CN106226157A - Concrete structure member crevices automatic detection device and method - Google Patents
Concrete structure member crevices automatic detection device and method Download PDFInfo
- Publication number
- CN106226157A CN106226157A CN201610799729.9A CN201610799729A CN106226157A CN 106226157 A CN106226157 A CN 106226157A CN 201610799729 A CN201610799729 A CN 201610799729A CN 106226157 A CN106226157 A CN 106226157A
- Authority
- CN
- China
- Prior art keywords
- image
- crack
- component
- concrete structure
- structure member
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 49
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000012360 testing method Methods 0.000 claims abstract description 38
- 238000012545 processing Methods 0.000 claims abstract description 23
- 239000000203 mixture Substances 0.000 claims description 32
- 239000000284 extract Substances 0.000 claims description 23
- 238000012946 outsourcing Methods 0.000 claims description 16
- 230000009194 climbing Effects 0.000 claims description 14
- 230000033001 locomotion Effects 0.000 claims description 13
- 230000000052 comparative effect Effects 0.000 claims description 12
- 238000006243 chemical reaction Methods 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 5
- 238000001914 filtration Methods 0.000 claims description 5
- 238000009499 grossing Methods 0.000 claims description 4
- 230000005540 biological transmission Effects 0.000 abstract description 4
- 238000010276 construction Methods 0.000 abstract description 3
- 238000012797 qualification Methods 0.000 abstract description 3
- 238000005286 illumination Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000007689 inspection Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000012216 screening Methods 0.000 description 2
- 230000003068 static effect Effects 0.000 description 2
- 241000196324 Embryophyta Species 0.000 description 1
- 240000002853 Nelumbo nucifera Species 0.000 description 1
- 235000006508 Nelumbo nucifera Nutrition 0.000 description 1
- 235000006510 Nelumbo pentapetala Nutrition 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
- 230000007423 decrease Effects 0.000 description 1
- 230000009365 direct transmission Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000003709 image segmentation Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000011218 segmentation Effects 0.000 description 1
- 239000002689 soil Substances 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
Abstract
The present invention open a kind of concrete structure member crevices automatic detection device, method and system, this detection device, method and system are by image acquisition device bridge member component deformation and crack pattern picture of producing when by load, and the transmission of this image is processed to image processing system, it is thus achieved that component produces the image information in crack.This device, method and system use the mode automatically obtaining image to obtain the crack information of component, can objectively judge according to image information whether different parts, width, the crack of length belong to the qualification determination standard in stress crack, and this image information is capable of data and uploads to Environment in Railway Engineering Construction information management platform data center, facilitates the acquisition of bridge member load test data and improves the verity of bridge member load test data, correctness, reliability.
Description
Technical field
The present invention relates to component quality inspection apparatus field, particularly relate to a kind of concrete structure member crevices and automatically detect dress
Put, method and system.
Background technology
As shown in Figure 8, prior art has a kind of bridge static loading test automaton, including for controlling whole examination
Test the test master control set of process, also include the loading actuator, the load measurement device that are all connected with test master control set, scratch
Degree measurement apparatus, deviation capacity checking device and anomaly alarming device.Test master control set is also configured with uploading for data and image
The remotely long-distance monitorng device of monitoring, manual-operated emergent device, full-automatic/semiautomatic plant and for completing examination by a key operation
Test a key control device of overall process.The arrangement achieves bridge static loading test realization synchronization loading and each load(ing) point load is automatic
Balance, it is ensured that test data true, accurate, reliable, improves automaticity, decreases experimental labor and equipment, it is achieved
Test data is uploaded and is remotely monitored.
But the detection of the Bridge Crack of this device need nonetheless remain for manual observation to be carried out, not only everyone to different parts,
The qualification determination standard whether width, the crack of length belong to stress crack is different, and the responsibility of observer is different, also has
" anopia " imitation behavior etc., directly influences the verity of bridge member load test data, correctness, reliability.
Summary of the invention
It is an object of the invention to provide a kind of concrete structure member crevices automatic detection device, method and system, this detection fills
Put, method and system are by image acquisition device bridge member component deformation and crack pattern of producing when by load
Picture, and the transmission of this image is processed to image processing system, it is thus achieved that component produces the image information in crack.This device,
Method and system use the mode automatically obtaining image to obtain the crack information of component, it is possible to objectively judge according to image information
Whether different parts, width, the crack of length belong to the qualification determination standard in stress crack, and this image information is capable of
Data upload to Environment in Railway Engineering Construction information management platform data center, facilitate bridge member load test data acquisition and
Improve the verity of bridge member load test data, correctness, reliability.
For achieving the above object, the invention provides a kind of concrete structure member crevices automatic detection device, including:
Image collecting device, for gathering the image of described component；
Image processing apparatus, described image processing apparatus is connected with described image collecting device, is used for identifying described figure
Crack in Xiang；
Moving bearing device, is used for carrying described image collecting device, and described moving bearing device can be along described structure
To be detected movement of at least one of part.
