CN110763697A - Method for detecting engineering structure surface crack by using aircraft - Google Patents
Method for detecting engineering structure surface crack by using aircraft Download PDFInfo
- Publication number
- CN110763697A CN110763697A CN201910789063.2A CN201910789063A CN110763697A CN 110763697 A CN110763697 A CN 110763697A CN 201910789063 A CN201910789063 A CN 201910789063A CN 110763697 A CN110763697 A CN 110763697A
- Authority
- CN
- China
- Prior art keywords
- aircraft
- distance
- measured
- images
- working distance
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
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
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/9515—Objects of complex shape, e.g. examined with use of a surface follower device
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
- G01N21/9515—Objects of complex shape, e.g. examined with use of a surface follower device
- G01N2021/9518—Objects of complex shape, e.g. examined with use of a surface follower device using a surface follower, e.g. robot
Abstract
The invention provides a method for detecting cracks on the surface of an engineering structure by using an aircraft, which comprises the following steps: determining a flight route of the aircraft and a plurality of image shooting points; the aircraft flies along the flight route, and images are shot at all image shooting points; obtaining an initial surface three-dimensional model of the object to be measured according to the shot image; recording the serial number of the image with the crack; according to the images of the cracks, the aircraft flies to the cracks to perform close-range shooting to obtain close-range images of the cracks; obtaining a surface three-dimensional model of the object to be measured according to the images shot at the image shooting points and the close-range images of the cracks; projecting and pasting the close-range image of each crack to a surface three-dimensional model of the object to be detected, and realizing position marking of the crack on the surface of the object to be detected; the basic parameters of each fracture are determined. The method can realize comprehensive quantitative detection of the surface cracks of the existing engineering structures such as piers and the like by the unmanned aerial vehicle platform.
Description
Technical Field
The application relates to the technical field of engineering structure detection, in particular to a method for detecting cracks on the surface of an engineering structure by using an aircraft.
Background
Surface crack identification is an important index for representing the safety condition of an existing engineering structure (such as a bridge, a tunnel, a dam, a building and the like), and has important significance in monitoring or detecting the existing structure. Surface cracks typically occur for a variety of reasons. For example, in the case of a bridge pier, surface cracks are generated due to various causes including abutment displacement, shrinkage and creep of concrete, deformation of a member, fatigue load, and the like.
At present, the detection of surface cracks of existing engineering structures (for example, piers) mainly depends on manual means. With the development of software and hardware technologies, the method for identifying the cracks on the surface of the pier by adopting the unmanned aerial vehicle system is gradually mature and applied. Compared with an artificial method, the unmanned aerial vehicle platform is adopted and a digital image method is combined, so that the identification efficiency of surface cracks of the existing engineering structure (such as a pier) can be effectively improved, and the safety of operation is improved.
In the prior art, the main steps of adopting the unmanned aerial vehicle system to identify the cracks on the surface of the pier comprise:
first, the drone platform may take a picture at a location close to the pier surface, obtaining a close-range view similar to a manual inspection. Secondly, the digital image method is reasonably used, and quantitative measurement of crack parameters can be realized. The digital image method utilizes a picture shot on the surface of a structure, and obtains parameters such as width, length, distribution and the like of a crack through the processes of crack existence judgment, crack extraction, crack correction, parameter calculation and the like, wherein the crack existence judgment refers to the judgment of whether the crack exists in an image and is different from other objects similar to the crack; the crack extraction is to extract cracks in a cracked image and eliminate the influence of background and noise; the crack correction means that the deformation of the crack in the image is corrected according to different imaging environments and structural surface shapes to obtain the shape of the crack; the crack parameter calculation refers to calculating parameters such as crack width, length and distribution by using a real crack form.
However, the width of the crack on the surface of the actual pier is about 0.1mm to 10mm, and the width of a large number of cracks is within 1 mm. If the unmanned aerial vehicle is used for remotely inspecting the bridge pier, cracks within the width of 1mm can not be found due to insufficient image resolution, and the practicability is not strong; however, if the crack is observed in a close range only by using the unmanned aerial vehicle, the visual field range of the shot image is too small, the crack obtained by recognition is incomplete, and the position of the crack can not be positioned in the later period. The technical application of the unmanned aerial vehicle method for detecting the cracks on the surface of the pier is restricted by the problems.
Disclosure of Invention
In view of the above, the invention provides a method for detecting cracks on the surface of an engineering structure by using an aircraft, so that comprehensive quantitative detection of the surface of the existing engineering structure by an unmanned aerial vehicle system platform can be realized, and fine cracks can be accurately identified.
The technical scheme of the invention is realized as follows:
a method of detecting cracks in a surface of an engineered structure using an aircraft, the method comprising:
determining a flight path of the aircraft and a plurality of image shooting points on the flight path according to the minimum crack width to be identified and the shape of the object to be detected;
the aircraft carrying the camera device flies along a flight path, images are shot at each image shooting point, and a unique serial number is set for each image;
performing multi-view geometry-based three-dimensional reconstruction according to the shot images to obtain an initial surface three-dimensional model of the object to be detected and aircraft positions and shooting views corresponding to the images;
judging whether cracks exist in the shot images, recording the serial numbers of the images with the cracks, and determining the positions and the visual angles of the aircrafts corresponding to the images with the cracks;
according to the aircraft position and the shooting visual angle corresponding to each image with cracks, the aircraft flies to each crack to carry out close-range shooting, and close-range images of each crack are obtained;
merging the image sets according to the images shot at the image shooting points and the close-range images of the cracks, and performing three-dimensional reconstruction again to obtain a surface three-dimensional model of the object to be measured;
the method comprises the following steps of (1) projecting and pasting the close-range images of all cracks to a surface three-dimensional model of an object to be detected by using a crack projection method, and realizing position marking of the cracks on the surface of the object to be detected;
and determining basic parameters of each crack according to the close-range image of each crack.
Further, the determining the flight path of the aircraft and the plurality of image shooting points on the flight path according to the minimum crack width to be identified and the shape of the object to be detected comprises:
setting the flight path of the aircraft into one or more concentric circular tracks around the center of the object to be measured; each circular track is vertically distributed, and the vertical distance between any two adjacent circular tracks is equal;
determining the working distance of the aircraft and the radius of each circular track according to the minimum crack width to be identified and the radius of the minimum circumcircle of the cross section of the object to be detected;
according to the radius of the minimum circumscribed circle of the cross section of the object to be measured and the working distance of the aircraft, a plurality of image shooting points are determined on the circular track, so that the coincidence rate of the images shot by two adjacent image shooting points is larger than or equal to a preset percentage.
