CN110031476A - A kind of multi-view stereo vision detection device and method that bridge pedestal nut-screw is loosened or ruptured - Google Patents
A kind of multi-view stereo vision detection device and method that bridge pedestal nut-screw is loosened or ruptured Download PDFInfo
- Publication number
- CN110031476A CN110031476A CN201910235216.9A CN201910235216A CN110031476A CN 110031476 A CN110031476 A CN 110031476A CN 201910235216 A CN201910235216 A CN 201910235216A CN 110031476 A CN110031476 A CN 110031476A
- Authority
- CN
- China
- Prior art keywords
- nut
- screw
- rent
- rupture
- pixel
- 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.)
- Withdrawn
Links
- 238000001514 detection method Methods 0.000 title claims abstract description 38
- NJPPVKZQTLUDBO-UHFFFAOYSA-N novaluron Chemical compound C1=C(Cl)C(OC(F)(F)C(OC(F)(F)F)F)=CC=C1NC(=O)NC(=O)C1=C(F)C=CC=C1F NJPPVKZQTLUDBO-UHFFFAOYSA-N 0.000 title claims abstract description 30
- 238000000034 method Methods 0.000 title claims abstract description 12
- 238000012423 maintenance Methods 0.000 claims abstract description 5
- 230000006378 damage Effects 0.000 claims description 7
- 238000009434 installation Methods 0.000 claims description 7
- 238000012937 correction Methods 0.000 claims description 6
- 238000012545 processing Methods 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000000875 corresponding effect Effects 0.000 claims description 5
- 238000012544 monitoring process Methods 0.000 claims description 4
- 230000002596 correlated effect Effects 0.000 claims description 2
- 238000003708 edge detection Methods 0.000 claims description 2
- 239000000284 extract Substances 0.000 claims description 2
- 238000000605 extraction Methods 0.000 claims description 2
- 238000013178 mathematical model Methods 0.000 claims description 2
- 239000011159 matrix material Substances 0.000 claims description 2
- 230000035772 mutation Effects 0.000 claims description 2
- 230000011218 segmentation Effects 0.000 claims description 2
- VIKNJXKGJWUCNN-XGXHKTLJSA-N norethisterone Chemical compound O=C1CC[C@@H]2[C@H]3CC[C@](C)([C@](CC4)(O)C#C)[C@@H]4[C@@H]3CCC2=C1 VIKNJXKGJWUCNN-XGXHKTLJSA-N 0.000 claims 1
- 238000007781 pre-processing Methods 0.000 abstract description 3
- 238000011897 real-time detection Methods 0.000 abstract description 2
- 238000013461 design Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000007787 solid Substances 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000000007 visual effect Effects 0.000 description 2
- 241000208340 Araliaceae Species 0.000 description 1
- 241000237536 Mytilus edulis Species 0.000 description 1
- 235000005035 Panax pseudoginseng ssp. pseudoginseng Nutrition 0.000 description 1
- 235000003140 Panax quinquefolius Nutrition 0.000 description 1
- 229910000831 Steel Inorganic materials 0.000 description 1
- 238000003916 acid precipitation Methods 0.000 description 1
- 208000003464 asthenopia Diseases 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000005336 cracking Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000006735 deficit Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000013505 freshwater Substances 0.000 description 1
- 235000008434 ginseng Nutrition 0.000 description 1
- 230000003116 impacting effect Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000000691 measurement method Methods 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 235000020638 mussel Nutrition 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 239000010959 steel Substances 0.000 description 1
- 238000012876 topography Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/95—Investigating the presence of flaws or contamination characterised by the material or shape of the object to be examined
-
- G06T5/80—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
- G06T7/001—Industrial image inspection using an image reference approach
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/80—Analysis of captured images to determine intrinsic or extrinsic camera parameters, i.e. camera calibration
- G06T7/85—Stereo camera calibration
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/84—Systems specially adapted for particular applications
- G01N21/88—Investigating the presence of flaws or contamination
- G01N21/8851—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges
- G01N2021/8887—Scan or image signal processing specially adapted therefor, e.g. for scan signal adjustment, for detecting different kinds of defects, for compensating for structures, markings, edges based on image processing techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10028—Range image; Depth image; 3D point clouds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30164—Workpiece; Machine component
Abstract
The multi-view stereo vision detection device and method for loosening or rupturing the invention discloses a kind of bridge pedestal nut-screw, multiple micro-cameras are mounted in bionical mounting rack, form stereo vision detection system, nut-screw in one group of circumference can be detected, it is associated with by camera coordinates, image preprocessing, images match, three-dimensional point cloud reconstruct, denoising etc. obtains the three-dimensional parameter of nut-screw assembly, it is calculated by algorithm and geometric parameter, it is compared with standard assembly nut-screw data, obtain reduced parameter, obtain the quantitative data of nut-screw loosening or breaking loose, maintenance parameter is provided for technical staff.It is detection accuracy height of the invention, real-time detection, at low cost.
