CN106226157B - Concrete structure member crevices automatic detection device and method - Google Patents
Concrete structure member crevices automatic detection device and method Download PDFInfo
- Publication number
- CN106226157B CN106226157B CN201610799729.9A CN201610799729A CN106226157B CN 106226157 B CN106226157 B CN 106226157B CN 201610799729 A CN201610799729 A CN 201610799729A CN 106226157 B CN106226157 B CN 106226157B
- Authority
- CN
- China
- Prior art keywords
- image
- crack
- component
- dark area
- concrete structure
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 49
- 238000000034 method Methods 0.000 title claims abstract description 30
- 238000012360 testing method Methods 0.000 claims abstract description 37
- 238000012545 processing Methods 0.000 claims abstract description 25
- 239000004615 ingredient Substances 0.000 claims description 32
- 239000000284 extract Substances 0.000 claims description 17
- 238000012946 outsourcing Methods 0.000 claims description 15
- 230000009194 climbing Effects 0.000 claims description 14
- 238000006243 chemical reaction Methods 0.000 claims description 7
- 238000001914 filtration Methods 0.000 claims description 6
- 238000009499 grossing Methods 0.000 claims description 6
- 238000000605 extraction Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 abstract description 3
- 238000012797 qualification Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 7
- 230000033001 locomotion Effects 0.000 description 6
- 238000005286 illumination Methods 0.000 description 4
- 240000002853 Nelumbo nucifera Species 0.000 description 2
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 2
- 235000006510 Nelumbo pentapetala Nutrition 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 241001269238 Data Species 0.000 description 1
- 241000196324 Embryophyta Species 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015271 coagulation Effects 0.000 description 1
- 238000005345 coagulation Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000009365 direct transmission Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 230000001360 synchronised effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N3/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N3/02—Details
- G01N3/06—Special adaptations of indicating or recording means
- G01N3/068—Special adaptations of indicating or recording means with optical indicating or recording means
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2203/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N2203/0058—Kind of property studied
- G01N2203/006—Crack, flaws, fracture or rupture
- G01N2203/0062—Crack or flaws
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N2203/00—Investigating strength properties of solid materials by application of mechanical stress
- G01N2203/02—Details not specific for a particular testing method
- G01N2203/06—Indicating or recording means; Sensing means
- G01N2203/0641—Indicating or recording means; Sensing means using optical, X-ray, ultraviolet, infrared or similar detectors
- G01N2203/0647—Image analysis
Landscapes
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Materials By The Use Of Optical Means Adapted For Particular Applications (AREA)
- Image Analysis (AREA)
- Image Processing (AREA)
Abstract
The present invention discloses a kind of concrete structure member crevices automatic detection device, method and system, the detection device, method and system are the crack images that component deformation generates when by load by image acquisition device bridge member, and the image is sent in image processing system and is handled, obtain the image information that component generates crack.The device, method and system obtain the crack information of component by the way of obtaining image automatically, can objectively be judged according to image information different parts, width, length crack whether belong to the qualification determination standard in stress crack, and the image information can be realized data and upload to Environment in Railway Engineering Construction information management platform data center, facilitates the acquisition of bridge member load test data and improves the authenticity, correctness, reliability of bridge member load test data.
Description
Technical field
The present invention relates to component qualities to examine apparatus field, detects dress automatically more particularly to a kind of concrete structure member crevices
It sets, method and system.
Background technique
As shown in figure 8, having a kind of bridge static loading test automatic control device in the prior art, including for controlling entire examination
The test master control set for testing process further includes the loading actuator connecting with test master control set, load measurement device, scratches
It spends measuring device, deviate capacity checking device and anomaly alarming device.Test master control set is also configured with for data upload and image
The long-distance monitorng device that remotely monitors, manual-operated emergent device, full-automatic/semiautomatic plant and for completing examination by a key operation
Test a key control device of overall process.Synchronous load is realized the arrangement achieves bridge static loading test and each load point loading is automatic
Balance ensure that the true, accurate, reliable of test data, improves the degree of automation, reduces experimental labor and equipment, realize
Test data uploads and long-range monitoring.
But the detection of the Bridge Crack of the device is carried out there is still a need for artificial observation, not only everyone to different parts,
Width, length crack whether belong to stress crack qualification determination standard it is different, the sense of responsibility of observer is different, also
" turning a blind eye to " imitation behavior etc. directly influences the authenticity, correctness, reliability of bridge member load test data.
Summary of the invention
The object of the present invention is to provide a kind of concrete structure member crevices automatic detection device, method and system, detection dresses
It sets, method and system are by the image acquisition device bridge member crack pattern that component deformation generates when by load
Picture, and the image is sent in image processing system and is handled, obtain the image information that component generates crack.The device,
Method and system obtain the crack information of component by the way of obtaining image automatically, can objectively be judged according to image information
Different parts, width, length crack whether belong to the qualification determination standard in stress crack, and the image information can be realized
Data upload to Environment in Railway Engineering Construction information management platform data center, facilitate bridge member load test data acquisition and
Improve the authenticity, correctness, reliability of bridge member load test data.
To achieve the above object, the present invention provides a kind of concrete structure member crevices automatic detection devices, comprising:
Image collecting device, for acquiring the image of the component；
Image processing apparatus, described image processing unit are connected with described image acquisition device, for identification the figure
Crack as in；
Moving bearing device, for carrying described image acquisition device, and the moving bearing device can be along the structure
At least one of part face to be detected is mobile.