Further, the determining the working distance of the aircraft and the radius of each circular track according to the minimum crack width to be identified and the radius of the minimum circumscribed circle of the cross section of the object to be measured includes:
presetting a minimum crack width;
determining the maximum object distance between the aircraft and the object to be detected according to the minimum crack width;
determining the working distance of the aircraft according to the maximum object distance and the radius of the minimum circumcircle of the cross section;
and determining the radius of the circular track according to the radius of the minimum circumcircle of the cross section and the working distance.
Further, the following formula is used to determine the maximum object distance u between the aircraft and the object to be measuredmax：
Wherein, Wr、WpFor a preset minimum crack width, PcAnd v is a device parameter of the camera on the aircraft.
Further, when the cross section of the object to be measured is circular, the working distance of the aircraft is determined according to the following formula:
S≤l≤umax；
wherein S is the distance meeting the requirement of safe flight of the aircraft, l is the working distance of the aircraft, and u is the working distance of the aircraftmaxThe maximum object distance between the aircraft and the surface of the object to be measured.
Further, when the cross section of the object to be measured is non-circular, the working distance of the aircraft is determined according to the following formula:
wherein S is the distance meeting the requirement of safe flight of the aircraft, l is the working distance of the aircraft, and u is the working distance of the aircraftmaxThe maximum object distance between the aircraft and the surface of the object to be measured, r is the minimum circumscribed circle radius of the cross section of the object to be measured, and lambda is the length ratio of the long side and the short side of the cross section.
Further, the radius of the circular track is set as the sum of the minimum circumscribed circle radius of the cross section of the object to be measured and the working distance.
Further, determining a plurality of image shooting points on a circular track according to the radius of the minimum circumscribed circle of the cross section of the object to be detected and the working distance of the aircraft, so that the coincidence rate of the images shot by two adjacent image shooting points is greater than or equal to a preset percentage comprises:
according to the radius of the minimum circumscribed circle of the cross section of the object to be measured and the working distance of the aircraft, the central angle theta corresponding to two adjacent image shooting points is calculated by the following formula:
wherein r is the radius of the minimum circumcircle of the cross section of the object to be measured, l is the working distance of the aircraft, and gamma is the horizontal visual angle of the camera device;
according to the central angle theta, the number N of the image shooting points is calculated by using the following formular：
Wherein the content of the first and second substances,
the operation of rounding up;
according to the central angle theta and the number N of image shooting pointsrA plurality of image capturing points are arranged on a circular trajectory.
Further, the determining the flight path of the aircraft and the plurality of image shooting points on the flight path according to the minimum crack width to be identified and the shape of the object to be detected comprises:
when the cross section of the object to be detected is a chamfer rectangle, setting the flight path of the aircraft to be one or more chamfer rectangle tracks around the center of the object to be detected; each chamfer rectangular track is vertically distributed and has the same central axis, and any two adjacent chamfer rectangular tracks have the same vertical distance;
determining the working distance of the aircraft, and enabling the vertical distance between any point on the rectangular track of the chamfer angle and the object to be measured to be the working distance of the aircraft;
and determining a plurality of image shooting points on the rectangular chamfer track according to the working distance of the aircraft, so that the coincidence rate of the images shot by two adjacent image shooting points is greater than or equal to a preset percentage.
Further, determining a plurality of image shooting points on the rectangular chamfer track according to the working distance of the aircraft, so that the coincidence rate of the images shot by two adjacent image shooting points is greater than or equal to a preset percentage comprises:
according to the working distance of the aircraft, the distance d between two adjacent image shooting points is calculated by the following formula:
wherein d is the distance between two adjacent image shooting points, l is the working distance of the aircraft, and gamma is the horizontal visual angle of the camera device;
according to the distance d between two adjacent image shooting points, the number N of the image shooting points is calculated by using the following formular：
Wherein C is the perimeter of the chamfered rectangular track,
the operation of rounding up;
according to the distance d and the number N of image shooting pointsrAnd setting a plurality of image shooting points on the chamfered rectangular track.
As can be seen from the above, in the method for detecting a crack on a surface of an engineering structure by using an aircraft, since a flight path of the aircraft and a plurality of image shooting points on the flight path are determined according to the minimum crack width to be identified and the shape of an object to be detected, the aircraft flies along the flight path, images are shot at each image shooting point, a unique serial number is set for each image, and then three-dimensional reconstruction based on multi-view geometry is performed according to the shot images, so that an initial surface three-dimensional model of the object to be detected and aircraft positions and shooting views corresponding to each image are obtained; and then recording the sequence numbers of the images with cracks, determining the positions and visual angles of the aircrafts corresponding to the images with cracks, flying the aircrafts to the cracks for close-range shooting again to obtain close-range images of the cracks, merging the image sets according to the images shot at the image shooting points and the close-range images of the cracks, performing three-dimensional reconstruction again to obtain a surface three-dimensional model of the object to be detected, projecting and pasting the close-range images of the cracks to the surface three-dimensional model of the object to be detected, realizing position marking of the cracks on the surface of the object to be detected, and further combining methods such as a convolutional neural network and multi-visual angle geometric three-dimensional reconstruction to realize comprehensive quantitative detection of the unmanned aerial vehicle platform on the surface cracks of the existing engineering structure such as a bridge pier and accurately identify the tiny cracks.
Drawings
Fig. 1 is a flowchart of a method for detecting cracks on a surface of an engineered structure according to an embodiment of the present invention.
Fig. 2 is a schematic diagram of a circular trajectory in a first embodiment of the present invention.
Fig. 3 is a schematic view of the imaging principle of the camera device on the aircraft in the embodiment of the present invention.
FIG. 4 is a schematic diagram of a non-circular locus in a second embodiment of the present invention.
Fig. 5 is a schematic view of a crack width cloud effect in an embodiment of the invention.
Detailed Description
In order to make the technical scheme and advantages of the invention more apparent, the invention is further described in detail with reference to the accompanying drawings and specific embodiments.
Fig. 1 is a flowchart of a method for detecting cracks on a surface of an engineered structure according to an embodiment of the present invention.
As shown in fig. 1, the method for detecting a crack on a surface of an engineering structure in an embodiment of the present invention includes the following steps:
step 101, determining a flight path of the aircraft and a plurality of image shooting points on the flight path according to the minimum crack width required to be identified and the shape of the object to be detected.
And 102, flying the aircraft carrying the camera device along a flying route, shooting images at each image shooting point, and setting a unique serial number for each image.
And 103, performing multi-view geometry-based three-dimensional reconstruction according to the shot images to obtain an initial surface three-dimensional model of the object to be detected and aircraft positions and shooting views corresponding to the images.
And 104, judging whether the shot images have cracks or not, recording the serial numbers of the images with the cracks, and determining the positions and the visual angles of the aircrafts corresponding to the images with the cracks.
And 105, flying the aircraft to each crack to perform close-range shooting according to the aircraft position and the shooting angle corresponding to each crack-existing image, so as to obtain close-range images of each crack.