Description
Technical field
The present invention relates to detection technique field, in particular to a kind of bridge pedestal nut-screw loosens or more mesh of rupture are vertical
Body vision detection device and method.
Background technique
Bridge steel frame base nut and screw rod are cooperatively connected, due to being shaken, impacting, sleet and Acid rain damages, spiral shell
Loosening or fracture damage can be generated between female and screw rod, needs manually to be judged with eyes, some dead angles, it manually also not necessarily can be with
It detects, simultaneously because subjective factor and visual fatigue will appear detection error or missing inspection.As it can be seen that artificial detection bridge pedestal spiral shell
The problems such as female screw rod there are high-altitudes dangerous, high labor cost and low efficiency.Have at present and is manually examined with the method that camera is taken pictures
Survey whether bridge pedestal nut-screw loosens or rupture, by manually seeing photo to determine whether loosening, still, if hand shaking
It is dynamic, the image of acquisition be it is fuzzy, be unable to judge accurately, in addition there is also the dead angles that manually can't detect with camera.And people
Work is manually all unable to real-time monitoring with phase machine testing, and the single image that one camera obtains can not obtain essence by three-dimensionalreconstruction
True quantitative loosening numerical value, can not provide the design parameter of maintenance for technical staff.
Summary of the invention
It is an object of the invention to overcome disadvantage existing in the prior art, provide a kind of detection accuracy height, real-time detection,
Bridge pedestal nut-screw at low cost loosens or the multi-view stereo vision detection device and method of rupture, by multiple micro-cameras
It is mounted in bionical mounting rack, forms stereo vision detection system, the nut-screw in one group of circumference can be detected, be passed through
Camera coordinates association, image preprocessing, images match, three-dimensional point cloud reconstruct, denoising etc. obtain the three-dimensional ginseng of nut-screw assembly
Number is calculated by algorithm and geometric parameter, is compared with standard assembly nut-screw data, is obtained reduced parameter, obtain spiral shell
The quantitative data of female screw bolt loosening or breaking loose provides maintenance parameter for technical staff.
The purpose of the invention is achieved by the following technical solution:
A kind of multi-view stereo vision detection method that bridge pedestal nut-screw is loosened or ruptured, includes the following steps:
(1) camera calibration and pixel calibration: video camera has 4 or more, the abutting video camera of each video camera
A camera shooting unit is constituted, for example four video cameras may make up four camera shooting units, form the detection within the scope of 360 degree；Pass through
Camera calibration is to obtain intrinsic parameters of the camera and distortion parameter for correcting captured pattern distortion；By pixel demarcate with
Obtain the transformational relation of pixel distance and actual physics distance, the i.e. corresponding mm length of unit pixel；Be completed at the same time four mesh or
The calibration of the above stereoscopic vision；
(2) it corrects image: the digital picture of nut-screw is captured by video camera, then according to the calibration result of video camera
Distortion correction is carried out to digital picture, obtains the correction image of nut-screw；
(3) gray processing and smooth: carrying out gray processing for the correction image of nut-screw, by three components of its red, green, blue with
Different weights are weighted and averaged；Then detection zone is smoothed with Gaussian function, it is smooth obtains nut-screw
Then single channel gray level image carries out feature extraction；
(4) images match: being compared with image object with the template of standard nut screw rod work-in parameters and matched, and obtains spiral shell
The shape of female screw rod, identifies nut-screw；
(5) Stereo matching three-dimensionalreconstruction: is carried out to the image of left and right cameras；Using the disparity map that Stereo matching obtains with
And the re-projection matrix obtained when camera calibration, three-dimensional point cloud is generated, and three-dimensionalreconstruction is carried out to three-dimensional point cloud；
(6) parameter calculates: in bridge installation, it is known that the elemental height of original nut, therefore the mesh according to three-dimensionalreconstruction
Mark form and its position, by founding mathematical models and its calculation method, calculate nut diameter, height, nut rent it is flat
Rupture the parameters such as width, maximum rupture width, mean depth and depth capacity；
(7) loosening or break up assessment: and then system assesses these parameters, and correlated results is transferred to user,
Maintenance parameter is provided for user.
In step (3), the weight of gray processing weighting is using classical value disclosed in document；Smoothly located using Gaussian function
It manages, the number in the core of Gaussian filter is that Gaussian Profile is presented, this is different from mean filter, the core of mean filter
Each value be it is equal, therefore, the information in crack in original image can be more preferably obtained using Gaussian filter.In order to eliminate
Noise jamming and the information for not influencing crack area, when carrying out picture smooth treatment, the choosing of the standard variance σ of Gaussian function
It takes most important.To overcome classical Canny algorithm to make variance in N × N window using the defect that the parameter is manually set
For one of the module for choosing σ, topography's information in window has thus been taken into account.And it non-edge or is made an uproar in image
The lesser region of sound pollution is often the lesser pixel of variance, can be using these pixels as the reference of marginal point and noise spot.
In view of the overall permanence of image, using minimum variance as the module for choosing σ value, wherein M, E, σ are in N × N window respectively
Mean value, variance and Gauss standard variance；EminIt is minimum variance, when variance minimum, σ minimum value is 1；
Emin=min (E) (3)
No matter variance E value is very big or very little, σ value will be less than the value of formula (4) calculating, can prevent image mistake in this way
Degree is smooth or edge fogs.
In step (5), the principle of Stereo matching is to choose the matching basic unit such as point, line, surface, by it along corrected
The horizontal direction of image pair afterwards carries out traversal search, and the similarity determination according to matching basic unit is matching or mismatches,
So as to find out the matching relationship of pixel in left images；Since the visual field of left and right cameras is different, match point is imaged at two
The position of machine is inevitable different, it is possible thereby to calculate corresponding disparity map；Core concept of the solid four with algorithm is first sufficiently
Using more solutions in basic constraint condition elimination matching process, ambiguity problem, energy function then is converted by matching problem
Optimization problem；The solution form of Stereo Matching Algorithm is adopted by establishing the cost energy function based on Matching unit
Take different matching strategies that this cost energy function is minimized to estimate pixel parallax value.Step is arrived into step (2) are crossed
Suddenly after (4) processing, the non-targeted part of left images is had been removed, only remaining nut-screw part, therefore in solid
The parallax obtained when matching also only has nut-screw part.
In step (5), the generation method of three-dimensional point cloud is the principle of triangulation using similar triangles, the depth of certain point
There are following relationships between degree and its parallax:Wherein z is the depth distance of certain point, and d is parallax, and f is focal length, b
For the parallax range between two video cameras；The disparity map that Stereo matching obtains is actually the view of each pixel on image
Therefore the three-dimensional point cloud of target can be generated in difference set；Three-dimensional point cloud is the set of target surface three-dimensional coordinate point.From intuitive
Angle sees that, if there is damages for nut-screw, the part and nut-screw surface be not in a depth.
In step (6), calculation method is as follows: the conversion that pixel distance and actual physics distance are obtained after camera calibration is closed
System, i.e. the corresponding mm length of unit pixel, and then nut is set as area-of-interest, count respectively the zone length direction and
The number of pixels of width direction converts to obtain the diameter and height of nut by transformational relation；Likewise, after according to three-dimensionalreconstruction
Rent point cloud each point depth value, convert to obtain the mean depth and depth capacity of nut rent by transformational relation；
The calculation method of Average Broken width and maximum rupture width is as follows:
Average Broken width: if generating rupture on nut, the depth value and gray value of rent point can be attached with rent
The depth value and gray value of close nut region point have obvious mutation, can judge that it belongs to rent by Threshold segmentation；It will break
The point for splitting place extracts, and divides rent using edge detection, the left edge pixel coordinate of rent is denoted as (xELi,
yELi), right hand edge pixel coordinate is denoted as (xERi, yERi), rent center pixel coordinate is represented by (xERi-xELi, yERi-
yELi), the pixel quantity at rent center is counted, Sumpix is denoted asmedia, the total pixel quantity in rent region is counted, is denoted as
Sumpixarea, rent mean breadth Avgwidth:
Avgwidth=Sumpixarea÷Sumpixmedia
Maximum rupture width: asking each left edge pixel to the shortest distance of right hand edge, and calculated result, which is constituted, to be gathered
De min, the maximum value Maxwidth in the set is then the maximum width of the rent, remembers set De minElement be de min
……
De min={ de min 1, de min 2, de min 3... ...
Maxwidth=max (Demin)。
Result from above is pixel distance, the relationship of the pixel distance and physical distance that obtain after camera calibration,
The physical distance of each parameter of rent can be calculated by this relationship.
Step (7) compares nut-screw position and the elemental height parameter of vision-based detection, can obtain loosening feelings
Condition；For the degree of rupture, I, II, III grade can be divided into, first calculate nut area pixel sum SumpixnutareaWith nut diameter
Widthdiam, rent maximum width Maxwidth, judge level of breakage rule it is as follows:
A kind of multi-view stereo vision detection device that bridge pedestal nut-screw is loosened or ruptured, is using above-mentioned detection side
Method, loosening or rupture event to bridge pedestal nut-screw are detected and are monitored in real time, including bionical clam shell open frame
8, microcam 9；The bionical freshwater mussel of installation four or more is evenly arranged in the circumference of 7 lower part of intermediolateral column of bridge pedestal 6
Shell-type rack 8, installs 1 microcam 9 in each clam shell, and every 2 adjacent microcams partner stereoscopic vision,
The centre of clam shell is provided with an aperture, the nut 1, trapezoidal spiral shell for stretching out the camera lens of microcam, on alignment lens pedestal
Bar 3.
Cable 10 and electric wire are passed through from clam shell tail portion, and the computer 11 of cable 10 and end of the bridge monitoring room interconnects, and can also be led to
It crosses wireless network forms and is sent to computer 11.
The quantity of bionical clam shell open frame preferably 4~6.
Bionical clam shell is closed substantially, and the structure of bionical clam shell can prevent wind, rainwater, and cable and electric wire are worn from clam shell tail portion
It crosses.
The present invention has the following advantages that compared with prior art and effect:
(1) detection accuracy degree of the invention can be measured in real time and Real-time Feedback result.
(2) present invention uses multi-vision visual, can will test range and be extended to 360 degree without dead angle.Pass through Stereo matching, three-dimensional
Reconstruct, can rebuild the threedimensional model of nut-screw, so that accurately whether detection nut loosens, if there is rupture；As nut is deposited
It is rupturing, the information such as mean breadth, the cracking depth of rent can be calculated.
(3) bionical clam shell open frame of the invention, shell mechanism is close, has radix saposhnikoviae, waterproof performance well, can protect
Internal element and circuit are protected from the infringement of natural medium.
(4) structure of the invention is simple, easy for installation, at low cost.
Detailed description of the invention
Fig. 1 is the working state schematic representation of multi-view stereo vision detection device of the present invention.
Fig. 2 is the connection schematic diagram of multi-view stereo vision detection device of the present invention.
Fig. 3 is the bionical clam shell open frame schematic diagram of multi-view stereo vision detection device of the present invention.
Wherein, 1, nut；2, nut；3, ladder type screw rod；4, washer；5 screw rod mounting seats；6, bridge pedestal；7, intermediate
Column；8, bionical clam shell open frame；9, microcam；10, cable；11, computer；12, voice device.
Specific embodiment
Further detailed description is done to the present invention below with reference to embodiment, embodiments of the present invention are not limited thereto.
Embodiment 1
The installation form of the nut-screw of bridge pedestal is general are as follows: multiple nuts such as nut 1, nut 2 are sleeved and fixed in ladder
On type screw rod 3, ladder type screw rod 3 is mounted in screw rod mounting seat 5, there is washer 4 between ladder type screw rod 3 and screw rod mounting seat 5.
A kind of multi-view stereo vision detection device that bridge pedestal nut-screw is loosened or ruptured, including bionical clampshell machine
Frame 8, microcam 9；Four bionical clampshell machines of installation are evenly arranged in the circumference of 7 lower part of intermediolateral column of bridge pedestal 6
Frame 8, each clam shell is interior to install 1 microcam 9, and bionical clam shell is closed substantially, and the structure of bionical clam shell can prevent wind, rain
Water, cable and electric wire are passed through from clam shell tail portion.2 adjacent microcams partner stereoscopic vision, and the centre of clam shell is set
It is equipped with an aperture, the nut 1, trapezoidal screw 3 for stretching out the camera lens of microcam, on alignment lens pedestal.10 He of cable
Electric wire is passed through from clam shell tail portion, and the computer 11 of cable 10 and end of the bridge monitoring room interconnects, and can also be sent out by wireless network forms
Computer 11 is given, is furnished with voice device 12 on computer 11.
When work, video camera acquires nut-screw image, and cable and computer interconnect, and can also pass through wireless network forms
It is sent to computer.Vision software part on computer contains image preprocessing, image procossing and its recognizer, three-dimensional
The reconstruct of point cloud, damage measurement method, nut and screw bolt loosening destroy the modules such as assessment.When system assesses these parameters
When, it is loosened or level of breakage, may also occur the existing degree of impairment for loosening and also having destruction in practice, be provided certainly to repair
Plan data.Computer and its vision software should include voice system, prompt technology or operator.
The above description is only a preferred embodiment of the present invention, is not intended to limit the scope of the invention, all at this
Under the design of invention, using equivalent structure transformation made by description of the invention and accompanying drawing content, or directly/it is used in it indirectly
He is included in scope of patent protection of the invention relevant technical field.
Claims (10)
1. a kind of bridge pedestal nut-screw loosens or the multi-view stereo vision detection method of rupture, it is characterised in that including following
Step:
(1) camera calibration and pixel calibration: video camera has 4 or more, and the abutting video camera of each video camera is constituted
One camera shooting unit forms the detection within the scope of 360 degree；By camera calibration to obtain for correcting captured pattern distortion
Intrinsic parameters of the camera and distortion parameter；It is demarcated by pixel to obtain the transformational relation of pixel distance and actual physics distance,
That is the corresponding mm length of unit pixel；It is completed at the same time the calibration of four mesh or the above stereoscopic vision；
(2) it corrects image: the digital picture of nut-screw is captured by video camera, then according to the calibration result logarithm of video camera
Word image carries out distortion correction, obtains the correction image of nut-screw；
(3) gray processing and smooth: the correction image of nut-screw is subjected to gray processing, by three components of its red, green, blue with difference
Weight be weighted and averaged；Then detection zone is smoothed with Gaussian function, obtains the smooth single-pass of nut-screw
Then road gray level image carries out feature extraction；
(4) images match: being compared with image object with the template of standard nut screw rod work-in parameters and matched, and obtains nut spiral shell
The shape of bar, identifies nut-screw；
(5) Stereo matching three-dimensionalreconstruction: is carried out to the image of left and right cameras；It the disparity map that is obtained using Stereo matching and takes the photograph
The re-projection matrix obtained when camera calibration generates three-dimensional point cloud, and carries out three-dimensionalreconstruction to three-dimensional point cloud；
(6) parameter calculates: in bridge installation, it is known that the elemental height of original nut, therefore the target shape according to three-dimensionalreconstruction
State and its position are calculated nut diameter, height, the average of nut rent and are broken by founding mathematical models and its calculation method
Split the parameters such as width, maximum rupture width, mean depth and depth capacity；
(7) loosen or break up assessment: and then system assesses these parameters, and correlated results is transferred to user, for
Family provides maintenance parameter.
2. bridge pedestal nut-screw according to claim 1 loosens or the multi-view stereo vision detection method of rupture,
It is characterized in that: in step (3), being smoothed using Gaussian function, the number in the core of Gaussian filter is that height is presented
This distribution, in order to eliminate noise jamming and not influence the information of damage field, when carrying out picture smooth treatment, Gaussian function
The selection of several standard variance σ is the overall permanence in view of image, using minimum variance as the module for choosing σ value, wherein
M, E, σ are mean value, variance and the Gauss standard variance in N × N window respectively；EminIt is minimum variance, when variance minimum, σ is most
Small value is 1；
Emin=min (E) (3)
3. bridge pedestal nut-screw according to claim 1 loosens or the multi-view stereo vision detection method of rupture,
Be characterized in that: in step (5), the generation method of three-dimensional point cloud is the principle of triangulation using similar triangles, certain point
There are following relationships between depth and its parallax:Wherein z is the depth distance of certain point, and d is parallax, and f is focal length,
B is the parallax range between two video cameras；The parallax set of each pixel on the disparity map that Stereo matching obtains i.e. image,
To generate the three-dimensional point cloud of target；Three-dimensional point cloud is the set of target surface three-dimensional coordinate point；If there is damages for nut-screw
Wound, then the part and nut-screw surface be not in a depth.
4. bridge pedestal nut-screw according to claim 1 loosens or the multi-view stereo vision detection method of rupture,
It is characterized in that: in step (6), nut diameter, height, the Average Broken width of nut rent, the maximum calculating for rupturing width
Method is as follows: the transformational relation of pixel distance and actual physics distance, the i.e. corresponding milli of unit pixel are obtained after camera calibration
Meter Chang Du, and then nut is set as area-of-interest, the number of pixels in the zone length direction and width direction is counted respectively, is led to
Transformational relation is crossed to convert to obtain the diameter of nut and height；Likewise, deep according to each point of the rent point cloud after three-dimensionalreconstruction
Angle value converts to obtain the mean depth and depth capacity of nut rent by transformational relation.
5. bridge pedestal nut-screw according to claim 1 loosens or the multi-view stereo vision detection method of rupture,
Be characterized in that: in step (6), the calculation method of the Average Broken width of nut rent and maximum rupture width is as follows:
Average Broken width: if generating rupture on nut, the depth value and gray value of rent point can near rent
The depth value and gray value of nut region point have obvious mutation, can judge that it belongs to rent by Threshold segmentation；By rent
Point extract, using edge detection divide rent, the left edge pixel coordinate of rent is denoted as (xELi, yELi),
Right hand edge pixel coordinate is denoted as (xERi, yERi), rent center pixel coordinate is represented by (xERi-xELi, yERi-yELi), system
The pixel quantity for counting rent center, is denoted as Sumpixmedia, the total pixel quantity in rent region is counted, is denoted as
Sumpixarea, rent mean breadth Avgwidth:
Avgwidth=Sumpixarea÷Sumpixmedia
Maximum rupture width: ask each left edge pixel to the shortest distance of right hand edge, calculated result composition set Demin, should
Maximum value Maxwidth in set is then the maximum width of the rent, remembers set DeminElement be demin
……
Demin={ demin1, demin2, demin3... ...
Maxwidth=max (Demin)。
6. bridge pedestal nut-screw according to claim 1 loosens or the multi-view stereo vision detection method of rupture,
Be characterized in that: step (7) compares nut-screw position and the elemental height parameter of vision-based detection, can obtain loosening feelings
Condition；For the degree of rupture, I, II, III grade can be divided into, first calculate nut area pixel sum SumpixnutareaWith nut diameter
Widthdiam, rent maximum width Maxwidth, judge level of breakage rule it is as follows:
7. a kind of bridge pedestal nut-screw loosens or the multi-view stereo vision detection device of rupture, it is characterised in that: be to use
Multi-view stereo vision detection method according to any one of claims 1 to 6, loosening or rupture to bridge pedestal nut-screw
Situation is detected and is monitored in real time；Including bionical clam shell open frame, microcam；In the intermediolateral column lower part of bridge pedestal
Circumference in be evenly arranged the bionical clam shell open frame of installation four or more, 1 microcam is installed in each clam shell, often
2 adjacent microcams partner stereoscopic vision, and the centre of clam shell is provided with an aperture, for stretching out microcam
Camera lens, nut, trapezoidal screw on alignment lens pedestal.
8. bridge pedestal nut-screw according to claim 7 loosens or the multi-view stereo vision detection device of rupture,
Be characterized in that: cable and electric wire are passed through from clam shell tail portion, and the computer of cable and end of the bridge monitoring room interconnects, can also be by wireless
Latticed form is sent to computer.
9. bridge pedestal nut-screw according to claim 7 loosens or the multi-view stereo vision detection device of rupture,
Be characterized in that: the quantity of bionical clam shell open frame is 4~6.
10. bridge pedestal nut-screw according to claim 7 loosens or the multi-view stereo vision detection device of rupture,
Be characterized in that: bionical clam shell is closed substantially, and the structure of bionical clam shell can prevent wind, rainwater, and cable and electric wire are from clam shell tail portion
It passes through.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910235216.9A CN110031476A (en) | 2019-03-27 | 2019-03-27 | A kind of multi-view stereo vision detection device and method that bridge pedestal nut-screw is loosened or ruptured |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910235216.9A CN110031476A (en) | 2019-03-27 | 2019-03-27 | A kind of multi-view stereo vision detection device and method that bridge pedestal nut-screw is loosened or ruptured |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110031476A true CN110031476A (en) | 2019-07-19 |
Family
ID=67236729
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910235216.9A Withdrawn CN110031476A (en) | 2019-03-27 | 2019-03-27 | A kind of multi-view stereo vision detection device and method that bridge pedestal nut-screw is loosened or ruptured |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110031476A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111442723A (en) * | 2020-03-27 | 2020-07-24 | 江苏理工学院 | Method and device for integrally detecting shape and position of nut on mobile phone middle plate |
| CN112381791A (en) * | 2020-11-13 | 2021-02-19 | 北京图知天下科技有限责任公司 | Bolt looseness detection method based on 3D point cloud |
| CN112819752A (en) * | 2021-01-05 | 2021-05-18 | 中国铁建重工集团股份有限公司 | Fastener state detection method, system and readable storage medium |
| CN112986146A (en) * | 2021-05-06 | 2021-06-18 | 上海建工集团股份有限公司 | Image recognition-based guide rail frame bolt connection reliability detection device |
| CN113379712A (en) * | 2021-06-23 | 2021-09-10 | 西南交通大学 | Steel bridge bolt disease detection method and system based on computer vision |
| CN114485434A (en) * | 2022-01-27 | 2022-05-13 | 南京航空航天大学 | Installation detection method for guide rod of flexible three-dimensional weaving equipment based on multi-view distance measurement |
| CN117564131A (en) * | 2024-01-17 | 2024-02-20 | 海顿直线电机(常州)有限公司 | Motor screw straightening method based on visual detection control system |
-
2019
- 2019-03-27 CN CN201910235216.9A patent/CN110031476A/en not_active Withdrawn
Cited By (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111442723A (en) * | 2020-03-27 | 2020-07-24 | 江苏理工学院 | Method and device for integrally detecting shape and position of nut on mobile phone middle plate |
| CN111442723B (en) * | 2020-03-27 | 2022-02-11 | 江苏理工学院 | Method and device for integrally detecting shape and position of nut on mobile phone middle plate |
| CN112381791A (en) * | 2020-11-13 | 2021-02-19 | 北京图知天下科技有限责任公司 | Bolt looseness detection method based on 3D point cloud |
| CN112819752A (en) * | 2021-01-05 | 2021-05-18 | 中国铁建重工集团股份有限公司 | Fastener state detection method, system and readable storage medium |
| CN112986146A (en) * | 2021-05-06 | 2021-06-18 | 上海建工集团股份有限公司 | Image recognition-based guide rail frame bolt connection reliability detection device |
| CN113379712A (en) * | 2021-06-23 | 2021-09-10 | 西南交通大学 | Steel bridge bolt disease detection method and system based on computer vision |
| CN113379712B (en) * | 2021-06-23 | 2022-07-29 | 西南交通大学 | Steel bridge bolt disease detection method and system based on computer vision |
| CN114485434A (en) * | 2022-01-27 | 2022-05-13 | 南京航空航天大学 | Installation detection method for guide rod of flexible three-dimensional weaving equipment based on multi-view distance measurement |
| CN114485434B (en) * | 2022-01-27 | 2022-10-21 | 南京航空航天大学 | Installation detection method for guide rod of flexible three-dimensional weaving equipment based on multi-view distance measurement |
| CN117564131A (en) * | 2024-01-17 | 2024-02-20 | 海顿直线电机(常州)有限公司 | Motor screw straightening method based on visual detection control system |
| CN117564131B (en) * | 2024-01-17 | 2024-04-02 | 海顿直线电机(常州)有限公司 | Motor screw straightening method based on visual detection control system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110031476A (en) | A kind of multi-view stereo vision detection device and method that bridge pedestal nut-screw is loosened or ruptured | |
| CN107704844B (en) | Power transmission line icing thickness identification method based on binocular parallax images of unmanned aerial vehicle | |
| CN107392247B (en) | Real-time detection method for ground object safety distance below power line | |
| CN103984961B (en) | A kind of image detecting method for being used to detect underbody foreign matter | |
| CN109443480A (en) | Gauge positioning and water level measurement method based on image procossing | |
| WO2018028103A1 (en) | Unmanned aerial vehicle power line inspection method based on characteristics of human vision | |
| CN105894574B (en) | A kind of binocular three-dimensional reconstruction method | |
| CN111308448B (en) | External parameter determining method and device for image acquisition equipment and radar | |
| CN108230344B (en) | Automatic identification method for tunnel water leakage diseases | |
| CN110009610A (en) | A kind of reservoir dam slope protection surface damage visible detection method and bionic device | |
| CN107179322A (en) | A kind of bridge bottom crack detection method based on binocular vision | |
| CN108169142B (en) | Water colour exception method for rapidly positioning and device based on remote sensing image | |
| CN106023185A (en) | Power transmission equipment fault diagnosis method | |
| CN107631782B (en) | Water level detection method based on Harris angular point detection | |
| CN108537170A (en) | A kind of power equipment firmware unmanned plane inspection pin missing detection method | |
| CN110675449B (en) | Binocular camera-based offshore flow detection method | |
| CN107742307A (en) | Based on the transmission line galloping feature extraction and parameters analysis method for improving frame difference method | |
| CN109376740A (en) | A kind of water gauge reading detection method based on video | |
| CN107578397A (en) | A kind of novel non-contact abrasion of contact wire detection method | |
| Huang et al. | Online apple grading based on decision fusion of image features | |
| CN102621154B (en) | Method and device for automatically detecting cloth defects on line based on improved differential box multi-fractal algorithm | |
| CN114255405A (en) | Hidden danger target identification method and device | |
| CN108665468B (en) | Device and method for extracting tangent tower insulator string | |
| CN111461138A (en) | Power line automatic extraction method based on L iDAR point cloud data | |
| CN103281513A (en) | Method for recognizing pedestrian in monitoring system without overlapped area |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190719 |