Optionally, the moving bearing device includes moving track, and described image acquisition device is set to the moving track
Upper and described image acquisition device can move on the moving track, and the moving track can be along the component at least
One face to be detected is mobile, the shifting of described image the acquisition device moving direction on the moving track and the moving track
The angle in dynamic direction is greater than 0 ° and less than 180 °.
Optionally, the moving track and the component contact position are equipped with mobile mechanism, and the moving track is equipped with and climbs
Wall robot, the top surface of the climbing robot are in contact with the surface of the component, and the climbing robot is along the component
Surface creep and drive the moving track to move along the component；The mobile mechanism includes being set to the moving track two
The idler wheel at end, the idler wheel are contacted with the component.
Optionally, described image acquisition device includes camera lens and light compensating lamp, and the light compensating lamp is used to shoot for the camera lens
Image provides supplementary lighting sources.
Another object of the present invention is to provide a kind of concrete structure member crevices automatic testing methods, comprising:
Obtain the image of component；
Extract grayscale information in described image；
The dark area in described image is determined according to the grayscale information；
The crack of the component is identified based on the dark area.
Optionally, after described based on the crack of dark area identification means, further includes:
The angle of straight line where obtaining the crack and the component laterally,
Judge whether the angle is greater than 45 °, obtains the first judging result；
When first judging result expression is, determine that the crack is target crack；
When first judging result indicates no, determine that the crack is non-targeted crack
Optionally, the crack that the component is identified based on the dark area, is specifically included:
Low-pass filtering is carried out to the image comprising the dark area using Gaussian smoothing filter method；
Obtain the error image of the image of filtered image and the dark area；
Extract the directional information in crack in the error image；
In conjunction with the directional information, binary conversion treatment is carried out to the filtered crack image, obtains binary image；
The desultory point and agglomerate in the binary image are rejected, crack is extracted.
Optionally, the directional information for extracting crack in the error image, specifically includes:
Choose a pixel (i, j) in the filtered crack image；
Centered on the pixel (i, j), choosing height is h, and width is the rectangular area of w；
Calculate the gradient mean value in the direction x and y in the rectangular area；
The phase angle of any pixel (i, j) in the rectangular area is calculated according to the gradient mean value.
Optionally, the desultory point and agglomerate rejected in the binary image, extracts crack, specifically includes:
Obtain the outsourcing rectangle of gloomy ingredient in the binary image；
Calculate the length-width ratio of the outsourcing rectangle；
Judge whether the length-width ratio is greater than setting length-width ratio, obtains the second judging result；
When second judging result expression is, non-crack area is rejected according to the syntople of each outsourcing rectangle, really
The gloomy ingredient that the fixed remaining outsourcing rectangle is surrounded is target crack；
When second judging result indicates no, determine gloomy ingredient that the outsourcing rectangle is surrounded be desultory point or
Agglomerate, and reject the desultory point or the agglomerate.
Optionally, the detection method further include:
The image for obtaining the crack position again, obtains secondary image；
Identify the secondary crack in the secondary image；
Compare the length in the secondary crack and the crack in the secondary image, obtains comparison result；
When the comparison result indicate the secondary crack length be greater than the crack length, determine the quadratic diagram
Crack ingredient as in is target crack；
When the comparison result indicates that the length in the secondary crack is not more than the length in the crack, rejecting is described gloomy
Region records testing result.
Optionally, the detection method further include:
Obtain the crack image information collected in advance；
Based on the crack image information, extract containing the crack general character in crannied image；
The crack in the image of the component is identified according to the crack general character.
Another object of the present invention is to provide a kind of concrete structure member crevices automatic checkout system, comprising:
Image acquisition unit, for obtaining the image of component；
Grayscale information extraction unit, for extracting grayscale information in described image；
Dark area determination unit determines the dark area in described image according to the grayscale information；
Crack identification unit identifies the crack of the component based on the dark area.
The specific embodiment provided according to the present invention, the invention discloses following technical effects: coagulation provided by the invention
Image of the native structure member crevices automatic detection device using the image acquisition device component surface that can be moved on component, warp
After crossing image processing apparatus processing, the crack ingredient in image is obtained, to realize the Crack Detection of component.Through the invention
Crack detecting device progress Crack Detection avoids artificial observation and judges security risk existing for crack, and can be objective, true
It is real, accurate to obtain crack information, improve the authenticity, correctness, reliability of bridge member load test data.The present invention
A kind of concrete structure member crevices automatic testing method and system are additionally provided, this method and system pass through the neighborhood ash scale in crack
Different significant properties detects crack, and this method and system can accurately identify true crack present in the image of acquisition,
And recognition result is recorded, realize the transmission of crack data.
Detailed description of the invention
It in order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, below will be to institute in embodiment
Attached drawing to be used is needed to be briefly described, it should be apparent that, the accompanying drawings in the following description is only some implementations of the invention
Example, for those of ordinary skill in the art, without any creative labor, can also be according to these attached drawings
Obtain other attached drawings.
