CN106645168B - A kind of detection method of crane boom cylinder concave-convex surface defect - Google Patents

A kind of detection method of crane boom cylinder concave-convex surface defect Download PDF

Info

Publication number
CN106645168B
CN106645168B CN201611174854.7A CN201611174854A CN106645168B CN 106645168 B CN106645168 B CN 106645168B CN 201611174854 A CN201611174854 A CN 201611174854A CN 106645168 B CN106645168 B CN 106645168B
Authority
CN
China
Prior art keywords
arm cylinder
concave
convex
gray level
image
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201611174854.7A
Other languages
Chinese (zh)
Other versions
CN106645168A (en
Inventor
朱江
徐雁冰
许海霞
田淑娟
印峰
裴廷睿
关屋大雄
崔荣埈
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Xiangtan University
Original Assignee
Xiangtan University
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Xiangtan University filed Critical Xiangtan University
Priority to CN201611174854.7A priority Critical patent/CN106645168B/en
Publication of CN106645168A publication Critical patent/CN106645168A/en
Application granted granted Critical
Publication of CN106645168B publication Critical patent/CN106645168B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G01N21/8851—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
    • G01N2021/8854—Grading and classifying of flaws
    • G01N2021/8861—Determining coordinates of flaws
    • G01N2021/8864—Mapping zones of defects

Abstract

The invention proposes a kind of detection methods of crane boom cylinder concave-convex surface defect.Step of the present invention: firstly, the actual range of laser sensor to arm cylinder that laser sensor measures is mapped to actual grey image, the distance of laser sensor to arm cylinder index plane is mapped to normal grayscale image；Then, difference is carried out to actual grey image and normal grayscale image, obtains concave-convex target image, concave-convex target image is subjected to Threshold segmentation, obtain measurement gray level image；Finally, determining the relief region number of arm cylinder, position, area and concave-convex peak value.The advantages that there is the present invention detection process to be not necessarily to manual intervention, not need described point label, can detect multiple faces simultaneously, and detection speed is fast, and precision is high.

Description

A kind of detection method of crane boom cylinder concave-convex surface defect
Technical field
The present invention relates to flatness detection field more particularly to the detection methods of crane boom cylinder concave-convex surface defect.
Background technique
Crane arm is the main building block of crane, and crane arm is usually composed of several different size of arm cylinders, Expansion or the contractile function of crane arm are realized by arm cylinder of stretching, therefore the concavity and convexity on arm cylinder surface is to be related to crane arm to stretch The important morpheme influence factor of mechanism quality.Actual surface is relative to standard after the concavity and convexity on arm cylinder surface refers to arm cylinder processing The fluctuating situation on surface, in order to can guarantee that crane arm can be carried out normal flexible running, the crane arm accuracy of manufacture must satisfy requirement, Its arm cylinder concave-convex surface has to control in the Form and position error of permission.Fast implement to the concave-convex defect of crane boom cylinder into Row detects and positions the problem of being current urgent need to resolve.
Currently, the detection of crane boom cylinder concave-convex surface is directed in actual production, it is general manually to use three-dimensional coordinates measurement Machine, amesdial beat the methods of alignment measurement of table measurement, electrolevel and autocollimator measurement minute angle to realize.Just rise For heavy-duty machine arm cylinder, table mensuration is beaten for three coordinate measuring machine and amesdial, due to crane boom cylinder region area to be measured compared with Greatly, it is limited by measuring rod length and datum level selection, arm cylinder surface portion region can only be measured, entire plane cannot be covered, Hardly result in the correct measurement result on entire arm cylinder surface.Level meter method measurement body surface concavity and convexity needs to consolidate measuring instrument It is scheduled on surface to be measured, since arm cylinder is factory's batch production, the process of fixation measuring tool makes work on arm cylinder one by one Amount increases, and efficiency reduces.
The range data of laser sensor to arm cylinder that laser sensor samples is mapped to gray value by the present invention, is obtained To gray level image, then obtained gray level image is handled using image processing techniques, is realized to arm cylinder concave-convex surface Detection.Measured data is converted to the method that gray level image is handled by the present invention, and it is real-time both to have solved traditional detection method Property poor, the low problem of detection confidence level, in turn avoid dependence of the detection method based on machine vision to environmental factors such as light Property.The entire detection process of the present invention is not necessarily to manual intervention, does not need described point label, and detection speed is fast, and precision is high, and system stabilization can It leans on, it is at subsequent corrective that testing result, which can provide the specifying informations such as arm cylinder relief region number, position, area and concave-convex peak value, Reason provides foundation.
Summary of the invention
In view of the deficiencies of the prior art, the present invention proposes a kind of detection method of crane boom cylinder concave-convex surface defect, should Method can efficiently detect the concave-convex situation of crane boom cylinder.
The present invention is realized by the following scheme:
Step 1: actual range of the laser sensor that laser sensor is measured to arm cylinderIt is mapped to actual grey figure Picture,
By laser sensor to the distance of arm cylinder index planeIt is mapped to normal grayscale image；
Step 2: to actual grey imageAnd normal grayscale imageDifference is carried out, concave-convex target image is obtained, will Concave-convex target imageThreshold segmentation is carried out, measurement gray level image is obtained；
Step 3: determining the relief region number of arm cylinder, position, area and concave-convex peak value.
The invention has the following advantages that
1, equipment used in the implementation present invention is less, and structure is simple, low in cost；
2, the present invention utilizes image processing techniques, is automatically detected to arm cylinder concavity and convexity, testing result can provide arm The specifying informations such as cylinder relief region number, position, area and concave-convex peak value provide foundation for subsequent corrective processing；
3, the present invention can calculate the collected data in multiple faces, analyze simultaneously, and entire detection process is without artificial Intervene, do not need described point label, largely save human resources, detection speed is fast, and precision is high, and system is reliable and stable.
Detailed description of the invention
Fig. 1 is implementation flow chart of the invention；
Fig. 2 is crane boom cylinder top view；
Fig. 3 is standard arm cylinder sectional view；
Fig. 4 is the arm cylinder schematic cross-section for having concave-convex defect；
Fig. 5 is actual grey image；
Fig. 6 is normal grayscale image；
Fig. 7 is concave-convex target image；
Fig. 8 is measurement gray level image；
Fig. 9 is the measurement gray level image after label；
Specific embodiment
Embodiment 1
It is illustrated by taking the face to be detected of the left side of the crane boom cylinder of model QY20 as an example, the detection in other faces to be detected Journey is consistent with the detection process in left side face to be detected.
As shown in Fig. 2, 8810 mm of arm cylinder tube length, respectively has a laser sensor, laser sensor to mark in arm cylinder two sides The distance on quasi- arm cylinder surface is 300 mm.The direction y is tube length direction, and arm cylinder is under the transport of conveyer belt along y-axis to laser sensing The movement of device direction, sampling should be carried out for the laser sensor of the every 5 mm triggering left and right sides of advancing of arm cylinder.
As shown in figure 3, wide 482 mm of arm cylinder cylinder, the laser sensor of left and right sides is along the wide respectively every primary generation one of sampling of cylinder Organize data, 5 mm of neighbouring sample point interval in every group of data.
Now with A point start along 50 mm(of tube length direction along tube length direction sample 10 times), along 50 mm(of cylinder wide direction along tube length The every sampling in direction once generates one group of data, takes first 10 since the end A) sampled data in region says this method It is bright.
As shown in figure 4, arm cylinder index plane allowable error is 3 mm.
In conjunction with Fig. 1, of the invention the specific implementation steps are as follows:
Step 1: actual range of the laser sensor that laser sensor is measured to arm cylinderIt is mapped to actual grey figure Picture,
By laser sensor to the distance of arm cylinder index planeIt is mapped to normal grayscale image:
1) it combining and provides parameter, start to sample 10 times along tube length direction with A point, every sampling once generates one group of column vector, Every group of column vector takes preceding 10 data since the end A, successively combines obtain 10 groups of column vectors, obtains actual range matrixIt is as follows:
；
2) gray value interval is [0,255], by distanceIt is mapped to gray value, whereinIndicate the end A starts the Row measurement point,Indicate the end A starts theColumn measurement point, as follows:
,
Calculate matrixIn the corresponding gray value of each element, obtain actual grey imageSuch as Fig. 5；
3) distance on laser sensor to standard arm cylinder surface is 300 mm, is obtained and actual range matrixRow, column number Identical standard distance matrixIt is as follows:
；
4) gray value interval is [0,255], by distanceIt is mapped to gray value, whereinIndicate the end A starts theRow Measurement point,Indicate the end A starts theColumn measurement point, as follows:
,
Obtain normal grayscale imageSuch as Fig. 6；
Step 2: to actual grey imageAnd normal grayscale imageDifference is carried out, concave-convex target image is obtained, will Concave-convex target imageThreshold segmentation is carried out, measurement gray level image is obtained:
1) actual grey value matrixAnd normal grayscale imageIt carries out difference and obtains concave-convex target imageSuch as Fig. 7；
2) with threshold segmentation method to concave-convex target imageIt is further processed:
In conjunction in step 1 2), arm cylinder index plane allowable error be 3 mm, be mapped to gray value error be 38, then set threshold Value,
,
Indicate theRow measurement point,Arm cylinder tube length is prolonged in expressionColumn measurement point,Indicate theRow, theColumn are surveyed Measure the pixel value of point；
Obtain measurement gray level imageSuch as Fig. 8；
3) in measurement gray level imageMiddle differentiation concave, convex and background area:
,
That is white area is background in Fig. 8, and gray area is concave region, and black region is convex domain；
Step 3: determine the relief region number of arm cylinder, position, area and concave-convex peak value process:
1) to measurement gray level imageRelief region is split and is marked with connected region labeling method, is usedLabel TheEach pixel in a concave region is usedIndicate theEach pixel in a convex domain measures grayscale image PictureSuch as Fig. 9 after label；
2) the relief region number of arm cylinder is determined:
All recessed area field marksInMaximum value be 2, i.e. arm cylinder concave region number；
All convex region field marksInMaximum value be 1, i.e. arm cylinder convex domain number；
Cylinder arm relief region sum；
I.e. there is the region one of concave-convex defect to share at 3 for arm cylinder side to be checked, wherein having at concave region 2, at convex domain 1；
3) the relief region position of arm cylinder is determined:
Relief region is in measurement gray level imageIn position centroid coordinate representation,
Concave regionIn measurement gray level imageIn centroid coordinateMeet:
,；
Convex domainIn measurement gray level imageIn centroid coordinateMeet:
,；
Then concave regionIn measurement gray level imageIn centroid coordinate are as follows:,
Concave regionIn measurement gray level imageIn centroid coordinate are as follows:,
Convex domainIn measurement gray level imageIn centroid coordinate are as follows:；
Measure gray level imageIn adjacent element represents in every group of column vector 5 mm of sampled point interval, in every group of column vector 5 mm of sampled point interval that adjacent element represents,
Then measure gray level imageMiddle concave regionArm cylinder tested surface A point is mapped in start along 50 mm of tube length direction, along cylinder Coordinate in 50 region mm of wide direction are as follows:,
Measure gray level imageMiddle concave regionArm cylinder tested surface A point is mapped in start along 50 mm of tube length direction, wide along cylinder Coordinate in 50 region mm of direction are as follows:,
Measure gray level imageMiddle convex domainArm cylinder tested surface A point is mapped in start along 50 mm of tube length direction, wide along cylinder Coordinate in 50 region mm of direction are as follows:；
4) the relief region area of arm cylinder is determined:
Measure gray level imageMiddle concave regionInterior pixel number, then gray level image is measuredMiddle concave regionThe areal calculation for being mapped to arm cylinder concave region is as follows:
,
Measure gray level imageMiddle concave regionInterior pixel number, then gray level image is measuredMiddle concave regionThe areal calculation for being mapped to arm cylinder concave region is as follows:
,
Measure gray level imageMiddle convex domainInterior pixel number, then gray level image is measuredMiddle convex domainThe areal calculation for being mapped to arm cylinder convex domain is as follows:
；
5) the relief region peak value of arm cylinder is determined:
Measure gray level imageMiddle concave regionThe recess peak computational of the arm cylinder concave region of representative is as follows:
,
Measure gray level imageMiddle concave regionThe recess peak computational of the arm cylinder concave region of representative is as follows:
,
Measure gray level imageMiddle convex domainThe protrusion peak computational of the arm cylinder convex domain of representative is as follows:
。

