cracks can reduce the bearing capacity, the waterproofness and the durability of concrete, even can lead to the concrete to fall off, influence driving safety. Compared with the 2003 edition, the technical specification of highway tunnel maintenance (JTG _ H12-2015) clearly provides a working principle of 'prevention is the main and prevention and control combination', and the preventive maintenance is required to be strengthened. The preventive maintenance plays an important role in reducing the whole life cycle cost of the tunnel, improving the durability and the service life of the facility, and is also a direct embodiment of saving resources and protecting the environment. In the tunnel structure inspection work, the daily inspection is separated from the daily inspection from the inspection content and frequency, the daily inspection is adjusted to be the frequent inspection, the frequent inspection is regulated in the fourth chapter, a mode of combining manual and informatization means is adopted, the road inspection frequency of the first-level, second-level and third-level maintenance levels is 1 time/month, 1 time/2 month and 1 time/3 month respectively, and the maintenance grading concept is embodied. The evaluation condition of the cracks of the highway tunnel lining is shown in tables 1 and 2, and when the evaluation condition value of the important structural division technical condition is found to be 3 or 4 in the frequent inspection, the regular inspection should be immediately carried out. The cracks in the table mainly take horizontal cracks and shear cracks as objects, and for transverse cracks, the evaluation condition value is correspondingly reduced by 1 grade. When the crack with the width of more than 0.3-0.5mm and the distribution area of more than 200cm/m < 2 >, the evaluation grade can be increased or the judgment with higher classification in the judgment is adopted.
At present, most crack detection methods adopt a two-dimensional image analysis technology. Due to the characteristics of multiple textures, multiple cracks, multiple image light intensity and the like of the tunnel lining, lining oil stain, shadow and mechanical scratch are difficult to distinguish from actual cracks by simply depending on a two-dimensional gray image analysis method. In consideration of the post-processing algorithm, some automatic crack detection algorithms have imperfections, and the post-processing data processing still adopts a man-machine combination or even a complete manual mode, so that the efficiency is low and the subjectivity is strong. For a long time, scholars in relevant fields at home and abroad are consistently dedicated to research on related technologies of automatic crack detection, but most of research works are only under the conditions of good image quality, simple pavement diseases and obvious characteristics, and a real practical and effective automatic detection method is lacked.
Disclosure of Invention
The invention aims to overcome the defects of the prior art, provides an adjustable tunnel disease three-dimensional detection system, solves the problems of high light intensity and stain interference, less available information, low disease automatic detection and identification efficiency and the like in a two-dimensional camera image for tunnel detection in the prior art, obtains rich characteristics of disease signals by adding one-dimensional depth information, further provides an apparent disease detection technology capable of obtaining disease three-dimensional objective entities such as cracks, pits and the like, obtains the depth information of diseases by adding a structured light sensor, and can effectively provide three-dimensional characterization information of the diseases by combining plane information measured by a digital camera. Meanwhile, a data processing technology for fusing a structured light image and a camera image is provided, and three-dimensional digital presentation of the apparent tunnel diseases is realized.
The technical scheme is as follows:
the utility model provides an adjustable tunnel disease three-dimensional detection system, includes knot tunnel apparent disease collection system, mechanical body structure and data storage and processing apparatus, wherein:
1) The tunnel apparent disease collecting device consists of a structured light laser collecting system and an image collecting system,
the structured light laser acquisition system for acquiring depth information of apparent tunnel diseases comprises a structured light laser light source and a structured light laser, wherein the structured light laser, an area array camera and a target form a triangle, the transmitting plane of the structured light laser is as high as the receiving center of the area array camera, the structured light laser emits laser through a cylindrical lens to expand, the laser line of the fluctuant target is deformed, and the area array camera acquires information corresponding to the contour line of the target, wherein the grating formed by irradiating the target with the laser is acquired by capturing the area array camera;
the image acquisition device for acquiring the two-dimensional plane information of the apparent tunnel diseases consists of a digital camera, a lens and an image data acquisition card, wherein the digital camera acquires black and white images, the lens adjusts the focal length, the depth of field and the field of view, and the image data acquisition card is connected with the kilomega network card and realizes CameraLink transmission through a PCI interface;
2) The mechanical body structure for detecting the mechanical motion function of the system consists of an electric control cabinet, a servo motor, a roller, a displacement sensor, a positioning device and a guide rail; the servo motor outputs pulses matched with the shooting frequency of the camera, and the matching of the roller speed and the actual running speed is controlled through the electronic tooth number function of the servo controller; the displacement sensor comprises an encoder and a distance laser range finder, the encoder is coaxially connected with the automobile hub, and the rotating speeds of the encoder and the automobile hub are equal; the distance laser range finder keeps the constant distance between the vehicle and the inner wall of the tunnel so as to avoid different fields of view and resolution; the positioning device is a GPS positioner and records the position in the acquisition process; the guide rail ensures the smooth movement of the instrument;
3) The data storage and processing device consists of a large-capacity memory, a processor, image processing software and an output system and is used for carrying out image preprocessing, image splicing correction and multi-source data fusion on the collected image and outputting the apparent disease depth.