Fig. 1 is the structural schematic diagram of concrete structure member crevices automatic detection device provided in an embodiment of the present invention；
Fig. 2 provides the structural schematic diagram of small rail car for the embodiment of the present invention；
Fig. 3 is the structural schematic diagram of climbing robot provided in an embodiment of the present invention；
Fig. 4 is the structural schematic diagram of image collecting device provided in an embodiment of the present invention；
Fig. 5 is the structural schematic diagram of component far infrared cruise target point provided in an embodiment of the present invention；
Fig. 6 is the overview flow chart of concrete structure member crevices automatic testing method provided in an embodiment of the present invention；
Fig. 7 is the flow chart of secondary detection in concrete structure member crevices automatic testing method provided in an embodiment of the present invention；
Fig. 8 is the flow chart in the crack provided in an embodiment of the present invention based on dark area identification means；
Fig. 9 is the flow chart of the directional information in crack in extraction error image provided in an embodiment of the present invention；
Figure 10 is in image provided in an embodiment of the present invention by the grid chart of the straight line of a pixel；
Figure 11 is the binary image provided in an embodiment of the present invention by binary conversion treatment；
Figure 12 is the closed operation image provided in an embodiment of the present invention handled by space closed operation；
Figure 13 is desultory point and agglomerate in rejecting binary image provided in an embodiment of the present invention, extracts crack and marks
The flow chart in crack；
Figure 14 is screening crack provided in an embodiment of the present invention image；
Figure 15 is the image provided in an embodiment of the present invention in original image behind mark crack.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
The present invention provides a kind of concrete structure member crevices automatic detection devices, as shown in Figure 1, comprising:
Image collecting device 3, the image for acquisition member 1；
Image processing apparatus (not shown in figure 1), image processing apparatus are connected with image collecting device 3, for identification
Crack in image；
Moving bearing device 2, for carrying image collecting device 3, and moving bearing device 2 can be along component 1 at least
One face to be detected is mobile.
Present embodiment is to utilize the image on the 3 acquisition member surface of image collecting device that can be moved on component 1, warp
After crossing image processing apparatus processing, the crack ingredient in image is obtained, to realize the Crack Detection of component.Through the invention
Crack detecting device progress Crack Detection avoids artificial observation and judges security risk existing for crack, and can be objective, true
It is real, accurate to obtain crack information, improve the authenticity, correctness, reliability of bridge member load test data.
As an alternative embodiment, unlike other embodiments, as shown in figs. 1 and 3, mobile carrying dress
Setting 2 includes moving track 4, and image collecting device 3 is set on moving track 4 and image collecting device 3 can be on moving track 4
Mobile, moving track 4 can be moved along at least one face to be detected of component 1, and in the present embodiment, moving track 4 is along structure
The bottom surface of part 1 is mobile；The angle of the moving direction of moving direction of the image collecting device 3 on moving track 4 and moving track 4
Greater than 0 ° and less than 180 °.Specifically, moving track 4 and 1 contact position of component are equipped with mobile mechanism, moving track is equipped with and climbs wall
Robot 5, the top surface of climbing robot 5 are adsorbed in 1 surface of component, and climbing robot 5 is adsorbed in component 1 and along 1 surface of component
The impetus creeped is able to drive moving track 4 and vertically moves along component, to realize the image collecting device 3 of carrying along structure
Part longitudinal movement, realizes the acquisition of longitudinal member image.
Mobile mechanism in present embodiment can be the idler wheel 5 that moving track both ends are arranged in, and pass through idler wheel 5 and component
1 contact, and rolled along component 1, realize the movement of moving track 4.
Mobile mechanism in present embodiment can be the sliding block (not shown in figure 1) being arranged on moving track and set
The sliding rail (not shown in figure 1) compatible with sliding block on component is set, such moving track can be moved along the sliding rail, be secured
Motion track of the moving track on component, while also can be avoided the problem of moving track deviates the detection faces of component, it can
Improve detection accuracy.
Different from the embodiment described above is that moving bearing device can also be that unmanned plane by manual remote control, image are adopted
Acquisition means are set on unmanned plane, and image collecting device and image processing apparatus can pass through wirelessly transmitting data.Personnel can pass through
Remote controlled drone shoots the image of component any part.
As an alternative embodiment, unlike other embodiments, as Fig. 2 and 3 image collecting devices 3 are wrapped
Include camera lens 8.The camera lens 8 further includes industrial lens including one or two kinds of in line-scan digital camera, area array cameras.Optionally, the camera lens
8 are arranged on small rail car 6, which is arranged on moving track 4, can move along moving track 4, small rail car 6
Moving direction it is different from the moving direction of moving track 4, so that camera lens 8 be enable to take the entire detection faces of component, cover
Lid detection is wide, is not in missing inspection situation, and then improves the comprehensive and accuracy in detection crack.It is another optional real
Mode is applied, camera lens 8 can also be arranged on climbing robot 5, it is connected by a shooting arm 9 with the climbing robot 5, the bat
Taking the photograph arm 9 can be 180 ° around 5 horizontal hunting of climbing robot.The camera lens of the set-up mode is to carry out structure with circular scanning process
The Image Acquisition of part detection faces, the structure of small rail car 6 is eliminated in this way, simplifies acquisition device, while utilizing shooting arm 9
Swing realize the acquisition of component detection faces image, and when moving track 4 is moved to a certain position, the mirror of the set-up mode
First 8 can take larger range of image, improve collecting efficiency.
