CN104729426B - Angle steel automatic on-line detecting system and method based on machine vision - Google Patents
Angle steel automatic on-line detecting system and method based on machine vision Download PDFInfo
- Publication number
- CN104729426B CN104729426B CN201510157577.8A CN201510157577A CN104729426B CN 104729426 B CN104729426 B CN 104729426B CN 201510157577 A CN201510157577 A CN 201510157577A CN 104729426 B CN104729426 B CN 104729426B
- Authority
- CN
- China
- Prior art keywords
- angle steel
- image
- encoder
- area array
- array cameras
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Abstract
The invention discloses a kind of angle steel automatic on-line detecting system and method based on machine vision, including：Light-source system, lighting source must assure that the edge that punching can be irradiated to from all angles, it is impossible to lose marginal information；Mechanical driving device, ensure that angle steel can be according to predetermined track easy motion；Optical detection apparatus and upper-computer processing software, complete the collection and judgement of diagonal steel image, and output in real time and the comparing result of normal data.Above-mentioned various devices have good cooperation, and guarantee is not in missing inspection, the situation of false retrieval.The present invention also discloses the method using the system.
Description
Technical field
The present invention relates to a kind of angle steel automatic on-line detection technique, and in particular to a kind of angle steel based on machine vision is automatic
On-line detecting system and method.
Background technology
Angle steel eyelet work detection be detection project common in industrial production, mainly detect angle steel on punching circularity, spacing,
Whether punching satisfies the criteria away from parameters such as root linear distances.The country relies primarily on traditional artificial detection at present, and artificial detection is consolidated
The shortcomings of some costs are high, efficiency is low, subjectivity is strong turns into the unfavorable factor for restricting enterprise development, and based on machine vision
Angle steel automatic on-line detection technique gathers image by camera, image is handled with computer to obtain testing result, has
Have that precision is high, speed is fast, efficiency high, real-time are good and many advantages, such as contact with workpiece.
The content of the invention
The purpose of the present invention is to overcome above-mentioned the deficiencies in the prior art, and it is automatic to design a set of angle steel based on machine vision
On-line detecting system, the system have the accurate function of obtaining the parameters such as angle steel eyelet work physical dimension, the unqualified production of automatic discrimination
Product.Tested angle steel is sent on streamline by the system by feed mechanism, and area array cameras is installed on production by design mechanical device
Line both sides, when tested angle steel entering surface array camera acquisition range, it is responsible for the encoder hair of position detection and camera triggering sampling
Pulse signal notice area array cameras is sent to start to gather image, the image that the main program of industrial computer collects to area array cameras is carried out in fact
When analyze and process, actually detected value and theoretical standard value are compared judgement, meanwhile, testing result is real on industrial computer screen
When show, facilitate administrative staff to check.
To achieve the above object, the present invention uses following technical proposals：
A kind of angle steel automatic on-line detecting system based on machine vision, including：
Light-source system, described light-source system irradiates the edge of angle steel eyelet work to be detected from all angles, and ensures angle steel
Detection zone it is bright uniform and stable, without dark line；
Mechanical driving device, make angle steel to be detected in detection zone easy motion；
Optical detection apparatus, the angle steel for being pointed to detection zone ceaselessly carries out IMAQ, and the image of collection is sent
Give image identification system system；
Image identification system, the image of optical detection apparatus collection is handled and shown, the system detectio angle of departure
Contrasted after the series of parameters of steel with normal data, show testing result.
A coding for being responsible for transmitting a signal to image identification system is respectively equipped with the both ends of described mechanical driving device
Device, it is responsible for transmission signal and informs when area array cameras starts to gather, be not in missing inspection situation to ensure.
Described optical detection apparatus includes two area array cameras, and two area array cameras are respectively positioned at mechanical driving device
Both sides.
The lens plane of two described area array cameras parallel to angle steel two faces, lens plane parallel to angle steel two
Individual face, it can at utmost ensure that shooting image is undistorted.