Optionally, described moving bearing device includes that moving track, described image collector are arranged in described moving track
Upper and described image collecting device can move on described moving track, and described moving track can along described component at least
The shifting of one to be detected movement, described image collecting device moving direction on described moving track and described moving track
The angle in dynamic direction is more than 0 ° and less than 180 °.
Optionally, described moving track and described component contact position are provided with travel mechanism, and described moving track is provided with climbs
Wall robot, the end face of described climbing robot contacts with the surface of described component, and described climbing robot is along described component
Surface creep and drive described moving track to move along described component；Described travel mechanism includes being located at described moving track two
The roller of end, described roller contacts with described component.
Optionally, described image collecting device includes camera lens and light compensating lamp, and described light compensating lamp is used for as described lens shooting
Image provides supplementary lighting sources.
Another object of the present invention is to provide a kind of concrete structure member crevices automatic testing method, including:
Obtain the image of component；
Extract half-tone information in described image；
The dark area in described image is determined according to described half-tone information；
The crack of described component is identified based on described dark area.
Optionally, after described crack based on dark area identification means, also include:
Obtain the angle in described crack and described component horizontal place straight line,
Judge that whether described angle is more than 45 °, it is thus achieved that the first judged result；
When described first judged result represent be time, determine that described crack is target crack；
When described first judged result represents no, determine that described crack is non-targeted crack
Optionally, the described crack identifying described component based on described dark area, specifically include:
Utilize Gaussian smoothing filter method that the image comprising described dark area is carried out low-pass filtering；
Obtain the error image of filtered image and the image of described dark area；
Extract the directional information in crack in described error image；
In conjunction with described directional information, described filtered crack pattern picture is carried out binary conversion treatment, it is thus achieved that binary image；
Reject the spuious point in described binary image and agglomerate, extract crack.
Optionally, the directional information in crack in the described error image of described extraction, specifically include:
Choose a pixel in described filtered crack pattern picture (i, j)；
With described pixel (i, j) centered by, choose height for h, width is the rectangular area of w；
Calculate the gradient mean value in x and y direction in described rectangular area；
Any pixel (i, phase angle j) in calculating described rectangular area according to described gradient mean value.
Optionally, the spuious point in the described binary image of described rejecting and agglomerate, extract crack, specifically include:
Obtain the outsourcing rectangle of gloomy composition in described binary image；
Calculate the length-width ratio of described outsourcing rectangle；
Judge that whether described length-width ratio is more than setting length-width ratio, it is thus achieved that the second judged result；
When described second judged result represent be time, reject non-crack area according to the syntopy of each outsourcing rectangle, really
The gloomy composition that fixed described residue outsourcing rectangle is surrounded is target crack；
When described second judged result represents no, determine the gloomy composition that described outsourcing rectangle is surrounded be spuious point or
Agglomerate, and reject described spuious point or described agglomerate.
Optionally, described detection method also includes:
Again obtain the image at position, described crack, obtain secondary image；
Identify the secondary crack in described secondary image；
The relatively secondary crack in described secondary image and the length in described crack, it is thus achieved that comparative result；
When described comparative result represents the length length more than described crack in described secondary crack, determine described quadratic diagram
Crack composition in Xiang is target crack；
When described comparative result represents that the length in described secondary crack is not more than the length in described crack, reject described gloomy
Region, records testing result.
Optionally, described detection method also includes:
Obtain the crack image information collected in advance；
Based on described crack image information, extract containing the crack general character in crannied image；
The crack in image according to component described in the general character identification of described crack.
A further object of the present invention there are provided a kind of concrete structure member crevices automatic checkout system, including:
Image acquisition unit, for obtaining the image of component；
Half-tone information extraction unit, is used for extracting half-tone information in described image；
Dark area determines unit, determines the dark area in described image according to described half-tone information；
Crack identification unit, identifies the crack of described component based on described dark area.
The specific embodiment provided according to the present invention, the invention discloses techniques below effect: the coagulation that the present invention provides
Soil structure member crevices automatic detection device utilize can on component the image of the image acquisition device component surface of movement, warp
After crossing image processing apparatus process, it is thus achieved that the crack composition in image, thus realize the Crack Detection of component.By the present invention's
Crack detecting device carries out Crack Detection and avoids the potential safety hazard that manual observation judges that crack exists, and can be objective, true
Obtain crack information in fact, accurately, improve the verity of bridge member load test data, correctness, reliability.The present invention
Additionally provide a kind of concrete structure member crevices automatic testing method and system, the method and the system neighborhood ash jump by crack
Different significant properties detects crack, and the method and system can accurately identify true crack present in the image of collection,
And record recognition result, it is achieved the transmission of crack data.
Accompanying drawing explanation
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to institute in embodiment
The accompanying drawing used is needed to be briefly described, it should be apparent that, the accompanying drawing in describing below is only some enforcements of the present invention
Example, for those of ordinary skill in the art, on the premise of not paying creative work, it is also possible to according to these accompanying drawings
Obtain other accompanying drawing.
The structural representation of the concrete structure member crevices automatic detection device that Fig. 1 provides for the embodiment of the present invention；
Fig. 2 provides the structural representation of small rail car for the embodiment of the present invention；
The structural representation of the climbing robot that Fig. 3 provides for the embodiment of the present invention；
The structural representation of the image collecting device that Fig. 4 provides for the embodiment of the present invention；
The structural representation of the component far infrared cruise target point that Fig. 5 provides for the embodiment of the present invention；
The overview flow chart of the concrete structure member crevices automatic testing method that Fig. 6 provides for the embodiment of the present invention；
The flow chart of secondary detection in the concrete structure member crevices automatic testing method that Fig. 7 provides for the embodiment of the present invention；
The flow chart in the crack based on dark area identification means that Fig. 8 provides for the embodiment of the present invention；
Fig. 9 extracts the flow chart of the directional information in crack in error image for what the embodiment of the present invention provided；
By the grid chart of the straight line of a pixel in the image that Figure 10 provides for the embodiment of the present invention；
The binary image through binary conversion treatment that Figure 11 provides for the embodiment of the present invention；
The closed operation image processed through space closed operation that Figure 12 provides for the embodiment of the present invention；
The spuious point rejected in binary image that Figure 13 provides for the embodiment of the present invention and agglomerate, extract crack and also mark
The flow chart in crack；
The screening crack pattern picture that Figure 14 provides for the embodiment of the present invention；
The image in artwork behind mark crack that Figure 15 provides for the embodiment of the present invention.
Detailed description of the invention
Below in conjunction with the accompanying drawing in the embodiment of the present invention, the technical scheme in the embodiment of the present invention is carried out clear, complete
Describe, it is clear that described embodiment is only a part of embodiment of the present invention rather than whole embodiments wholely.Based on
Embodiment in the present invention, it is every other that those of ordinary skill in the art are obtained under not making creative work premise
Embodiment, broadly falls into the scope of protection of the invention.
The invention provides a kind of concrete structure member crevices automatic detection device, as it is shown in figure 1, include:
Image collecting device 3, for the image of acquisition member 1；
Image processing apparatus (not shown in figure 1), image processing apparatus is connected with image collecting device 3, is used for identifying
Crack in image；
Moving bearing device 2, is used for carrying image collecting device 3, and moving bearing device 2 can along component 1 at least
One to be detected movement.
Present embodiment be utilize can on component 1 image on the image collecting device 3 acquisition member surface of movement, warp
After crossing image processing apparatus process, it is thus achieved that the crack composition in image, thus realize the Crack Detection of component.By the present invention's
Crack detecting device carries out Crack Detection and avoids the potential safety hazard that manual observation judges that crack exists, and can be objective, true
Obtain crack information in fact, accurately, improve the verity of bridge member load test data, correctness, reliability.
As the optional embodiment of one, unlike other embodiments, as shown in figs. 1 and 3, mobile carrying dress
Put 2 and include that moving track 4, image collecting device 3 are located on moving track 4 and image collecting device 3 can be on moving track 4
Mobile, moving track 4 can be along to be detected movement of at least one of component 1, and in the present embodiment, moving track 4 is along structure
The bottom surface of part 1 is moved；The angle of the moving direction of the image collecting device 3 moving direction on moving track 4 and moving track 4
More than 0 ° and less than 180 °.Concrete, moving track 4 and component 1 contact position are provided with travel mechanism, and moving track is provided with climbs wall
Robot 5, the end face of climbing robot 5 is adsorbed in component 1 surface, and climbing robot 5 is adsorbed in component 1 and along component 1 surface
The impetus creeped can drive moving track 4 to vertically move along component, thus realizes the image collecting device 3 of carrying along structure
Part vertically moves, it is achieved the collection of longitudinal member image.
Travel mechanism in present embodiment can be provided in the roller 5 at moving track two ends, by roller 5 and component
1 contact, and roll along component 1, it is achieved the movement of moving track 4.
Slide block (not shown in figure 1) that travel mechanism in present embodiment can be provided on moving track and setting
Putting slide rail (not shown in figure 1) suitable with slide block on component, such moving track can move along this slide rail, secure
Moving track motion track on component, the problem also simultaneously being able to avoid the detection faces of moving track deviation component, it is possible to
Improve accuracy of detection.
Different from the embodiment described above is unmanned plane that moving bearing device can also is that by manual remote control, image is adopted
Acquisition means is located on unmanned plane, and image collecting device and image processing apparatus can pass through wirelessly transmitting data.Personnel can pass through
Remotely pilotless machine shoots the image of component any part.