Furthermore, the included angle between the axial direction of the light emitted by the structured light laser and the axial direction of the area array camera is 40-48 degrees, and the receiving center of the structured light emitting plane and the area array camera is 2.5-3 meters away from the detection tunnel face so as to ensure the detection precision and the normal driving speed.
Furthermore, the resolution of the digital Camera is greater than 8K, the line frequency is 44.4K, the output interface is a Base Camera Link interface, and the focal length of the lens is 50mm.
Further, the running speed of a carrier of the detection system is 0-80Km/h, and the encoder triggers the camera to shoot through the counting trigger module so as to keep the fixed relation between the shooting frequency and the vehicle speed and avoid the overlapping of the shot pictures; the resolution of the encoder is matched with the circumference of the tire of the vehicle-mounted system; the encoder outputs pulses to control the triggering and shooting frequency of the camera through a control line interface; the GPS positioning device records the image position in the information acquisition process so as to check the position of the tunnel pile number, and the GPS receiving device in the detection system receives the information and transmits the information to the industrial personal computer.
Furthermore, a data transmission system of the adjustable tunnel defect three-dimensional detection system is realized by a gigabit Ethernet card and an RJ-45 twisted pair access interface by utilizing a TCP/IP protocol; the data storage adopts a disk array with 8TB storage capacity, and the data reading speed can reach 6 Gb/s.
Further, the data storage and processing device working program is as follows:
a) Acquiring image data of a digital camera, correcting, cutting and splicing the image data, and denoising, enhancing and morphologically processing the processed image data;
b) And (3) calibrating and matching the coordinates of the structured light visual image: calculating corresponding points of the space points on the plane of the area-array camera and the projection equipment by using a Zhang-Yongyou calibration method;
structured light encoding: searching each unique coding pattern in the image, and searching the position of the test image through the pattern ID to complete image matching;
acquiring a plurality of checkerboard images with line structured light by virtue of a mobile platform and a checkerboard, processing the light bars, wherein the checkerboard images comprise binaryzation, morphological processing, image denoising and skeletonization, acquiring two-dimensional coordinates and three-dimensional coordinates of the line structured light bars, and fitting a plane equation;
light strip center extraction: acquiring sub-pixel light strip center image coordinates of the light strip image, and converting the two-dimensional light strip center coordinates into three-dimensional world coordinates by a calibration module according to the relationship between the calibrated two-dimensional image and the three-dimensional world coordinates so as to acquire three-dimensional contour data of the road surface;
three-dimensional reconstruction: the method comprises the steps of collecting a line structured light image of a measurement target, obtaining a three-dimensional coordinate corresponding to a light bar based on system parameters and two-dimensional coordinates of the light bar after skeletonization of the light bar, fusing the three-dimensional coordinate with camera image data after morphological processing to obtain target three-dimensional coordinate data, analyzing the three-dimensional contour data according to three-dimensional point cloud coordinates, calculating corresponding tolerance characteristics, and reconstructing a three-dimensional image.
Further, light strip center extraction at a pixel level is obtained by adopting a light strip gray scale feature extraction method of kernel distribution; and obtaining the morphological characteristics of the light bars by combining a threshold value method and a skeleton extraction method.
Furthermore, a phase-frequency domain-based structured light three-dimensional space positioning splicing method is adopted, and a matching mapping relation is obtained through phase and frequency comparison of adjacent structured light images.
Further, the disease analysis method of multi-scale feature clustering is adopted to process the image disease data, and different scale space expressions of the same disease are obtained from a plurality of decomposition scale spaces, so that different diseases are identified.
Drawings
Fig. 1 is a schematic structural diagram of an adjustable tunnel defect three-dimensional detection system.
FIG. 2 is a schematic diagram of data storage, processing and display.
Fig. 3 is a schematic diagram of coordinate transformation of a three-dimensional detection system.
Fig. 4 is a schematic diagram of a data processing flow.
Description of reference numerals:
the device comprises a movable test bed-1, an electric control cabinet-2, a driving simulation device-3, a motor-4, a roller-5, a speed encoder-6, a data storage and processing device-7, a data acquisition device-8, a support base-9, an adjustable angle arm-10, a longitudinal adjustable telescopic arm-11, a camera-12, a structured light laser-13, a data storage device-14, a data processing device-15, a display device-16, an image data preprocessing module-17 and a tunnel lining wall-18, wherein for a crack-19 on the lining wall and a pixel coordinate system 20 in a picture plane.
Detailed Description
In order to make those skilled in the art better understand the technical solution of the present invention, the following describes in detail an adjustable three-dimensional tunnel defect detection system provided by the present invention with reference to an embodiment. The following examples are intended to illustrate the invention only and are not intended to limit the scope of the invention.
In order to overcome the problem that a two-dimensional gray scale image processing technology is sensitive to interference factors such as shadow, stains and the like, the automatic crack recognition efficiency is effectively improved, a three-dimensional detection technology is gradually developed, and rich characteristics of crack signals are obtained by adding one-dimensional information. Moreover, diseases such as cracks and potholes are three-dimensional objective entities, and all reflect three-dimensional information of the road surface, and the two-dimensional crack detection based on the image method can only give information of the position, the length and the width of the crack, and the depth information of the crack is difficult to detect. With the development of laser scanning technology, laser radar technology, camera stereoscopic vision technology and optical technology, the three-dimensional crack detection technology becomes a new development direction. Meanwhile, the disease information is displayed in a three-dimensional visual mode, and the maintenance utilization efficiency of the traffic infrastructure can be effectively improved. And according to the decision deployment of the transportation department about promoting digital economic development in 2019, the spirit of the integration of advanced information technology and transportation depth is promoted, and according to the guiding thought of 'digital transportation development planning outline', 'a data link' is taken as a main line, a digital acquisition system, a networked transmission system and an intelligent application system are constructed, and the development of transportation informatization to digitization, networking and intelligence is accelerated; the content of the ' construction of a digital acquisition system ' clearly shows that ' all-element and all-period digitalization of planning, design, construction, maintenance, operation management and the like of traffic infrastructure is promoted ', a high-precision traffic geographic information platform covering the whole country is constructed, element information of traffic engineering and the like is perfected, three-dimensional digital presentation of physical facilities is realized, and professional navigation application of automatic driving, large piece transportation and the like under all-weather complex traffic scenes is supported '. By utilizing the complementarity between the original two-dimensional image and the structured light three-dimensional detection technology of the tunnel detection system, the tunnel detection system has the advantages of large two-dimensional image information amount and insensitivity of the structured light three-dimensional detection technology to interference factors such as shadow, stain and the like, and can realize automatic identification and three-dimensional display of tunnel diseases.
A three-dimensional detection system for tunnel diseases comprises a junction tunnel apparent disease acquisition device, a mechanical body structure and a data storage and processing device. The tunnel apparent disease acquisition device consists of a structured light laser acquisition system and an image acquisition system, wherein the structured light laser acquisition system comprises a structured light laser light source and a structured light laser and is used for completing the depth information acquisition of the tunnel apparent diseases; the image acquisition device consists of a digital camera, a lens and an image acquisition card and is used for completing the two-dimensional plane information acquisition of the apparent tunnel diseases; the mechanical body structure consists of an encoder, a gyroscope, an accelerometer, a laser displacement sensor and an industrial personal computer, and the mechanical motion function of the detection system is completed; the data storage and processing device consists of a large-capacity memory, a processor, image processing software and an output system, and is used for preprocessing, splicing, fusing and the like of the acquired images and outputting the processed images. The invention realizes the three-dimensional detection of the apparent tunnel diseases by adopting a structured light and camera fusion mode, and solves the problem that the apparent tunnel diseases cannot reflect the disease depth in the prior art through signal processing technologies such as image preprocessing, image splicing correction, multi-source data fusion and the like.
