CN108458668A - Slab edge and Head and Tail Shape automatic checkout system based on binocular vision and method - Google Patents
Slab edge and Head and Tail Shape automatic checkout system based on binocular vision and method Download PDFInfo
- Publication number
- CN108458668A CN108458668A CN201810009526.4A CN201810009526A CN108458668A CN 108458668 A CN108458668 A CN 108458668A CN 201810009526 A CN201810009526 A CN 201810009526A CN 108458668 A CN108458668 A CN 108458668A
- Authority
- CN
- China
- Prior art keywords
- image
- slab
- module
- slab edge
- edge
- 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.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01B—MEASURING LENGTH, THICKNESS OR SIMILAR LINEAR DIMENSIONS; MEASURING ANGLES; MEASURING AREAS; MEASURING IRREGULARITIES OF SURFACES OR CONTOURS
- G01B11/00—Measuring arrangements characterised by the use of optical techniques
- G01B11/24—Measuring arrangements characterised by the use of optical techniques for measuring contours or curvatures
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Processing (AREA)
- Length Measuring Devices By Optical Means (AREA)
- Image Analysis (AREA)
Abstract
The present invention provides a kind of slab edge and Head and Tail Shape automatic checkout system based on binocular vision comprising image capture module, image processing module, system communication module, software interactive interface and Machine Vision Detection algoritic module, wherein：Image Acquisition of the image capture module for slab side and end to end；Image processing module is used to carry out image preprocessing to the slab edge and tail portion real time video image of acquisition；System communication module is used to collect the collected slab edge of industrial camera and tail portion real time video image and be sent to client, and sends acquisition control signal to industrial camera and control the output of Machine Vision Detection algoritic module recognition result signal；Machine Vision Detection algoritic module includes computing module and judgment module.Present device is simple, flexible for installation, does not influence original production line arrangement and operation, and equipment operational reliability is high and easy to operate, can avoid worker and works in the presence of a harsh environment, reduces human cost.
Description
Technical field
The invention patent relates to slab hot rolling production slab edge and Head and Tail Shape detection field, more particularly to one kind to be based on
The slab edge and Head and Tail Shape automatic checkout system and method for binocular vision.
Background technology
Cast sturcture is changed by aluminium alloy thick plate hot rolling slab because heavy reduction rolling eliminates cast sturcture's defect
Deformed microstructure, continue product has prodigious advantage in terms of deep drawability, surface quality and precision controlling, can extensive use
In the national economy key areas such as aerospace, automobile, machine-building, ship and chemical industry, nearly its production process of more than ten years from
Dynamicization degree has to develop on a large scale very much, but intelligence also realizes far away that most key technique still relies on artificial experience.
The more crucial problem of one of which is that aluminium alloy thick plate hot rolling slab original depth is big (500-800mm), rolling
Drafts can not penetrate into center portion, and accumulated deformation easily occurs Double drum type defect in edge and end to end, at present industry actual production
It is to control blank shape by using input edger roll rolling and the mode that cuts off end to end in journey, but due to lacking effective inspection
Survey means, edger roll timing input in production process, rolling drafts, the control such as resection is mainly by hand inspection or production end to end
Experience realizes, not only operation bad environments, can also influence of rolled regulation formulation, cause the huge waste of slab,
Greatly reduce lumber recovery.
Machine vision technique developed in recent years has the advantages that reliability is high, reaction is fast, production cost is low etc., can
It really realizes the intelligence of production, therefore, in face of the rising of human cost and the increase of competitive pressure, how to be regarded by machine
Feel technology, improving its production efficiency, product lumber recovery and product quality becomes key technical problem urgently to be resolved hurrily.
Invention content
The purpose of the present invention is being directed in current aluminium alloy plate hot rolling roughing production to lack blank shape detection device, cause
Edger roll input cuts off the problem of opportunity and numerical value can not accurately control end to end, provides a kind of detection simple in structure, real-time and accurate
Property high binocular vision slab edge and Head and Tail Shape detecting system and method.
The purpose of the present invention is achieved through the following technical solutions：
The present invention provides a kind of slab edge and Head and Tail Shape automatic checkout system based on binocular vision comprising image
Acquisition module, image processing module, system communication module, software interactive interface and Machine Vision Detection algoritic module, wherein：
Image Acquisition of the described image acquisition module for slab side and end to end, described image acquisition module includes multiple
Industrial camera and locating support, the locating support are fixed on milling train outlet roller-way both sides, and the industrial camera is mounted on institute
It states for obtaining production line slab edge and tail portion real time video image on locating support, each two industrial camera forms one pair
Mesh system；
Described image processing module is used to carry out image to the slab edge and tail portion real time video image of acquisition pre-
Processing, image preprocessing includes the foreground extraction and image enhancement of slab area-of-interest, obtains slab edge and tail portion image；
The system communication module is for collecting the collected slab edge of industrial camera and tail portion real time video image simultaneously
It is sent to client, and sends acquisition control signal to industrial camera and Machine Vision Detection algoritic module recognition result is believed
Number output controlled；
The software interactive interface is for showing that slab edge and tail portion real time video image and Machine Vision Detection are calculated
The operation result of method module, and realize the operating parameter control of Machine Vision Detection algoritic module；
The Machine Vision Detection algoritic module includes computing module and judgment module,
The computing module is to treated slab edge and image information is analyzed end to end, obtains detection slab side
And form parameter end to end,
Form parameter of the judgment module by detection slab side and end to end is compared with default passage deformation parameter,
To judge whether to need edger roll input and end to end excision and rolling drafts and cut off numerical quantity end to end.
Preferably, the industrial camera is CCD camera.
Preferably, the edge detection parallel installation of two CCD cameras used, the CCD camera is for acquiring on slab
Image；The camera detected end to end is mounted on slab position end to end, acquires image end to end, can be in order to acquire good image
By camera end to end on slideway, itself and aluminium alloy thick plate is allowed to have identical speed to move.
Preferably, further include database generation module, the database generation module is used for according to acquisition image and processing
As a result it establishes technological procedure database, records the change procedure of slab edge in production process and shape end to end.
The present invention also provides a kind of slab edge and Head and Tail Shape automated detection method based on machine vision, including with
Lower step：
S1, arrangement detection device, install CCD camera；
S2, image/video acquisition, aluminum alloy slab edge and image/video information collection end to end are carried out by CCD camera；
S3, image preprocessing, image preprocessing include the foreground extraction and image enhancement of slab area-of-interest；
S4, calculating form parameter obtain CCD camera coordinate, image by the calibration of CCD camera parameter calibration and system
Then edge and its end to end shape is calculated under world coordinate system by Binocular Vision Principle in the relationship of coordinate and world coordinate system
Shape profile；
S5, default road subparameter compare and judge, by being fitted obtained slab edge and its Head and Tail Shape profile and pre-
If passage deformation parameter is compared, input edger roll carries out billowing side and crop end after reaching default passage deformation parameter.
Preferably, described in arrangement detection device is as follows in S1：
S11, first with binocular CCD camera monitoring slab then figure is passed through by foreground extraction slab area-of-interest
Image intensifying protrudes the edge and head-tail feature of slab；
S12, CCD camera calibration, are obtained by calibration between CCD camera coordinate system, image coordinate system and world coordinate system
Relationship；
S13, edge deformation parameter is detected using binocular CCD camera.
Preferably, edge and its end to end crucial point coordinates are calculated under world coordinate system by Binocular Vision Principle in S4
Specifically comprise the following steps：
S41, imaging plane is set at the optical center front focal length f of camera lens, left and right imaging surface coordinate origin is in CCD camera light
The intersection point O of axis and plane1And O2Locate, certain point P corresponding coordinates in left imaging plane and right imaging plane are P in spacel(ul,
vl) and Pr(ur,vr), it is now assumed that the image of CCD camera is in same plane, i.e. vl=vr, obtained by geometrical relationship：
(x in above formulac,yc,zc) it is coordinates of the point P in left CCD camera coordinate system, b is baseline distance, and f is two CCD cameras
Focal length, (ul,vl) and (ur,vr) it is coordinates of the point P in two images of left and right；
S42, the alternate position spike that parallax is certain point respective point in two images is defined：
It is possible thereby to calculate coordinates of certain point P in left CCD camera coordinate system in space and be：
S43, world coordinate system is enabled to be overlapped with left CCD camera coordinate system, obtained (xc,yc,zc) it is under world coordinate system
P point coordinates.
Preferably, further include S6, generate technological procedure database, the technological procedure database root is according to acquisition image and place
It manages result to establish, records the change procedure of slab edge and shape end to end in production process.
Preferably, passage deformation parameter includes at least side and the maximum length being recessed end to end in the operation of rolling.
Compared to existing detection method, the beneficial effects of the invention are as follows：
1. present device is simple, flexible for installation, original production line arrangement and operation are not influenced, and equipment operational reliability is high
And it is easy to operate, it can avoid worker and work in the presence of a harsh environment, reduce human cost.
2. the present invention uses machine vision technique, online acquisition slab edge and end to end image, Real-time Feedback edge and head
The deformed contour shape of tail is realized rolling drafts and is cut off end to end to the timing input for controlling edger roll and cutting off end to end
Amount accurately controls, and achievees the purpose that the lumber recovery for improving aluminum alloy slab and product quality, increases production economy benefit.
3. the present invention can establish technological procedure database according to acquisition image and handling result, slab in production process is recorded
Edge and Head and Tail Shape change procedure can be used as the reference of Technician Training and technological procedure optimization.
Description of the drawings
Fig. 1 is the structural schematic block diagram of the present invention；
Fig. 2 is the image capture module structural schematic diagram of the present invention；
Fig. 3 is the detection principle diagram of the binocular vision of the present invention；
Fig. 4 is the three dimensional structure diagram of the present invention；
Fig. 5 is the workflow schematic diagram of the present invention；
Fig. 6 is the Threshold segmentation image in the embodiment of the present invention 1；
Fig. 7 is the part of the zoning connection in the embodiment of the present invention 1；
Fig. 8 is the aluminium alloy contour feature that the extraction in the embodiment of the present invention 1 obtains；
Fig. 9 is the figure after the convex closure operation in the embodiment of the present invention 1；
Figure 10 is " twin drum " notch profile extracting method in the embodiment of the present invention 1；
Figure 11 is that the practical rolled slab of factory in the embodiment of the present invention 2 deforms schematic diagram；
Figure 12 is the image schematic diagram of the left camera acquisition in the embodiment of the present invention 2；
Figure 13 is the image schematic diagram of the right camera acquisition in the embodiment of the present invention 2；
Figure 14 is the disparity map schematic diagram in the embodiment of the present invention 2；
Figure 15 is the matching score value schematic diagram in the embodiment of the present invention 2.
Specific implementation mode
Below with reference to the attached drawing exemplary embodiment that the present invention will be described in detail, feature and aspect.It is identical attached in attached drawing
Icon note indicates functionally the same or similar element.Although the various aspects of embodiment are shown in the accompanying drawings, unless special
It does not point out, it is not necessary to attached drawing drawn to scale.
Patent specific implementation mode of the present invention is described further below in conjunction with the accompanying drawings：
The present invention provides a kind of slab edge and Head and Tail Shape automatic checkout system based on binocular vision, as shown in Figure 1, Figure 2
And shown in Fig. 4 comprising image capture module 10, image processing module 11, system communication module 12, software interactive interface 13 with
And Machine Vision Detection algoritic module 14, wherein：
Image Acquisition of the image capture module 10 for slab side and end to end, image capture module 10 include multiple industry
Camera and locating support 6, locating support 6 are fixed on milling train outlet roller-way both sides, and industrial camera is mounted on locating support 6 and uses
In obtaining production line slab edge and tail portion real time video image, each two industrial camera forms a biocular systems.
Image processing module 11 is used to carry out image to the slab edge and tail portion real time video image of acquisition to locate in advance
Reason, image preprocessing includes the foreground extraction and image enhancement of slab area-of-interest, obtains slab edge and tail portion image.
System communication module 12 is used to collect the collected slab edge of industrial camera and tail portion real time video image is concurrent
It send to client 15, and sends acquisition control signal to industrial camera and Machine Vision Detection algoritic module recognition result is believed
Number output controlled.
Software interactive interface 13 is for showing slab edge and tail portion image and algorithm operation result and realizing algorithm fortune
Row state modulator.
Machine Vision Detection algoritic module 14 for analyzing slab edge and tail portion image, calculate by Machine Vision Detection
Method module 14 includes computing module 141 and judgment module 142.
Computing module 141 using collected slab edge and image information analysis end to end, obtain detection slab side and
Form parameter end to end.
Result of calculation is compared judgment module 142 with default passage deformation parameter, to judge whether to need edger roll
Input and end to end excision and rolling drafts and numerical quantity is cut off end to end.
Passage deformation parameter is exactly side and the maximum critical length " being recessed " end to end, also other ginsengs in the operation of rolling
Number, but length is most apparent, and other parameters can be used as auxiliary, for example, in the operation of rolling " recess " area gap width.It is false
If " recess " maximum critical length is set as 200mm, then think it for the follow-up of entire slab when physical length is more than 200mm
Rolling lumber recovery has an impact, so rolling and crop end is needed to operate.Briefly passage deformation parameter is exactly according to practical experience
Artificial one value of setting, rolling is sent out when reaching this value in the operation of rolling and crop end judges.
Preferably, further include database generation module, the database generation module is used for according to acquisition image and processing
As a result it establishes technological procedure database, records the change procedure of slab edge in production process and shape end to end.
The present invention also provides a kind of slab edge and Head and Tail Shape automated detection method based on machine vision, including with
Lower step：
S1, arrangement detection device, install CCD camera；
S2, image/video acquisition, aluminum alloy slab edge and image/video information collection end to end are carried out by CCD camera；
S3, image preprocessing, image preprocessing include the foreground extraction and image enhancement of slab area-of-interest；
S4, calculating form parameter obtain CCD camera coordinate, image by the calibration of CCD camera parameter calibration and system
Then the relationship of coordinate and world coordinate system is calculated edge under world coordinate system by Binocular Vision Principle and its closes end to end
Key point coordinates obtains slab edge and its Head and Tail Shape profile by fitting；
S5, default passage deformation parameter compare and judge, by being fitted obtained slab edge and its Head and Tail Shape profile
It is compared with default passage deformation parameter, input edger roll carries out rolling and crop end after reaching default passage deformation parameter.
S6, technological procedure database is generated, the technological procedure database root is established according to acquisition image and handling result, note
Record slab edge and Head and Tail Shape change procedure in production process.
The each passage of the operation of rolling has different deformation parameters, and database can record these deformation parameters,
For use in subsequent analysis.For example, can by each passage edge and end to end " recess " deformation length and profile record,
Analysis and self study are carried out using digital image processing methods such as characteristic matchings, it is final to realize slab edge and head in the operation of rolling
The online real-time prediction of tail " recess " contour feature, optimize technique.
Each modular construction connection of device is carried out according to 2 schematic diagram of attached drawing, attached drawing 2 and Fig. 4 include aluminium alloy to be detected
Slab 2, left CCD camera 3, right CCD camera 5 and locating support 6.
Slab edge and Head and Tail Shape automated detection system operating process based on binocular machine vision are as follows：
(1) device arrangement is as shown in Figure 2 and Figure 4, aluminum alloy slab is monitored first with binocular CCD camera, by preceding
Scape extracts area-of-interest (aluminum alloy slab of movement), and the edge feature of aluminum alloy slab is then protruded by image enhancement,
Facilitate late detection.
(2) CCD camera is demarcated.It is obtained between CCD camera coordinate system, image coordinate system and world coordinate system by calibration
Relationship.
(4) disparity map of image is obtained using parallel binocular vision imaging principle, aluminium alloy edge is calculated using disparity map
Be recessed distance.
(5) the concave profile length of the edge recess length and the setting of default passage that are calculated is compared, and calculating is worked as
When obtained length reaches presetting length, input rolling and crop end are carried out.
Attached drawing 3 is the parallel visual imaging theory figure of binocular.In fact CCD camera imaging plane is after the optical center of camera lens,
In order to facilitate calculating, imaging plane is set in before the optical center of camera lens at f (focal length).Left and right imaging surface coordinate origin is in CCD phases
The intersection point O of machine optical axis and plane1And O2Place.Certain point P corresponding coordinates in left imaging plane and right imaging plane are P in spacel
(ul,vl) and Pr(ur,vr).If two CCD camera inner parameters are identical, and installation site in same plane, then two imagings are flat
Face is in same plane.It is now assumed that the image of CCD camera is in same plane, i.e. vl=vr, obtained by geometrical relationship：
(x in above formulac,yc,zc) it is coordinates of the point P in left CCD camera coordinate system, b is baseline distance, and f is two CCD cameras
Focal length, (ul,vl) and (ur,vr) it is coordinates of the point P in two images of left and right.
Parallax is defined as the alternate position spike of certain point respective point in two images：
It is possible thereby to calculate coordinates of certain point P in left CCD camera coordinate system in space and be：
World coordinate system is enabled to be overlapped with left CCD camera coordinate system, obtained (xc,yc,zc) it is P points under world coordinate system
Coordinate.Under the premise of two CCD camera internal and external parameters are consistent, to any point in Mr. Yu's platform CCD camera image plane, as long as
Its Corresponding matching point is found in another CCD camera plane, so that it may to calculate the three-dimensional coordinate of the point.
Embodiment one：The measurement of aluminum alloy slab end to end.
(1), area-of-interest is arranged.
ROI is the abbreviation of RegionOfInterest, as area-of-interest.For needing the image of extraction feature, I
Area-of-interest be aluminium alloy plate, others such as factory's background, roll, roller-way we be not relevant for, so setting
Area-of-interest aluminium alloy plate need to only be included.It should be noted that the image of collection in worksite is coloured image, the areas ROI
Coloured image is needed to be converted into gray-scale map before the setting of domain.
(2) carrying out image threshold segmentation
The basic thought of Threshold segmentation is：For giving gray level image f (x, y), for giving tonal range [Z1,Z2], t
∈[Z1,Z2], if：
Then claim ft(x, y) is image f (x, y) using t as the bianry image of thresholding.The threshold value thresholding taken herein is 97, threshold
Image after value segmentation is illustrated in fig. 6 shown below.
(3) the contour feature extraction of aluminium alloy thick plate
After Threshold segmentation, the range to link together after threshold value is calculated, the results are shown in Figure 7, and different ranges is different
Color indicate, then selection with target signature region.The target signature of this paper is region area, be will become apparent from by Fig. 7
The area of the aluminium alloy thick plate profile extracted is needed to be much larger than the area in other regions, so setting target signature is more than for area
100000 pixels (concrete numerical value is adjusted according to program), the contour feature of the aluminium alloy extracted are as shown in Figure 8.
(4), " twin drum " measurement of length
After feature extraction, it is the wheel of the first aluminium alloy extraction then to need the length for measuring " twin drum ", concrete thought
Exterior feature carries out convex closure operation, and the contour feature of obtained figure and extraction asks poor, obtains the notch geometry of " twin drum ", then seek notch
Minimum enclosed rectangle, the width of minimum enclosed rectangle is the length of " twin drum ".
(4.1) convex closure operation
Convex closure is the basic structure of computer geometry, is widely applied in many graph image related fields.One
Convex polygon is exactly the polygon of no any recess, is exactly the part filling graph recess after convex closure operation.Convex closure is transported
The figure obtained after calculation is as shown in Figure 9.
3.2 " twin drum " notch profiles are extracted and are measured
The contour feature of figure and extraction that convex closure obtains carries out seeking difference operation, as shown in Figure 10, obtains " twin drum " notch
Profile.
The minimum enclosed rectangle of obtained notch profile, width are the length of " twin drum ", and length value is 174.065 pictures
Element.The actual distance that " twin drum " can be measured by camera calibration is 200mm.
Embodiment two：The measurement of aluminum alloy slab edge.
Aluminium alloy thick plate edge deformation is as shown in figure 11 during practical rolling, is simulated using the intermediate groove of aluminium section bar
The deformation of edge in the operation of rolling.
Figure 12 and Figure 13 is the image acquired respectively with binocular camera, and Figure 14 is the disparity map generated, and Figure 15 is matching point
Value, the software used is halocn13.The depth of aluminium section bar intermediate groove can be calculated by the gray value of obtained disparity map,
The depth represents aluminum alloy slab hot rolling edge deformation depth, when the depth reaches setting value, just puts into edger roll rolling.
Finally it should be noted that：Above-described embodiments are merely to illustrate the technical scheme, rather than to it
Limitation；Although the present invention is described in detail referring to the foregoing embodiments, it will be understood by those of ordinary skill in the art that：
It can still modify to the technical solution recorded in previous embodiment, or to which part or all technical features into
Row equivalent replacement；And these modifications or substitutions, it does not separate the essence of the corresponding technical solution various embodiments of the present invention technical side
The range of case.
Claims (9)
1. a kind of slab edge and Head and Tail Shape automatic checkout system based on binocular vision, it is characterised in that：It includes image
Acquisition module, image processing module, system communication module, software interactive interface and Machine Vision Detection algoritic module, wherein：
Image Acquisition of the described image acquisition module for slab side and end to end, described image acquisition module includes multiple industry
Camera and locating support, the locating support are fixed on milling train outlet roller-way both sides, and it is described fixed that the industrial camera is mounted on
For obtaining production line slab edge and tail portion real time video image on the holder of position, each two industrial camera forms a binocular system
System；
Described image processing module is used to carry out image preprocessing to the slab edge and tail portion real time video image of acquisition,
Image preprocessing includes the foreground extraction and image enhancement of slab area-of-interest, obtains slab edge and tail portion image；
The system communication module is for collecting the collected slab edge of industrial camera and tail portion real time video image and sending
To client, and to industrial camera transmission acquisition control signal and to Machine Vision Detection algoritic module recognition result signal
Output is controlled；
The software interactive interface is for showing slab edge and tail portion real time video image and Machine Vision Detection algorithm mould
The operation result of block and the operating parameter control for realizing Machine Vision Detection algoritic module；
The Machine Vision Detection algoritic module includes computing module and judgment module, and the computing module is to treated slab
Edge and image information is analyzed end to end obtains detection slab side and form parameter end to end；
Form parameter of the judgment module by detection slab side and end to end is compared with default passage deformation parameter, to
Judge whether to need edger roll input and end to end excision and rolling drafts and cuts off numerical quantity end to end.
2. slab edge and Head and Tail Shape automatic checkout system according to claim 1 based on binocular vision, feature
It is：The industrial camera is CCD camera.
3. slab edge and Head and Tail Shape automatic checkout system according to claim 2 based on binocular vision, feature
It is：The parallel installation of described two CCD cameras, the CCD camera is used to acquire the edge of aluminum alloy slab and image regards end to end
Frequency information.
4. slab edge and Head and Tail Shape automatic checkout system according to claim 1 based on binocular vision, feature
It is：Further include database generation module, the database generation module is used to establish work according to acquisition image and handling result
Skill protocol data library records the change procedure of slab edge and shape end to end in production process.
5. a kind of slab edge and Head and Tail Shape automatic testing method based on binocular vision, it is characterised in that：Including following step
Suddenly：
S1, arrangement detection device, install CCD camera；
S2, image/video acquisition, aluminum alloy slab edge and image/video information collection end to end are carried out by CCD camera；
S3, image preprocessing, image preprocessing include the foreground extraction and image enhancement of slab area-of-interest；
S4, calculating form parameter obtain CCD camera coordinate, image coordinate by the calibration of CCD camera parameter calibration and system
With the relationship of world coordinate system, edge and its Head and Tail Shape wheel under world coordinate system are then calculated by Binocular Vision Principle
It is wide；
S5, default passage deformation parameter compare and judge, the slab edge and its Head and Tail Shape obtained by machine vision metrology
Profile and default passage deformation parameter are compared, and input edger roll carries out rolling and cropping after reaching default passage deformation parameter
Tail.
6. slab edge and Head and Tail Shape automatic testing method according to claim 5 based on binocular vision, feature
It is：It is described to arrange that detection device is as follows in S1：
S11, then increased by image by foreground extraction slab area-of-interest first with binocular CCD camera monitoring slab
The edge and head-tail feature of strong prominent slab；
S12, CCD camera calibration, the pass between CCD camera coordinate system, image coordinate system and world coordinate system is obtained by calibration
System；
S13, the deformation that slab edge is measured using binocular CCD camera and the deformation using monocular camera measurement end to end.
7. slab edge and Head and Tail Shape automatic testing method according to claim 5 based on binocular vision, feature
It is：In S4 by Binocular Vision Principle be calculated under world coordinate system edge and its end to end crucial point coordinates specifically include as
Lower step：
S41, imaging plane is set at the optical center front focal length f of camera lens, left and right imaging surface coordinate origin CCD camera optical axis with
The intersection point O of plane1And O2Locate, certain point P corresponding coordinates in left imaging plane and right imaging plane are P in spacel(ul,vl) and
Pr(ur,vr), it is now assumed that the image of CCD camera is in same plane, i.e. vl=vr, obtained by geometrical relationship：
(x in above formulac,yc,zc) it is coordinates of the point P in left CCD camera coordinate system, b is baseline distance, and f is the coke of two CCD cameras
Away from (ul,vl) and (ur,vr) it is coordinates of the point P in two images of left and right；
S42, the alternate position spike that parallax is certain point respective point in two images is defined：
It is possible thereby to calculate coordinates of certain point P in left CCD camera coordinate system in space and be：
S43, world coordinate system is enabled to be overlapped with left CCD camera coordinate system, obtained (xc,yc,zc) it is P points under world coordinate system
Coordinate.
8. slab edge and Head and Tail Shape automatic testing method according to claim 5 based on binocular vision, feature
It is：Further include S6, generate technological procedure database, the technological procedure database root is built according to acquisition image and handling result
It is vertical, record slab edge and Head and Tail Shape change procedure in production process.
9. slab edge and Head and Tail Shape automatic testing method according to claim 5 based on binocular vision, feature
It is：Default passage deformation parameter includes at least side and the maximum length being recessed end to end in the operation of rolling.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810009526.4A CN108458668A (en) | 2018-01-05 | 2018-01-05 | Slab edge and Head and Tail Shape automatic checkout system based on binocular vision and method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810009526.4A CN108458668A (en) | 2018-01-05 | 2018-01-05 | Slab edge and Head and Tail Shape automatic checkout system based on binocular vision and method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108458668A true CN108458668A (en) | 2018-08-28 |
Family
ID=63221302
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810009526.4A Pending CN108458668A (en) | 2018-01-05 | 2018-01-05 | Slab edge and Head and Tail Shape automatic checkout system based on binocular vision and method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108458668A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108195653A (en) * | 2017-09-16 | 2018-06-22 | 南京福怡科技发展股份有限公司 | One kind redyes staining kit and preparation and application |
| CN109540918A (en) * | 2018-11-28 | 2019-03-29 | 鞍钢集团自动化有限公司 | A kind of hot rolled coil edge fault detection device and method |
| CN110779926A (en) * | 2019-11-06 | 2020-02-11 | 山东建筑大学 | Machine vision detection system for correcting surface defects in artificial board transportation |
| CN110773574A (en) * | 2019-11-15 | 2020-02-11 | 中冶华天工程技术有限公司 | Hydraulic control system and method for automatically adjusting prestress of rolling mill |
| CN112668525A (en) * | 2020-12-31 | 2021-04-16 | 深圳云天励飞技术股份有限公司 | People flow counting method and device, electronic equipment and storage medium |
| CN112958636A (en) * | 2021-04-11 | 2021-06-15 | 燕山大学 | Flexible sensing device and method for detecting head and tail defects of hot-rolled aluminum plate |
| CN113065596A (en) * | 2021-04-02 | 2021-07-02 | 鑫安利中（北京）科技有限公司 | Industrial safety real-time monitoring system based on video analysis and artificial intelligence |
| CN113263155A (en) * | 2021-06-07 | 2021-08-17 | 燕山大学 | Alignment method suitable for roll casting |
| CN113390344A (en) * | 2021-07-06 | 2021-09-14 | 桂林电子科技大学 | Method for rapidly detecting dimension and geometric tolerance of stepped shaft |
| CN113458159A (en) * | 2020-03-31 | 2021-10-01 | 宝山钢铁股份有限公司 | Method for detecting upwarp amount of hot-rolled finish-rolled strip steel |
| CN113486854A (en) * | 2021-07-29 | 2021-10-08 | 北京超维世纪科技有限公司 | Recognition detection algorithm for realizing industrial inspection robot based on depth camera |
| CN113552139A (en) * | 2021-06-23 | 2021-10-26 | 番禺得意精密电子工业有限公司 | Automatic vision detection system and detection method |
| CN114049323A (en) * | 2021-11-15 | 2022-02-15 | 武汉易思达科技有限公司 | Compartment vehicle deformation real-time measurement method and system based on binocular vision |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2772122A1 (en) * | 1997-12-05 | 1999-06-04 | Premium Instr Sa | METHOD AND DEVICE FOR MEASURING THE SHAPE AND / OR THE POSITION OF A PROFILE OF A SIDE SURFACE OF AN ELONGATED PRODUCT |
| CN101658954A (en) * | 2009-09-10 | 2010-03-03 | 上海交通大学 | Billet shearing device based on image sensing and shearing method thereof |
| CN103353282A (en) * | 2013-06-09 | 2013-10-16 | 河北工业大学 | On-line vision measurement apparatus for end shapes of hot rolled strip steel |
| CN103868460A (en) * | 2014-03-13 | 2014-06-18 | 桂林电子科技大学 | Parallax optimization algorithm-based binocular stereo vision automatic measurement method |
| CN106197315A (en) * | 2016-07-21 | 2016-12-07 | 赵艳丽 | Energy multiple spot detects the detection device of electric power tower steel pipe circular section profile simultaneously |
| CN107490342A (en) * | 2017-06-30 | 2017-12-19 | 广东工业大学 | A kind of cell phone appearance detection method based on single binocular vision |
-
2018
- 2018-01-05 CN CN201810009526.4A patent/CN108458668A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| FR2772122A1 (en) * | 1997-12-05 | 1999-06-04 | Premium Instr Sa | METHOD AND DEVICE FOR MEASURING THE SHAPE AND / OR THE POSITION OF A PROFILE OF A SIDE SURFACE OF AN ELONGATED PRODUCT |
| CN101658954A (en) * | 2009-09-10 | 2010-03-03 | 上海交通大学 | Billet shearing device based on image sensing and shearing method thereof |
| CN103353282A (en) * | 2013-06-09 | 2013-10-16 | 河北工业大学 | On-line vision measurement apparatus for end shapes of hot rolled strip steel |
| CN103868460A (en) * | 2014-03-13 | 2014-06-18 | 桂林电子科技大学 | Parallax optimization algorithm-based binocular stereo vision automatic measurement method |
| CN106197315A (en) * | 2016-07-21 | 2016-12-07 | 赵艳丽 | Energy multiple spot detects the detection device of electric power tower steel pipe circular section profile simultaneously |
| CN107490342A (en) * | 2017-06-30 | 2017-12-19 | 广东工业大学 | A kind of cell phone appearance detection method based on single binocular vision |
Non-Patent Citations (1)
| Title |
|---|
| 燕猛等: "板坯头/尾部平面形状对铝合金厚板粗轧头尾切除量的影响", 《中国有色金属学报》 * |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108195653A (en) * | 2017-09-16 | 2018-06-22 | 南京福怡科技发展股份有限公司 | One kind redyes staining kit and preparation and application |
| CN109540918A (en) * | 2018-11-28 | 2019-03-29 | 鞍钢集团自动化有限公司 | A kind of hot rolled coil edge fault detection device and method |
| CN109540918B (en) * | 2018-11-28 | 2021-04-16 | 鞍钢集团自动化有限公司 | Hot-rolled coil edge defect detection device and method |
| CN110779926A (en) * | 2019-11-06 | 2020-02-11 | 山东建筑大学 | Machine vision detection system for correcting surface defects in artificial board transportation |
| CN110773574A (en) * | 2019-11-15 | 2020-02-11 | 中冶华天工程技术有限公司 | Hydraulic control system and method for automatically adjusting prestress of rolling mill |
| CN113458159A (en) * | 2020-03-31 | 2021-10-01 | 宝山钢铁股份有限公司 | Method for detecting upwarp amount of hot-rolled finish-rolled strip steel |
| CN112668525A (en) * | 2020-12-31 | 2021-04-16 | 深圳云天励飞技术股份有限公司 | People flow counting method and device, electronic equipment and storage medium |
| CN112668525B (en) * | 2020-12-31 | 2024-05-07 | 深圳云天励飞技术股份有限公司 | People flow counting method and device, electronic equipment and storage medium |
| CN113065596B (en) * | 2021-04-02 | 2022-01-28 | 鑫安利中（北京）科技有限公司 | Industrial safety real-time monitoring system based on video analysis and artificial intelligence |
| CN113065596A (en) * | 2021-04-02 | 2021-07-02 | 鑫安利中（北京）科技有限公司 | Industrial safety real-time monitoring system based on video analysis and artificial intelligence |
| CN112958636A (en) * | 2021-04-11 | 2021-06-15 | 燕山大学 | Flexible sensing device and method for detecting head and tail defects of hot-rolled aluminum plate |
| CN112958636B (en) * | 2021-04-11 | 2022-02-25 | 燕山大学 | Flexible sensing device and method for detecting head and tail defects of hot-rolled aluminum plate |
| CN113263155A (en) * | 2021-06-07 | 2021-08-17 | 燕山大学 | Alignment method suitable for roll casting |
| CN113552139A (en) * | 2021-06-23 | 2021-10-26 | 番禺得意精密电子工业有限公司 | Automatic vision detection system and detection method |
| CN113390344A (en) * | 2021-07-06 | 2021-09-14 | 桂林电子科技大学 | Method for rapidly detecting dimension and geometric tolerance of stepped shaft |
| CN113486854A (en) * | 2021-07-29 | 2021-10-08 | 北京超维世纪科技有限公司 | Recognition detection algorithm for realizing industrial inspection robot based on depth camera |
| CN114049323A (en) * | 2021-11-15 | 2022-02-15 | 武汉易思达科技有限公司 | Compartment vehicle deformation real-time measurement method and system based on binocular vision |
| CN114049323B (en) * | 2021-11-15 | 2024-04-30 | 武汉易思达科技有限公司 | Real-time deformation measuring method for van vehicle based on binocular vision |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108458668A (en) | Slab edge and Head and Tail Shape automatic checkout system based on binocular vision and method | |
| CN102565072B (en) | Stereoscopic vision on-line detection method for surface crack of stretched aluminum alloy plate | |
| US11893724B2 (en) | Methods of artificial intelligence-assisted infrastructure assessment using mixed reality systems | |
| KR102423561B1 (en) | Intelligent dam management system based on digital twin | |
| WO2016055031A1 (en) | Straight line detection and image processing method and relevant device | |
| WO2023045299A1 (en) | Road surface technical condition detection method and device based on three-dimensional contour | |
| CN115482195B (en) | Train part deformation detection method based on three-dimensional point cloud | |
| CN108645375B (en) | Rapid vehicle distance measurement optimization method for vehicle-mounted binocular system | |
| CN107796373B (en) | Distance measurement method based on monocular vision of front vehicle driven by lane plane geometric model | |
| EP2476999B1 (en) | Method for measuring displacement, device for measuring displacement, and program for measuring displacement | |
| WO2023207257A1 (en) | Tailing dam surface deformation patrol method based on rail-mounted rail robot | |
| CN111754560B (en) | High-temperature smelting container erosion early warning method and system based on dense three-dimensional reconstruction | |
| CN116486287A (en) | Target detection method and system based on environment self-adaptive robot vision system | |
| CN114118253B (en) | Vehicle detection method and device based on multi-source data fusion | |
| CN105184792A (en) | Circular saw web wear extent online measuring method | |
| Drews Jr et al. | Tracking system for underwater inspection using computer vision | |
| CN111612907A (en) | Multidirectional repairing system and method for damaged ancient building column | |
| CN116681912A (en) | Rail gauge detection method and device for railway turnout | |
| Bosurgi et al. | Automatic crack detection results using a novel device for survey and analysis of road pavement condition | |
| CN113869407A (en) | Monocular vision-based vehicle length measuring method and device | |
| CN112734840A (en) | Power transmission line safety distance measuring method | |
| Appio et al. | Automatic surface inspection in steel products ensures safe, cost-efficient and timely defect detection in production | |
| CN116823737B (en) | Tunnel wall abnormity detection method and system in low-texture environment | |
| CN114384078B (en) | Method and equipment for detecting wave abrasion damage of steel rail in positioning mode | |
| CN106251327A (en) | A kind of sub-pix border method for quick for cutting tools measurement |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180828 |