And 106, merging the image sets according to the images shot at the image shooting points and the close-range images of the cracks, and performing three-dimensional reconstruction again to obtain a surface three-dimensional model of the object to be measured.
And 107, projecting and mapping the close-range images of the cracks to a three-dimensional model of the surface of the object to be detected by using a crack projection method, so as to realize position marking of the cracks on the surface of the object to be detected.
And step 108, determining basic parameters of each crack according to the close-range image of each crack.
In addition, in the technical solution of the present invention, the step 101 can be implemented by using various implementation methods according to the requirements of the actual application. The technical solution of the present invention will be described in detail below by taking several implementation modes thereof as examples.
First embodiment (flight path is circular track):
for example, in a preferred embodiment of the present invention, the step 101 may include the following steps:
step 11, setting the flight path of the aircraft into one or more concentric circular tracks around the center of an object to be measured; the circular tracks are vertically distributed, and the vertical distance between any two adjacent circular tracks is equal.
When the cross section of the object to be measured is in various shapes such as a circle, a rectangle, a square, a chamfered rectangle and the like, the flight path of the aircraft can be set to be a circular track around the center of the object to be measured.
As shown in fig. 2, when the cross section of the object to be measured is circular, the circular track is a concentric circle of the cross section of the object to be measured. When the cross section of the object to be measured is non-circular (for example, rectangular, square or chamfered rectangle), the circular trajectory is a concentric circle of the smallest circumscribed circle of the cross section of the object to be measured.
In addition, since the object to be measured generally has a certain height, if the object to be measured is photographed only at a certain height around the object to be measured, it may be difficult to photograph all the outer surfaces of the object to be measured. Therefore, at this time, a plurality of concentric circular tracks are required to be arranged for the aircraft, and the plurality of concentric circular tracks are vertically distributed around the object to be measured, and the vertical distances between any two adjacent circular tracks are equal. When the aircraft starts to work, the aircraft can sequentially fly around the object to be measured along the circular tracks in a preset sequence (for example, a sequence from low to high or a sequence from high to low), and corresponding images are taken at the image taking points, so that images of all the outer surfaces to be measured of the object to be measured can be obtained.
And step 12, determining the working distance of the aircraft and the radius of each circular track according to the minimum crack width required to be identified and the radius of the minimum circumcircle of the cross section of the object to be detected.
Since the lens used by the imaging device (e.g., camera, etc.) disposed on the aircraft is typically the primary lens with a fixed focal length, the distance of the aircraft from the surface of the object to be measured will determine the size of the imaged scene and the width of the smallest crack that can be detected.
As shown in fig. 2, when the flight path of the aircraft is a circular trajectory around the center of the object to be measured in step 11, the distance from the aircraft to the surface of the object to be measured is the distance between the aircraft and the minimum circumscribed circle of the cross section of the object to be measured (referred to as the working distance of the aircraft).
When the cross section of the object to be measured is circular, the minimum circumscribed circle of the cross section coincides with the cross section. Therefore, when the aircraft flies along the circular track, the distance between the aircraft and the surface of the object to be measured is constant all the time and is a fixed value. When the cross section of the object to be measured is non-circular (for example, rectangular, square or chamfered rectangle), the minimum circumcircle of the cross section surrounds the cross section and does not completely coincide with the cross section. Therefore, when the aircraft flies along a circular track, the distance between the aircraft and the surface of the object to be measured changes with the position of the aircraft, and is not a constant value but a variable which changes with time or position.
Therefore, in the technical solution of the present invention, after the minimum crack width to be identified and the radius of the minimum circumscribed circle of the cross section of the object to be detected are determined, the radius of a circular track can be selected or calculated according to the minimum crack width and the radius of the minimum circumscribed circle, so that when the aircraft flies along the circular track, the aircraft can shoot the object to be detected at a relatively suitable distance (the distance also needs to meet the requirement of safe flight of the aircraft), so that the image shot by the aircraft has sufficient definition, and thus the crack with the minimum crack width can be identified from the shot image, so as to identify all the cracks to be detected from the shot images in the subsequent step 104.
In the technical solution of the present invention, the step 12 can be implemented by using various implementation methods. The technical solution of the present invention will be described in detail below by taking several specific implementation manners as examples.
For example, in a preferred embodiment of the present invention, a minimum crack width may be preset (e.g., a minimum crack width is preset according to the specific situation of the object to be tested and the requirements of the relevant structural inspection specifications), the minimum crack width is the detectable minimum crack width, and in general, the minimum crack width may be 0.1mm, and then the maximum object distance u between the aircraft and the object to be tested is determined according to the preset minimum crack widthmax(i.e. the maximum distance between the aircraft and the surface of the object to be measured in one circle of the aircraft flying along the circular track), and according to the maximum object distance umaxAnd determining the distance l between the aircraft and the minimum circumcircle of the cross section of the object to be detected (the working distance of the aircraft for short) according to the radius r of the minimum circumcircle of the cross section, and then determining the radius of the circular track according to the radius r of the minimum circumcircle of the cross section and the working distance l.
In addition, the inventionIn the technical scheme, the maximum object distance u between the aircraft and the object to be measured can be determined by using various implementation methods according to the requirements of actual application conditionsmax. The technical solution of the present invention will be described in detail below by taking one specific implementation manner as an example.
For example, as shown in fig. 3, the lens 31 in the figure may be used to represent a lens of an image pickup device on an aircraft, with the right side of the lens being a surface 32 of an object to be measured and the left side of the lens being an imaging area 33 (e.g., a camera sensor CMOS or CCD, etc.) of the image pickup device. According to the pinhole imaging formula, the method comprises the following steps:
where u is the object distance (i.e., the distance between the lens and the surface of the object to be measured), v is the image distance (i.e., the distance between the lens and the imaging area), and f is the focal length of the lens.
The minimum crack width that needs to be detected and identified can generally be determined by industry specifications or standards in the art, for example, typically the minimum crack width that needs to be identified is 0.1 millimeters (mm).
From the thin lens model shown in fig. 3, the minimum crack width that can be detected and identified by the camera on the aircraft can be expressed as:
wherein, WrIs the minimum crack width in millimeters, WpIs the minimum crack width in pixels, PcThe image sensor is a camera sensor (e.g., CMOS or CCD), and includes pixels per millimeter (ppmm, i.e., the number of pixels per millimeter), u is an object distance (i.e., the distance between the aircraft and the surface of the object to be measured), and v is an image distance.