The tunnel apparent disease acquisition device consists of a structured light laser acquisition system and an image acquisition system; the structured light laser, the camera and the target form a triangle, and the emitting plane of the structured light laser and the receiving center of the camera are at the same height;
the structured light laser acquisition system comprises a structured light laser light source and a structured light laser, and is characterized in that: the structured light laser emits a laser light source through a cylindrical lens, a fluctuant target laser line is deformed, and a grating formed by irradiating a target with laser is acquired through the capture of an area array camera and corresponds to the information of a target contour line;
the image acquisition system comprises a digital camera, a lens, a data acquisition card and an industrial personal computer, and is characterized in that: collecting black and white images by a digital camera; the lens can adjust the focal length, the depth of field, the field of view and the like; the network cable transmission of the data acquisition card is connected with the kilomega network card, and the CameraLink transmission realizes the communication between the acquisition card and the computer through a PCI interface; the industrial personal computer comprises a case, a power supply, a mainboard, a processor, a memory, a display card and the like;
the mechanical body structure is composed of an electric control cabinet, a servo motor, a roller, a displacement sensor, a positioning device and a guide rail, and is characterized in that: the output pulse of the servo motor is matched with the shooting frequency of the camera and is realized by the electronic tooth number function of the servo controller, and the speed of the roller is controlled to be matched with the actual running speed; the displacement sensor comprises an encoder and a distance meter, the encoder is coaxially connected with the automobile hub, and the rotating speeds of the encoder and the automobile hub are equal; the distance measuring instrument is a distance laser distance measuring instrument and keeps a constant distance between the vehicle and the inner wall of the tunnel so as to avoid the problems of different fields of view, different resolutions and the like; the positioning device is a GPS positioner and records the position in the acquisition process; the guide rail is made of stainless steel, so that smooth movement of the instrument is guaranteed;
the data storage and processing device is characterized in that: the data storage device has large memory capacity and high data reading speed, and can realize the real-time storage and output of the acquired images; the data processing device is integrated with a data preprocessing module, comprises a structured light vision image coordinate calibration and matching algorithm, and acquires two-dimensional and three-dimensional coordinates of a structured light bar through binaryzation, morphology, denoising, skeletonization and the like of the structured light bar; analyzing the three-dimensional contour data through the two-dimensional and three-dimensional coordinates after the optical strips are thinned, and reconstructing a three-dimensional image; the data processing device comprises the following processing steps:
a) Acquiring camera image data, and correcting, cutting and splicing the images;
b) Denoising, image enhancing and morphological processing are carried out on the camera image data processed in the step a);
c) And (3) calibrating and matching the coordinates of the structured light visual image: calculating corresponding points of the space points on the camera plane and the projection equipment by using a Zhang Zhengyou calibration method; designing a structured light coding method, searching each unique coding pattern in a shot image, searching the position of a test image through a pattern ID, and completing image matching;
d) Laser calibration: acquiring a plurality of checkerboard images with structured light by means of a mobile platform and a checkerboard, processing the light bars, including binaryzation, morphology, denoising and thinning (skeletonization), acquiring two-dimensional coordinates and three-dimensional coordinates of the structured light bars, acquiring the three-dimensional coordinates similar to a camera calibration method, and fitting a plane equation;
e) Light strip center extraction: the calibration module converts the two-dimensional light bar central coordinate into a three-dimensional world coordinate according to the relationship between a two-dimensional image calibrated in advance and the three-dimensional world coordinate, thereby acquiring three-dimensional contour data of the road surface;
f) Three-dimensional reconstruction: the method comprises the steps of collecting a line structured light image of a measurement target, thinning a light bar, obtaining a three-dimensional coordinate corresponding to the light bar based on system parameters and two-dimensional coordinates of the light bar, analyzing three-dimensional contour data according to a three-dimensional point cloud coordinate, calculating corresponding tolerance characteristics, and reconstructing a three-dimensional image.
Example 1
Fig. 1 shows a schematic structural diagram of a test platform of a three-dimensional tunnel apparent disease detection system in an embodiment of the invention, which mainly comprises a movable test bed 1, an electric control cabinet 2, a driving simulation device 3, a data storage and processing device 7 and a data acquisition device 8.
The electric control cabinet 2 is a semi-closed metal cabinet, consists of equipment such as switch equipment, measuring instruments, protective circuits and the like, has the functions of power distribution, electric appliance control and the like, and can be manually or automatically switched on or partially switched off.
The driving simulator 3 is composed of a motor 4, a roller 5 and a speed encoder 6. The motor 4 utilizes the electronic tooth number in the servo controller to realize the matching of the roller linear speed and the actual detection running speed, and the simulation speed range is 0-80km/h. Crack diseases with different lengths and widths are marked on the roller 5 so as to simulate apparent crack diseases of tunnel linings; the speed encoder 6 can acquire the speed of the roller in real time and trigger the data acquisition device to acquire data according to the speed.
The data storage and processing device 7 is composed of a data storage device 14, a data processing device 15 and a display device 6, as shown in fig. 2. The data storage device 14 has a reading speed of 6Gb/s and a storage capacity of 8TB, and can store the acquired image data in real time; the data processing device 15 integrates a data preprocessing module to realize image preprocessing and splicing functions.
The data acquisition device 8 consists of a bracket base 9, an angle-adjustable arm 10, a longitudinal adjustable telescopic arm 11, a camera 12 and a structured light laser 13. The angle-adjustable arm 10 can realize the adjustment of the pitch angle of-30 degrees to 90 degrees and can be used for adjusting the combined collection angle of a camera and a structured light laser. The length of the strut can be adjusted up and down by the longitudinal adjustable telescopic arm 11. The camera 12 is an industrial camera satisfying a resolution of 8k and a line frequency of 44.4 k; the structured light laser 13 is a structured light laser which emits laser wavelength of 660nm, has power of 100mw and has a fan angle of 75 degrees.
In fig. 3, the camera 12 and the structured light laser 13 irradiate the tunnel lining wall 18 at an included angle of 45 degrees simultaneously, and for a point Q on a crack 19 on the lining wall, the coordinates of the point Q in a world coordinate system O (x, y, z) are set as (u, v, k), and the camera coordinate system O is set as c (x c ,y c ,z c ) The pixel coordinate system 20 in the image plane is O p (x p ,y p ,z p ) Then the world coordinate and pixel coordinate of point Q on crack 19 are transformed by:
wherein (x) p0 ,y p0 ) As coordinates of the origin of the camera in the image plane, f x 、f y The focal lengths of the cameras in the x and y directions, respectively, and R, T are the rotation matrix and the translation vector, respectively.
As shown in fig. 2, at 17, an example of image data preprocessing in the data processing device 15 is to acquire 3 images of a tunnel lining, and realize the crack display of each image through the functions of removing interference noise, image equalization, brightness adjustment, image enhancement, and the like, and then realize the crack display of a plurality of images through the functions of image stitching, image fusion, and the like.
A flow chart of structured light laser data and image data fusion processing is shown in fig. 4, and structured light laser data processing is performed by reading in an image, binarizing light bars, morphologically processing, denoising a structured light image, refining the light bars and calculating three-dimensional coordinates of the light bars; reading image data, correcting the image, cutting, denoising and removing interference of the image, enhancing a camera image and carrying out morphological processing on the camera image; and obtaining three-dimensional coordinate data of the crack through the calibration and fusion of the two images, and finally reconstructing the three-dimensional crack image.
The present invention is not limited to the above-described examples, and various changes can be made without departing from the spirit and scope of the present invention within the knowledge of those skilled in the art.
Claims (8)
1. The utility model provides an adjustable three-dimensional detecting system of tunnel disease which characterized in that, includes knot tunnel apparent disease collection system, mechanical body structure and data storage and processing apparatus, wherein:
1) The tunnel apparent disease acquisition device consists of a structured light laser acquisition system and an image acquisition system,
the structured light laser acquisition system for acquiring depth information of apparent tunnel diseases comprises a structured light laser light source and a structured light laser, wherein the structured light laser, an area array camera and a target form a triangle, the transmitting plane of the structured light laser is as high as the receiving center of the area array camera, the structured light laser emits laser through a cylindrical lens to expand, the laser line of the fluctuant target is deformed, and the area array camera acquires information corresponding to the contour line of the target, wherein the grating formed by irradiating the target with the laser is acquired by capturing the area array camera;
the image acquisition device for acquiring the two-dimensional plane information of the apparent tunnel diseases consists of a digital camera, a lens and an image data acquisition card, wherein the digital camera acquires black and white images, the lens adjusts the focal length, the depth of field and the field of view, and the image data acquisition card is connected with the kilomega network card and realizes CameraLink transmission through a PCI interface;
2) The mechanical body structure for detecting the mechanical motion function of the system consists of an electric control cabinet, a servo motor, a roller, a displacement sensor, a positioning device and a guide rail; the servo motor outputs pulses matched with the shooting frequency of the camera, and the matching of the roller speed and the actual running speed is controlled through the electronic tooth number function of the servo controller; the displacement sensor comprises an encoder and a distance laser range finder, the encoder is coaxially connected with the automobile hub, and the rotating speeds of the encoder and the automobile hub are equal; the distance laser range finder keeps the constant distance between the vehicle and the inner wall of the tunnel so as to avoid different fields of view and resolution; the positioning device is a GPS positioner and records the position in the acquisition process; the guide rail ensures the smooth movement of the instrument;
3) The data storage and processing device consists of a large-capacity memory, a processor, image processing software and an output system and is used for carrying out image preprocessing, image splicing correction and multi-source data fusion on the collected image and outputting apparent disease depth;
the data storage and processing device working program is as follows:
a) Acquiring image data of a digital camera, correcting, cutting and splicing the image data, and denoising, enhancing and morphologically processing the processed image data;
b) And (3) calibrating and matching the coordinates of the structured light visual image: calculating corresponding points of the space points on the plane of the area-array camera and the projection equipment by using a Zhang Zhengyou calibration method;
structured light encoding: searching each unique coding pattern in the image, and searching the position of the test image through the pattern ID to complete image matching;
acquiring a plurality of checkerboard images with line structured light by means of a mobile platform and a checkerboard, processing the light bars, including binaryzation, morphological processing, image denoising and skeletonization, acquiring two-dimensional coordinates and three-dimensional coordinates of the line structured light bars, and fitting a plane equation;
light strip center extraction: acquiring sub-pixel light strip center image coordinates of the light strip image, and converting the two-dimensional light strip center coordinates into three-dimensional world coordinates by a calibration module according to the relationship between the calibrated two-dimensional image and the three-dimensional world coordinates so as to acquire three-dimensional contour data of the road surface;
three-dimensional reconstruction: the method comprises the steps of collecting a line structured light image of a measurement target, obtaining a three-dimensional coordinate corresponding to a light bar based on system parameters and two-dimensional coordinates of the light bar after skeletonization of the light bar, fusing the three-dimensional coordinate with camera image data after morphological processing to obtain target three-dimensional coordinate data, analyzing the three-dimensional contour data according to three-dimensional point cloud coordinates, calculating corresponding tolerance characteristics, and reconstructing a three-dimensional image.
2. The adjustable three-dimensional tunnel defect detection system according to claim 1, wherein an included angle between the axial direction of light emitted by the structured light laser and the axial direction of the area array camera is 40-48 degrees, and the distance between the structural light emitting plane and the receiving center of the area array camera is 2.5-3 meters away from the detection tunnel face so as to ensure detection precision and normal driving speed.
3. The adjustable three-dimensional tunnel disease detection system of claim 1, wherein a resolution of the digital Camera is greater than 8K, a line frequency is 44.4K, the output interface is a Base Camera Link interface, and a focal length of the lens is 50mm.
4. The adjustable three-dimensional tunnel disease detection system according to claim 1, wherein the speed of the carrier of the detection system is 0-80Km/h, and the encoder triggers the camera to shoot through the counting trigger module so as to keep the fixed relation between the shooting frequency and the vehicle speed and avoid overlapping of the shot pictures; encoder resolution and vehicle mounted matching the circumferences of the system tires; the encoder outputs pulses to control the triggering and shooting frequency of the camera through a control line interface; the GPS positioning device records the image position in the information acquisition process so as to check the position of the tunnel stake mark, and the GPS receiving device in the detection system receives information and transmits the information to the industrial personal computer.
5. The adjustable three-dimensional tunnel defect detection system of claim 1, wherein a data transmission system of the adjustable three-dimensional tunnel defect detection system is implemented by a gigabit ethernet card and an RJ-45 twisted pair access interface using a TCP/IP protocol; the data storage adopts a disk array with 8TB storage capacity, and the data reading speed can reach 6 Gb/s.
6. The three-dimensional detection system for tunnel diseases capable of being adjusted according to claim 1, characterized in that extraction of light strip centers at pixel level is obtained by a light strip gray scale feature extraction method of kernel distribution; and obtaining the morphological characteristics of the light bars by combining a threshold value method and a skeleton extraction method.
7. The adjustable three-dimensional tunnel disease detection system according to claim 6, wherein a phase-frequency domain based structured light three-dimensional space positioning and splicing method is adopted, and a matching mapping relationship is obtained by comparing the phase and the frequency of adjacent structured light images.
8. The three-dimensional detection system for tunnel diseases according to claim 7, characterized in that the disease analysis method of multi-scale feature clustering is adopted to process the image disease data, and different scale space expressions of the same disease are obtained from a plurality of decomposed scale spaces, so as to identify different diseases.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010537816.3A CN111855664B (en) | 2020-06-12 | 2020-06-12 | Adjustable three-dimensional tunnel defect detection system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010537816.3A CN111855664B (en) | 2020-06-12 | 2020-06-12 | Adjustable three-dimensional tunnel defect detection system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111855664A CN111855664A (en) | 2020-10-30 |
| CN111855664B true CN111855664B (en) | 2023-04-07 |
Family
ID=72987174
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010537816.3A Active CN111855664B (en) | 2020-06-12 | 2020-06-12 | Adjustable three-dimensional tunnel defect detection system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111855664B (en) |
Families Citing this family (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112381009B (en) * | 2020-11-18 | 2023-01-17 | 安徽国钜工程机械科技有限公司 | Tunnel image acquisition and image splicing method of linear array camera |
| CN112630223B (en) * | 2020-12-07 | 2023-12-26 | 杭州申昊科技股份有限公司 | Tunnel crack detection system and method |
| CN112669438A (en) * | 2020-12-31 | 2021-04-16 | 杭州海康机器人技术有限公司 | Image reconstruction method, device and equipment |
| CN112556600B (en) * | 2021-02-22 | 2021-05-18 | 南京派光智慧感知信息技术有限公司 | Tunnel deformation real-time monitoring method and device |
| CN113914933A (en) * | 2021-09-27 | 2022-01-11 | 广西大学 | Tunnel overhaul robot |
| CN114136219B (en) * | 2021-11-18 | 2024-02-13 | 大连海事大学 | Tunnel wet spraying vehicle guniting thickness real-time detection device and method based on line structured light |
| CN113822891B (en) * | 2021-11-24 | 2022-03-11 | 深圳市智源空间创新科技有限公司 | Tunnel disease detection method fusing laser point cloud and panoramic image |
| CN114164736A (en) * | 2021-12-01 | 2022-03-11 | 山西省交通科技研发有限公司 | Integrated intelligent detection system for road apparent and internal diseases |
| CN115013650A (en) * | 2022-05-16 | 2022-09-06 | 华北水利水电大学 | Tracking means for intelligent image recognition of degree of deep learning |
| CN114910484B (en) * | 2022-07-19 | 2022-11-04 | 山西省信息产业技术研究院有限公司 | Tunnel disease detection point marking method, system, industrial control unit and medium |
| CN115326809B (en) * | 2022-08-02 | 2023-06-06 | 山西省智慧交通研究院有限公司 | Tunnel lining apparent crack detection method and detection device |
| CN115115823B (en) * | 2022-08-25 | 2023-02-03 | 深圳市城市交通规划设计研究中心股份有限公司 | Road disease positioning and correcting method, device and equipment and readable storage medium |
| CN115937289B (en) * | 2022-11-24 | 2023-10-20 | 深圳市城市交通规划设计研究中心股份有限公司 | Rut depth calculation method based on three-dimensional reconstruction of pavement rut disease |
| CN116297495A (en) * | 2023-05-09 | 2023-06-23 | 武汉理工大学 | Tube wall detection method and tube wall detection device based on structured light image |
| 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 |
Family Cites Families (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101089548B (en) * | 2007-07-06 | 2010-05-26 | 哈尔滨工业大学 | 3D information detection method for pavement treadway |
| CN102706880B (en) * | 2012-06-26 | 2014-04-02 | 哈尔滨工业大学 | Road information extraction device based on two-dimensional image and depth information and road crack information detection method based on same |
| CN104299261B (en) * | 2014-09-10 | 2017-01-25 | 深圳大学 | Three-dimensional imaging method and system for human body |
| CN105606150B (en) * | 2015-12-22 | 2017-10-20 | 中国矿业大学(北京) | A kind of road synthetic detection method and system based on line-structured light and geological radar |
| CN107655898B (en) * | 2017-10-10 | 2023-11-03 | 山西省智慧交通研究院有限公司 | Stereoscopic scanning robot for road tunnel detection and implementation method thereof |
| CN207300902U (en) * | 2017-10-10 | 2018-05-01 | 山西省交通科学研究院 | A kind of stereoscan machine people for existing vcehicular tunnel |
| CN107764205B (en) * | 2017-11-06 | 2020-05-12 | 长安大学 | Three-dimensional detection device and detection method for high-frequency resistance welding seam appearance based on line structure light scanning |
| CN108088386B (en) * | 2017-12-15 | 2019-11-29 | 深圳大学 | A kind of the binary area-structure light detection method and system of micro-nano magnitude |
| CN109142382A (en) * | 2018-10-12 | 2019-01-04 | 成都精工华耀科技有限公司 | A kind of track visualization inspection two dimension and three-dimensional fusion imaging system |
| CN110541341B (en) * | 2019-09-04 | 2021-10-22 | 山西省交通科技研发有限公司 | Highway structure disease detection device and method based on stable vision |
-
2020
- 2020-06-12 CN CN202010537816.3A patent/CN111855664B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN111855664A (en) | 2020-10-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111855664B (en) | Adjustable three-dimensional tunnel defect detection system | |
| US11486548B2 (en) | System for detecting crack growth of asphalt pavement based on binocular image analysis | |
| CN104392224B (en) | A kind of highway pavement crack detecting method | |
| CN104005325B (en) | Based on pavement crack checkout gear and the method for the degree of depth and gray level image | |
| CN102635056B (en) | Measuring method for construction depth of asphalt road surface | |
| CN103778681A (en) | Vehicle-mounted high-speed road inspection system and data acquisition and processing method | |
| CN107256636A (en) | A kind of traffic flow acquisition methods for merging laser scanning and video technique | |
| CN106978774A (en) | A kind of road surface pit automatic testing method | |
| CN104700395A (en) | Method and system for detecting appearance crack of structure | |
| CN110930415B (en) | Method for detecting spatial position of track contact net | |
| CN103617611A (en) | Automatic threshold segmentation detection method for center and size of light spot | |
| CN103679167A (en) | Method for processing CCD images | |
| Wang et al. | Automated pavement distress survey: a review and a new direction | |
| Medina et al. | Automated visual inspection of road surface cracks | |
| CN104878679A (en) | Vehicle-mounted rut real-time detection system and detection method | |
| JP6929207B2 (en) | Road image processing device, road image processing method, road image processing program, and recording medium | |
| JP2009052907A (en) | Foreign matter detecting system | |
| EP4250245A1 (en) | System and method for determining a viewpoint of a traffic camera | |
| CN109559356B (en) | Expressway sight distance detection method based on machine vision | |
| CN116883483A (en) | Fish body measuring method based on laser camera system | |
| Laureshyn et al. | Automated video analysis as a tool for analysing road user behaviour | |
| Ziqiang et al. | Research of the algorithm calculating the length of bridge crack based on stereo vision | |
| CN110969875B (en) | Method and system for road intersection traffic management | |
| CN113077465A (en) | Pavement crack detection and extraction device and detection method thereof | |
| CN111539279A (en) | Road height limit height detection method, device, equipment and storage medium |
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 |