Claims (3)

1. a kind of detection method of crane boom cylinder concave-convex surface defect, the method includes at least following steps:
Step 1: the actual range d of laser sensor to arm cylinder that laser sensor measures is mapped to actual grey image G,
The distance l of laser sensor to arm cylinder index plane that laser sensor measures is mapped to normal grayscale image H；
Step 2: carrying out difference to actual grey image G and normal grayscale image H, concave-convex target image T is obtained, by concave-convex mesh Logo image T carries out Threshold segmentation, obtains measurement gray level image C；
1) actual grey image G and normal grayscale image H carries out difference and obtains concave-convex target image T:
T=G-H；
2) concave-convex target image T is further processed with threshold segmentation method, given threshold k, obtains measurement gray level image C:
I indicates the i-th row measurement point, j is indicated along arm cylinder tube length jth column measurement point, and C (i, j) indicates the i-th row, jth column measurement point Pixel value；
3) concave, convex and background area are distinguished in measurement gray level image C:
Step 3: determining the relief region number of arm cylinder, position, area and concave-convex peak value.
2. the detection method of crane boom cylinder concave-convex surface defect according to claim 1, it is characterised in that by arm cylinder two The data that the laser sensor of side repeatedly measures are mapped to gray level image and reflect the distance of laser sensor to arm cylinder index plane The process of gray level image is penetrated into, at least further comprising the steps of:
1) with laser sensor to laser sensor to the distance samples on arm cylinder surface, every sampling once generates one group of column vector, The sampled point interval p mm that adjacent element represents in every group of column vector；
Laser sensor carries out repeated sampling by arm cylinder tube length direction with the interval of q mm, samples j times altogether, generates j group column vector, I.e. from sampling for the first time, jth is secondary to sample end detection arm cylinder tube length q × j mm altogether；
It successively combines obtained j group column vector by sampling order, obtains actual range matrix D；
Element d in DijIn section [dmin,dmax] in, wherein i indicates the i-th row measurement point, and j is indicated to arrange along arm cylinder tube length jth and be surveyed Measure point, dmaxIt indicates to sample the maximum value in obtained actual range matrix D, dminIndicate the actual range matrix D that sampling obtains In minimum value；
2) gray value interval is [0,255], will distance dijIt is mapped to gray value gij, wherein i indicates the i-th row measurement point, and j indicates edge Arm cylinder tube length jth column measurement point, as follows:
3) the corresponding gray value of each element in matrix D is calculated, actual grey image G is obtained；
4) gauged distance matrix L identical with the row, column number of actual range matrix D, the element l in L are automatically generatedijIt is equal to sharp Distance l of the optical sensor to arm cylinder index plane；
5) gray value interval is [0,255], will distance lijIt is mapped to gray value hij, wherein i indicates the i-th row measurement point, and j indicates edge Arm cylinder tube length jth column measurement point, as follows:
Obtain normal grayscale image H.
3. the detection method of crane boom cylinder concave-convex surface defect according to claim 1, it is characterised in that determine arm cylinder Relief region number, position, area and concave-convex peak value process, at least further include following steps:
1) measurement gray level image C is split and is marked to relief region with connected region labeling method, use wmM-th of label recessed Each pixel in region, uses vnIndicate each pixel in n-th of convex domain；
2) the relief region number of arm cylinder is determined:
Arm cylinder concave region number e is equal to recessed area field mark wmThe maximum value of middle m, arm cylinder convex domain number f are equal to convex region field mark vn The maximum value of middle n；
Cylinder arm relief region sum s=e+f；
3) the relief region position of arm cylinder is determined:
Position centroid coordinate representation of the relief region in measurement gray level image C,
Concave region wmCentroid coordinate w in measurement gray level image Cm(i0,j0) meet:
Convex domain vnCentroid coordinate v in measurement gray level image Cn(i1,j1) meet:
Measure the sampled point interval p mm that adjacent element represents in every group of column vector in gray level image C, it is adjacent in every group of column vector The sampled point interval q mm that element represents,
Then measure concave region w in gray level image CmThe coordinate for being mapped in arm cylinder surface is Wm(x0,y0):
x0=q × i0, y0=p × j0；
Measure convex domain v in gray level image CnThe coordinate for being mapped in arm cylinder surface is Vn(x1,y1):
x1=q × i1, y1=p × j1；
4) the relief region area of arm cylinder is determined:
Concave region w in detection measurement gray level image CmInterior pixel number γm, then concave region w in gray level image C is measuredmMapping Areal calculation to arm cylinder concave region is as follows:
φm=p × q × γmmm2；
Convex domain v in detection measurement gray level image CnInterior pixel number λn, then convex domain v in gray level image C is measurednMapping Areal calculation to arm cylinder convex domain is as follows:
5) the relief region peak value of arm cylinder is determined:
Search concave region w in measurement gray level image CmCorresponding element d of the interior pixel in actual range matrix Dij, then recessed area Domain wmThe recess peak computational of the arm cylinder concave region of representative is as follows:
Wm=max (| dij-lij|)；
Search convex domain v in measurement gray level image CnCorresponding element d of the interior pixel in actual range matrix Dij, then convex region Domain vnThe protrusion peak computational of the arm cylinder convex domain of representative is as follows:
Vn=max (| dij-lij|)。
CN201611174854.7A 2016-12-19 2016-12-19 A kind of detection method of crane boom cylinder concave-convex surface defect Active CN106645168B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201611174854.7A CN106645168B (en) 2016-12-19 2016-12-19 A kind of detection method of crane boom cylinder concave-convex surface defect

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201611174854.7A CN106645168B (en) 2016-12-19 2016-12-19 A kind of detection method of crane boom cylinder concave-convex surface defect

Publications (2)

Publication Number Publication Date
CN106645168A CN106645168A (en) 2017-05-10
CN106645168B true CN106645168B (en) 2019-05-03

Family

ID=58823005

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201611174854.7A Active CN106645168B (en) 2016-12-19 2016-12-19 A kind of detection method of crane boom cylinder concave-convex surface defect

Country Status (1)

Country Link
CN (1) CN106645168B (en)

Families Citing this family (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN109596637A (en) * 2017-09-30 2019-04-09 湖南海擎智能科技有限责任公司 Object bumps flaw visible detection method and detection device
CN111612769A (en) * 2020-05-22 2020-09-01 湘潭市锦程半导体科技有限公司 Method for detecting surface concave-convex defect of triode packaging metal cap
CN117132563A (en) * 2023-08-24 2023-11-28 广东理工学院 Glass defect detection method and device, electronic equipment and storage medium

Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101655464A (en) * 2009-09-16 2010-02-24 重庆大学 Surface defect form and depth on-line lossless detection method of high-temperature continuous casting blank
CN101694472A (en) * 2009-10-23 2010-04-14 郭震 Defect hole image recognition method
CN103344190A (en) * 2013-06-26 2013-10-09 科瑞自动化技术(深圳)有限公司 Method and system for measuring postures of elastic arm based on line scanning
CN103543161A (en) * 2013-10-16 2014-01-29 湖南镭目科技有限公司 On-line detection method of continuous casting billet surface quality
CN104251687A (en) * 2014-10-11 2014-12-31 盐城工学院 Part surface evenness detection method based on mirror image processing
CN104535577A (en) * 2014-12-05 2015-04-22 燕山大学 Workpiece quality loss detection equipment and workpiece quality loss detection method
CN105783782A (en) * 2016-05-12 2016-07-20 电子科技大学 Surface curvature abrupt change optical contour measurement method

Patent Citations (7)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101655464A (en) * 2009-09-16 2010-02-24 重庆大学 Surface defect form and depth on-line lossless detection method of high-temperature continuous casting blank
CN101694472A (en) * 2009-10-23 2010-04-14 郭震 Defect hole image recognition method
CN103344190A (en) * 2013-06-26 2013-10-09 科瑞自动化技术(深圳)有限公司 Method and system for measuring postures of elastic arm based on line scanning
CN103543161A (en) * 2013-10-16 2014-01-29 湖南镭目科技有限公司 On-line detection method of continuous casting billet surface quality
CN104251687A (en) * 2014-10-11 2014-12-31 盐城工学院 Part surface evenness detection method based on mirror image processing
CN104535577A (en) * 2014-12-05 2015-04-22 燕山大学 Workpiece quality loss detection equipment and workpiece quality loss detection method
CN105783782A (en) * 2016-05-12 2016-07-20 电子科技大学 Surface curvature abrupt change optical contour measurement method

Also Published As

Publication number Publication date
CN106645168A (en) 2017-05-10

Similar Documents

Publication Publication Date Title
CN103575227B (en) A kind of vision extensometer implementation method based on digital speckle
CN109696356B (en) Geosynthetic material tensile sample global strain field measuring device and method
CN102410811B (en) Method and system for measuring parameters of bent pipe
CN106643549B (en) A kind of ceramic tile dimension detection method based on machine vision
CN102519400B (en) Large slenderness ratio shaft part straightness error detection method based on machine vision
CN106645168B (en) A kind of detection method of crane boom cylinder concave-convex surface defect
CN110672020A (en) Stand tree height measuring method based on monocular vision
CN112629441B (en) 3D curved surface glass contour scanning detection method and system
JP2011053157A (en) Strain measuring method, strain measuring device, and program
CN109297436A (en) Binocular line laser measurement in space benchmark calibration method
CN109520436A (en) A kind of butterfly spring three-dimensional dimension automatic measurement system and its measurement method based on machine vision
CN102798349A (en) Three-dimensional surface extraction method based on equal-gray line search
CN113134683A (en) Laser marking method and device based on machine learning
CN110197485A (en) A kind of measuring system of ancient building colored drawing Liang Sicheng
CN111322950B (en) Method for positioning cylinder position by line structured light sensor and its use
CN107167088B (en) The measurement method and device of glass deformation amount
CN105783735B (en) A kind of real-time extensometer measuring method based on two-dimensional digital image correlative compensation algorithm
CN112665523B (en) Combined measurement method for complex profile
Cai et al. Methods for long-distance crack location and detection of concrete bridge structures
CN108917595A (en) Glass on-line measuring device based on machine vision
CN109990734A (en) Depth information camera module precision automatic checkout system and its accuracy checking method
CN112990190A (en) Method and device for identifying reading of pointer instrument
CN110146024A (en) Double precision displacement measurement method based on adaptable search
CN114266835A (en) Deformation monitoring control method and system for non-measuring camera
Ziqiang et al. Research of the algorithm calculating the length of bridge crack based on stereo vision

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant