CN109764807A - The 2D visible detection method and detection system of engine cylinder body location position - Google Patents
The 2D visible detection method and detection system of engine cylinder body location position Download PDFInfo
- Publication number
- CN109764807A CN109764807A CN201910033056.XA CN201910033056A CN109764807A CN 109764807 A CN109764807 A CN 109764807A CN 201910033056 A CN201910033056 A CN 201910033056A CN 109764807 A CN109764807 A CN 109764807A
- Authority
- CN
- China
- Prior art keywords
- cylinder body
- point
- value
- positioning
- steps
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Landscapes
- Length Measuring Devices By Optical Means (AREA)
Abstract
The present invention provides the 2D visible detection method and detection system of a kind of engine cylinder body location position, wherein 2D visible detection method following steps: 100. determine that cylinder body is moved to Image Acquisition within sweep of the eye by shooting；The distance between several test points in 200. acquisition robots to cylinder body；300. in several test points, grab point using the center of four cylinder holes of cylinder body as positioning, obtain the positioning crawl point P of cylinder body1Spatial value [X, Y, Z, α, beta, gamma] in robot tool coordinate system.The present invention only needs to complete the acquisition of related data using a described image acquisition equipment and the distance measuring sensor, described image acquires equipment and the distance measuring sensor and collected data is transferred to the industrial personal computer, the industrial personal computer is processed into the spatial value of positioning crawl point, realize 3D vision positioning effect, algorithm is simplified reliably, has many advantages, such as that system cost is low, crawl is convenient, good reliability and high-efficient.
Description
Technical field
The present invention relates to robotic technology fields, more particularly, to a kind of 2D vision-based detection of engine cylinder body location position
Method and detection system.
Background technique
As industrial automatization is higher and higher, robot industrially using more and more extensive, for example, utilizing machine
Device people carries out the work such as arc welding, stacking, carrying, goods sorting.In automobile industry, engine be vehicle core component it
One, it is ensured that engine stabilizer volume production is crucial.On engine automation production line, five big processes are broadly divided into, are hair respectively
Motivation cylinder casting, eliminates thermal stress, finishing, assembly at cylinder body deburring.In cylinder body deburring operation, since cylinder body comes
Derived from previous step casting process, outer surface of cylinder block burr is more, influences being normally carried out for subsequent handling.Therefore, it is necessary to be gone
Burring process, and during this, it needs mechanical arm to pinpoint crawl engine cylinder body from feeding roller table, puts it into processing machine
Bed in, after the completion of lathe deburring, then with manipulator by its from machining tool take out be placed in delivery roller table, so far complete
Cylinder body deburring production process.
Since the cylinder body burr after casting is larger, cause cylinder body fully horizontal can not rest on roller-way, this is to machinery
Hand carries out fixed point crawl and brings very big difficulty, and Conventional enterprise generally takes 3D binocular vision to carry out fixed point crawl, such method at
This height, reliability are also unable to get good guarantee, and later maintenance is got up more difficult.
Summary of the invention
In order to overcome the above problem, the present invention provides 2D visible detection method and the inspection of a kind of engine cylinder body location position
Examining system, this system cost is low, crawl is convenient and good reliability.
A kind of technical solution of the invention is: providing a kind of 2D visible detection method of engine cylinder body location position, wraps
Include following steps:
100. determining that cylinder body is moved to Image Acquisition within sweep of the eye by shooting；
The distance between several test points in 200. acquisition robots to cylinder body；
300. in several test points, grab point using the center of four cylinder holes of cylinder body as positioning, obtain cylinder body
Positioning grab point P1Spatial value [X, Y, Z, α, beta, gamma] in robot tool coordinate system.
1. the 2D visible detection method of engine cylinder body location position according to claim 1, which is characterized in that
In above-mentioned steps 100, include the following steps:
101. after sensing cylinder body, stopping mobile cylinder body；
102. obtaining the reference picture of cylinder body, reference picture middle cylinder bore dia D is obtainedhole, the long D of cylinder bodylengthIt is wide with cylinder body
Dwide；
103. acquiring the sampled images of cylinder body, sampled images middle cylinder bore dia D is obtainedhole1, the long D of cylinder bodylength1And cylinder body
Wide Dwide1；
104. working as
Wherein, T is error threshold, then cylinder body Image Acquisition within sweep of the eye；Otherwise, cylinder body is not or not the Image Acquisition visual field
In range；
105. cylinder body not Image Acquisition within sweep of the eye, mobile image acquisition equipment preset distance repeats the above steps
103 and 104.
As improvement of the present invention, in above-mentioned steps 200, formula ranging is scanned to test points several on cylinder body.
Include the following steps: in above-mentioned steps 300 as improvement of the present invention
301. positioning for obtaining cylinder body grab point P1α value in robot tool coordinate system.
Include the following steps: in above-mentioned steps 301 as improvement of the present invention
3011. obtain four central coordinate of circle of four cylinder holes, four central coordinate of circle of cylinder body in the sampled images of cylinder body
It is respectively as follows: O1=[OX1, OY1], O2=[OX2, OY2], O3=[OX3, OY3], O4=[OX4, OY4]；Four central coordinate of circle institutes of cylinder body
L is denoted as in straight lineo, slope K；
3012. in robot tool coordinate system, positioning crawl point P1Angle with X-axis is α=arctan (k), positioning
Grab point P1Position in XY coordinate system are as follows:
Include the following steps: in above-mentioned steps 300 as improvement of the present invention
302. positioning for obtaining cylinder body grab point P1X value and Y value in robot tool coordinate system.
Include the following steps: in above-mentioned steps 302 as improvement of the present invention
3021. by xq, yqIt imported into formulaIn, wherein w is object distance, and v is image distance, and u is target size, and q is shadow
As size；It obtains
Include the following steps: in above-mentioned steps 300 as improvement of the present invention
303. positioning for obtaining cylinder body grab point P1Z value, β value and γ value in robot tool coordinate system.
Include the following steps: in above-mentioned steps 303 as improvement of the present invention
3031. obtain several detection point set G0={ h1, h2... hw}；
3032. distance values for rejecting non-cylinder body upper surface are greater than the useless point of H, and from left to right ascending sequence carries out
Sequence, obtains new apart from point set G '0={ h1, h2... hj, it is recorded in the matrix form according to scanning sequenceWherein, G '0Value formation with corresponding position in D maps one by one, and H is default value, and i and j are
Integer more than or equal to 2；
3033. for any point h in matrix Dlm, form nine grids with adjacent 8 points, wherein l and m be greater than etc.
In 2 integer；
3034. according to gradient algorithm, the h at any pointlmWith adjacent 8 points of progress gradiometer calculation,
Gradient k is greater than threshold value Th, then hlmFor marginal point, on the contrary then hlmIt is not marginal point, side is calculated
Edge point set is combined into G "0, G "0Value formation with the corresponding position D maps one by one；
3035. assume according to G "0It is (x, y) that middle element, which is mapped to position in matrix D, then with the phase on same side
Neighbors point is mapped to the condition that position line number and row number difference are 1 in matrix D, obtains each line set；
First vegetarian refreshments total amount size of 3036. more each line sets, obtain cylinder body long side 1 apart from point set be G1={ h11,
h22... h2c, cylinder body long side 2 apart from point set be G2={ h11, h22... h2d, cylinder body short side 1 apart from point set be G3=
{h11, h22... h2e, cylinder body short side 2 apart from point set be G4={ h11, h22... h2f}；Z=median (G '0)。
Another technical solution of the invention is: a kind of 2D vision detection system of engine cylinder body location position is provided,
Include:
One image capture device acquires equipment shooting by described image and determines that cylinder body is moved to Image Acquisition field range
It is interior；
One distance measuring sensor, the distance measuring sensor acquire the distance between several test points in robot to cylinder body；
One industrial personal computer, the industrial personal computer are stored with computer program, the computer program be executed by processor completion with
Lower step: in several test points, point is grabbed using the center of four cylinder holes of cylinder body as positioning, obtains the positioning of cylinder body
Grab point P1Spatial value [X, Y, Z, α, beta, gamma] in robot tool coordinate system.
The present invention is due to using an image capture device, distance measuring sensor and industrial personal computer, it is only necessary to use a figure
The acquisition of related data can be completed as acquiring equipment and distance measuring sensor, the 3D data of acquisition cylinder body is not needed, is also not required to
3D binocular is used to acquire, collected data are transferred to industrial personal computer by image capture device and distance measuring sensor, and industrial personal computer will
Its spatial value for being processed into positioning crawl point, realizes 3D vision positioning effect, and algorithm is simplified reliably, has system cost
It is low, crawl is convenient, good reliability and it is high-efficient the advantages that.
Detailed description of the invention
Fig. 1 is the principle process block diagram of the 2D visible detection method of engine cylinder body location position in the present invention.
Fig. 2 is the scanning route map of distance measuring sensor in the present invention.
Principle box signal when Fig. 3 is the 2D vision detection system application of engine cylinder body location position in the present invention
Figure.
Wherein: 1, distance measuring sensor；2, industrial personal computer；3, image capture device；5, PLC controller；, 4, touch display screen；
6, robot；7, cylinder body.
Specific embodiment
In the description of the present invention, it is to be understood that, "center" in term, "upper", "lower", "front", "rear", " left side ",
The orientation or positional relationship of instructions such as " right sides " is to be based on the orientation or positional relationship shown in the drawings, and is merely for convenience of describing this hair
Bright and simplified description, rather than the device or component of indication or suggestion meaning must have a particular orientation, with specific orientation
Construction and operation, therefore be not considered as limiting the invention.In addition, term " first ", " second " are used for description purposes only,
It is not understood to indicate or imply relative importance.
In the description of the present invention, it should be noted that unless otherwise clearly defined and limited, term " installation " " connects
Connect ", " connected " shall be understood in a broad sense, for example, it may be being fixedly connected, be also possible to dismantling connection, or be integrally connected；It can be with
It is mechanical connection, is also possible to be electrically connected；It can be directly connected, be also possible to indirectly connected through an intermediary, can be
The connection of two component internals.For the ordinary skill in the art, above-mentioned term can be understood at this with concrete condition
The concrete meaning of invention.