Thus, by way of example, in a preferred embodiment of the invention, the following formula may be used to determine the maximum object distance u between the aircraft and the object to be measuredmax：
Wherein, Wr、WpIs a preset minimum crack width, and PcAnd v are the equipment parameters of the camera on the aircraft (i.e. the physical parameters of the imaging element), these 4 parameters being all preset or known parameters. Therefore, according to the preset minimum crack width WrThe maximum object distance u between the aircraft and the object to be measured can be calculated by the formulamax. Therefore, when the distance between the aircraft and the surface of the object to be measured is less than or equal to the maximum object distance umaxIn this case, the minimum crack width to be identified can be detected and identified by means of a camera device on the aircraft.
In addition, in the technical scheme of the invention, the W can be preset according to the requirements of practical application conditionsrAnd WpThe value of (a). For example, in a preferred embodiment of the invention, W may berAnd WpIs set to the narrowest detectable crack should contain at least 1, 2 or 3 pixels in the width direction on the image, i.e. WpIs 1, 2 or 3, corresponding to WrCan be taken from PcAnd (4) calculating the value of the (A). Of course, in the technical solution of the present invention, W is as defined aboverAnd WpThe value of (b) may also be set to other suitable values according to the needs of the practical application (for example, quantitative identification of a crack smaller than 1 pixel width can be achieved by using methods such as sub-pixel or gray gradient, etc.), which is not described herein again.
In the present embodiment, the maximum object distance u between the aircraft and the surface of the object to be measured is determinedmaxThen, the maximum object distance u can be obtainedmaxAnd determining the distance between the aircraft and the minimum circumcircle of the cross section of the object to be measured, namely the working distance l of the aircraft.
For example, in a preferred embodiment of the invention, when the cross section of the object to be measured is circular, the working distance l of the aircraft can be determined according to the following formula, since the minimum circumcircle of the cross section coincides with the cross section:
S≤l≤umax(4)
wherein S is a safe distance (i.e. a distance meeting the requirement of safe flight of the aircraft), l is a working distance of the aircraft, and u ismaxThe maximum object distance between the aircraft and the surface of the object to be measured.
Therefore, in the technical scheme of the invention, when the cross section of the object to be measured is circular, the working distance l of the aircraft can be set as the maximum object distance u between the aircraft and the object to be measuredmaxThe working distance l of the aircraft can be set to be greater than or equal to S and less than or equal to u according to the requirements of the practical application environmentmaxAny value of (a).
For another example, in another preferred embodiment of the present invention, when the cross section of the object to be measured is non-circular (for example, rectangular, square or chamfered rectangle), since the minimum circumcircle of the cross section does not completely coincide with the cross section, the working distance l may be determined according to the following formula:
wherein S is a safe distance (i.e. a distance meeting the requirement of safe flight of the aircraft), l is a working distance of the aircraft, and u ismaxThe maximum object distance between the aircraft and the surface of the object to be measured, r is the minimum circumscribed circle radius of the cross section of the object to be measured, and lambda is the length ratio of the long side and the short side of the cross section.
Therefore, in the technical scheme of the invention, when the cross section of the object to be measured is non-circular, the working distance l of the aircraft can be set to be greater than or equal to S and less than or equal to S
Any one ofA value.
In addition, in the technical scheme of the invention, after the working distance l of the aircraft is determined, the radius of the circular track can be determined according to the minimum circumcircle radius r of the cross section and the working distance l of the aircraft.
For example, in a preferred embodiment of the present invention, the radius of the circular trajectory may be set as the sum of the minimum circumcircle radius r of the cross section of the object to be measured and the working distance l, that is:
R＝l+r (6)
wherein, R is the radius of the circular track, l is the working distance of the aircraft (i.e. the distance between the aircraft and the minimum circumscribed circle of the cross section of the object to be measured), and R is the radius of the minimum circumscribed circle of the cross section of the object to be measured.
And step 13, determining a plurality of image shooting points on the circular track according to the radius r of the minimum circumcircle of the cross section of the object to be detected and the working distance l of the aircraft, so that the coincidence rate of the images shot by two adjacent image shooting points is greater than or equal to a preset percentage.
In the technical scheme of the invention, in order to facilitate the three-dimensional reconstruction based on multi-view geometry according to the shot images in the subsequent steps, certain requirements are required for the coincidence rate of the images shot by two adjacent image shooting points.
For example, in a preferred embodiment of the present invention, the predetermined percentage may be 50%. Of course, in the technical solution of the present invention, the value of the percentage may also be set to other suitable values (for example, a value greater than 50%, such as 55%, 60%, etc.) according to the needs of the actual application situation, and is not described herein again.
Through the steps 11-13, when the cross section of the object to be detected is circular, the flight path of the aircraft and a plurality of image shooting points on the flight path can be determined according to the shape of the object to be detected.
In addition, in the technical solution of the present invention, a plurality of implementation methods may be used to determine a plurality of image capturing points on a circular trajectory. The technical solution of the present invention will be described in detail below by taking one specific implementation manner as an example.
In the technical scheme of the invention, in order to enable the coincidence rate of the images shot by two adjacent image shooting points to be greater than or equal to the preset percentage, the positions of the image shooting points on the track need to be reasonably set.
For example, as shown in fig. 2, when the cross section of the object to be measured is circular, the flight path of the aircraft is a concentric circular track, and the radius of the circular track is l + r, where r is the radius of the minimum circumscribed circle of the cross section of the object to be measured (in this case, the radius of the cross section of the object to be measured), and l is the working distance of the aircraft (i.e., the distance between the aircraft and the minimum circumscribed circle of the cross section of the object to be measured). The camera on the aircraft takes a picture of the center O of the object to be measured (e.g., a bridge pier). P1And P2Are two adjacent shot points on a circular locus, the optical axes of both shot points being directed toward the center O. Circular arc Q1Q3As a shot point P1Area photographed, arc Q2Q4As a shot point P2Area photographed, arc Q2Q3For two adjacent shot points P1And P2The overlapping area of the captured images. At this time, two adjacent shot points P1And P2The coincidence ratio of the captured images is exactly 50%. theta is the central angle ∠ P1O P2And gamma is the horizontal viewing angle of the camera device, namely the central angle of the range which can be shot by the camera device in the horizontal direction. As shown in fig. 2, when the coincidence rate of the images captured by two adjacent image capturing points is 50%, the two adjacent image capturing points P can be calculated and obtained according to the radius r of the minimum circumscribed circle of the cross section and the working distance l of the aircraft1And P2The corresponding central angle theta.
For example, in a preferred embodiment of the present invention, the step 13 may include the following steps:
according to the radius r of the minimum circumcircle of the cross section of the object to be measured and the working distance l of the aircraft, the central angle theta corresponding to two adjacent image shooting points is calculated by the following formula:
where γ is the horizontal viewing angle of the image pickup device, i.e., the central angle of the range that the image pickup device can capture in the horizontal direction.
From the central angle θ, the number N of image capturing points is calculated using the following formular：
Wherein the content of the first and second substances,
is an operation of rounding up.
According to the central angle theta and the number N of image shooting pointsrA plurality of image capturing points are arranged on a circular trajectory.
For example, as shown in FIG. 2, the number N of image capturing points is calculatedrAnd after the central angles theta corresponding to the two adjacent image shooting points, the positions of the image shooting points can be uniformly arranged on the circular track.
In addition, in the present invention, the central angle θ calculated according to the formula (7) satisfies the following condition: "the coincidence ratio of images captured by two adjacent image capturing points is equal to 50%".
If the coincidence rate of the images captured by two adjacent image capturing points is required to be greater than 50%, the central angle corresponding to the two adjacent image capturing points may be set to be smaller than the central angle θ calculated according to the formula (7), and then the number N of image capturing points is calculated according to the formula (8)r(ii) a On the other hand, if the coincidence rate of the images photographed by two adjacent image photographing points is required to be less than 50%, the central angle corresponding to the two adjacent image photographing points may be set to be greater than the central angle θ calculated according to the above formula (7), and thenThen the number N of the image shooting points is calculated according to the formula (8)r. The specific implementation is not described in detail herein.
In addition, when the cross section of the object to be measured is non-circular, the central angle θ calculated according to the above formula (7) may be calculated, and then the number N of image capturing points calculated according to the formula (8) may be obtainedr. However, since the minimum circumscribed circle of the cross section of the object to be measured does not completely coincide with the cross section of the object to be measured, the shot point P is taken when the cross section of the object to be measured is non-circular under the condition that the central angles θ are the same1And P2The coincidence rate of the shot images is larger than the shot point P when the cross section of the object to be measured is circular1And P2Coincidence ratio of the photographed images.
That is, when the cross section of the object to be measured is circular, if the central angle θ can make the shot point P1And P2The coincidence ratio of the photographed images is exactly 50%, and when the cross section of the object to be measured is non-circular, if the central angle θ is still used, the point P is photographed1And P2The coincidence of the captured images will tend to be conservatively greater than 50%.
In a second embodiment (when the cross section of the object to be measured is non-circular, the flight path is a non-circular trajectory):
according to the first embodiment, when the cross section of the object to be measured is non-circular, the flight path of the aircraft may also be a circular trajectory. However, the arrangement is more conservative, and the coincidence rate of the images captured by two adjacent image capturing points is greater than a preset percentage.
Therefore, in the present embodiment, when the cross section of the object to be measured is non-circular, the flight path of the aircraft may be set to be a non-circular track, so that the flight path of the aircraft is more consistent with the shape of the cross section of the object to be measured, thereby further improving the work efficiency.
For example, in an embodiment of the present invention, the step 101 may also include the following steps:
step 21, when the cross section of the object to be detected is a chamfer rectangle, setting the flight path of the aircraft as one or more chamfer rectangle tracks around the center of the object to be detected; the chamfer rectangular tracks are vertically distributed and have the same central axis, and any two adjacent chamfer rectangular tracks have the same vertical distance.
And step 22, determining the working distance l of the aircraft, and enabling the vertical distance between any point on the chamfer rectangular track and the object to be detected to be the working distance l of the aircraft.
In the technical solution of the present invention, the above step 22 can be implemented by using various implementation methods. The technical solution of the present invention will be described in detail below by taking one specific implementation manner as an example.
For example, in a preferred embodiment of the present invention, the maximum object distance u between the aircraft and the object to be measured may be determined according to a preset minimum crack width (i.e., the width of the minimum crack that can be detected) firstmaxAnd according to the maximum object distance umaxA working distance l of the aircraft is determined (e.g., S ≦ l ≦ umax). After the working distance l of the aircraft is determined, because the vertical distance between any point on the rectangular track of the chamfer and the object to be detected is the working distance l of the aircraft, the corresponding rectangular track of the chamfer can be determined according to the working distance l of the aircraft and the size of the cross section of the object to be detected.
In addition, in the technical scheme of the invention, the maximum object distance u between the aircraft and the object to be measured can be determined by using various implementation methods according to the requirements of practical application conditionsmax。
For example, in a preferred embodiment of the present invention, the above equation (3) may be used to determine the maximum object distance u between the aircraft and the object under testmax。
When the distance between the aircraft and the object to be measured (i.e. the working distance) is less than or equal to the maximum object distance umaxIn the process, the minimum crack width to be identified can be detected and identified by a camera device on the aircraft.
In addition, in the technical scheme of the invention, the W can be preset according to the requirements of actual application conditionsrAnd WpThe values of (a) are not described in detail herein.
In the present embodiment, the maximum object distance u between the aircraft and the object to be measured is determinedmaxThen, the maximum object distance u can be obtainedmaxThe working distance l of the aircraft is determined.
For example, in a preferred embodiment of the invention, the working distance l of the aircraft may be set to the maximum object distance u between the aircraft and the object to be measuredmax。
Of course, in the technical solution of the present invention, the working distance l of the aircraft may also be set to be greater than the safety distance (i.e. the distance satisfying the requirement of safe flight of the aircraft) S and less than or equal to u according to the requirement of the practical application environmentmaxAny value of (i.e., S < l ≦ u)max) Therefore, the description is omitted.
After the working distance l of the aircraft is determined, the corresponding chamfer rectangular track can be determined according to the working distance l of the aircraft and the size of the cross section of the object to be measured, so that the vertical distance between any point on the chamfer rectangular track and the object to be measured is the working distance l of the aircraft.
And step 23, determining a plurality of image shooting points on the chamfer rectangular track according to the working distance l of the aircraft, so that the coincidence rate of the images shot by two adjacent image shooting points is greater than or equal to a preset percentage.
For example, in a preferred embodiment of the present invention, the predetermined percentage may be 50%. Of course, the above percentage can also be set to other suitable values according to the requirements of the practical application, and will not be described herein again.
Through the steps 21-23, when the cross section of the object to be detected is a chamfered rectangle, the flight path of the aircraft and a plurality of image shooting points on the flight path can be determined according to the shape of the object to be detected.
In addition, in the technical solution of the present invention, a plurality of implementation methods may be used to determine a plurality of image capturing points on the chamfered rectangular trajectory. The technical solution of the present invention will be described in detail below by taking one specific implementation manner as an example.
For example, as shown in fig. 4, the cross section of the object to be measured is a chamfered rectangle, the flight path of the aircraft is a chamfered rectangular trajectory around the object to be measured, and the vertical distance from any point on the chamfered rectangular trajectory to the cross section of the object to be measured is the working distance l of the aircraft. P1And P2Are two adjacent shot points on the chamfered rectangular trajectory. Q1Q3Segment is shot point P1Area photographed, Q2Q4Segment is shot point P2Area photographed, Q2Q3The section is two adjacent shooting points P1And P2The overlapping area of the captured images. At this time, two adjacent shot points P1And P2The coincidence ratio of the captured images was exactly 50%. As shown in fig. 4, when the coincidence rate of the images captured by two adjacent image capturing points is 50%, a plurality of image capturing points can be determined on the chamfered rectangular trajectory according to the working distance l of the aircraft.
For example, in a preferred embodiment of the present invention, the step 23 may include the following steps:
according to the working distance l of the aircraft, the distance d between two adjacent image shooting points is calculated by the following formula:
wherein d is the distance between two adjacent image shooting points, l is the working distance of the aircraft, and γ is the horizontal viewing angle of the camera device, i.e. the central angle of the range that the camera device can shoot in the horizontal direction.
According to the distance d between two adjacent image shooting points, the number N of the image shooting points can be calculated by using the following formular：
Wherein C is the perimeter of the chamfered rectangular track,
is an operation of rounding up.
According to the distance d and the number N of image shooting pointsrAnd a plurality of image shooting points can be arranged on the chamfered rectangular track.
For example, the number N of image capturing points is calculatedrAnd the distance d between two adjacent image capture points, the positions of the respective image capture points can be uniformly set on the circular trajectory.
In addition, in the technical solution of the present invention, the distance d between two adjacent image capturing points calculated according to the above formula (9) satisfies the condition: "the coincidence ratio of images captured by two adjacent image capturing points is equal to 50%".
If the coincidence rate of the images captured by two adjacent image capturing points is required to be greater than 50%, the distance between the two adjacent image capturing points may be set to be smaller than the distance d calculated according to the above formula (9), and then the number N of image capturing points may be calculated according to the formula (10)r(ii) a If the coincidence rate of the images captured by two adjacent image capturing points is required to be less than 50%, the distance between the two adjacent image capturing points may be set to be greater than the distance d calculated according to the formula (9), and then the number N of image capturing points may be calculated according to the formula (10)r. The specific implementation is not described in detail herein.
In addition, in the technical solution of the present invention, one or more shooting points (such as the shooting point P in fig. 4) may be added at the corner of the chamfered rectangular track as appropriate3、P4And P5) So as to ensure that the coincidence rate of the images shot by two adjacent image shooting points meets the preset requirement.
Furthermore, when the aircraft moves along the straight section of the chamfered rectangular trajectory, the images taken by the respective shooting points will be parallel to each other. Furthermore, in order to avoid the larger area of uncertainty that may be caused by multiple parallel images (the area of the region of uncertainty), reducing the quality of the three-dimensional reconstruction in the subsequent steps, slightly tilted shots and denser shots may be taken on the straight segment of the chamfered rectangular trajectory.
Similarly, when the cross section of the object to be measured is rectangular, the flight path of the aircraft can also be set to be one or more rectangular tracks around the center of the object to be measured, each rectangular track is vertically distributed and has the same central axis, and any two adjacent rectangular tracks have the same vertical distance. Then, the subsequent steps are the same as the above steps 22 and 23, and thus are not described in detail herein.
In addition, in the technical solution of the present invention, if the flight path is set to a plurality of concentric circular tracks or non-circular tracks around the object to be measured, the aircraft may fly around the object to be measured along each track in the order from low to high or in the order from high to low, and capture corresponding images at each image capture point.
In addition, in the technical scheme of the invention, the vertical distance between two adjacent tracks can be preset according to the requirements of practical application conditions.
For example, in a preferred embodiment of the present invention, the vertical distance between two adjacent circular tracks or non-circular tracks may be set to 1/2, which is the height of the captured image. Of course, in the technical solution of the present invention, the value of the vertical distance may also be set to other suitable values according to the needs of the actual application, and is not described in detail herein.
In addition, as an example, in a preferred embodiment of the present invention, whether or not there is a crack in each captured image may be determined by a Convolutional Neural Network (CNN) method.
In addition, in step 105, the aircraft flies to each crack and takes a close-range shooting to obtain each crackA close-up image of the seam. According to the technical scheme, the distance between the aircraft and the crack in the situation can be preset according to the requirements of practical application conditions, so that the aircraft can shoot a clearer close-range image of the crack. In general, the distance between the aircraft and the crack in this case should be smaller than the maximum object distance u between the aircraft and the object to be measured in step 101max。
In addition, as an example, in a preferred embodiment of the present invention, when the aircraft flies to each crack for close-range shooting, the distance between the aircraft and the crack should satisfy the requirement that the width of the crack is more than 3 pixel points in the imaged image. Of course, in the technical solution of the present invention, the value of the number of the pixel points may also be set to other suitable values according to the needs of the actual application, for example, the number of the pixel points may be further reduced when a sub-pixel or gray scale gradient method is adopted, and so on, which is not described herein again.
In addition, as an example, in a preferred embodiment of the present invention, the basic parameter of the crack may be information of the width, the length, and the like of the crack.
In addition, as an example, in a preferred embodiment of the present invention, the aircraft may be a drone carrying a camera or other flying device which can carry a camera and fly according to a specified trajectory.
In the technical scheme of the invention, through the steps 101-108, the surface of the object to be detected can be comprehensively detected through the aircraft, cracks on the surface of the object to be detected can be detected, and related information of each crack can be marked at the image position where the crack exists, so that the crack can be displayed in a step-by-step manner through a crack width cloud chart and other forms. Fig. 5 is a schematic view of a crack width cloud effect in an embodiment of the invention. Fig. 5 is a typical projected crack width cloud effect. As shown in fig. 5, the position and distribution of each crack on the surface of the object to be measured can be visually and clearly obtained through the crack width cloud map, and the related information of each crack can be further obtained. Furthermore, different crack widths can be represented on the crack width cloud picture through different gray scales, so that a more intuitive crack width cloud picture can be formed.
In conclusion, the invention provides a method for quantitatively detecting surface cracks of piers by using an unmanned aerial vehicle, which combines methods such as a convolutional neural network and multi-view geometric three-dimensional reconstruction to realize comprehensive quantitative detection of the surface cracks of existing engineering structures such as piers by using an unmanned aerial vehicle platform and can accurately identify fine cracks.
The above description is only for the purpose of illustrating the preferred embodiments of the present invention and is not to be construed as limiting the invention, and any modifications, equivalents, improvements and the like made within the spirit and principle of the present invention should be included in the scope of the present invention.
Claims (10)
1. A method of detecting cracks in a surface of an engineered structure using an aircraft, the method comprising:
determining a flight path of the aircraft and a plurality of image shooting points on the flight path according to the minimum crack width to be identified and the shape of the object to be detected;
the aircraft carrying the camera device flies along a flight path, images are shot at each image shooting point, and a unique serial number is set for each image;
performing multi-view geometry-based three-dimensional reconstruction according to the shot images to obtain an initial surface three-dimensional model of the object to be detected and aircraft positions and shooting views corresponding to the images;
judging whether cracks exist in the shot images, recording the serial numbers of the images with the cracks, and determining the positions and the visual angles of the aircrafts corresponding to the images with the cracks;
according to the aircraft position and the shooting visual angle corresponding to each image with cracks, the aircraft flies to each crack to carry out close-range shooting, and close-range images of each crack are obtained;
merging the image sets according to the images shot at the image shooting points and the close-range images of the cracks, and performing three-dimensional reconstruction again to obtain a surface three-dimensional model of the object to be measured;
the method comprises the following steps of (1) projecting and pasting the close-range images of all cracks to a surface three-dimensional model of an object to be detected by using a crack projection method, and realizing position marking of the cracks on the surface of the object to be detected;
and determining basic parameters of each crack according to the close-range image of each crack.
2. The method of claim 1, wherein determining the flight path of the aircraft and the plurality of image capture points on the flight path according to the minimum crack width to be identified and the shape of the object to be tested comprises:
setting the flight path of the aircraft into one or more concentric circular tracks around the center of the object to be measured; each circular track is vertically distributed, and the vertical distance between any two adjacent circular tracks is equal;
determining the working distance of the aircraft and the radius of each circular track according to the minimum crack width to be identified and the radius of the minimum circumcircle of the cross section of the object to be detected;
according to the radius of the minimum circumscribed circle of the cross section of the object to be measured and the working distance of the aircraft, a plurality of image shooting points are determined on the circular track, so that the coincidence rate of the images shot by two adjacent image shooting points is larger than or equal to a preset percentage.
3. The method of claim 2, wherein determining the working distance of the aircraft and the radius of each circular track according to the minimum crack width to be identified and the radius of the minimum circumcircle of the cross section of the object to be measured comprises:
presetting a minimum crack width;
determining the maximum object distance between the aircraft and the object to be detected according to the minimum crack width;
determining the working distance of the aircraft according to the maximum object distance and the radius of the minimum circumcircle of the cross section;
and determining the radius of the circular track according to the radius of the minimum circumcircle of the cross section and the working distance.
4. A method according to claim 3, characterized in that the maximum object distance u between the aircraft and the object to be measured is determined using the following formulamax：
Wherein, Wr、WpFor a preset minimum crack width, PcAnd v is a device parameter of the camera on the aircraft.
5. Method according to claim 4, characterized in that when the cross-section of the object to be measured is circular, the working distance of the aircraft is determined according to the following formula:
S≤l≤umax；
wherein S is the distance meeting the requirement of safe flight of the aircraft, l is the working distance of the aircraft, and u is the working distance of the aircraftmaxThe maximum object distance between the aircraft and the surface of the object to be measured.
6. The method according to claim 4, characterized in that, when the cross section of the object to be measured is non-circular, the working distance of the aircraft is determined according to the following formula:
wherein S is the distance meeting the requirement of safe flight of the aircraft, l is the working distance of the aircraft, and u is the working distance of the aircraftmaxThe maximum object distance between the aircraft and the surface of the object to be measured, r is the minimum circumscribed circle radius of the cross section of the object to be measured, and lambda is the length ratio of the long side and the short side of the cross section.
7. The method according to claim 5 or 6, characterized in that:
and setting the radius of the circular track as the sum of the minimum circumscribed circle radius of the cross section of the object to be measured and the working distance.
8. The method of claim 7, wherein determining a plurality of image capturing points on a circular track according to the radius of the minimum circumcircle of the cross section of the object to be measured and the working distance of the aircraft, so that the coincidence ratio of the images captured by two adjacent image capturing points is greater than or equal to a preset percentage comprises:
according to the radius of the minimum circumscribed circle of the cross section of the object to be measured and the working distance of the aircraft, the central angle theta corresponding to two adjacent image shooting points is calculated by the following formula:
wherein r is the radius of the minimum circumcircle of the cross section of the object to be measured, l is the working distance of the aircraft, and gamma is the horizontal visual angle of the camera device;
according to the central angle theta, the number N of the image shooting points is calculated by using the following formular：
Wherein the content of the first and second substances,
the operation of rounding up;
according to the central angle theta and the number N of image shooting pointsrA plurality of image capturing points are arranged on a circular trajectory.
9. The method of claim 1, wherein determining the flight path of the aircraft and the plurality of image capture points on the flight path according to the minimum crack width to be identified and the shape of the object to be tested comprises:
when the cross section of the object to be detected is a chamfer rectangle, setting the flight path of the aircraft to be one or more chamfer rectangle tracks around the center of the object to be detected; each chamfer rectangular track is vertically distributed and has the same central axis, and any two adjacent chamfer rectangular tracks have the same vertical distance;
determining the working distance of the aircraft, and enabling the vertical distance between any point on the rectangular track of the chamfer angle and the object to be measured to be the working distance of the aircraft;
and determining a plurality of image shooting points on the rectangular chamfer track according to the working distance of the aircraft, so that the coincidence rate of the images shot by two adjacent image shooting points is greater than or equal to a preset percentage.
10. The method of claim 9, wherein determining a plurality of image capture points on a chamfered rectangular trajectory based on a working distance of the aircraft such that a coincidence of images captured by two adjacent image capture points is greater than or equal to a preset percentage comprises:
according to the working distance of the aircraft, the distance d between two adjacent image shooting points is calculated by the following formula:
wherein d is the distance between two adjacent image shooting points, l is the working distance of the aircraft, and gamma is the horizontal visual angle of the camera device;
according to the distance d between two adjacent image shooting points, the number N of the image shooting points is calculated by using the following formular：
Wherein C is the perimeter of the chamfered rectangular track,
the operation of rounding up;
according to the distance d and the number N of image shooting pointsrAnd setting a plurality of image shooting points on the chamfered rectangular track.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910789063.2A CN110763697B (en) | 2019-08-26 | 2019-08-26 | Method for detecting engineering structure surface crack by using aircraft |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910789063.2A CN110763697B (en) | 2019-08-26 | 2019-08-26 | Method for detecting engineering structure surface crack by using aircraft |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110763697A true CN110763697A (en) | 2020-02-07 |
| CN110763697B CN110763697B (en) | 2020-11-06 |
Family
ID=69329259
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910789063.2A Active CN110763697B (en) | 2019-08-26 | 2019-08-26 | Method for detecting engineering structure surface crack by using aircraft |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110763697B (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111457854A (en) * | 2020-04-16 | 2020-07-28 | 福建汇川物联网技术科技股份有限公司 | Deformation monitoring method and device based on building |
| CN111751211A (en) * | 2020-06-30 | 2020-10-09 | 中国科学院地质与地球物理研究所 | Rock fracturing network topological structure depicting method |
| CN112540089A (en) * | 2020-12-16 | 2021-03-23 | 江苏法尔胜材料分析测试有限公司 | Application method of digital imaging system in concrete bridge crack detection and analysis |
| CN112748121A (en) * | 2020-12-31 | 2021-05-04 | 天津大学 | Unmanned aerial vehicle detection method and device based on hydraulic structure surface cracks |
| CN113503793A (en) * | 2021-07-05 | 2021-10-15 | 贵州黔源电力股份有限公司普定发电公司 | Method for rapidly monitoring cracks of dam of hydropower station |
| CN113566730A (en) * | 2021-07-29 | 2021-10-29 | 广东电网有限责任公司 | Battery expansion deformation detection system and method |
| CN115217084A (en) * | 2022-07-22 | 2022-10-21 | 中国华能集团清洁能源技术研究院有限公司 | Reservoir area expansive soil surface crack rate detection method and system |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106645205A (en) * | 2017-02-24 | 2017-05-10 | 武汉大学 | Unmanned aerial vehicle bridge bottom surface crack detection method and system |
| CN107014827A (en) * | 2017-04-24 | 2017-08-04 | 国家电网公司 | Transmission line of electricity defect analysis method based on image processing, device and system |
| CN107328344A (en) * | 2017-07-01 | 2017-11-07 | 浙江大学宁波理工学院 | Unmanned plane for monitoring concrete structural surface fracture width |
| EP3273266A1 (en) * | 2016-07-21 | 2018-01-24 | Grupo Empresarial Copisa, S.L. | A system and a method for surface aerial inspection |
| CN109580649A (en) * | 2018-12-18 | 2019-04-05 | 清华大学 | A kind of identification of engineering structure surface crack and projection modification method and system |
-
2019
- 2019-08-26 CN CN201910789063.2A patent/CN110763697B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP3273266A1 (en) * | 2016-07-21 | 2018-01-24 | Grupo Empresarial Copisa, S.L. | A system and a method for surface aerial inspection |
| CN106645205A (en) * | 2017-02-24 | 2017-05-10 | 武汉大学 | Unmanned aerial vehicle bridge bottom surface crack detection method and system |
| CN107014827A (en) * | 2017-04-24 | 2017-08-04 | 国家电网公司 | Transmission line of electricity defect analysis method based on image processing, device and system |
| CN107328344A (en) * | 2017-07-01 | 2017-11-07 | 浙江大学宁波理工学院 | Unmanned plane for monitoring concrete structural surface fracture width |
| CN109580649A (en) * | 2018-12-18 | 2019-04-05 | 清华大学 | A kind of identification of engineering structure surface crack and projection modification method and system |
Non-Patent Citations (2)
| Title |
|---|
| BARKAVI, T.ET AL.: "Processing Digital Image for Measurement of Crack Dimensions in Concrete", 《CIVIL ENGINEERING INFRASTRUCTURES JOURNAL》 * |
| 厉狄龙等: "无人机在沿海腐蚀环境桥梁病害巡检中的应用", 《低温建筑技术》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111457854A (en) * | 2020-04-16 | 2020-07-28 | 福建汇川物联网技术科技股份有限公司 | Deformation monitoring method and device based on building |
| CN111751211A (en) * | 2020-06-30 | 2020-10-09 | 中国科学院地质与地球物理研究所 | Rock fracturing network topological structure depicting method |
| CN112540089A (en) * | 2020-12-16 | 2021-03-23 | 江苏法尔胜材料分析测试有限公司 | Application method of digital imaging system in concrete bridge crack detection and analysis |
| CN112540089B (en) * | 2020-12-16 | 2022-11-25 | 江苏法尔胜材料分析测试有限公司 | Application method of digital imaging system in concrete bridge crack detection and analysis |
| CN112748121A (en) * | 2020-12-31 | 2021-05-04 | 天津大学 | Unmanned aerial vehicle detection method and device based on hydraulic structure surface cracks |
| CN113503793A (en) * | 2021-07-05 | 2021-10-15 | 贵州黔源电力股份有限公司普定发电公司 | Method for rapidly monitoring cracks of dam of hydropower station |
| CN113566730A (en) * | 2021-07-29 | 2021-10-29 | 广东电网有限责任公司 | Battery expansion deformation detection system and method |
| CN113566730B (en) * | 2021-07-29 | 2023-09-08 | 广东电网有限责任公司 | Battery expansion deformation detection system and method |
| CN115217084A (en) * | 2022-07-22 | 2022-10-21 | 中国华能集团清洁能源技术研究院有限公司 | Reservoir area expansive soil surface crack rate detection method and system |
| CN115217084B (en) * | 2022-07-22 | 2023-07-28 | 中国华能集团清洁能源技术研究院有限公司 | Method and system for detecting surface fracture rate of expansive soil in reservoir area |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110763697B (en) | 2020-11-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110763697B (en) | Method for detecting engineering structure surface crack by using aircraft | |
| JP6734583B2 (en) | Image processing system, image processing method and program for inspecting structures such as bridges | |
| CN111260615B (en) | Laser and machine vision fusion-based method for detecting apparent diseases of unmanned aerial vehicle bridge | |
| KR101569193B1 (en) | Crack measuring device for long distance and crack measuring method using same | |
| JP6408434B2 (en) | Road marking body deterioration detection method | |
| CN105953741B (en) | System and method for measuring local geometric deformation of steel structure | |
| CN108476282A (en) | Radiography assisting device and photography householder method | |
| CN102589529B (en) | Scanning close-range photogrammetry method | |
| CN114462646B (en) | Pole number plate identification method and system based on contact network safety inspection | |
| CN110809779B (en) | Image synthesizing method, image synthesizing device and recording medium | |
| JP2007212187A (en) | Stereo photogrammetry system, stereo photogrammetry method, and stereo photogrammetry program | |
| CN109447946B (en) | Overhead communication optical cable abnormality detection method | |
| Murao et al. | Concrete crack detection using uav and deep learning | |
| CN115330726A (en) | Quick evaluation system for quality of steel bar protection layer and wall quality | |
| CN110634136B (en) | Pipeline wall damage detection method, device and system | |
| JP7314466B2 (en) | Unmanned aerial vehicle, imaging system, and program | |
| Merkle et al. | Sensor evaluation for crack detection in concrete bridges | |
| RU2519005C1 (en) | Method of prestart check of printboards | |
| CN112734721A (en) | Optical axis deflection angle detection method, device, equipment and medium | |
| CN111738148A (en) | Fault identification method by utilizing infrared inspection shooting | |
| JP6132221B1 (en) | Image acquisition method and image acquisition apparatus | |
| CN109342439A (en) | Cable Structure appearance detecting method based on unmanned plane | |
| CN112257514B (en) | Infrared vision intelligent detection shooting method for equipment fault inspection | |
| JP7433623B2 (en) | Structure image management system | |
| CN116934756B (en) | Material detection method based on image processing |
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 |