As the optional embodiment of one, unlike other embodiments, as Fig. 2 and 3 image collecting devices 3 wrap
Include camera lens 8.This camera lens 8 includes in line-scan digital camera, area array cameras one or both, also includes industrial lens.Optionally, this camera lens
8 are arranged on small rail car 6, and this small rail car 6 is arranged on moving track 4, it is possible to move along moving track 4, small rail car 6
Moving direction different from the moving direction of moving track 4 so that camera lens 8 can photograph the whole detection faces of component, cover
Lid detection is wide, does not haves missing inspection situation, and then improves the comprehensive and accuracy in detection crack.Another kind of optional real
Executing mode, camera lens 8 can also be arranged on climbing robot 5, is connected with this climbing robot 5 by a shooting arm 9, this bat
Taking the photograph arm 9 can be around climbing robot 5 horizontal hunting 180 °.The camera lens of this set-up mode is to carry out structure with circular scanning process
The image acquisition of part detection faces, this eliminate the structure of small rail car 6, simplify harvester, utilize shooting arm 9 simultaneously
Swing realize the collection of component detection faces image, and when moving track 4 moves to a certain position, the mirror of this set-up mode
8 can photograph larger range of image, improve collecting efficiency.
As the optional embodiment of one, unlike other embodiments, as shown in Figure 4, image collecting device 3
Also including light compensating lamp 10, light compensating lamp 10 provides supplementary lighting sources for shooting image for camera lens 8.Light compensating lamp can be annular light source or
Strip source.Generally, bridge upper surface can be bent downwardly deformation by lower surface after load, in order to detect bridge member
Whether crack occurs after lower surface stand under load, is all to carry out image acquisition at the lower surface of component, but component lower surface illumination is not enough,
The definition of image acquisition can be had a strong impact on, accordingly, it would be desirable to this light compensating lamp provides for camera lens compensates light, to ensure image acquisition
Clearly, and then improve the accuracy of crack identification 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.Use kilomega network industry area array CCD (charge
Coupled device) camera 11, industrial lens 12 as camera lens 8, use machine vision LED bar graph light source 10 as light compensating lamp
10.Kilomega network industry area array cameras 11 uses ccd sensor, it is achieved high speed fine definition is stable into picture, makes camera applications in more
Industrial occasions widely.This industrial camera 12 have high-resolution, at high speed, in high precision, the feature such as fine definition, low noise,
Kilomega network exports, and direct transmission range, up to 100m, is widely used in the field of machine vision of high-speed, high precision.Machine vision
LED bar graph light source is suitable for the surface illumination of tested object in machine vision, can provide the oblique fire of matching object from any angle
Illumination, has the distribution of high brightness in strip structure, is widely used in surface crack detection etc..Its brightness and setting angle are equal
Adjustable, there is the features such as high brightness, low temperature, equilibrium, flicker free.Make machine vision LED bar graph light source with maximum power output, adjust
The aperture of whole industrial lens, focal length, so that image is best sharpness.The time of exposure of camera is also unsuitable excessive, prevents image
It is image blurring that image streaking in gatherer process causes.
The detection range of this concrete structure member crevices automatic detection device covers at the bottom of the bridge box and beam component span centre each 2m in left and right
The cambered surface of upwards 15cm at face and base angle, lower flange.
As the optional embodiment of one, unlike other embodiments, concrete structure member crevices as shown in Figure 5
Automatic detection device also include control device, far infrared cruise target point 13, control device respectively with climbing robot 5, image
Harvester 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
Boat impact point 13 moves；Control image collecting device 3 to move also according to far infrared cruise target point 13 on moving bearing device 2
Gather image；And control the crack composition in image processing apparatus identification image, and by after image processing apparatus processes
Image transmitting is to Environment in Railway Engineering Construction information management platform data center.This control device arranges the component being capable of automatization
Image acquisition and the identification of structure member crevices, it is to avoid the criterion that manual observation occurs is different and causes crack information to be forbidden
True problem produces, and improves accuracy of detection and the detection efficiency of structure member crevices, improves the safety of engineering test.
As the optional embodiment of one, unlike other embodiments, this concrete structure member crevices is examined automatically
Surveying device and also include alarm device, this alarm device includes that acoustic alarm and light are reported to the police, in image processing apparatus detects image
When there is crack, this alarm device is reported to the police, to remind workman determine crack and take corresponding measure.
Another object of the present invention is to provide a kind of concrete structure member crevices automatic testing method, as shown in Figure 6, bag
Include:
Step 601: obtain the image of component；
Step 602: extract half-tone information in image；
Step 603: determine the dark area in image according to half-tone information；
Step 604: crack based on dark area identification means.
Wherein, dark area is that gray scale is less than the region setting gray threshold, and the crack in image is gray value in image
Less region, therefore, when gray scale is only possible to crack occur less than the region setting gray threshold, reduces identification range, adds
Fast recognition rate.
This concrete structure member crevices automatic testing method utilizes above-mentioned concrete structure member crevices automatic detection device to carry out
Detection, uses image collecting device to move back and forth on moving bearing device, and moving bearing device moves on component, right
Bridge box and beam component bears bigger moment of flexure position and is scanned, in the Processing Algorithm identification image in motion picture processing device
Crack composition, and record Crack Detection result.
As the optional embodiment of one, after crack based on dark area identification means, also include:
Obtain the angle in crack and component horizontal place straight line,
Judge that whether angle is more than 45 °, it is thus achieved that the first judged result；
When the first judged result represent be time, determine that crack is target crack；
When the first judged result represents no, determine that crack is non-targeted crack.
As the optional embodiment of one, as it is shown in fig. 7, described detection method also includes:
Step 701: again obtain the image at position, crack, obtain secondary image；
Step 702: identify the secondary crack in secondary image；
Step 703: compare the length in the secondary crack in secondary image and crack, it is thus achieved that comparative result；
When comparative result represents the length length more than crack in secondary crack, determine that the crack composition in secondary image is
Target crack, and send alarm signal；
When comparative result represents that the length in secondary crack is not more than the length in crack, reject dark area, record detection knot
Really.
Before on-test, above-mentioned concrete structure member crevices automatic testing method is utilized first the detection region of component to be swept
Retouch, detect once, the coordinate of the incipient crack at the bottom of recording member beam.In process of the test, need component is applied 1.00 grades extremely
The load of 1.20 grades, controls device control moving bearing device carrying image harvester and sweeps component beam body key area
Retouching, scanogram transmission carries out processing, detect and extract crack coordinate to image processing apparatus.At different levels before 1.20 grades execute
Complete in adding load 5min 1 time, 1.20 grades hold lotus 20min in complete the collection of 4 view data, process and stress crack and sentence
Fixed, wherein, also obtain the position coordinates that this initial pictures is corresponding while obtaining initial pictures, also obtain when again obtaining image
The position coordinates that image is corresponding, and the image of twice same position coordinate is compared, compare the crack in the image of both sides and become
The length divided, if comparative result represents: the crack composition length in secondary image is more than the crack composition in previous image
Length, then the crack produced after the crack composition in secondary image is true crack, i.e. imposed load, extract and record quadratic diagram
Picture, and report to the police, in order to workman confirms crack and positions.If when comparative result represents: the crack composition length in secondary image
The length of the crack composition being not more than in previous image, rejects previous image and secondary image, records testing result, illustrates initial
Crack in image is not imposed load and produces, and therefore rejects, and records testing result.
Wherein, the position coordinates of image is according to the far infrared cruise target point arranged and the fortune controlling climbing robot
The movement locus of dynamic track and image collecting device determines.
In the above-described embodiment, from the bridge bottom diagram picture collected, crack composition detected, need to enter image
Row binary conversion treatment, belongs to the category of image segmentation.Then the composition after processing filters spuious point and sheet of region, extracts
Crack composition.In order to use the mode of dynamic threshold binaryzation to carry out the segmentation of image, and in view of the grain distribution in crack
Characteristic gets rid of spuious point, the interference of agglomerate, proposes the crack detection method of a kind of local binarization based on fractuer direction distribution,
The step in the most above-mentioned crack based on dark area identification means, as shown in Figure 8, specifically includes:
Step 801: utilize the Gaussian smoothing filter method image to comprising dark area to carry out low-pass filtering；
Step 802: obtain the error image of filtered image and the image of dark area；
Step 803: extract the directional information in crack in error image；
Step 804: bonding position information, carries out binary conversion treatment to the image of dark area, it is thus achieved that binary image；
Step 805: reject the spuious point in binary image and agglomerate, extracts crack and marks crack.
Wherein, single channel image is obtained after the image collected being carried out gray processing process.Due to illumination in gatherer process,
The problems such as shake, are mixed with noise in image so that in image, part pixel value is bigger with its neighborhood territory pixel deviation.Therefore carrying out
Need before crack extract image is carried out Gaussian smoothing, after low-pass filtering, obtain the low pass composition of image.Then lead to
After crossing artwork and low-pass filtering, image is poor, obtains the radio-frequency component of crack pattern picture.To ensure the accuracy of crack extract.
Wherein, in order to obtain the directional information of each point in image, it is necessary first to obtain the direction gradient of x, y, Grad
Obtain the first differential used and obtain the gradient in both directionWithIn order to make the direction of each pixel believe
Breath is accurate as far as possible, have employed regional area pixel in the present embodiment as a reference to calculate.As it is shown in figure 9,
Concrete, extract the step of the directional information in crack in filtered crack pattern picture and specifically include:
Step 901: choose a pixel in filtered crack pattern picture (i, j)；
Step 902: with pixel (i, j) centered by, choose height for h, width is the rectangular area of w；
Step 903: the gradient mean value in x and y direction in calculating rectangular area；
Step 904: any pixel (i, phase angle j) in calculating rectangular area according to gradient mean value.
Wherein, the computing formula of gradient mean value is:
Obtain in rectangular area, after x, y direction gradient average, being estimated often by the average in rectangular area by above formula
The phase place of individual point, the computing formula of phase place is:After obtaining the directional information in crack, i.e.
Multistage crack figure can be integrated into a crack, more can accurately determine crack location, improve the precision of Crack Detection.
The local binarization method of the dynamic threshold in present embodiment, is based on Niblack method, will
The algorithm that Niblack binarization method combines with the phase place of each point in image.
In the picture a bit (i, j), as shown in Figure 10, be first according to this point (i, j) phase place in the x and y direction and
The coordinate of point can be obtained by this straight line, takes the poincare half plane of this straight line, each N number of point of lower half-plane, adds up this straight
On line 2N+1 point average m (i, j) with variance s (i, j):
In this algorithm, I (i, j) be point (i, j) the pixel value size at place, impact point (i, j) on take this phase place straight line
On pixel as reference, using this straight line as template, the threshold value obtained be: T (x, y)=m (and x, y)+k s (x, y)
In above formula, k is correction factor, is generally given by requirement of engineering.After obtaining the decision threshold of object pixel, the most permissible
This point is judged:
After each pixel in image is calculated by this algorithm, just obtain the binary image of target image.In order to
Making narrow breach up, have employed space closed operation, smooth binary image result, effect is as shown in FIG. 11 and 12.
As the optional embodiment of one, as shown in figure 13, reject the spuious point in binary image and agglomerate, extract
Crack also marks the step in crack, specifically includes:
Step 1301: obtain the outsourcing rectangle of gloomy composition in binary image；
Step 1302: calculate the length-width ratio of outsourcing rectangle；
Step 1303: judge that whether length-width ratio is more than setting length-width ratio, it is thus achieved that judged result；
Step 1304: when judged result represent be time, reject non-crack area according to the syntopy of each outsourcing rectangle, really
The gloomy composition that fixed described residue outsourcing rectangle is surrounded is target crack；
Step 1305: when comparative result represents no, determines that the gloomy composition that outsourcing rectangle is surrounded is spuious point or group
Block, and reject spuious point or agglomerate.
There is the most spuious point, agglomerate by image after binaryzation, in order to filter these compositions, present embodiment is adopted
By target outsourcing rectangular aspect ratio restriction, length limitation, area constraints etc., it is achieved dirty point or the automatic fitration of agglomerate, screening
Go out long and narrow composition.Then by interstitial syntopy, isolated composition is rejected.As shown in FIG. 14 and 15, rectangle frame bag
The composition of quilt is the crack composition that meets the requirements, and finally marks out crack composition in artwork to observe.
As the optional embodiment of one, described detection method also includes:
Obtain the crack image information collected in advance；
Based on crack image information, extract containing the crack general character in crannied image；
The crack in image according to crack general character identification means.
The present embodiment uses Machine self-learning method, study to identify crack, reduce identification difficulty, improve identification
Rate.
A further object of the present invention there are provided a kind of concrete structure member crevices automatic checkout system, including:
Image acquisition unit, for obtaining the image of component；
Half-tone information extraction unit, is used for extracting half-tone information in image；
Dark area determines unit, determines the dark area in image according to half-tone information；
Crack identification unit, crack based on dark area identification means.
This concrete structure member crevices automatic testing method utilizes above-mentioned concrete structure member crevices automatic detection device to carry out
Detection, uses image collecting device to move back and forth on moving bearing device, and moving bearing device moves on component, right
Bridge box and beam component bears bigger moment of flexure position and is scanned, in the Processing Algorithm identification image in motion picture processing device
Crack composition, and record Crack Detection result.
In this specification, each embodiment uses the mode gone forward one by one to describe, and what each embodiment stressed is and other
The difference of embodiment, between each embodiment, identical similar portion sees mutually.For system disclosed in embodiment
For, owing to it corresponds to the method disclosed in Example, so describe is fairly simple, relevant part sees method part and says
Bright.
Principle and the embodiment of the present invention are set forth by specific case used herein, saying of above example
Bright method and the core concept thereof being only intended to help to understand the present invention；Simultaneously for one of ordinary skill in the art, foundation
The thought of the present invention, the most all will change.In sum, this specification content is not
It is interpreted as limitation of the present invention.
Claims (12)
1. a concrete structure member crevices automatic detection device, it is characterised in that including:
Image collecting device, for gathering the image of described component；
Image processing apparatus, described image processing apparatus is connected with described image collecting device, is used for identifying in described image
Crack；
Moving bearing device, is used for carrying described image collecting device, and described moving bearing device can be along described component
At least one to be detected movement.
Concrete structure member crevices automatic detection device the most according to claim 1, it is characterised in that described mobile carrying dress
Putting and include moving track, described image collector is arranged on described moving track and described image collecting device can be described
Moving on moving track, described moving track can be along to be detected movement of at least one of described component, described image acquisition
Device moving direction on described moving track more than 0 ° and is less than 180 ° with the angle of the moving direction of described moving track.
Concrete structure member crevices automatic detection device the most according to claim 2, it is characterised in that described moving track with
Described component contact position is provided with travel mechanism, and described moving track is provided with climbing robot, the end face of described climbing robot
Contacting with the surface of described component, described climbing robot is along the surface creep of described component and drives described moving track edge
Described component moves；Described travel mechanism includes the roller being located at described moving track two ends, and described roller connects with described component
Touch.
Concrete structure member crevices automatic detection device the most according to claim 1, it is characterised in that described image collector
Putting and include camera lens and light compensating lamp, described light compensating lamp is for providing supplementary lighting sources for described lens shooting image.
5. a concrete structure member crevices automatic testing method, it is characterised in that including:
Obtain the image of component；
Extract half-tone information in described image；
The dark area in described image is determined according to described half-tone information；
The crack of described component is identified based on described dark area.
Concrete structure member crevices automatic testing method the most according to claim 5, it is characterised in that described based on gloomy
After the crack of region recognition component, also include:
Obtain the angle in described crack and described component horizontal place straight line,
Judge that whether described angle is more than 45 °, it is thus achieved that the first judged result；
When described first judged result represent be time, determine that described crack is target crack；
When described first judged result represents no, determine that described crack is non-targeted crack.
Concrete structure member crevices automatic testing method the most according to claim 5, it is characterised in that described based on described ash
The crack of component described in dark areas identification, specifically includes:
Utilize Gaussian smoothing filter method that the image comprising described dark area is carried out low-pass filtering；
Obtain the error image of filtered image and the image of described dark area；
Extract the directional information in crack in described error image；
In conjunction with described directional information, the image of described dark area is carried out binary conversion treatment, it is thus achieved that binary image；
Reject the spuious point in described binary image and agglomerate, extract crack.
Concrete structure member crevices automatic testing method the most according to claim 7, it is characterised in that the described difference of described extraction
The directional information in crack in value image, specifically includes:
Choose a pixel in described filtered crack pattern picture (i, j)；
With described pixel (i, j) centered by, choose height for h, width is the rectangular area of w；
Calculate the gradient mean value in x and y direction in described rectangular area；
Any pixel (i, phase angle j) in calculating described rectangular area according to described gradient mean value.
Concrete structure member crevices automatic testing method the most according to claim 7, it is characterised in that described rejecting described two
Spuious point in value image and agglomerate, extract crack, specifically include:
Obtain the outsourcing rectangle of gloomy composition in described binary image；
Calculate the length-width ratio of described outsourcing rectangle；
Judge that whether described length-width ratio is more than setting length-width ratio, it is thus achieved that the second judged result；
When described second judged result represent be time, reject non-crack area according to the syntopy of each outsourcing rectangle, determine institute
Stating the residue gloomy composition that surrounded of outsourcing rectangle is target crack；
When described second judged result represents no, determine that the gloomy composition that described outsourcing rectangle is surrounded is spuious point or group
Block, and reject described spuious point or described agglomerate.
Concrete structure member crevices automatic testing method the most according to claim 5, it is characterised in that described detection method
Also include:
Again obtain the image at position, described crack, obtain secondary image；
Identify the secondary crack in described secondary image；
The relatively secondary crack in described secondary image and the length in described crack, it is thus achieved that comparative result；
When described comparative result represents the length length more than described crack in described secondary crack, determine in described secondary image
Crack composition be target crack；
When described comparative result represents that the length in described secondary crack is not more than the length in described crack, reject described ash dark space
Territory, records testing result.
11. concrete structure member crevices automatic testing methods according to claim 5, it is characterised in that described detection method
Also include:
Obtain the crack image information collected in advance；
Based on described crack image information, extract containing the crack general character in crannied image；
The crack in image according to component described in the general character identification of described crack.
12. 1 kinds of concrete structure member crevices automatic checkout systems, it is characterised in that including:
Image acquisition unit, for obtaining the image of component；
Half-tone information extraction unit, is used for extracting half-tone information in described image；
Dark area determines unit, determines the dark area in described image according to described half-tone information；
Crack identification unit, identifies the crack of described component based on described dark area.
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 true CN106226157A (en) | 2016-12-14 |
| CN106226157B 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) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106643541A (en) * | 2016-12-26 | 2017-05-10 | 深圳高速工程顾问有限公司 | Method and device for management and analysis of real-time monitoring data of bridge |
| 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 |
| CN107436304A (en) * | 2017-09-20 | 2017-12-05 | 程丹秋 | A kind of surface of concrete structure detection means |
| 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 |
| CN109342216A (en) * | 2018-09-27 | 2019-02-15 | 国网宁夏电力有限公司电力科学研究院 | Concurrent mechanics properties testing system |
| 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 |
| CN110132152A (en) * | 2019-05-29 | 2019-08-16 | 河海大学 | A kind of automatically controlled itinerant monitor system device of concrete gravity dam underwater crack |
| 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 |
| 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 |
| CN111105401A (en) * | 2019-12-20 | 2020-05-05 | 姜通渊 | Concrete crack detection and repair method and device and electronic equipment |
| CN111311555A (en) * | 2020-01-22 | 2020-06-19 | 哈尔滨工业大学 | Large-scale 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 |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1563891A (en) * | 2004-04-20 | 2005-01-12 | 长安大学 | System and method for discriminating road gap |
| CN102937593A (en) * | 2012-10-20 | 2013-02-20 | 山东理工大学 | Ceramic radome crack automatic detection method |
| JP2013036888A (en) * | 2011-08-09 | 2013-02-21 | Mitsubishi Electric Corp | Silicon substrate inspection device and inspection method |
| CN103439338A (en) * | 2013-08-30 | 2013-12-11 | 无锡金视界科技有限公司 | Classification method for film defects |
| CN104198498A (en) * | 2014-09-12 | 2014-12-10 | 河海大学常州校区 | Method and device for detecting cloth flaws based on adaptive orthogonal wavelet transform |
| US20150003720A1 (en) * | 2013-06-26 | 2015-01-01 | Samsung Display Co., Ltd. | Method of inspecting substrate |
| CN104504388A (en) * | 2014-12-17 | 2015-04-08 | 长安大学 | Pavement crack identification and feature extraction algorithm and system |
| 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 |
| CN105784710A (en) * | 2014-12-23 | 2016-07-20 | 桂林电子科技大学 | Concrete bridge crack detection device based on digital image processing |
| 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 |
| JP6121253B2 (en) * | 2013-06-11 | 2017-04-26 | Nok株式会社 | Work surface defect inspection system |
-
2016
- 2016-08-31 CN CN201610799729.9A patent/CN106226157B/en active Active
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1563891A (en) * | 2004-04-20 | 2005-01-12 | 长安大学 | System and method for discriminating road gap |
| JP2013036888A (en) * | 2011-08-09 | 2013-02-21 | Mitsubishi Electric Corp | Silicon substrate inspection device 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 |
| US20150003720A1 (en) * | 2013-06-26 | 2015-01-01 | Samsung Display Co., Ltd. | Method of inspecting substrate |
| CN103439338A (en) * | 2013-08-30 | 2013-12-11 | 无锡金视界科技有限公司 | Classification method for film defects |
| CN104198498A (en) * | 2014-09-12 | 2014-12-10 | 河海大学常州校区 | Method and device for detecting cloth flaws based on adaptive orthogonal wavelet transform |
| CN104504388A (en) * | 2014-12-17 | 2015-04-08 | 长安大学 | Pavement crack identification and feature extraction algorithm and system |
| CN105784710A (en) * | 2014-12-23 | 2016-07-20 | 桂林电子科技大学 | Concrete bridge crack 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 |
Cited By (16)
| 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 |
| CN106643541A (en) * | 2016-12-26 | 2017-05-10 | 深圳高速工程顾问有限公司 | Method and device for management and analysis of real-time monitoring data of bridge |
| 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 |
| CN109342216A (en) * | 2018-09-27 | 2019-02-15 | 国网宁夏电力有限公司电力科学研究院 | Concurrent mechanics properties testing system |
| 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 |
| CN110132152A (en) * | 2019-05-29 | 2019-08-16 | 河海大学 | A kind of automatically controlled itinerant monitor system device of concrete gravity dam underwater crack |
| 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 |
| CN111105401A (en) * | 2019-12-20 | 2020-05-05 | 姜通渊 | Concrete crack detection and repair method and device and electronic equipment |
| CN111311555A (en) * | 2020-01-22 | 2020-06-19 | 哈尔滨工业大学 | Large-scale 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN106226157B (en) | 2019-04-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106226157A (en) | Concrete structure member crevices automatic detection device and method | |
| CN105158257B (en) | Slide plate measurement method and device | |
| CN106767423A (en) | Automatic Visual Inspection instrument | |
| CN105426894B (en) | Railway plug pin image detecting method and device | |
| CN109374636B (en) | Pantograph image acquisition system, detection system and detection method | |
| CN104483320A (en) | Digitized defect detection device and detection method of industrial denitration catalyst | |
| CN102175692A (en) | System and method for detecting defects of fabric gray cloth quickly | |
| CN111768417B (en) | Railway wagon overrun detection method based on monocular vision 3D reconstruction technology | |
| CN108287165A (en) | Defect inspection method and defect inspection system | |
| CN102455171A (en) | Method for detecting geometric shape of back of tailor-welding weld and implementing device thereof | |
| JP2010210318A (en) | Measuring device of dust, and estimation method of generation source | |
| CN109254010A (en) | A kind of pantograph detection device and detection method | |
| CN110953993A (en) | Detection device and method for sag and distance limit of power transmission line | |
| CN110991360A (en) | Robot inspection point location intelligent configuration method based on visual algorithm | |
| CN111307812A (en) | Welding spot appearance detection method based on machine vision | |
| CN104103069B (en) | Image processing apparatus, image processing method and recording medium | |
| CN105241811B (en) | Multi-level focus adopts drawing method and system automatically | |
| CN114812403A (en) | Large-span steel structure hoisting deformation monitoring method based on unmanned aerial vehicle and machine vision | |
| CN105067629B (en) | A kind of chromatic circle resistance open defect and resistance value integrated testing method | |
| CN105391998B (en) | Automatic detection method and apparatus for resolution of low-light night vision device | |
| CN107449786B (en) | Device for finely observing surface of object | |
| CN116091506B (en) | Machine vision defect quality inspection method based on YOLOV5 | |
| JP5274173B2 (en) | Vehicle inspection device | |
| CN116359233B (en) | Square battery appearance defect detection method and device, storage medium and electronic equipment | |
| CN206353107U (en) | A kind of bridge static loading test automaton |
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 |
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 |
|
| CB03 | Change of inventor or designer information | ||
| 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. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |