CN112329531B - Linear array binocular imaging system for pipe gallery apparent disease detection and working method - Google Patents
Linear array binocular imaging system for pipe gallery apparent disease detection and working method Download PDFInfo
- Publication number
- CN112329531B CN112329531B CN202011065679.4A CN202011065679A CN112329531B CN 112329531 B CN112329531 B CN 112329531B CN 202011065679 A CN202011065679 A CN 202011065679A CN 112329531 B CN112329531 B CN 112329531B
- Authority
- CN
- China
- Prior art keywords
- disease
- linear array
- pipe gallery
- camera
- rotating
- 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
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/10—Terrestrial scenes
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/22—Matching criteria, e.g. proximity measures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
Abstract
The invention belongs to the field of pipe gallery apparent disease detection, and provides a linear array binocular imaging system and a working method for pipe gallery apparent disease detection. The linear array binocular imaging system comprises: a guide rail laid within the pipe gallery; the first rotating cloud platform and the second rotating cloud platform are both hung on the guide rail and can move along the guide rail; the image acquisition and detection device is arranged on the first rotating holder through the first rotating bracket; the image acquisition and detection device comprises a binocular structure linear array camera and an area array camera; the auxiliary calibration device is arranged on the second rotating holder through a second rotating bracket; and the processor is used for receiving the pipe gallery apparent images acquired by the binocular structure linear array camera and the area array camera simultaneously, identifying the type and the outline of the disease, and calibrating the outline of the disease through the position of the auxiliary calibration device to obtain the size of the disease.
Description
Technical Field
The invention belongs to the field of pipe gallery apparent disease detection, and particularly relates to a linear array binocular imaging system and a working method for pipe gallery apparent disease detection.
Background
The statements in this section merely provide background information related to the present disclosure and may not necessarily constitute prior art.
The pipe gallery is an effective way for solving the problem of arrangement of various underground pipe networks. The city utility tunnel implemented at present mainly integrates various pipelines such as electric power, communication, radio and television, fuel gas, water supply and drainage, heat power and the like into a whole, and an integrated box culvert is built in the underground space of a city road. The urban underground comprehensive pipe gallery is in a high-speed development stage, but the construction technology in China is still immature, the problems of unqualified laying quality of waterproof coiled materials, unqualified construction quality of deformation joints and the like are easily caused in construction, the surface of a pipeline is inevitably damaged under the influence of transportation objects and uncontrollable factors in the natural world, and cracks, holes, scratches and the like are caused in common damage. Because the urban underground comprehensive pipe gallery belongs to the places with closed space, poor ventilation condition, easy accumulation of harmful gas, large fire hazard and difficult manual inspection, the daily toxic and harmful gas is not easy to be discharged, the fire is very easy to flash and the fire suppression difficulty is very high during the fire. Therefore, the underground comprehensive pipe gallery is subjected to daily inspection, and the potential safety hazard is found in time to be very important.
At present, the daily safety inspection of the established urban underground comprehensive pipe gallery adopts a mode of combining installation and fixation of detection equipment and manual inspection and a mode of inspection of a rail-hanging type device. The inventor discovers that the influence of the work experience, the skill level and the external environment of the personnel are patrolled and examined by the spatial layout of the pipe gallery, the manual detection workload is large, the detection period is long, time and labor are wasted, the detection blind area exists in the mode of laying the fixed monitoring nodes at the limited position in the pipe gallery, the pipeline surface scene is difficult to be completely covered, and the problems of false alarm, missed alarm and the like are caused. The pipe gallery detection technology based on the automatic inspection device is the current development trend, the mainstream rail hanging type inspection device mainly carries a thermal infrared imager, a gas detector and the like to monitor the internal temperature and the gas change of the pipe gallery, and the visible light high-definition camera is used for automatically detecting the apparent structure diseases of the pipe gallery, so that the potential safety hazard of the pipe gallery is comprehensively evaluated. However, in the environment of uneven illumination and the like in the pipe gallery, the difference between the tiny apparent diseases such as cracks, peeling and the like existing in the pipe gallery and the background features is small, and under the condition that pipelines and the like in the pipe gallery are shielded, clear images of the tiny diseases are difficult to effectively acquire, the disease types and the outlines of the diseases are difficult to identify, and the disease sizes cannot be accurately estimated.
The binocular camera is a detection method for obtaining depth information of a target body by using a parallax principle of human eyes so as to identify the size, the conventional binocular camera adopts an area-array camera, the image acquisition resolution of the area-array camera is low, the outline of a disease can be only roughly estimated, and the requirement for measuring the small-scale apparent disease size of a pipe gallery structure is difficult to meet. Compared with an area-array camera, the linear array camera has higher image resolution, the image resolution acquired by the linear array camera is higher than that of the area-array camera in the same visual field, and the image of the apparent disease with small size can be effectively measured.
The linear array camera has the characteristics of high resolution and high frame rate, so that the linear array camera has higher precision due to the high resolution, has good advantages for large and small objects and real-time dynamic acquisition due to the high frame rate and seamless acquisition, has a simple structure and lower cost, can form a binocular structure, and is favorable for improving the precision of detecting the small disease size.
The inventor finds that a binocular structure is formed by commonly adopting a mode of coplanar placement of two cameras for a double-line-array camera at present, the overlapping of shooting visual fields of the coplanar structure is small, the overlapping images of the two cameras are easy to deviate due to the influence of jitter and the like, the images cannot be matched, and the size is difficult to measure.
Disclosure of Invention
In order to solve the above problems, a first aspect of the present invention provides a linear array binocular imaging system for detecting apparent diseases of pipe galleries, which uses the high resolution characteristics of a linear array camera to form a binocular structure for size measurement. The linear array camera adopts a non-coplanar structure placement mode to increase the view field overlap, and simultaneously the area array camera carries out the control of macroscopic view field and positions the characteristic points, thereby avoiding the problem that the image characteristic points can not be matched due to shake and the like and improving the precision of disease measurement and size measurement. On this basis, designed from calibration device, solved the normal position of different piping lane scenes and markd the problem.
In order to achieve the purpose, the invention adopts the following technical scheme:
a binocular imaging system of linear array for apparent disease detection of piping lane, includes:
a guide rail laid within the pipe gallery;
the first rotating holder and the second rotating holder are both hung on the guide rail and can move along the guide rail;
the image acquisition and detection device is arranged on the first rotating holder through the first rotating bracket; the image acquisition and detection device comprises a binocular structure linear array camera and an area array camera;
the auxiliary calibration device is arranged on the second rotating holder through a second rotating bracket;
and the processor is used for receiving the pipe gallery apparent images simultaneously acquired by the binocular structure linear array camera and the area array camera, identifying the type and the outline of the disease, and calibrating the outline of the disease through the position of the auxiliary calibration device to obtain the size of the disease.
In order to solve the above problems, a second aspect of the present invention provides a working method of a linear array binocular imaging system for detecting apparent diseases of a pipe gallery, wherein a pan-tilt device carrying a dual linear array camera and an area-array camera is installed in the pipe gallery and moves along a guide rail to detect safety conditions and potential safety hazards in real time, so that the danger of manual inspection is avoided, and the dangerous conditions can be found in time.
In order to achieve the purpose, the invention adopts the following technical scheme:
a working method of a linear array binocular imaging system for pipe gallery apparent disease detection comprises the following steps:
triggering the binocular structure linear array camera and the area array camera to acquire an apparent image of the pipe gallery at the same time;
identifying the type and outline of the disease in the collected image;
calibrating the outline of the disease to obtain the size of the disease;
the process of calibrating the disease outline comprises the following steps:
imaging any space point P to be measured on the two linear array cameras respectively, and calibrating the coordinate of the space point P under a pixel coordinate system;
establishing a world coordinate system by taking the optical center of the double linear array camera as an origin, converting points under a pixel coordinate system into points under the world coordinate system, and calculating to obtain the coordinates of the point P under the world coordinate system;
and (3) solving the three-dimensional coordinates of the two points to be detected on the disease contour, namely world coordinates, and solving the distance between the two points to be detected, namely the size of the disease.
The invention has the beneficial effects that:
(1) The invention adopts an image segmentation algorithm based on deep learning to automatically realize disease identification and contour identification, solves the problem of difficult disease identification caused by serious interference of pipelines, artificial marks, power distribution facilities, uneven illumination and the like in the pipe gallery, effectively avoids the danger of artificial routing inspection and the detection blind area of fixed node monitoring, and improves the accuracy of multi-disease identification.
(2) According to the invention, a binocular structure is formed by arranging the linear array cameras in a front-back manner, the linear array binocular corridor is driven to carry out comprehensive inspection by controlling the cloud platform to move along the guide rail, and then the position and the size of a disease are obtained according to the acquired image information, so that the system is simple, and auxiliary devices such as laser ranging are not needed.
(3) The invention utilizes the characteristic of high precision of the linear array camera, realizes linear array binocular by designing a special camera loading structure on the holder, has higher identification precision compared with common binocular, and obviously improves the size detection precision.
(4) The invention utilizes the characteristic that the imaging of the area-array camera is more stable to totally control the detection process, and carries out characteristic matching on the images shot by the area-array camera and the images shot by the linear array camera, thereby improving the matching precision.
(5) The invention adopts the auxiliary calibration device, and the data transmission is carried out through the guide rail and the image acquisition detection device, thereby realizing the synchronization of the two devices in motion, being beneficial to the automatic calibration of the camera and improving the efficiency of the automatic calibration.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, are included to provide a further understanding of the invention, and are incorporated in and constitute a part of this specification, illustrate exemplary embodiments of the invention and together with the description serve to explain the invention and not to limit the invention.
Fig. 1 is a schematic structural diagram of a linear array binocular imaging system for detecting apparent diseases of a pipe gallery according to an embodiment of the present invention;
fig. 2 is a schematic side structure diagram of the expanded telescopic rod and the expanded folding rod of the auxiliary calibration device of the linear array binocular imaging system for detecting apparent diseases of pipe corridors according to the embodiment of the present invention;
fig. 3 is a schematic structural diagram of a pan-tilt control device provided in an embodiment of the present invention;
fig. 4 is a flowchart of a working method of a linear array binocular imaging system for pipe gallery apparent disease detection according to an embodiment of the present invention;
fig. 5 is a coordinate relationship diagram of the spatial position of the point P on the marked defect of the linear array binocular imaging system for detecting the apparent defect of the pipe gallery provided by the embodiment of the present invention.
Detailed Description
The invention is further described with reference to the following figures and examples.
It is to be understood that the following detailed description is exemplary and is intended to provide further explanation of the invention as claimed. Unless defined otherwise, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this invention belongs.
It is noted that the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of exemplary embodiments according to the invention. As used herein, the singular forms "a", "an" and "the" are intended to include the plural forms as well, and it should be understood that when the terms "comprises" and/or "comprising" are used in this specification, they specify the presence of stated features, steps, operations, devices, components, and/or combinations thereof, unless the context clearly indicates otherwise.
In the present invention, terms such as "upper", "lower", "left", "right", "front", "rear", "vertical", "horizontal", "side", "bottom", and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only terms of relationships determined for convenience of describing structural relationships of the parts or elements of the present invention, and are not intended to refer to any parts or elements of the present invention, and are not to be construed as limiting the present invention.
In the present invention, terms such as "fixedly connected", "connected", and the like are to be understood in a broad sense, and mean either a fixed connection or an integrally connected or detachable connection; may be directly connected or indirectly connected through an intermediate. The specific meanings of the above terms in the present invention can be determined according to specific situations by persons skilled in the art, and should not be construed as limiting the present invention.
The linear array binocular imaging system for pipe gallery apparent disease detection is suitable for the field of tunnel detection.
As shown in fig. 1, the linear array binocular imaging system for detecting apparent diseases of pipe corridors of the present embodiment includes: the device comprises a guide rail 1, a rotating holder, an image acquisition and detection device and an auxiliary calibration device;
the guide rail 1 is laid in the pipe gallery and used as a track of the image acquisition and detection device and the auxiliary calibration device and power supply and data transmission equipment;
two rotating holders are hung on the guide rail, can move along the guide rail and can carry the whole system to rotate around a vertical shaft; the two rotating cloud platforms are respectively a first rotating cloud platform 2 and a second rotating cloud platform 6;
the image acquisition and detection device is arranged on a first rotating bracket 13 of the first rotating cloud deck 2, acquires a target area image, and obtains the size of a target disease through processing by the processor, so that the omnibearing detection of the pipe gallery is completed;
as shown in fig. 2, the auxiliary calibration device is installed on the second rotating support 25 of the second rotating pan/tilt head 6, and the position of the calibration plate 7 of the auxiliary calibration device is adjusted by controlling the movement of the second rotating pan/tilt head 6, so as to achieve automatic calibration of the system.
In a specific embodiment, the image acquisition and detection device comprises a binocular structure linear array camera and an area array camera 5; two linear array cameras 4 are installed on stabilizing the cloud platform, and stabilize the cloud platform and install on first runing rest.
The binocular linear array camera is composed of two linear array cameras 4. The two linear array cameras 4 adopt a non-coplanar structure and are embedded into the stabilizing pan-tilt in a front-back arrangement mode; the shooting planes of the two linear array cameras form a preset included angle, the normals of the two shooting planes are positioned in the same plane, and the linear array cameras respectively and completely scan the same plane at different visual angles to form a binocular structure;
the area-array camera 5 is embedded into the stabilizing pan-tilt and positioned behind the two linear-array cameras, so that a plane can be shot more completely, and the shot image of the plane can be matched with the characteristics of the images collected by the two linear-array cameras, thereby being beneficial to realizing the integral control of the collected detection plane images and improving the precision of image matching;
the pan-tilt control device 8 is connected and fixed on the stable pan-tilt, connected with the first rotating pan-tilt 2, used for transmitting the motion data of the pan-tilt, and connected with the processor through the feedback module;
and the processor is used for receiving the apparent images of the pipe gallery acquired by the two linear-array cameras and the area-array camera simultaneously, identifying the disease type and the disease outline in the acquired images, calibrating the disease outline and obtaining the size of the disease.
In specific implementation, a deep learning pixel level segmentation algorithm based on a local loss function is adopted in a processor, such as FL-SegNet and the like, so as to identify the type and the outline of the disease in the acquired image, wherein the identification process is a known process.
It is understood that in other embodiments, the method for identifying the type and outline of the disease in the acquired image may be implemented by other existing methods.
Specifically, the whole system is composed of an image acquisition detection device and an auxiliary calibration device, and the image acquisition detection device and the auxiliary calibration device move synchronously on the guide rail 1. In the automatic calibration process, the image acquisition and detection device stops moving, the auxiliary calibration device is controlled to move at the same speed as the acquired image, and the telescopic module is automatically controlled to extend the height of the calibration plate, so that a plurality of groups of multi-scale calibration data can be conveniently acquired.
In a specific embodiment, the pan/tilt head control device 8 includes a deflection angle detection module 9, a micro control module 10, a driving module 11, and a feedback module 12;
the deflection angle detection module 9 detects the angle change of the rotational cradle head 2 caused by rotation or jitter and the angle change of each camera, and transmits the angle change to the micro control module 10 and the feedback module 12.
The micro control module 10 is used for receiving the information sent by the deflection angle detection module 9, and the control drive module 11 controls the angles of the first rotating bracket 13 on the first rotating pan/tilt 2 and the camera support frame 14 on the stabilizing pan/tilt 3, so as to adjust the shooting posture of the camera, thereby achieving the purpose of adjusting the shooting angle.
In a specific implementation, the deflection angle detection device 9 is composed of a high-sensitivity nine-axis gyroscope 15 and an acceleration sensor 16, and the deflection angle detection device 9 is respectively connected with the rotating support 13 of the rotating pan/tilt head 2, the camera support frame 14 of the stabilizing pan/tilt head 3 and each camera loading module; the acceleration sensor 16 is used to detect changes in the pan/tilt movement and rotational speed, and the nine-axis gyroscope 15 is used to detect changes in the pan/tilt position and scan angle of each camera caused by pan/tilt rotation or shake.
In this embodiment, the driving module 11 is a stepping motor.
It is understood that the driving module may also adopt other structural forms, such as a hydraulic cylinder mechanism, and those skilled in the art can specifically select the structural form of the driving module according to actual situations.
In one embodiment, the micro control module 10 may be implemented using a microcontroller or other programmable logic device.
As a specific embodiment, the deflection angle detection module 9, the driving module 11, the micro control module 10 and the feedback module 12 are integrated on a control circuit board 8, as shown in fig. 3. In the embodiment, the deflection angle detection module, the driving module, the micro-control module and the feedback module are integrally arranged on one control circuit board, so that the holder control device has a compact structure, and the volume of the whole linear array binocular imaging system is reduced.
In this embodiment, the fixed feedback module 12 on the stabilizing pan/tilt 3 is connected to the deflection angle detection module 9, and is configured to receive the angle deviation information transmitted by the deflection angle detection module 9, calculate the angle deviation data, and feed the angle deviation data back to the processor and the manual console, so that the angle deviation of each part can be compensated, and the accuracy of identifying the size of the disease can be improved.
In specific implementation, the auxiliary calibration device comprises a telescopic module and a calibration plate 7, wherein the telescopic module can be composed of a vertical telescopic rod 18 and a horizontal telescopic rod 17; the calibration plate 7 is connected with the second rotating holder 6 through a telescopic module, and the joint of two telescopic rods of the telescopic module can rotate, so that the calibration plate 7 can be conveniently unfolded and folded; the telescopic module is made of carbon fiber materials, the stability of the whole device is improved through the light weight and the flexibility of the device, and the device is convenient to install and use.
Referring to fig. 1, a triangular suction cup 27 is additionally arranged in the auxiliary calibration device and fixed on the vertical telescopic rod 18, the position angle between the telescopic rods is well adjusted, and the other side of the triangular suction cup 27 can be adsorbed on the horizontal telescopic rod 17, so that the stability of the auxiliary calibration device in the moving process is enhanced.
In fig. 1, the first rotating platform 2 includes a first moving mechanism 19, the first moving mechanism 19 is shaped to fit with the guide rail 1, the guide rail 1 is wrapped, four first rollers 20 are mounted on the first moving mechanism 19, and the four first rollers 20 are divided into two groups and are symmetrically mounted on two sides of the guide rail 1 respectively; the first moving mechanism 19 moves the carrying device on the guide rail at a speed matched with the scanning resolution of the linear array camera 4 and the area array camera 5. The second rotating holder 6 comprises a second moving mechanism 21, the second moving mechanism 21 is matched with the guide rail 1 in shape and wraps the guide rail 1, four second rollers 22 are mounted on the second moving mechanism 21, and the four second rollers 22 are divided into two groups and symmetrically mounted on two sides of the guide rail 1 respectively.
In one or more embodiments, the shape of the first moving mechanism and the second moving mechanism is rectangular, square, or circular, so long as the first moving mechanism and the second moving mechanism are matched with the guide rail and wrap the guide rail.
In order to reduce the vibration between the rotating tripod head and the moving mechanism and improve the quality of binocular imaging and the calibration accuracy, a first bidirectional damping shock absorber 23 is connected between the base of the first rotating tripod head 2 and the first moving mechanism 19; a second bidirectional damping shock absorber 24 is connected between the base of the second rotating tripod head 6 and the second moving mechanism 21.
The first rotating bracket 13 on the rotating pan/tilt head of the first rotating pan/tilt head 2 is designed to be groove-shaped when rotating to the positions of the guide rail and the first moving mechanism 19, so that the rotary camera can shoot an omnibearing detection area.
In the process that the device moves on the guide rail, the linear array camera and the area array camera scan the measured pipe gallery to finish the detection of the apparent diseases and the abnormal pipeline of the pipe gallery and the size estimation of the corroded, worn and broken part of the pipeline or the wall, and the linear array camera has high scanning precision and accurate estimation of the sizes of the diseases.
Specifically, the linear array camera loading module is mounted on the camera support frame 14 of the stabilizing pan/tilt 3 to form a certain included angle, the area array camera loading module is mounted at a backward position, and a light source 26 is mounted between the two cameras, so that the scanning and imaging quality of the cameras is improved.
The camera loading module is realized by adopting a camera mounting seat, and is used for mounting a camera. The camera and the camera mounting seat can be fixed by adopting a screw fixing mode or a clamping mode and the like.
The technical scheme has the advantages that the offset angle of the camera support frame can be adjusted by the micro-control device, so that the shooting angle of the camera is adjusted, and the scanning imaging quality of the camera is improved; the camera loading module is fixed on the camera support frame to keep the relative position of the camera unchanged, which is beneficial to image matching and calculation of the size of the disease.
Specifically, in the processor, the process of calibrating the disease profile is as follows:
imaging any space point P to be measured on the two linear array cameras respectively, and calibrating the coordinate of the corresponding space point P to be measured under a pixel coordinate system;
establishing a world coordinate system by taking the optical centers of the double linear array cameras as original points respectively, and converting points under the pixel coordinate system into points under the world coordinate system;
calculating the coordinate of the point P in a world coordinate system according to the similar triangle and the projection relation;
and (4) solving the three-dimensional coordinates of the two points to be detected on the disease contour, namely the world coordinates, and further solving the distance between the two points to be detected, namely the size of the disease.
The technical scheme has the advantages that the pixel coordinates of the disease matching points are determined through image calibration, the coordinates of the matching points in a world coordinate system are calculated according to the similar triangles and the projection relation, the sizes of the diseases are estimated according to the relative coordinates between the matching points, the double-linear-array camera is driven to carry out comprehensive inspection on the pipe gallery by controlling the holder to move along the guide rail, the disease identification and the outline identification are automatically realized, the sizes of the diseases are automatically calculated, and the inspection efficiency is improved.
As shown in fig. 4, the working method of the linear array binocular imaging system for pipe gallery apparent disease detection in this embodiment includes:
triggering the binocular structure linear array camera and the area array camera to acquire an apparent image of the pipe gallery at the same time;
identifying the type and outline of the disease in the collected image;
automatically calibrating a camera in the shooting process, and calibrating the outline of the disease to obtain the size of the disease; the process is as follows:
imaging any space point P to be measured on the two linear array cameras respectively, and calibrating the coordinate of the corresponding space point P to be measured under a pixel coordinate system;
establishing a world coordinate system by taking the optical centers of the double-linear-array cameras as original points respectively, and converting points under the pixel coordinate system into points under the world coordinate system;
calculating the coordinate of the point P in a world coordinate system according to the similar triangle and the projection relation;
and (4) solving the three-dimensional coordinates of the two points to be detected on the disease contour, namely world coordinates, and further solving the distance between the two points to be detected, namely the size of the disease.
As shown in fig. 5, the specific example of obtaining the size of the disease by calibrating the disease contour is as follows:
imaging a certain point P in the space on the two linear array cameras respectively, calibrating the coordinate of the point P in a pixel coordinate system, and recording the coordinate as (u 1, v 1) in a first coordinate system and as (u 2, v 2) in a second coordinate system;
converting points under a pixel coordinate system into points under a world coordinate system, establishing the world coordinate system by taking optical centers of a double-linear-array camera as original points respectively, wherein the distance between the optical centers is b, the two world coordinate systems are Ol-x1y1z1 and Or-x2y2z2 respectively, and coordinates of a point P under the world coordinate system are (x 1, y1, z 1), (x 1-b, y1, z 1) respectively;
and f is the focal length of the linear array camera through the coordinate representation of the point P, and can be obtained by the relation of similar triangles and projections:
the coordinate relation of the point P can be obtained by the following formula:
the three-dimensional coordinates (x 1, y1, z 1), (x 1', y1', z1 ') of the two points to be measured are obtained by the above method, and further, the distance between the two points to be measured can be conveniently obtained, namely, the size of the disease is as follows:
this embodiment application is installed the cloud platform of carrying double-line camera in the piping lane and is removed along the guide rail and come real-time detection safety situation and potential safety hazard, avoids the danger of artificial patrolling and examining, still can in time discover dangerous condition.
According to the method, the pixel coordinates of the disease matching points are determined through image calibration, the coordinates of the matching points in a world coordinate system are calculated according to the similar triangles and the projection relation, the sizes of the diseases are finally estimated according to the relative coordinates between the matching points, the cradle head is controlled to move along the guide rail to drive the double-linear-array camera to carry out comprehensive inspection on the porch, the disease identification and the outline identification are automatically realized, the sizes of the diseases are further automatically calculated, and the inspection efficiency is improved.
The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention, and various modifications and changes may be made by those skilled in the art. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (9)
1. The utility model provides a two mesh imaging system of linear array for apparent disease detection of piping lane which characterized in that includes:
a guide rail laid within the pipe gallery;
the first rotating cloud platform and the second rotating cloud platform are both hung on the guide rail and can move along the guide rail;
the image acquisition and detection device is arranged on the first rotating holder through the first rotating bracket; the image acquisition and detection device comprises a binocular structure linear array camera and an area array camera; the binocular structure linear array camera is characterized in that two linear array cameras are placed in a non-coplanar structure to form a binocular structure, the linear array cameras are embedded into a camera support frame in a front-back arrangement mode, and the linear array cameras respectively and completely scan the same plane at different visual angles; the area array camera is embedded into the camera support frame and is positioned behind the binocular structure linear array camera so as to shoot a more complete detection surface; the image shot by the area-array camera and the images collected by the two linear-array cameras are subjected to feature matching together, so that the integrity of the detected target is controlled, and the image matching precision is improved;
the method comprises the following steps: triggering the binocular structure linear array camera and the area array camera to acquire an apparent image of the pipe gallery at the same time;
identifying the type and outline of the disease in the collected image;
calibrating the outline of the disease to obtain the size of the disease;
the process of calibrating the disease outline comprises the following steps:
imaging any space point P to be measured on the two linear array cameras respectively, and calibrating the coordinate of the space point P under a pixel coordinate system;
establishing a world coordinate system by taking the optical center of the double linear array camera as an origin, converting points under a pixel coordinate system into points under the world coordinate system, and calculating to obtain the coordinates of the point P under the world coordinate system;
solving three-dimensional coordinates, namely world coordinates, of two points to be detected on the disease outline, and solving the distance between the two points to be detected, namely the size of the disease;
the auxiliary calibration device is arranged on the second rotating holder through a second rotating bracket;
and the processor is used for receiving the pipe gallery apparent images acquired by the binocular structure linear array camera and the area array camera simultaneously, identifying the type and the outline of the disease, and calibrating the outline of the disease through the position of the auxiliary calibration device to obtain the size of the disease.
2. The linear array binocular imaging system for pipe gallery apparent disease detection of claim 1, wherein the image acquisition detection device is mounted on a camera support frame, the camera support frame is fixed on a stabilizing pan/tilt head, and the stabilizing pan/tilt head is mounted on the first rotating support.
3. The linear array binocular imaging system for pipe gallery apparent disease detection according to claim 2, wherein a pan/tilt control device is further fixed to the stabilizing pan/tilt, the pan/tilt control device is connected with the first rotating pan/tilt, and the pan/tilt control device is used for controlling movement of the first rotating pan/tilt.
4. The linear array binocular imaging system for pipe gallery apparent disease detection of claim 3, wherein the pan-tilt control device includes a deflection angle detection module, a micro control module, a drive module and a feedback module; the deflection angle detection module is used for detecting the angle change of the first rotating holder and the angle change of each camera and transmitting the angle changes to the micro-control module and the feedback module; the micro-control module is used for controlling the driving module to control the angles of the first rotating bracket and the camera support frame and adjust the shooting posture of the camera; the feedback device calculates and feeds back angle deviation information to the processor and the manual control platform to compensate the deviation angle of the disease size identification.
5. The linear array binocular imaging system for pipe gallery apparent disease detection according to claim 1, wherein the auxiliary calibration device includes a telescopic module and a calibration plate, the calibration plate being connected to the second rotary pan/tilt head through the telescopic module.
6. The linear array binocular imaging system for pipe gallery apparent disease detection according to claim 5, wherein the telescopic modules include vertical telescopic rods and horizontal telescopic rods, triangular suction cups are further fixed to the vertical telescopic rods, and the triangular suction cups are further adsorbed to the horizontal telescopic rods.
7. The linear array binocular imaging system for pipe gallery apparent disease detection according to claim 1, wherein the first rotating pan-tilt and the second rotating pan-tilt are both connected with corresponding moving mechanisms through bidirectional damping shock absorbers, and the moving mechanisms are matched with guide rails in shape and wrap the guide rails.
8. The linear array binocular imaging system for pipe gallery apparent disease detection according to claim 7, wherein the first rotating pan and the second rotating pan operate synchronously on the guide rails, and the moving mechanism moves on the guide rails at a speed matching the scanning resolution of the linear array camera and the area array camera.
9. A method of operation of the linear array binocular imaging system for pipe gallery apparent disease detection according to any one of claims 1 to 8, comprising:
triggering the binocular structure linear array camera and the area array camera to acquire an apparent image of the pipe gallery at the same time;
identifying the type and outline of the disease in the collected image;
calibrating the outline of the disease to obtain the size of the disease;
the process of calibrating the disease outline comprises the following steps:
imaging any space point P to be measured on the two linear array cameras respectively, and calibrating the coordinate of the space point P under a pixel coordinate system;
establishing a world coordinate system by taking the optical center of the double linear array camera as an origin, converting points under a pixel coordinate system into points under the world coordinate system, and calculating to obtain the coordinates of the point P under the world coordinate system;
and (3) solving the three-dimensional coordinates of the two points to be detected on the disease contour, namely world coordinates, and solving the distance between the two points to be detected, namely the size of the disease.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011065679.4A CN112329531B (en) | 2020-09-30 | 2020-09-30 | Linear array binocular imaging system for pipe gallery apparent disease detection and working method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011065679.4A CN112329531B (en) | 2020-09-30 | 2020-09-30 | Linear array binocular imaging system for pipe gallery apparent disease detection and working method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112329531A CN112329531A (en) | 2021-02-05 |
| CN112329531B true CN112329531B (en) | 2023-04-07 |
Family
ID=74313338
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011065679.4A Active CN112329531B (en) | 2020-09-30 | 2020-09-30 | Linear array binocular imaging system for pipe gallery apparent disease detection and working method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112329531B (en) |
Families Citing this family (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114113118B (en) * | 2021-12-01 | 2023-10-13 | 同济大学 | Rapid detection device and detection method for subway tunnel lining crack leakage water disease |
| CN114419421A (en) * | 2022-01-21 | 2022-04-29 | 中国地质大学（北京） | Subway tunnel crack identification system and method based on images |
| CN115792747B (en) | 2023-02-13 | 2023-04-28 | 北京航空航天大学 | Multi-mode magnetic particle imaging fixing and registering calibration system |
| CN117646828B (en) * | 2024-01-29 | 2024-04-05 | 中国市政工程西南设计研究总院有限公司 | Device and method for detecting relative displacement and water leakage of pipe jacking interface |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100592350C (en) * | 2008-01-11 | 2010-02-24 | 长安大学 | A traffic information acquisition system based on linear array CCD video camera imaging |
| 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 |
| CN106289106B (en) * | 2016-08-04 | 2017-12-12 | 北京航空航天大学 | The stereo vision sensor and scaling method that a kind of line-scan digital camera and area array cameras are combined |
| CN207238542U (en) * | 2017-08-09 | 2018-04-17 | 中国计量大学 | A kind of thin bamboo strip defect on-line detecting system based on machine vision |
| CN207991478U (en) * | 2017-12-25 | 2018-10-19 | 中铁科学技术开发公司 | Railway tunnel lining surface disease rapid detection system |
| CN108896552A (en) * | 2018-05-09 | 2018-11-27 | 赵启林 | Disease automatic checkout system in bridge chamber |
| CN108918539B (en) * | 2018-07-27 | 2020-06-09 | 同济大学 | Apparent disease detection device and method for tunnel structure |
| CN109406525B (en) * | 2018-08-24 | 2023-06-16 | 辽宁省交通规划设计院有限责任公司 | Bridge apparent disease detection system and detection method thereof |
-
2020
- 2020-09-30 CN CN202011065679.4A patent/CN112329531B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN112329531A (en) | 2021-02-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112329531B (en) | Linear array binocular imaging system for pipe gallery apparent disease detection and working method | |
| WO2021068846A1 (en) | Multi-arm robot for tunnel lining detection and disease diagnosis in operating period | |
| CN104655047B (en) | The rapid integrated measuring system in tunnel | |
| CN110161043A (en) | A kind of subway tunnel structure synthetic detection vehicle | |
| CN102298818B (en) | Binocular shooting fire detecting and positioning device and fire positioning method thereof | |
| CN108303426B (en) | Cable tunnel defect nondestructive rapid detection device and detection method thereof | |
| CN209181784U (en) | A kind of video grammetry device applied to automated parking system | |
| CN111412342A (en) | Pipeline detection robot and pipeline detection method | |
| CN111413353A (en) | Tunnel lining disease comprehensive detection vehicle | |
| WO2013115454A1 (en) | Device for inspecting inside of sewer pipe using laser profiler | |
| US20210132195A1 (en) | Mobile apparatus and method for capturing an object space | |
| CN110389041A (en) | The test macro and method of vehicle looked around with the integrated system of ultrasonic wave | |
| CN207141381U (en) | Detect multiple wing unmanned plane in a kind of bridge bottom | |
| CN111398309A (en) | Apparent detection system of tunnel lining disease comprehensive detection vehicle | |
| CN111398950A (en) | Radar detection evasion system of tunnel defect comprehensive detection vehicle | |
| CN110702016A (en) | Power transmission line icing measurement system and method | |
| CN110954541A (en) | Device and method for detecting cracks of porcelain insulator of power transmission line of 10kV or below | |
| CN112907647B (en) | Three-dimensional space size measurement method based on fixed monocular camera | |
| CN105389824A (en) | Calibration apparatus and calibration method for optical imaging device of electrified railway catenary | |
| CN109579798A (en) | A kind of video grammetry method and measuring equipment applied to automated parking system | |
| CN205210957U (en) | Calibration arrangement for electronic railway connecting net optical imaging equipment | |
| KR102240507B1 (en) | Apparatus for inspecting inside of manhole and method for inspecting manhole using the same | |
| CN105180906B (en) | Underground photogrammeter and its mapping method | |
| CN110453578A (en) | A kind of urban road detection robot system | |
| KR101172873B1 (en) | 3d image photographing apparatus for tunnel surveying |
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 |