Described image identification system is an industrial computer, described industrial computer respectively with two face battle array phases
Machine, two encoders are connected, and image capture module, image registration module, image co-registration module are provided with described industrial computer
And the processing after panoramic picture and display module are obtained, after system detectio goes out the series of parameters such as aperture, pitch-row, hole heart coordinate
Contrasted with normal data, show testing result.
A kind of angle steel automatic on-line detection method based on machine vision, comprises the following steps：
Step 1) angle steel conveys, and angle steel to be checked is sent into the decompressor of run-in index placement through automatic feed mechanism, through overshoot
Angle steel after pressure is shifted onto on the mechanical driving device of detecting system by feeding rod；
Step 2) image data acquirings, when angle steel is sent to designated area by mechanical driving device, encoder can be sent
Instruction notification image capturing system starts collecting work；At this moment area array cameras carries out IMAQ under the light filling of strip source；
The image that collection is completed is sent to industrial computer and analyzed and processed in real time；
The angle steel items actual parameter and canonical parameter that step 3) has detected on the screen of industrial computer, manage real-time display
Reason personnel carry out contrast to data and checked, if error in allowed band, continues to detect next angle steel, if error
Not in allowed band, then prompting operating personnel the angle steel can be marked in host computer.
2 encoders are added in angle steel course of conveying in the step 2), 2 encoders one in front and one in back install additional respectively
In the both ends of conveying device, when angle steel to be checked passes through first encoder, first encoder action, it counts triggering arteries and veins
Punching, area array cameras detect that the trigger pulse starts to gather image, and the first encoder can output signal always afterwards；And work as angle steel
Two encoders can be made while act by moving on, and any one pulse is fallen in now system mask, when two encoders all do not have
During signal output, it was demonstrated that this section of angle steel has detected completely.
There is situation about retreating when being punched out, the external force effect such as shearing to prevent angle steel, to the arteries and veins of encoder
Rush output to be added up to obtain count value, encoder often exports a direct impulse, and count value adds 1, and encoder often exports one
Individual reverse impulse, count value subtract 1.When encoder exports reverse impulse, countdown is only carried out to its count value but is not sent
Trigger pulse, trigger pulse only can be just re-emitted after count value is returned to original counting position again.
The purpose using strip source in the step 2) is exactly to meet the needs of area array cameras illumination and raising
Angle steel surface information shows power, even if angle steel surface characteristics is more apparent relative to ambient background.
What the area array cameras in the step 2) detected is the angle steel in motion, and the reflected light on angle steel surface will pass through camera lens
Entering area array cameras after aperture, lens aperture can continuously be adjusted into the luminous flux of camera aperture, after lighting source is selected,
Aperture by adjusting aperture obtains clear and distortionless image.
The adjacent two images of area array cameras continuous acquisition in the step 2) have overlapping region, can use image mosaic
Mode by several angle steel image mosaics with overlapping region into panoramic picture of the width with complete angle steel information.
The principle of the present invention is to improve angle steel surface characteristics by hardware environment such as reasonable selection area array cameras, lighting sources
Show power, based on image mosaic and rim detection, the image of collection is handled using suitable image processing method, from
And the series of features such as angle steel length, punching physical dimension on angle steel are identified, and contrasted with standard value and complete angle steel production
The evaluation and test of quality.
Beneficial effects of the present invention are as follows：
The angle steel automatic testing method that the present invention is carried uses to gather based on area array cameras knows method for distinguishing with being imaged, with reference to
Light, mechanical, electrical integrated technique.The present invention is directed to the tested angle steel of different size, is detected using imaging identification, and detect
System is directly embedded on whole piece Automatic control, completes the demarcation of angle steel items actual parameter in real time in angle steel production process
And contrasted with canonical parameter and judge whether tested angle steel qualified, the operational efficiency of production system can be improved, greatlys save manpower
Cost and time cost.
Brief description of the drawings
Fig. 1 is angle steel detecting system schematic diagram；
Fig. 2 is angle steel detecting system partial schematic diagram；
Fig. 3 is angle steel detecting system partial schematic plan view；
Fig. 4 is angle steel detecting system workflow diagram；
Fig. 5 is untreated angle steel material object original graph；
Fig. 6 is image after Threshold segmentation processing；
Fig. 7 is image after edge detection process.