Referring to Figure 1 and Fig. 2, Fig. 1 are revealed is a kind of 2D visible detection method of engine cylinder body location position
Flow chart, it is the scanning route map of distance measuring sensor that Fig. 2 is revealed.2D visible detection method includes the following steps:
100. determining that cylinder body 7 is moved to Image Acquisition within sweep of the eye by shooting；
The distance between several test points in 200. acquisition robots to cylinder body 7；
300. in several test points, grab point using the center of four cylinder holes of cylinder body 7 as positioning, obtain cylinder body
7 positioning grabs point P1Spatial value [X, Y, Z, α, beta, gamma] in robot tool coordinate system.It should be noted that machine
In device people's tool coordinates system, X, Y, Z are the value in reference axis, and α is the angle with X-direction, and β is the angle with Y direction,
γ is the angle with Z-direction.
In the above-mentioned steps 100 of this method, include the following steps:
101. after sensing cylinder body 7, stopping mobile cylinder body 7.Cylinder body 7 is placed on feeding roller table, and photoelectric sensor is used
In sensing cylinder body 7.If sensing cylinder body 7, stop the rotation of feeding roller table material chain, robot is moved to initial shooting vertex.
102. obtaining the reference picture of cylinder body 7, reference picture middle cylinder bore dia D is obtainedhole, the long D of cylinder bodylengthAnd cylinder body
Wide Dwide.Reference picture refers to image when cylinder body 7 is placed at standard state, that is to say, that in robot in crawl cylinder body 7
When, robot does not need to do the adjustment of any angle.How reference picture middle cylinder bore dia D is obtainedhole, the long D of cylinder bodylengthWith
The wide D of cylinder bodywideInclude the following steps:
1021. obtain reference picture is pre-processed, pre-treatment step: using matlab tool function Premnmx into
Row image normalization；Image enhancement is carried out using histogram equalization method；Edge detection is carried out using sobel operator.
1022. pairs of reference pictures carry out the acquisition of characteristic point, acquisition cylinder holes characteristics of diameters point, the long characteristic point of cylinder body and cylinder body
Quant's sign point.
1023. engine cylinder hole characteristics of diameters points convert round detection method using hough and engine cylinder hole are calculated
Diameter Dhole, the long D of engine cylinder body is calculated using hough transformation straight-line detectionlengthWith the wide D of engine cylinder bodywide。
It is as follows that 10231.hough converts straight-line detection calculation method:
(1) in sampled images matrix TPIn, any point (x in imagei, yj) correspond in parameter space and indicate are as follows: ρ=
xicosθ+yjSin θ, wherein ρ indicates this point (x in image spacei, yj) distance in the center of circle is arrived, θ indicates this point (xi, yj) where
The angle of straight line and x-axis.
(2) to image T after processingY1Edge detection is carried out using canny operator again, the marginal point detected is stored in collection
Close TbIn, Tb=[(x1, y1)…(xj, yj)], wherein j indicates the number of marginal point.
(3) ρ is quantized into m parts, θ is quantized into n parts, then parameter space is quantized into m × n unit, to processing corresponding position
Each unit be arranged accumulator Dmn。
(4) to TbIn any pixel (xj, yj), it is updated to formula ρ=xicosθ+yjIt is empty in the parameter of quantization in sin θ
Between in corresponding position accumulator add 1, i.e. Dmn=Dmn+1；
(5) all T are traversedbMiddle all pixels point, accumulator DmnPreceding 4 maximum parameter space points correspond to image space
In, be the four edges of engine rigid body object that the present invention detects, by it is each while pixel it is cumulative obtain each while Dlength, Dwide
Length value.
10231. is as follows based on the round detection improvement method calculating of hough transformation:
(1) according to real engine cylinder body feature, the quantizing range that image space cylinder body round diameter is arranged is [rl, rk],
T is obtained with 2.2.3.1 step (2) same methodb=[(x1, y1)…(xj, yj)]。
(2) any point (x in imagei, yi) with the mapping relations of parameter space it is defined as (xi-a)2+yi-b)2=r2.It will
Parameter space (a, b, r) is quantized into m × n × J unit, and each unit is respectively provided with accumulator DmnJ。
(3) to TbIn any pixel (xj, yj), it is updated to formula (xi-a)2+yi-b)2=r2In, it is empty in the parameter of quantization
Between in corresponding position accumulator add 1, i.e. Dmnj=Dmnj+1；
(4) all T are traversedbMiddle all pixels point, accumulator DmnjPreceding 4 maximum parameter space point [am, bn, rj] corresponding
It is the central coordinate of circle and radius in the engine rigid body image space of the invention detected into image space.Wherein am, bnTable
Show central coordinate of circle, rjIndicate radius.
103. acquiring the sampled images of cylinder body 7, sampled images middle cylinder bore dia D is obtainedhole1, the long D of cylinder bodylength1And cylinder body
Wide Dwide1。
104. working asWherein, T is error
Threshold value, then cylinder body 7 Image Acquisition within sweep of the eye；Otherwise, cylinder body 7 not Image Acquisition within sweep of the eye.It needs to illustrate
It is T=5% or 4% etc., T value, which can according to need, to be selected, above-mentioned to be merely illustrative.
105. cylinder body 7 not Image Acquisition within sweep of the eye, mobile image acquisition equipment preset distance repeats the above steps
103 and 104.It should be noted that preset distance can be 50mm, 55mm, 45mm, 42mm, 40mm etc., preset distance can be with
It is selected as needed, it is above-mentioned to be merely illustrative.
In the above-mentioned steps 200 of this method, image capture device is scanned formula ranging to several test points on cylinder body 7
(referring to Fig. 2).The density of test point is a × b, wherein the scanning element of x-axis direction has a, and the scanning element in y-axis direction has b
A, a and b are the integer more than or equal to 2, and the mode of scanning is generally used and scanned back and forth.
In the above-mentioned steps 300 of this method, include the following steps: the positioning crawl point P of 301. acquisition cylinder bodies 71In machine
α value in device people's tool coordinates system.
In above-mentioned steps 301, include the following steps:
3011. obtain four central coordinate of circle of four cylinder holes in the sampled images of cylinder body 7, and four centers of circle of cylinder body 7 are sat
Mark is respectively as follows: O1=[OX1, OY1], O2=[OX2, OY2], O3=[OX3, OY3], O4=[OX4, OY4]；Four central coordinate of circle of cylinder body 7
Place straight line is denoted as Lo, slope K.It is sat it should be noted that each centre point is calculated using Hough transform circle detection
Mark.
3012. in robot tool coordinate system, positioning crawl point P1Angle with X-axis is α=arctan (k), positioning
Grab point P1Position in XY coordinate system are as follows:
In the above-mentioned steps 300 of this method, include the following steps: the positioning crawl point P of 302. acquisition cylinder bodies 71In machine
X value and Y value in device people's tool coordinates system.
In above-mentioned steps 302, include the following steps: 3021. by xq, yqIt imported into formulaIn, wherein w is
Object distance, v are image distance, and u is target size, and q is image size；It obtains
It should be noted that image distance v in order to obtain, carries out calibration experiment to camera image distance first.Specific process is:
It keeps the parameters of image capture device constant, selects a square as object of experiment object, measure object of experiment
The diameter u (target size) of object；The camera lens of image capture device and object of experiment object are placed in same level, and make two
Person's remains w apart from object distance；The image of image capture device object of experiment object obtained is passed through into image processing software
Processing obtains the image size q of object of experiment object, then substitutes into above-mentioned formula and obtain image distance v.
In the above-mentioned steps 300 of this method, include the following steps: the positioning crawl point P of 303. acquisition cylinder bodies 71In machine
Z value, β value and γ value in device people's tool coordinates system.
In above-mentioned steps 303, include the following steps:
3031. obtain several detection point set G0=(h1, h2... hw)；
3032. distance values for rejecting non-7 upper surfaces of cylinder body are greater than the useless point of H, from left to right ascending sequence into
Row sequence, obtains new apart from point set C '0=[h1, h2... hj, it is recorded in the matrix form according to scanning sequenceWherein, G '0Value formation with corresponding position in D maps one by one, and H is default value, and i and j are
Integer more than or equal to 2；
3033. for any point h in matrix Dlm, form nine grids with adjacent 8 points, wherein l and m be greater than etc.
In 2 integer.As shown in following figure A.And for cylinder body 7, the range points of 7 marginal position of cylinder body, the distance of adjacent position
Difference certainly will be very big, conversely, 7 marginal point of non-cylinder body, distance difference are smaller.
| h(l-1)(m-1) | h(l-1)m | h(l-1)(m+1) |
| hl(m-1) | hlm | hl(m+1) |
| h(l+1)(m-1) | h(l+1)m | h(l+1)(m+1) |
Scheme A
3034. according to gradient algorithm, the h at any pointlmWith adjacent 8 points of progress gradiometer calculation,Gradient k
Greater than threshold value Th, then hlmFor marginal point, on the contrary then hlmIt is not marginal point, it is G " that edge point set, which is calculated,0, G "0It is corresponding to D
The value formation of position maps one by one；
3035. assume according to G "0It is (x, y) that middle element, which is mapped to position in matrix D, then with the phase on same side
Neighbors point is mapped to the condition that position line number and row number difference are 1 in matrix D, obtains each line set；
First vegetarian refreshments total amount size of 3036. more each line sets, obtain cylinder body long side 1 apart from point set be G1={ h11,
h22... h2c, cylinder body long side 2 apart from point set be G2={ h11, h22... h2d, 7 short side 1 of cylinder body apart from point set be G3
={ h11, h22... h2e, 7 short side 2 of cylinder body apart from point set be G4={ h11, h22... h2f}；Z=median (G '0)。
In conclusion to obtain the positioning of cylinder body 7 crawl point P1Spatial value in robot tool coordinate system
X, Y, Z, α, beta, gamma], during grabbing cylinder body 7, by this P1Spatial value [X, Y, Z, α, beta, gamma] pass through industrial personal computer
It is sent to PLC controller, robot is being sent to by PLC controller, the crawl cylinder body 7 for completing robot acts.It needs to illustrate
, in the present invention, without specified otherwise, then all images are all 2D images, i.e. reference picture and sampled images is
2D image.The present invention is based on the calibration algorithms of MATLAB, will be analyzed and processed, and obtain apart from point set and sampled images matrix
The three-dimensional coordinate of point is grabbed, algorithm is simplified reliably, saves calculate the time in actual use, improves robot grasp handling
Efficiency.
The present invention is only needed due to using a described image acquisition equipment, the distance measuring sensor and the industrial personal computer
It to use a described image acquisition equipment and the distance measuring sensor that can complete the acquisition of related data, not need to acquire
The 3D data of cylinder body 7 do not need to acquire using 3D binocular yet, and described image acquisition equipment and the distance measuring sensor will collect
Data be transferred to the industrial personal computer, the industrial personal computer is processed into the spatial value of positioning crawl point, realizes 3D vision
Locating effect, algorithm are simplified reliably, have many advantages, such as that system cost is low, crawl is convenient, good reliability and high-efficient.
Refer to Fig. 3, Fig. 3 is revealed when being a kind of 2D vision detection system application of engine cylinder body location position
Principle block diagram, 2D vision detection system include:
One image capture device 3 acquires the shooting of equipment 3 by described image and determines that cylinder body is moved to Image Acquisition visual field model
In enclosing；
One distance measuring sensor 1, the distance between described acquisition robot 6 of distance measuring sensor 1 to test points several on cylinder body；
One industrial personal computer 2, the industrial personal computer 2 are stored with computer program, and the computer program is executed by processor completion
Following steps: in several test points, point is grabbed using the center of four cylinder holes of cylinder body as positioning, obtains determining for cylinder body
Position crawl point P1Spatial value [X, Y, Z, α, beta, gamma] in 6 tool coordinates system of robot.
It should be noted that present invention employs described images to acquire equipment 3, that is, use a camera or
One camera etc., it is 2D image that described image, which acquires the image that equipment 3 acquires,；The distance measuring sensor 1 is using laser
Distance measuring sensor 1；In above-mentioned 2D visible detection method, there are some software algorithms, these software algorithms belong to the calculating
Machine program, the computer program are stored in the industrial personal computer 2, and completed in the industrial personal computer 2, that is to say, that institute
It states and is stored with various software algorithms in industrial personal computer 2, the industrial personal computer 2 is computer, tablet computer, smart phone etc..
It further include PLC controller 5, touch display screen 4 and robot 6 in the present embodiment, the distance measuring sensor 1 and institute
It states industrial personal computer 2 and carries out RS232 serial communication, it is logical by Ethernet between the industrial personal computer 2 and described image acquisition equipment 3
Letter, communicates between the industrial personal computer 2 and the PLC controller 5 by RS232, the PLC controller 5 and the robot 6 it
Between communicated by CC-LINK, communicated between the PLC controller 5 and the touch display screen 4 by Ethernet.
Described image acquisition equipment 3 and the distance measuring sensor 1 are mounted on 6 handgrip of robot, 2 base of industrial personal computer
The serial class of RS232 and Ethernet and the distance measuring sensor 1 and described in MATLAB operating environment, calls tool case
Data exchange is carried out between image capture device 3, wherein described in the distance measuring sensor 1 and the described image acquisition conduct of equipment 3
Industrial personal computer 2 acquires the capital equipment of data, carries out analytical calculation by collected data, obtains the positioning crawl point of robot 6
Spatial value.The touch display screen 4 carries out monitoring of tools and operates with for the ease of operating personnel, and robot 6 makees
For the main body mechanism for completing stacking movement.Action logic control device of the PLC controller 5 as palletizing system is realized each
Cylinder body stacking task is completed in the mutually coordinated movement of equipment.
During grabbing cylinder body, by this P1Spatial value [X, Y, Z, α, beta, gamma] be sent to by industrial personal computer 2
PLC controller 5 is being sent to robot 6 by PLC controller 5, completes the crawl cylinder body movement of robot 6.
The present invention is only needed due to using a described image acquisition equipment, the distance measuring sensor and the industrial personal computer
It to use a described image acquisition equipment and the distance measuring sensor that can complete the acquisition of related data, not need to acquire
The 3D data of cylinder body do not need to acquire using 3D binocular yet, and described image acquisition equipment and the distance measuring sensor will collect
Data be transferred to the industrial personal computer, the industrial personal computer is processed into the spatial value of positioning crawl point, realizes 3D vision
Locating effect, algorithm are simplified reliably, have many advantages, such as that system cost is low, crawl is convenient, good reliability and high-efficient.
It should be noted that explaining in detail for the respective embodiments described above, purpose, which is only that, solves the present invention
It releases, in order to be able to preferably explain the present invention, still, these descriptions cannot be with any explanation at being to limit of the invention
System, in particular, each feature described in various embodiments can also mutual any combination, to form other implementations
Mode, in addition to there is clearly opposite description, these features should be understood to can be applied in any one embodiment, and simultaneously
It is not only limited to described embodiment.
Claims (10)
1. a kind of 2D visible detection method of engine cylinder body location position, which comprises the steps of:
100. determining that cylinder body is moved to Image Acquisition within sweep of the eye by shooting；
The distance between several test points in 200. acquisition robots to cylinder body；
300. in several test points, grab point using the center of four cylinder holes of cylinder body as positioning, obtain determining for cylinder body
Position crawl point P1Spatial value [X, Y, Z, α, beta, gamma] in robot tool coordinate system.
2. the 2D visible detection method of engine cylinder body location position according to claim 1, which is characterized in that above-mentioned
In step 100, include the following steps:
101. after sensing cylinder body, stopping mobile cylinder body；
102. obtaining the reference picture of cylinder body, reference picture middle cylinder bore dia D is obtainedhole, the long D of cylinder bodylengthWith the wide D of cylinder bodywide；
103. acquiring the sampled images of cylinder body, sampled images middle cylinder bore dia D is obtainedhole1, the long D of cylinder bodylength1It is wide with cylinder body
Dwide1；
104. working as
Wherein, T is error threshold, then cylinder body Image Acquisition within sweep of the eye；Otherwise, cylinder body is not in Image Acquisition field range
It is interior；
105. cylinder body not Image Acquisition within sweep of the eye, mobile image acquisition equipment preset distance, repeat the above steps 103 Hes
104。
3. the 2D visible detection method of engine cylinder body location position according to claim 1 or 2, which is characterized in that
In above-mentioned steps 200, formula ranging is scanned to test points several on cylinder body.
4. the 2D visible detection method of engine cylinder body location position according to claim 1 or 2, which is characterized in that
In above-mentioned steps 300, include the following steps:
301. positioning for obtaining cylinder body grab point P1α value in robot tool coordinate system.
5. the 2D visible detection method of engine cylinder body location position according to claim 4, which is characterized in that above-mentioned
In step 301, include the following steps:
3011. obtain four central coordinate of circle of four cylinder holes, four central coordinate of circle difference of cylinder body in the sampled images of cylinder body
Are as follows: O1=[OX1, OY1], O2=[OX2, OY2], O3=[OX3, OY3], O4=[OX4, OY4]；
Straight line where four central coordinate of circle of cylinder body is denoted as L0, slope K；
3012. in robot tool coordinate system, positioning crawl point P1Angle with X-axis is α=arctan (k), positioning crawl point
P1Position in XY coordinate system are as follows:
6. the 2D visible detection method of engine cylinder body location position according to claim 5, which is characterized in that above-mentioned
In step 300, include the following steps:
302. positioning for obtaining cylinder body grab point P1X value and Y value in robot tool coordinate system.
7. the 2D visible detection method of engine cylinder body location position according to claim 6, which is characterized in that above-mentioned
In step 302, include the following steps:
3021. by xq, yqIt imported into formulaIn, wherein w is object distance, and v is image distance, and u is target size, and q is image ruler
It is very little；It obtains
8. the 2D visible detection method of engine cylinder body location position according to claim 5, which is characterized in that above-mentioned
In step 300, include the following steps:
303. positioning for obtaining cylinder body grab point P1Z value, β value and γ value in robot tool coordinate system.
9. the 2D visible detection method of engine cylinder body location position according to claim 8, which is characterized in that above-mentioned
In step 303, include the following steps:
3031. obtain several detection point set G0=(h1, h2... hw)；
3032. distance values for rejecting non-cylinder body upper surface are greater than the useless point of H, and from left to right ascending sequence is arranged
Sequence obtains new apart from point set G '0={ h1, h2... hj, it is recorded in the matrix form according to scanning sequenceWherein, G '0Value formation with corresponding position in D maps one by one, and H is default value, and i and j are
Integer more than or equal to 2；
3033. for any point h in matrix Dlm, nine grids are formed with 8 adjacent points, wherein l and m is more than or equal to 2
Integer；
3034. according to gradient algorithm, the h at any pointlmWith adjacent 8 points of progress gradiometer calculation, Gradient k is greater than threshold
Value Th, then hlmFor marginal point, on the contrary then hlmIt is not marginal point, it is G " that edge point set, which is calculated,0, G "0With the corresponding position D
Value formation maps one by one；
3035. assume according to G "0It is (x, y) that middle element, which is mapped to position in matrix D, then with the adjacent member on same side
Vegetarian refreshments is mapped to the condition that position line number and row number difference are 1 in matrix D, obtains each line set；
First vegetarian refreshments total amount size of 3036. more each line sets, obtain cylinder body long side 1 apart from point set be G1={ h11,
h22... h2c, cylinder body long side 2 apart from point set be G2={ h11, h22... h2d, cylinder body short side 1 apart from point set be G3=
{h11, h22... h2e, cylinder body short side 2 apart from point set be G4={ h11, h22... h2f}；Z=median (G '0)。
10. a kind of 2D vision detection system of engine cylinder body location position characterized by comprising
One image capture device acquires equipment shooting by described image and determines that cylinder body is moved to Image Acquisition within sweep of the eye；
One distance measuring sensor, the distance measuring sensor acquire the distance between several test points in robot to cylinder body；
One industrial personal computer, the industrial personal computer are stored with computer program, and the computer program is executed by processor the following step of completion
It is rapid: in several test points, to grab point using the center of four cylinder holes of cylinder body as positioning, obtain the positioning crawl of cylinder body
Point P1Spatial value [X, Y, Z, α, beta, gamma] in robot tool coordinate system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910033056.XA CN109764807B (en) | 2019-01-14 | 2019-01-14 | 2D visual detection method and detection system for engine cylinder position calibration |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910033056.XA CN109764807B (en) | 2019-01-14 | 2019-01-14 | 2D visual detection method and detection system for engine cylinder position calibration |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN109764807A true CN109764807A (en) | 2019-05-17 |
| CN109764807B CN109764807B (en) | 2021-03-05 |
Family
ID=66453754
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910033056.XA Active CN109764807B (en) | 2019-01-14 | 2019-01-14 | 2D visual detection method and detection system for engine cylinder position calibration |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109764807B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110737253A (en) * | 2019-10-15 | 2020-01-31 | 浙江隐齿丽医学技术有限公司 | Film preparation device with automatic adaptation function, automatic adaptation system and method |
| CN112729117A (en) * | 2020-12-30 | 2021-04-30 | 郑州大学 | Compressor barrel electric box threaded hole detection device based on machine vision |
| CN116221231A (en) * | 2023-05-09 | 2023-06-06 | 湖南奥通智能研究院有限公司 | High-precision oil cylinder displacement detection method and hydraulic oil cylinder |
Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11509928A (en) * | 1995-07-26 | 1999-08-31 | ジェームス クランプトン，ステファン | Scanning apparatus and method |
| US20050162420A1 (en) * | 2004-01-19 | 2005-07-28 | Fanuc Ltd | Three-dimensional visual sensor |
| CN101357687A (en) * | 2008-09-26 | 2009-02-04 | 浙江大学 | Multitask aircraft auxiliary assembly system based on industrial robot |
| CN101909828A (en) * | 2007-12-27 | 2010-12-08 | 莱卡地球系统公开股份有限公司 | Method and system for the high-precision positioning of at least one object in a final location in space |
| CN101913076A (en) * | 2010-06-23 | 2010-12-15 | 中国科学院自动化研究所 | Industrial robot-based assembly method and device of piston, piston pin and connecting rod |
| CN104123540A (en) * | 2014-07-15 | 2014-10-29 | 北京天智航医疗科技股份有限公司 | Automatic identification method of positioning mark points of surgical robot |
| CN104690551A (en) * | 2015-03-18 | 2015-06-10 | 中国科学院自动化研究所 | Robot automatic assembly system |
| CN204868885U (en) * | 2015-03-26 | 2015-12-16 | 库卡系统有限责任公司 | A robot system for controlling work piece |
| CN105182905A (en) * | 2015-08-12 | 2015-12-23 | 西安费斯达自动化工程有限公司 | Vision-based large structural member mobile manipulator multi-coordinate machining center realizing method |
| CN105252251A (en) * | 2015-11-02 | 2016-01-20 | 西北工业大学 | Device and method for achieving automatic grabbing and accurate attaching of aircraft thermal insulation piece |
| CN105965519A (en) * | 2016-06-22 | 2016-09-28 | 江南大学 | Vision-guided discharging positioning method of clutch |
| CN106097323A (en) * | 2016-06-03 | 2016-11-09 | 江苏大学 | A kind of localization method of engine cylinder block foundry goods based on machine vision |
| CN106645182A (en) * | 2017-03-01 | 2017-05-10 | 河北省科学院应用数学研究所 | Three-point automatic visual detection apparatus for inner side surface of inner cap of automotive armrest |
| CN106956263A (en) * | 2017-04-28 | 2017-07-18 | 广州瑞松北斗汽车装备有限公司 | Automobile component vision guide handgrip |
| CN107009357A (en) * | 2017-04-05 | 2017-08-04 | 武汉科技大学 | A kind of method that object is captured based on NAO robots |
| CN107009391A (en) * | 2017-04-24 | 2017-08-04 | 珠海格力智能装备有限公司 | Robot crawl positioner, robot grasping system and grasping means |
| CN107584263A (en) * | 2017-10-18 | 2018-01-16 | 上海文什数据科技有限公司 | A kind of vision positioning guide device and bootstrap technique |
| CN207053346U (en) * | 2017-07-28 | 2018-02-27 | 上海科致电气自动化股份有限公司 | A kind of motor case heats automatic charging device |
| CN107972026A (en) * | 2016-10-25 | 2018-05-01 | 深圳光启合众科技有限公司 | Robot, mechanical arm and its control method and device |
| CN108759773A (en) * | 2018-05-07 | 2018-11-06 | 深圳市三宝创新智能有限公司 | A kind of monocular vision distance measuring method applied to robot crawl |
| CN108857330A (en) * | 2018-03-21 | 2018-11-23 | 南京理工大学 | A kind of wheel hub valve port automatic stopper device |
-
2019
- 2019-01-14 CN CN201910033056.XA patent/CN109764807B/en active Active
Patent Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11509928A (en) * | 1995-07-26 | 1999-08-31 | ジェームス クランプトン，ステファン | Scanning apparatus and method |
| US20050162420A1 (en) * | 2004-01-19 | 2005-07-28 | Fanuc Ltd | Three-dimensional visual sensor |
| CN101909828A (en) * | 2007-12-27 | 2010-12-08 | 莱卡地球系统公开股份有限公司 | Method and system for the high-precision positioning of at least one object in a final location in space |
| CN101357687A (en) * | 2008-09-26 | 2009-02-04 | 浙江大学 | Multitask aircraft auxiliary assembly system based on industrial robot |
| CN101913076A (en) * | 2010-06-23 | 2010-12-15 | 中国科学院自动化研究所 | Industrial robot-based assembly method and device of piston, piston pin and connecting rod |
| CN104123540A (en) * | 2014-07-15 | 2014-10-29 | 北京天智航医疗科技股份有限公司 | Automatic identification method of positioning mark points of surgical robot |
| CN104690551A (en) * | 2015-03-18 | 2015-06-10 | 中国科学院自动化研究所 | Robot automatic assembly system |
| CN204868885U (en) * | 2015-03-26 | 2015-12-16 | 库卡系统有限责任公司 | A robot system for controlling work piece |
| CN105182905A (en) * | 2015-08-12 | 2015-12-23 | 西安费斯达自动化工程有限公司 | Vision-based large structural member mobile manipulator multi-coordinate machining center realizing method |
| CN105252251A (en) * | 2015-11-02 | 2016-01-20 | 西北工业大学 | Device and method for achieving automatic grabbing and accurate attaching of aircraft thermal insulation piece |
| CN106097323A (en) * | 2016-06-03 | 2016-11-09 | 江苏大学 | A kind of localization method of engine cylinder block foundry goods based on machine vision |
| CN105965519A (en) * | 2016-06-22 | 2016-09-28 | 江南大学 | Vision-guided discharging positioning method of clutch |
| CN107972026A (en) * | 2016-10-25 | 2018-05-01 | 深圳光启合众科技有限公司 | Robot, mechanical arm and its control method and device |
| CN106645182A (en) * | 2017-03-01 | 2017-05-10 | 河北省科学院应用数学研究所 | Three-point automatic visual detection apparatus for inner side surface of inner cap of automotive armrest |
| CN107009357A (en) * | 2017-04-05 | 2017-08-04 | 武汉科技大学 | A kind of method that object is captured based on NAO robots |
| CN107009391A (en) * | 2017-04-24 | 2017-08-04 | 珠海格力智能装备有限公司 | Robot crawl positioner, robot grasping system and grasping means |
| CN106956263A (en) * | 2017-04-28 | 2017-07-18 | 广州瑞松北斗汽车装备有限公司 | Automobile component vision guide handgrip |
| CN207053346U (en) * | 2017-07-28 | 2018-02-27 | 上海科致电气自动化股份有限公司 | A kind of motor case heats automatic charging device |
| CN107584263A (en) * | 2017-10-18 | 2018-01-16 | 上海文什数据科技有限公司 | A kind of vision positioning guide device and bootstrap technique |
| CN108857330A (en) * | 2018-03-21 | 2018-11-23 | 南京理工大学 | A kind of wheel hub valve port automatic stopper device |
| CN108759773A (en) * | 2018-05-07 | 2018-11-06 | 深圳市三宝创新智能有限公司 | A kind of monocular vision distance measuring method applied to robot crawl |
Non-Patent Citations (2)
| Title |
|---|
| 李玉荣: "工业制动器缸体桁架机械手自动线应用开发", 《制造技术与机床》 * |
| 黎海; 黄海涛: "发动机生产线机器人视觉搬运系统", 《汽车与配件》 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110737253A (en) * | 2019-10-15 | 2020-01-31 | 浙江隐齿丽医学技术有限公司 | Film preparation device with automatic adaptation function, automatic adaptation system and method |
| CN112729117A (en) * | 2020-12-30 | 2021-04-30 | 郑州大学 | Compressor barrel electric box threaded hole detection device based on machine vision |
| CN116221231A (en) * | 2023-05-09 | 2023-06-06 | 湖南奥通智能研究院有限公司 | High-precision oil cylinder displacement detection method and hydraulic oil cylinder |
| CN116221231B (en) * | 2023-05-09 | 2023-08-15 | 湖南奥通智能研究院有限公司 | High-precision oil cylinder displacement detection method and hydraulic oil cylinder |
Also Published As
| Publication number | Publication date |
|---|---|
| CN109764807B (en) | 2021-03-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US20050273199A1 (en) | Robot system | |
| US9889561B2 (en) | Robot controller having function for displaying robot and force | |
| US7532949B2 (en) | Measuring system | |
| CN109764807A (en) | The 2D visible detection method and detection system of engine cylinder body location position | |
| CN110980276B (en) | Method for implementing automatic casting blanking by three-dimensional vision in cooperation with robot | |
| CN112010024B (en) | Automatic container grabbing method and system based on laser and vision fusion detection | |
| CN113379849B (en) | Robot autonomous recognition intelligent grabbing method and system based on depth camera | |
| CN112894815B (en) | Method for detecting optimal position and posture for article grabbing by visual servo mechanical arm | |
| JP2019113895A (en) | Imaging apparatus with visual sensor for imaging work-piece | |
| KR20140044054A (en) | Method for work using the sensor and system for performing thereof | |
| Xia et al. | Workpieces sorting system based on industrial robot of machine vision | |
| CN111452048A (en) | Calibration method and device for relative spatial position relationship of multiple robots | |
| CN109311604B (en) | Robot and method for adjusting posture of robot | |
| Li et al. | A calibration algorithm of the structured light vision for the arc welding robot | |
| CN114074331A (en) | Disordered grabbing method based on vision and robot | |
| CN115008477B (en) | Manipulator movement compensation method, manipulator movement compensation device and computer-readable storage medium | |
| CN116175542B (en) | Method, device, electronic equipment and storage medium for determining clamp grabbing sequence | |
| WO2023187006A1 (en) | Controlling a robotic manipulator for packing an object | |
| JPH02110788A (en) | Method for recognizing shape of three-dimensional object | |
| CN112053339A (en) | Rod finished product warehouse driving safety monitoring method, device and equipment based on machine vision | |
| CN114322752B (en) | Method, device and equipment for automatically transmitting glass | |
| CN116197888B (en) | Method and device for determining position of article, electronic equipment and storage medium | |
| CN108436333B (en) | Welding robot based on machine vision | |
| CN116175541B (en) | Grabbing control method, grabbing control device, electronic equipment and storage medium | |
| Grudziński et al. | A stereovision system for three-dimensional measurements of machines |
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 |