As an alternative embodiment, unlike other embodiments, as shown in figure 4, image collecting device 3
It further include light compensating lamp 10, light compensating lamp 10, which is used to shoot image for camera lens 8, provides supplementary lighting sources.Light compensating lamp can be annular light source or
Strip source.Under normal circumstances, bridge upper surface can be bent downwardly deformation by lower surface after load, in order to detect bridge member
Whether occur crack after lower surface is loaded, be all to carry out Image Acquisition in the lower surface of component, but component lower surface illumination is insufficient,
The clarity that Image Acquisition can be seriously affected, therefore, it is necessary to the light compensating lamps to provide compensation light for camera lens, to guarantee Image Acquisition
Clearly, so improve crack identification accuracy and precision.
Image collecting device includes kilomega network industry area array CCD (charge coupled in the present embodiment
Device) camera 11, industrial lens 12, machine vision LED bar graph light source 10.Using kilomega network industry area array CCD (charge
Coupled device) camera 11, the conduct camera lens 8 of industrial lens 12, light compensating lamp is used as using machine vision LED bar graph light source 10
10.Kilomega network industry area array cameras 11 uses ccd sensor, realizes that high speed fine definition stablizes imaging, makes camera applications in more
Extensive industrial occasions.The industrial camera 12 has the characteristics that high-resolution, high speed, high-precision, fine definition, low noise,
Kilomega network output, direct transmission range are widely used in the field of machine vision of high-speed, high precision up to 100m.Machine vision
LED bar graph light source is suitble to be detected the surface illumination of object in machine vision, can provide the oblique fire of matching object from any angle
Illumination is widely used in surface crack detection etc. with the distribution of high brightness in strip structure.Its brightness and setting angle are equal
It is adjustable, have the characteristics that high brightness, low temperature, equilibrium, flicker free.Make machine vision LED bar graph light source with maximum power output, adjusts
Aperture, the focal length of whole industrial lens, so that image is in best sharpness.The time for exposure of camera also should not be too large, and prevent image
Image caused by image streaking in collection process is fuzzy.
The detection range covering bridge box and beam component span centre of the concrete structure member crevices automatic detection device or so each bottom 2m
The cambered surface of upward 15cm at face and lower flange base angle.
As an alternative embodiment, unlike other embodiments, concrete structure member crevices as shown in Figure 5
Automatic detection device further includes control device, far infrared cruise target point 13, control device respectively with climbing robot 5, image
Acquisition device 3 is connected with image processing apparatus, and control device control climbing robot 5 is adsorbed in component 1 and patrols according to far infrared
The target point 13 that navigates is mobile；It is mobile simultaneously according to far infrared cruise target point 13 on moving bearing device 2 to control image collecting device 3
Acquire image；And the crack ingredient in control image processing apparatus identification image, and will treated through image processing apparatus
Image transmitting is to Environment in Railway Engineering Construction information management platform data center.The component that can be realized automation is arranged in the control device
The identification of Image Acquisition and structure member crevices avoids the judgment criteria difference of artificial observation appearance and causes crack information inaccurate
True problem generates, and improves the detection accuracy and detection efficiency of structure member crevices, improves the safety of engineering test.
As an alternative embodiment, the concrete structure member crevices are examined automatically unlike other embodiments
Surveying device further includes warning device, which includes acoustic alarm and light alarm, when image processing apparatus detects in image
There are when crack, which alarms, to remind worker to determine crack and take corresponding measure.
Another object of the present invention is to provide a kind of concrete structure member crevices automatic testing methods, as shown in fig. 6, packet
It includes:
Step 601: obtaining the image of component；
Step 602: extracting grayscale information in image；
Step 603: the dark area in image is determined according to grayscale information；
Step 604: the crack based on dark area identification means.
Wherein, dark area is the region that gray scale is less than setting gray threshold, and the crack in image is gray value in image
Lesser region, therefore, when gray scale be less than setting gray threshold region be likely to crack occur, reduce identification range, add
Fast recognition rate.
The concrete structure member crevices automatic testing method is carried out using above-mentioned concrete structure member crevices automatic detection device
Detection, is moved back and forth on moving bearing device, and moving bearing device moves on component using image collecting device, right
Bridge box and beam component bears larger moment of flexure position and is scanned, in the Processing Algorithm identification image in motion picture processing device
Crack ingredient, and record Crack Detection result.
As an alternative embodiment, after the crack based on dark area identification means, further includes:
The angle of straight line where obtaining crack and component laterally,
Judge whether angle is greater than 45 °, obtains the first judging result；
When the expression of the first judging result is, determine that crack is target crack；
When the first judging result indicates no, determine that crack is non-targeted crack.
As an alternative embodiment, as shown in fig. 7, the detection method further include:
Step 701: obtaining the image of crack position again, obtain secondary image；
Step 702: the secondary crack in identification secondary image；
Step 703: comparing the length in the secondary crack and crack in secondary image, obtain comparison result；
When comparison result indicate secondary crack length be greater than crack length, determine that the crack ingredient in secondary image is
Target crack, and issue alarm signal；
When comparison result indicates that the length in secondary crack is not more than the length in crack, rejecting dark area, record detection knot
Fruit.
Before on-test, the detection zone of component is swept first using above-mentioned concrete structure member crevices automatic testing method
It retouches, detect primary, the coordinate of the incipient crack of recording member beam bottom.During test, need to apply component 1.00 grades extremely
1.20 grades of load, control device control moving bearing device carrying image acquisition device sweep component beam body key area
It retouches, scan image is transmitted to image processing apparatus and is handled, detected and extracted crack coordinate.At different levels before 1.20 grades apply
Load the interior completion of lotus 5min 1 time, 1.20 grades of acquisition, processing and the stress crack for holding 4 image datas of completion in lotus 20min is sentenced
It is fixed, wherein also to obtain the corresponding position coordinates of the initial pictures while obtaining initial pictures, also obtained when obtaining image again
Corresponding position coordinates of image, and the image of same position coordinate twice is compared, compare crack in the image of two sides at
The length divided, if comparison result indicates: the crack ingredient length in secondary image is greater than the crack ingredient in previous image
Length, then the crack ingredient in secondary image is true crack, i.e., the crack generated after application load extracts and records quadratic diagram
Picture, and alarm, so that worker confirms crack and positions.If when comparison result indicates: the crack ingredient length in secondary image
No more than the length of the crack ingredient in previous image, previous image and secondary image are rejected, records testing result, is illustrated initial
Crack in image is not to apply load and generate, therefore reject, and record testing result.
Wherein, the position coordinates of image are the far infrared cruise target point according to setting and the fortune for controlling climbing robot
What the motion profile of dynamic rail mark and image collecting device determined.
In the above-described embodiment, detect crack ingredient from the image of collected bridge bottom, need by image into
Row binary conversion treatment belongs to the scope of image segmentation.Then from treated, ingredient filters out desultory point and sheet of region, extracts
Crack ingredient.In order to carry out the segmentation of image by the way of dynamic threshold binaryzation, and consider the grain distribution in crack
Characteristic excludes the interference of desultory point, agglomerate, proposes a kind of crack detection method of local binarization based on fractuer direction distribution,
The step of i.e. above-mentioned crack based on dark area identification means, as shown in figure 8, specifically including:
Step 801: low-pass filtering being carried out to the image comprising dark area using Gaussian smoothing filter method；
Step 802: obtaining the error image of the image of filtered image and dark area；
Step 803: extracting the directional information in crack in error image；
Step 804: bonding position information carries out binary conversion treatment to the image of dark area, obtains binary image；
Step 805: rejecting the desultory point and agglomerate in binary image, extract crack and mark crack.
Wherein, single channel image is obtained after acquired image being carried out gray processing processing.Due to illumination in collection process,
The problems such as shake, is mixed with noise in image, so that part pixel value and its neighborhood territory pixel deviation are larger in image.Therefore it is carrying out
It needs to carry out Gaussian smoothing to image before crack extract to obtain the low pass ingredient of image after low-pass filtering.Then lead to
It crosses original image and low-pass filtered image work is poor, obtain the radio-frequency component of crack image.To guarantee the accuracy of crack extract.
Wherein, in order to obtain in image each point directional information, it is necessary first to obtain x, the direction gradient of y, gradient value
It obtains the first differential used and obtains the gradient in both directionWithIn order to make the direction of each pixel
Information is accurate as far as possible, uses regional area pixel in the present embodiment as a reference to being calculated.Such as Fig. 9 institute
Show, specifically, the step of extracting the directional information in crack in filtered crack image specifically includes:
Step 901: choosing a pixel (i, j) in filtered crack image；
Step 902: centered on pixel (i, j), choosing height is h, and width is the rectangular area of w；
Step 903: calculating the gradient mean value in the direction x and y in rectangular area；
Step 904: the phase angle of any pixel (i, j) in rectangular area is calculated according to gradient mean value.
Wherein, the calculation formula of gradient mean value are as follows:
It is obtained in rectangular area after x, y direction gradient mean value, is estimated by the mean value in rectangular area every by above formula
The phase of a point, the calculation formula of phase are as follows:After obtaining the directional information in crack, i.e.,
Multistage crack figure can be integrated into a crack, can accurately more determine crack location, improve the precision of Crack Detection.
The local binarization method of dynamic threshold in present embodiment is incited somebody to action based on Niblack method
The algorithm that Niblack binarization method is combined with the phase of each point in image.
In the picture a bit (i, j), as shown in Figure 10, first, in accordance with the phase of point (i, j) in the x and y direction and
The coordinate of point, which can be found out, takes each N number of point of the poincare half plane of the straight line, lower half-plane by the straight line, and it is straight to count this
The mean value m (i, j) and variance s (i, j) of 2N+1 point on line:
In this algorithm, I (i, j) is the pixel value size at point (i, j), this phase straight line is taken on target point (i, j)
On pixel as reference, using the straight line as template, obtained threshold value are as follows: T (x, y)=m (x, y)+ks (x, y)
In above formula, k is correction factor, is usually provided by requirement of engineering.It, can after obtaining the decision threshold of object pixel
The point is determined:
After each pixel in image passes through algorithm calculating, the binary image of target image is just obtained.In order to
It makes narrow notch up, uses space closed operation, smooth binary image is as a result, effect is as shown in FIG. 11 and 12.
As an alternative embodiment, as shown in figure 13, rejecting the desultory point and agglomerate in binary image, extracting
Crack and the step of mark crack, specifically includes:
Step 1301: obtaining the outsourcing rectangle of gloomy ingredient in binary image；
Step 1302: calculating the length-width ratio of outsourcing rectangle；
Step 1303: judging whether length-width ratio is greater than setting length-width ratio, obtain judging result；
Step 1304: when judging result expression is, non-crack area being rejected according to the syntople of each outsourcing rectangle, really
The gloomy ingredient that the fixed remaining outsourcing rectangle is surrounded is target crack；
Step 1305: when comparison result indicates no, determining that the gloomy ingredient that outsourcing rectangle is surrounded is desultory point or group
Block, and reject desultory point or agglomerate.
There are many spuious points, agglomerate by the image after binaryzation, in order to filter out these ingredients, present embodiment is adopted
With the limitation of target outsourcing rectangular aspect ratio, length limitation, area limitation etc., realizes the automatic fitration of dirty point or agglomerate, screen
Long and narrow ingredient out.Then by interstitial syntople, isolated ingredient is rejected.As shown in FIG. 14 and 15, rectangle frame packet
The ingredient of quilt is the crack ingredient that meets the requirements, and marks out crack ingredient in original image finally to observe.
As an alternative embodiment, the detection method further include:
Obtain the crack image information collected in advance；
Based on crack image information, extract containing the crack general character in crannied image；
According to the crack in the image of crack general character identification means.
The present embodiment uses Machine self-learning method, and study identification crack reduces identification difficulty, improves identification
Rate.
Another object of the present invention is to provide a kind of concrete structure member crevices automatic checkout system, comprising:
Image acquisition unit, for obtaining the image of component；
Grayscale information extraction unit, for extracting grayscale information in image；
Dark area determination unit determines the dark area in image according to grayscale information；
Crack identification unit, the crack based on dark area identification means.
The concrete structure member crevices automatic testing method is carried out using above-mentioned concrete structure member crevices automatic detection device
Detection, is moved back and forth on moving bearing device, and moving bearing device moves on component using image collecting device, right
Bridge box and beam component bears larger moment of flexure position and is scanned, in the Processing Algorithm identification image in motion picture processing device
Crack ingredient, and record Crack Detection result.
Each embodiment in this specification is described in a progressive manner, the highlights of each of the examples are with other
The difference of embodiment, the same or similar parts in each embodiment may refer to each other.For system disclosed in embodiment
For, since it is corresponded to the methods disclosed in the examples, so being described relatively simple, related place is said referring to method part
It is bright.
Used herein a specific example illustrates the principle and implementation of the invention, and above embodiments are said
It is bright to be merely used to help understand method and its core concept of the invention；At the same time, for those skilled in the art, foundation
Thought of the invention, there will be changes in the specific implementation manner and application range.In conclusion the content of the present specification is not
It is interpreted as limitation of the present invention.
Claims (11)
1. a kind of concrete structure member crevices automatic detection device characterized by comprising
Image collecting device, for acquiring the image of the component；
Image processing apparatus, described image processing unit are connected with described image acquisition device, for identification in described image
Crack, it is described identification described image in crack method specifically include:
Obtain the image of component；
Extract grayscale information in described image；
The dark area in described image is determined according to the grayscale information；
The crack of the component is identified based on the dark area, specifically includes the following steps:
Low-pass filtering is carried out to the image comprising the dark area using Gaussian smoothing filter method；
Obtain the error image of the image of filtered image and the dark area；
Extract the directional information in crack in the error image；
In conjunction with the directional information, binary conversion treatment is carried out to the image of the dark area, obtains binary image；
The desultory point and agglomerate in the binary image are rejected, crack is extracted；
Moving bearing device, for carrying described image acquisition device, and the moving bearing device can be along the component
At least one face to be detected is mobile.
2. concrete structure member crevices automatic detection device according to claim 1, which is characterized in that the mobile carrying dress
It sets including moving track, described image acquisition device is set on the moving track and described image acquisition device can be described
It is moved on moving track, the moving track can be moved along at least one face to be detected of the component, described image acquisition
The angle of the moving direction of moving direction of the device on the moving track and the moving track is greater than 0 ° and less than 180 °.
3. concrete structure member crevices automatic detection device according to claim 2, which is characterized in that the moving track with
The component contact position is equipped with mobile mechanism, and the moving track is equipped with climbing robot, the top surface of the climbing robot
Be in contact with the surface of the component, the climbing robot along the component surface creep and drive the moving track edge
The component is mobile；The mobile mechanism includes the idler wheel set on the moving track both ends, and the idler wheel connects with the component
Touching.
4. concrete structure member crevices automatic detection device according to claim 1, which is characterized in that described image acquisition dress
It sets including camera lens and light compensating lamp, the light compensating lamp, which is used to shoot image for the camera lens, provides supplementary lighting sources.
5. a kind of concrete structure member crevices automatic testing method characterized by comprising
Obtain the image of component；
Extract grayscale information in described image；
The dark area in described image is determined according to the grayscale information；
The crack of the component is identified based on the dark area, specifically includes the following steps:
Low-pass filtering is carried out to the image comprising the dark area using Gaussian smoothing filter method；
Obtain the error image of the image of filtered image and the dark area；
Extract the directional information in crack in the error image；
In conjunction with the directional information, binary conversion treatment is carried out to the image of the dark area, obtains binary image；
The desultory point and agglomerate in the binary image are rejected, crack is extracted.
6. concrete structure member crevices automatic testing method according to claim 5, which is characterized in that described based on gloomy
After the crack of region recognition component, further includes:
The angle of straight line where obtaining the crack and the component laterally,
Judge whether the angle is greater than 45 °, obtains the first judging result；
When first judging result expression is, determine that the crack is target crack；
When first judging result indicates no, determine that the crack is non-targeted crack.
7. concrete structure member crevices automatic testing method according to claim 5, which is characterized in that described to extract the difference
It is worth the directional information in crack in image, specifically includes:
Choose a pixel (i, j) in the filtered crack image；
Centered on the pixel (i, j), choosing height is h, and width is the rectangular area of w；
Calculate the gradient mean value in the direction x and y in the rectangular area；
The phase angle of any pixel (i, j) in the rectangular area is calculated according to the gradient mean value.
8. concrete structure member crevices automatic testing method according to claim 5, which is characterized in that described to reject described two
Desultory point and agglomerate in value image are extracted crack, are specifically included:
Obtain the outsourcing rectangle of gloomy ingredient in the binary image；
Calculate the length-width ratio of the outsourcing rectangle；
Judge whether the length-width ratio is greater than setting length-width ratio, obtains the second judging result；
When second judging result expression is, non-crack area is rejected according to the syntople of each outsourcing rectangle, is determined surplus
Besides the gloomy ingredient that packet rectangle is surrounded is target crack；
When second judging result indicates no, determine that the gloomy ingredient that the outsourcing rectangle is surrounded is desultory point or group
Block, and reject the desultory point or the agglomerate.
9. concrete structure member crevices automatic testing method according to claim 5, which is characterized in that the detection method is also
Include:
The image for obtaining the crack position again, obtains secondary image；
Identify the secondary crack in the secondary image；
Compare the length in the secondary crack and the crack in the secondary image, obtains comparison result；
When the comparison result indicate the secondary crack length be greater than the crack length, determine in the secondary image
Crack ingredient be target crack；
When the comparison result indicates that the length in the secondary crack is not more than the length in the crack, the rejecting grey dark space
Domain records testing result.
10. concrete structure member crevices automatic testing method according to claim 5, which is characterized in that the detection method
Further include:
Obtain the crack image information collected in advance；
Based on the crack image information, extract containing the crack general character in crannied image；
The crack in the image of the component is identified according to the crack general character.
11. a kind of concrete structure member crevices automatic checkout system characterized by comprising
Image acquisition unit, for obtaining the image of component；
Grayscale information extraction unit, for extracting grayscale information in described image；
Dark area determination unit determines the dark area in described image according to the grayscale information；
Crack identification unit identifies the crack of the component based on the dark area, specifically includes the following steps:
Low-pass filtering is carried out to the image comprising the dark area using Gaussian smoothing filter method；
Obtain the error image of the image of filtered image and the dark area；
Extract the directional information in crack in the error image；
In conjunction with the directional information, binary conversion treatment is carried out to the image of the dark area, obtains binary image；
The desultory point and agglomerate in the binary image are rejected, crack is extracted.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610799729.9A CN106226157B (en) | 2016-08-31 | 2016-08-31 | Concrete structure member crevices automatic detection device and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610799729.9A CN106226157B (en) | 2016-08-31 | 2016-08-31 | Concrete structure member crevices automatic detection device and method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN106226157A CN106226157A (en) | 2016-12-14 |
| CN106226157B true CN106226157B (en) | 2019-04-16 |
Family
ID=58075114
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610799729.9A Active CN106226157B (en) | 2016-08-31 | 2016-08-31 | Concrete structure member crevices automatic detection device and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106226157B (en) |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106645171A (en) * | 2016-12-22 | 2017-05-10 | 江苏工程职业技术学院 | Method for detecting concrete cracks by using wall-climbing robot |
| CN106643541B (en) * | 2016-12-26 | 2019-09-06 | 深圳高速工程顾问有限公司 | A kind of method and device of real-time monitoring data of bridge administrative analysis |
| CN107436304A (en) * | 2017-09-20 | 2017-12-05 | 程丹秋 | A kind of surface of concrete structure detection means |
| CN110287976A (en) * | 2018-03-19 | 2019-09-27 | 中国科学院遥感与数字地球研究所 | A kind of device and method of automatic identification remote sensing Alteration anomaly |
| CN109342216B (en) * | 2018-09-27 | 2024-02-20 | 国网宁夏电力有限公司电力科学研究院 | Concrete pole mechanical property detecting system |
| CN109297977A (en) * | 2018-10-26 | 2019-02-01 | 华北水利水电大学 | A kind of equipment for the detection of bridge bottom stability |
| CN109459443A (en) * | 2018-11-08 | 2019-03-12 | 青海民族大学 | A kind of detection of extremely frigid zones Bridge Crack and analytic method based on machine vision |
| CN110132152B (en) * | 2019-05-29 | 2020-12-25 | 河海大学 | Automatically controlled touring monitoring devices of concrete gravity dam crack under water |
| CN110231347A (en) * | 2019-06-19 | 2019-09-13 | 湖南桥康智能科技有限公司 | A kind of bridge bottom surface detection device and method |
| CN111105401B (en) * | 2019-12-20 | 2020-10-27 | 浙江元本检测技术股份有限公司 | Concrete crack detection and repair method and device based on image processing and electronic equipment |
| CN111311555B (en) * | 2020-01-22 | 2023-07-14 | 哈尔滨工业大学 | Large intelligent temporary stand safety detection system |
| CN114002228A (en) * | 2021-11-05 | 2022-02-01 | 华能国际电力股份有限公司上海石洞口第二电厂 | Belt crack detection method based on image recognition |
| CN114413777A (en) * | 2022-01-18 | 2022-04-29 | 南京工程学院 | High-speed rail axle deformation detection device and method based on image definition evaluation function |
Family Cites Families (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1237327C (en) * | 2004-04-20 | 2006-01-18 | 长安大学 | System and method for discriminating road gap |
| JP5594254B2 (en) * | 2011-08-09 | 2014-09-24 | 三菱電機株式会社 | Silicon substrate inspection apparatus and inspection method |
| CN102937593A (en) * | 2012-10-20 | 2013-02-20 | 山东理工大学 | Ceramic radome crack automatic detection method |
| JP6121253B2 (en) * | 2013-06-11 | 2017-04-26 | Nok株式会社 | Work surface defect inspection system |
| KR20150001094A (en) * | 2013-06-26 | 2015-01-06 | 삼성디스플레이 주식회사 | Method of substrate inspection |
| CN103439338B (en) * | 2013-08-30 | 2015-08-12 | 无锡金视界科技有限公司 | Film defects sorting technique |
| CN104198498B (en) * | 2014-09-12 | 2016-10-19 | 河海大学常州校区 | Fabric Defects Inspection detection method based on adaptive orthogonal wavelet conversion and device |
| CN104504388B (en) * | 2014-12-17 | 2017-10-24 | 长安大学 | A kind of pavement crack identification and feature extraction algorithm and system |
| CN105784710B (en) * | 2014-12-23 | 2018-08-28 | 桂林电子科技大学 | A kind of glue into concrete beam cracks detection device based on Digital Image Processing |
| CN104568972A (en) * | 2015-02-09 | 2015-04-29 | 中核华泰建设有限公司 | Bottom surface crack detection device for concrete bridge |
| CN104897463A (en) * | 2015-04-16 | 2015-09-09 | 广东工业大学 | Real-time detection apparatus and real-time detection method of steel-concrete combination member deformation due to force applying |
| CN105891217A (en) * | 2016-04-27 | 2016-08-24 | 重庆大学 | System and method for detecting surface defects of steel rails based on intelligent trolley |
-
2016
- 2016-08-31 CN CN201610799729.9A patent/CN106226157B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN106226157A (en) | 2016-12-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106226157B (en) | Concrete structure member crevices automatic detection device and method | |
| CN104914111B (en) | A kind of steel strip surface defect online intelligent recognition detecting system and its detection method | |
| KR100898061B1 (en) | Hybrid tunnel scanning instrument | |
| CN111272366B (en) | Bridge displacement high-precision measurement method based on multi-sensor data fusion | |
| TR201910987T4 (en) | Train type identification method and system and security control method and system. | |
| CN105021628A (en) | Detection method for surface defects of optical fiber image inverter | |
| CN107428261B (en) | Lifting hook detection device based on image processing | |
| CN108287165A (en) | Defect inspection method and defect inspection system | |
| CN104483320A (en) | Digitized defect detection device and detection method of industrial denitration catalyst | |
| CN104103069B (en) | Image processing apparatus, image processing method and recording medium | |
| CN105241811B (en) | Multi-level focus adopts drawing method and system automatically | |
| CN109374636B (en) | Pantograph image acquisition system, detection system and detection method | |
| CN102455171A (en) | Method for detecting geometric shape of back of tailor-welding weld and implementing device thereof | |
| CN110174404A (en) | A kind of online defect detecting device of powder and system | |
| CN109254010A (en) | A kind of pantograph detection device and detection method | |
| CN110991360A (en) | Robot inspection point location intelligent configuration method based on visual algorithm | |
| CN109143001A (en) | pantograph detection system | |
| CN111307812A (en) | Welding spot appearance detection method based on machine vision | |
| CN114812403A (en) | Large-span steel structure hoisting deformation monitoring method based on unmanned aerial vehicle and machine vision | |
| CN115717867A (en) | Bridge deformation measurement method based on airborne double cameras and target tracking | |
| CN111458345A (en) | Visual detection mechanism for defects of mask | |
| CN105391998B (en) | Automatic detection method and apparatus for resolution of low-light night vision device | |
| CN105067629B (en) | A kind of chromatic circle resistance open defect and resistance value integrated testing method | |
| CN107449786B (en) | Device for finely observing surface of object | |
| KR101094968B1 (en) | System for Inspecting Defects on Glass Substrate Using Contrast Value, and Method of the same |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB03 | Change of inventor or designer information | ||
| CB03 | Change of inventor or designer information |
Inventor after: Sun Jingeng Inventor after: Li Shilin Inventor after: Zhou Yonggui Inventor after: Jiang Huizeng Inventor after: Wu Jun Inventor after: Gong Xingqi Inventor after: Li Quan Inventor after: Ma Xiang Inventor before: Sun Jingeng Inventor before: Zhou Yonggui Inventor before: Jiang Huizeng Inventor before: Liu Yue Inventor before: Li Shilin Inventor before: Wu Jun Inventor before: Gong Xingqi Inventor before: Li Quan |
|
| TA01 | Transfer of patent application right | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20170208 Address after: 100000 Beijing city Haidian District Daliushu Road No. 2 Applicant after: Beijing Huaheng New Technology Development Co., Ltd. Address before: 100000 Beijing city Haidian District Daliushu Road No. 2 Building No. 252 West 12 Applicant before: Sun Jingeng Applicant before: Zhou Yonggui Applicant before: Jiang Huizeng Applicant before: Liu Yue Applicant before: Li Shilin Applicant before: Wu Jun Applicant before: Gong Xingqi Applicant before: Li Quan Applicant before: Beijing Huaheng New Technology Development Co., Ltd. |
|
| GR01 | Patent grant | ||
| GR01 | Patent grant |