Wherein 1. strip sources, 2. area array cameras, 3. encoders, 4. industrial computers, 5. color background plates, 6. measured angles
Steel, 7. guide rails.
Embodiment
The present invention is further described with reference to the accompanying drawings and examples.
Angle steel automatic on-line detecting system based on machine vision, including：
Light-source system.Lighting source has considerable influence to the IMAQ quality of area array cameras 2, designs and select light source
Purpose is exactly to show power to meet the needs of camera CCD illuminations and improve angle steel surface information, and to configure suitable light source be
Ensure the necessary condition of successful acquisition image.Lighting source must assure that the edge that punching can be irradiated to from all angles, no
Marginal information can be lost, and to ensure be examined region it is bright it is uniform and stable, without dark line.As shown in figure 1, four are configured altogether
Strip source 1, each two strip source 1 form one group, it is possible to achieve illuminate the specified shooting area on angle steel；The monochromatic back of the body simultaneously
Scape plate 5 makes the background of shooting area uniform, is not influenceed by extraneous scene.
Mechanical driving device.It is detected angle steel 6 to be positioned on the guide rail 7 of detection platform, mechanical driving device ensures angle steel 6
Can be according to predetermined track easy motion；Two encoders 3 are equipped with, two encoders 3 are one in front and one in back installed in camera 2 respectively
Both sides, when angle steel 6 to be checked is by first encoder, only this encoder 3 is acted, and trigger pulse is counted with the encoder 3,
Area array cameras 2 detects that the trigger pulse starts to gather image, and this encoder 3 understands output signal always afterwards；And when angle steel 6 after
Continuous advance can make two encoders 3 while act, and at this moment mask a pulse, afterwards only when the two encoders 3 all do not have
Having just proves that this section of angle steel 6 has detected completely during signal output.It is being punched out to prevent angle steel 6, the external force such as shearing
Occurs situation about retreating during effect, the pulse output to encoder is added up to obtain count value, and encoder often exports one
Direct impulse, count value add 1, and encoder often exports a reverse impulse, and count value subtracts 1.When encoder exports reverse impulse,
Countdown is only carried out to its count value but does not send trigger pulse, only after count value is returned to original counting position again
Trigger pulse can just be re-emitted.
Optical detection apparatus, including two area array cameras 2, two area array cameras 2 are located at mechanical driving device both sides respectively,
As shown in Fig. 2 the lens plane of area array cameras 2 can at utmost ensure that shooting image is not lost parallel to two faces of angle steel 6
Very.
Image identification system includes the processing after collection, image registration, image co-registration and the acquisition panoramic picture of image
And display.Image registration portion uses the method for registering images based on gray scale.Using present image as reference picture, adjacent is next
Width image is image subject to registration.Under the conditions of preferable strip source light filling, the half-tone information of adjacent two images has height
Correlation.A kind of similarity measurement is selected, according to the half-tone information of image, object function is constructed, on this basis to target
Function is iterated optimizing, and it is required registration parameter to obtain optimized parameter.To ensure the accuracy of image registration results, figure
As fusion part uses the weighted average fusion rule based on pixel.The intensity of illumination of adjacent two arguments steel image is consistent, can lead to
Cross and calculate the average value of two image overlapping region pixels to fill up splicing seam, algorithm speed is very fast.The phase of image registration portion
Like property metric sebection normalized mutual information, optimizing algorithm uses Powell optimizing algorithms, and the initial value of optimizing carrys out self-encoding encoder
Given range information.
First it is pre-processed after the panoramic picture of splicing one section of angle steel of acquisition is carried out.Pretreatment refers to threshold value
Segmentation.From the angle steel image gathered, as shown in figure 5, circular hole information to be detected on image and the gray scale difference of other parts
It is different bigger, can be by setting gray threshold to separate circular hole information to be detected.Assuming that A represents the angle steel figure of input
Picture, A (i, j) represent the gray value at picture position (i, j) place, are T according to the gray threshold that gradation of image average is setg, B expressions
Image after Threshold segmentation, B (i, j) represent Threshold segmentation after picture position (i, j) place gray value, then threshold process tool
Body method is：
Threshold process is carried out to Fig. 2 using formula (1) mode, result is as shown in Figure 6.
Rim detection is carried out using Canny operators after Threshold segmentation, i.e., edge inspection is carried out to the image after Threshold segmentation
Survey, obtain the profile information of circular hole to be detected.The edge point set of each circular hole can be obtained by contour images, according to it is each set come
Calculate the parameter of each circular hole.The result that rim detection is carried out to Fig. 6 is as shown in Figure 7.
Circular hole detection parameters mainly include the center of circle, circularity etc..Assuming that the edge point set of current circular hole is Q={ p1(x1,y1),
p2(x2,y2),…,pN(xN,yN)}；Wherein, N represents the total number of point centrostigma；p1(x1,y1)、p2(x2,y2)、…、pN(xN,
yN) represent to form set Q marginal point (parameter in bracket is its coordinate value).
The center of circle refers to the barycenter of circular hole.The center-of-mass coordinate acquiring method of circular hole is：
In formula, i represents the abscissa of marginal point, and j represents the ordinate of marginal point,Represent the horizontal seat of current circular hole barycenter
Mark,Represent the ordinate of current circular hole barycenter.
Circularity is represented with the longest distance of marginal point to barycenter with beeline ratio.Travel through Q and calculate each point to barycenter
Distance：
In formula, dkRepresent point (xk,yk) arrive barycenterDistance.Can so calculate arrived a little in Q barycenter away from
From composition distance set D={ d1,d2,…,dN}.Find the longest distance d in set Dmax=max (D) and beeline dmin=
min(D).The ratio of longest distance and beeline is circularity, is expressed as：dmax/dmin, the ratio illustrates current closer to 1
Circular hole gets over approximate test circle.
System detectio contrasts after going out the series of parameters such as aperture, pitch-row, hole heart coordinate with normal data, display detection knot
Fruit.
On-line monitoring method based on said system, comprises the following steps：
1) angle steel conveys, and angle steel to be checked is sent into the decompressor of run-in index placement through automatic feed mechanism, after punching press
Angle steel shifted onto by feeding rod on the guide rail of detecting system；
2) image data acquirings, when angle steel is sent to designated area by guide rail, encoder can send instruction notification image
Acquisition system starts collecting work, and at this moment area array cameras carries out IMAQ under the light filling of strip source, gathers the figure of completion
Analyzed and processed as being sent to industrial computer in real time, every actual parameter and the canonical parameter of the angle steel detected will be real
When be shown on the screen of industrial computer, facilitate administrative staff contrast check, as angle steel every actual parameter beyond error permission
Scope, then host computer can be marked and prompt operating personnel.
Need to install 2 encoders additional in angle steel course of conveying in the step 2), 2 encoders one in front and one in back add respectively
Both sides loaded on camera, when angle steel to be checked passes through first encoder, only this encoder acts, and it sends trigger pulse,
Area array cameras detects that the trigger pulse starts to gather image, and this encoder can output signal always afterwards；And when angle steel continues
Advance can make two encoders while act, the trigger pulse of an encoder is fallen at this moment system mask, afterwards only work as this two
Individual encoder does not all have just to prove that this section of angle steel has detected completely during signal output.For prevent angle steel be punched out,
There is situation about retreating during the effect of the external force such as shearing, the pulse output to encoder is added up to obtain count value, encoder
A direct impulse is often exported, count value adds 1, and encoder often exports a reverse impulse, and count value subtracts 1.When encoder exports
During reverse impulse, countdown is only carried out to its count value but does not send trigger pulse, only when count value is returned to original again
Just re-emit trigger pulse after counting position.
The purpose using strip source in step 2) is exactly to meet the needs of area array cameras illumination and improve angle steel
Surface information shows power, even if angle steel surface characteristics is more apparent relative to ambient background.
What the area array cameras in step 2) detected is the angle steel in motion, and the reflected light on angle steel surface will pass through lens aperture
Enter area array cameras afterwards, lens aperture can continuously be adjusted into the luminous flux of camera aperture, after lighting source is selected, pass through
The aperture of adjustment aperture obtains clear and distortionless image.
The adjacent two images of area array cameras continuous acquisition in step 2) have overlapping region, can use the side of image mosaic
Formula is by several angle steel image mosaics with overlapping region into panoramic picture of the width with complete angle steel information.
Although above-mentioned the embodiment of the present invention is described with reference to accompanying drawing, model not is protected to the present invention
The limitation enclosed, one of ordinary skill in the art should be understood that on the basis of technical scheme those skilled in the art are not
Need to pay various modifications or deformation that creative work can make still within protection scope of the present invention.
Although above-mentioned the embodiment of the present invention is described with reference to accompanying drawing, model not is protected to the present invention
The limitation enclosed, one of ordinary skill in the art should be understood that on the basis of technical scheme those skilled in the art are not
Need to pay various modifications or deformation that creative work can make still within protection scope of the present invention.
Claims (5)
- A kind of 1. angle steel automatic on-line detecting system based on machine vision, it is characterised in that including：Light-source system, described light-source system irradiate the edge of angle steel eyelet work to be detected from all angles, and ensure angle steel detection Region it is bright uniform and stable, without dark line；Mechanical driving device, make angle steel to be detected in detection zone easy motion；Optical detection apparatus, the angle steel for being pointed to detection zone ceaselessly carries out IMAQ, and the image of collection is sent into figure As identifying system；Image identification system, handled and shown that the system detectio goes out angle steel to the image of optical detection apparatus collection Contrasted after series of parameters with normal data, show testing result；An encoder for being responsible for transmitting a signal to image identification system is respectively equipped with the both ends of described mechanical driving device；Described optical detection apparatus includes two area array cameras, and two area array cameras are located at the two of mechanical driving device respectively Side；The light-source system includes four strip sources, and each two strip source forms one group, it is possible to achieve illuminates on angle steel Specify shooting area;Described image identification system is an industrial computer, described industrial computer respectively with two area array cameras, two Individual encoder is connected；Image capture module, image registration module, image co-registration module are installed in described industrial computer and obtained Obtain the processing after panoramic picture and display module.
- 2. the angle steel automatic on-line detecting system based on machine vision as claimed in claim 1, it is characterised in that described two Two faces of the lens plane of individual area array cameras parallel to angle steel.
- 3. a kind of angle steel automatic on-line detection method based on machine vision, it is characterised in that comprise the following steps：Step 1) angle steel conveys, and angle steel to be checked is sent into the decompressor of run-in index placement through automatic feed mechanism, by punching press Angle steel afterwards is shifted onto on the mechanical driving device of detecting system by feeding rod；Step 2) image data acquirings, when angle steel is sent to designated area by mechanical driving device, encoder can send finger Order notice image capturing system starts collecting work；At this moment area array cameras carries out IMAQ under the light filling of strip source；Adopt The image that collection is completed is sent to industrial computer and analyzed and processed in real time；Step 3）The angle steel items actual parameter that has detected and canonical parameter by real-time display on the screen of industrial computer, custodian Member carries out contrast to data and checked, if error in allowed band, continues to detect next angle steel, if error does not exist In allowed band, then prompting operating personnel the angle steel can be marked in host computer；2 encoders are added in angle steel course of conveying in the step 2), 2 encoders are one in front and one in back installed in respectively The both ends of conveying device, when angle steel to be checked passes through first encoder, first encoder action, it counts trigger pulse, Area array cameras detects that the trigger pulse starts to gather image, and the first encoder can output signal always afterwards；And when angle steel after Continuous advance can make two encoders while act, and any one pulse is fallen in now system mask, when two encoders are not all believed Number output when, it was demonstrated that this section of angle steel has detected completely；When the adjacent two images of area array cameras continuous acquisition in the step 2) have overlapping region, using the side of image mosaic Several are had the angle steel image mosaic of overlapping region into the complete of the complete angle steel information of storage one of a width higher resolution by formula Scape image；Image registration module uses the method for registering images based on gray scale, using present image as reference picture, adjacent next width Image is image subject to registration, selects a kind of similarity measurement, according to the half-tone information of image, constructs object function, is used Powell optimizing algorithms are iterated optimizing to object function, and it is required registration parameter to obtain optimized parameter；Image co-registration Module uses the weighted average fusion rule based on pixel, and the intensity of illumination of adjacent two arguments steel image is consistent, by calculating two The average value of image overlapping region pixel fills up splicing seam, first after splicing is carried out and obtain the panoramic picture of one section of angle steel Row threshold division is entered to it；Rim detection is carried out using Canny operators after Threshold segmentation, i.e., the image after Threshold segmentation entered Row rim detection, the profile information of circular hole to be detected is obtained, the edge point set of each circular hole is obtained by contour images, according to It is each to gather to calculate the parameter of each circular hole.
- 4. the angle steel automatic on-line detection method based on machine vision as claimed in claim 3, it is characterised in that be anti-angle till There is situation about retreating in steel, and the pulse output to encoder is added up to obtain count value, and encoder often exports a forward direction Pulse, count value add 1, and encoder often exports a reverse impulse, and count value subtracts 1；It is only right when encoder exports reverse impulse Its count value carries out countdown but does not send trigger pulse, only just can after count value is returned to original counting position again Re-emit trigger pulse.
- 5. the angle steel automatic on-line detection method based on machine vision as claimed in claim 3, it is characterised in that described face Array camera detection is angle steel in motion, the reflected light on angle steel surface will by the way that area array cameras could be entered after lens aperture, Lens aperture can continuously be adjusted into the luminous flux of camera aperture, after lighting source is selected, by the aperture for adjusting aperture Obtain clear and distortionless image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510157577.8A CN104729426B (en) | 2015-04-03 | 2015-04-03 | Angle steel automatic on-line detecting system and method based on machine vision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510157577.8A CN104729426B (en) | 2015-04-03 | 2015-04-03 | Angle steel automatic on-line detecting system and method based on machine vision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104729426A CN104729426A (en) | 2015-06-24 |
| CN104729426B true CN104729426B (en) | 2018-01-12 |
Family
ID=53453552
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510157577.8A Active CN104729426B (en) | 2015-04-03 | 2015-04-03 | Angle steel automatic on-line detecting system and method based on machine vision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104729426B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110132166B (en) * | 2019-05-05 | 2021-07-23 | 广州佳帆计算机有限公司 | Product image detection method capable of automatically distributing light and comparison device |
Families Citing this family (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105547167B (en) * | 2016-03-11 | 2018-07-03 | 中冶赛迪电气技术有限公司 | Strip width measuring system and method based on machine vision |
| CN107421438B (en) * | 2017-01-22 | 2020-11-06 | 广东新德重智能装备有限公司 | Machine vision-based film size detection control system and method |
| CN109579715A (en) * | 2017-09-28 | 2019-04-05 | 宝山钢铁股份有限公司 | A kind of digitlization On-line Measuring Method improving hole expansibility measurement accuracy |
| CN108759727B (en) * | 2018-05-09 | 2020-06-26 | 上海大学 | Detection device and method for pitted surface and sticky skin on surface of prefabricated pipe piece |
| CN108627111A (en) * | 2018-06-06 | 2018-10-09 | 南京大吉铁塔制造有限公司 | Drilling hole on-line measuring device and its online test method |
| CN110614282A (en) * | 2018-06-19 | 2019-12-27 | 宝山钢铁股份有限公司 | Automatic detection device for surface cleaning quality defects of hot-rolled plate blanks |
| CN109685777B (en) * | 2018-12-11 | 2021-06-08 | 北京理工大学 | Image processing method and device |
| CN109709102A (en) * | 2019-01-17 | 2019-05-03 | 广州超音速自动化科技股份有限公司 | Die-cutting machine lithium battery pole slice physical imperfection detection system, method and device |
| CN110260790A (en) * | 2019-07-20 | 2019-09-20 | 龚烨飞 | A kind of detection device and its detection method of the punching angle steel based on 3D vision |
| CN112461143A (en) * | 2020-10-13 | 2021-03-09 | 山东法因数控机械设备有限公司 | Angle steel detection device and method |
| CN113340196A (en) * | 2021-05-31 | 2021-09-03 | 山东电工电气集团有限公司 | Intelligent power angle steel detection system and method based on image recognition |
| CN113977277B (en) * | 2021-11-06 | 2023-03-03 | 重庆瑜煌电力设备制造有限公司 | Intelligent power transmission tower production line and production method based on industrial internet |
| CN114322774A (en) * | 2022-01-05 | 2022-04-12 | 河北省送变电有限公司 | Quality inspection device for angle steel production line and positioning detection method thereof |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102393181A (en) * | 2011-09-22 | 2012-03-28 | 南京信息工程大学 | Automatic online detection method and device of angle steel geometric parameters |
| CN103471512A (en) * | 2013-09-06 | 2013-12-25 | 中国建材国际工程集团有限公司 | Glass plate width detection system based on machine vision |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2008185491A (en) * | 2007-01-31 | 2008-08-14 | Jfe Steel Kk | Angle steel size calculation method and device |
| CN102313747B (en) * | 2011-07-27 | 2013-06-05 | 国家林业局北京林业机械研究所 | Image acquisition system for sawn timber surface defects and detection method |
-
2015
- 2015-04-03 CN CN201510157577.8A patent/CN104729426B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102393181A (en) * | 2011-09-22 | 2012-03-28 | 南京信息工程大学 | Automatic online detection method and device of angle steel geometric parameters |
| CN103471512A (en) * | 2013-09-06 | 2013-12-25 | 中国建材国际工程集团有限公司 | Glass plate width detection system based on machine vision |
Non-Patent Citations (2)
| Title |
|---|
| PCB自动光学检测的图像检测与处理关键技术研究;乔闹生;《中国博士学位论文全文数据库 信息科技辑》;20110715(第7期);I138-39 * |
| 金属工件表面瑕疵检测技术的研究与开发;陈文达;《中国优秀硕士学位论文全文数据库 信息科技辑》;20140215(第2期);I140-365 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110132166B (en) * | 2019-05-05 | 2021-07-23 | 广州佳帆计算机有限公司 | Product image detection method capable of automatically distributing light and comparison device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104729426A (en) | 2015-06-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104729426B (en) | Angle steel automatic on-line detecting system and method based on machine vision | |
| CN110596134B (en) | Sheet glass edge flaw detection method based on image acquisition | |
| Reynolds et al. | Capturing time-of-flight data with confidence | |
| CA2615117C (en) | Apparatus and methods for inspecting a composite structure for inconsistencies | |
| US9074868B2 (en) | Automated borescope measurement tip accuracy test | |
| GB2511612A (en) | Apparatus and method for detecting vehicle weave | |
| US20070286471A1 (en) | Auto Distinction System And Auto Distinction Method | |
| CN106706653A (en) | High-speed wide board detection method | |
| CN101819024B (en) | Machine vision-based two-dimensional displacement detection method | |
| CN103454285A (en) | Transmission chain quality detection system based on machine vision | |
| CN103827626B (en) | Three-dimensional measuring apparatus | |
| CN102175692A (en) | System and method for detecting defects of fabric gray cloth quickly | |
| CN115334227B (en) | Gear image acquisition device and method, gear image acquisition method and electronic equipment | |
| CN215066222U (en) | Transmission belt system | |
| CN108195847A (en) | A kind of relief pattern Online Video detection device and its detection method | |
| CN105391998A (en) | Automatic detection method and apparatus for resolution of low-light night vision device | |
| CN214097211U (en) | Transparent plate glass's defect detecting device | |
| CN105787429A (en) | Method and apparatus for inspecting an object employing machine vision | |
| KR20190011200A (en) | System for defect inspection and method for defect inspection | |
| CN113189005A (en) | Portable surface defect integrated detection device and surface defect automatic detection method | |
| CN114324382A (en) | Panel terminal cleanliness detection method and panel terminal cleanliness detection device | |
| CN104586404A (en) | Method and system for identifying posture of fitness and health monitoring | |
| CN110672209A (en) | Online detection method for warp knitting cloth color difference | |
| CN115876695A (en) | Sole rubber coating quality check out test set | |
| KR20190011199A (en) | System for defect inspection and method for defect inspection |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |