CN110068271A - The PIN needle position degree detection method of the large size product of sub-pixel precision - Google Patents
The PIN needle position degree detection method of the large size product of sub-pixel precision Download PDFInfo
- Publication number
- CN110068271A CN110068271A CN201910317864.9A CN201910317864A CN110068271A CN 110068271 A CN110068271 A CN 110068271A CN 201910317864 A CN201910317864 A CN 201910317864A CN 110068271 A CN110068271 A CN 110068271A
- Authority
- CN
- China
- Prior art keywords
- image
- subdivision
- pin needle
- product
- coordinate system
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 73
- 238000000034 method Methods 0.000 claims abstract description 17
- 238000012545 processing Methods 0.000 claims abstract description 11
- 238000004891 communication Methods 0.000 claims description 8
- 230000005540 biological transmission Effects 0.000 claims description 6
- 101100117236 Drosophila melanogaster speck gene Proteins 0.000 claims description 5
- 238000000605 extraction Methods 0.000 claims description 4
- 230000000877 morphologic effect Effects 0.000 claims description 4
- 101100518987 Mus musculus Pax1 gene Proteins 0.000 claims description 3
- 101100518992 Mus musculus Pax2 gene Proteins 0.000 claims description 3
- 101100189471 Mus musculus Pbx1 gene Proteins 0.000 claims description 3
- 238000003709 image segmentation Methods 0.000 claims description 3
- 230000001360 synchronised effect Effects 0.000 claims description 2
- 238000005259 measurement Methods 0.000 description 4
- 238000004321 preservation Methods 0.000 description 2
- 241000930965 Spartobacteria Species 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000009776 industrial production Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000012797 qualification Methods 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 230000001960 triggered effect Effects 0.000 description 1
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
- G01B11/002—Measuring arrangements characterised by the use of optical techniques for measuring two or more coordinates
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Image Processing (AREA)
- Image Analysis (AREA)
- Length Measuring Devices By Optical Means (AREA)
Abstract
The PIN needle position degree detection method of the large size product of sub-pixel precision proposed by the present invention, pass through the position of fixed camera and light source, drive product mobile using servo-system, product is divided into the image that several subdivisions acquire each section respectively, utilize the common pixel point having in each image, by the unified image coordinate system of the image of each subdivision, it is created that the new frame of reference simultaneously, finally the distance between the PIN needle needle point being calculated and new benchmark are compared with the tolerance value of setting, to distinguish qualified product and non-qualified product.The present invention has abandoned the method for obtaining large size product size using image stitching method, can greatly reduce and splice and bring error, and processing pixel has the function of sub-pix.In addition, detection method of the invention is applicable in the camera of different brands, and it can be applied to the detection of different product, universal and compatibility is strong.
Description
Technical field
The present invention relates to PIN needle position degree detection fields, more particularly, to the PIN needle of the large size product of sub-pixel precision
Position degree detection method.
Background technique
In the industrial production, there is the product largely to come in every shape, need to carry out high-precision dimensional measurement, and for larger
The product of size, since traditional image detection system can only be handled for piece image, measurement accuracy is not able to satisfy and wants
It asks.
For the product of larger size, the method for directly suturing two images is generallyd use at present, and precision is poor, because of seam
Error caused by conjunction is more than 1 pixel, it is impossible to be used in dimensional measurement；In addition, traditional image detection system sweeps camera using line
Image, due to being easy to be influenced when obtaining image by factors such as the stability and external vibration moved, not applicable and dimensional measurement,
And time of measuring is long.
Summary of the invention
To solve the above problems, there is Asia the invention proposes the PIN needle position degree detection method for being directed to large size product
Pixel function, system accuracy is high, and reproducible, convenient for safeguarding.
Main contents of the invention are as follows:
The PIN needle position degree detection method of the large size product of sub-pixel precision, includes the following steps:
S1. product to be measured is divided into several subdivision A in the longitudinal directioni, and be arranged on product for detecting position
The first datum mark and the second datum mark of degree, wherein the value of i is more than or equal to 1；Adjacent subsection AiBetween have overlapping region
Bi, and the first datum mark on product is located in first subdivision, the second datum mark on product is located at the last one sub-portion
On point；
S2. each subdivision A is successively acquired using PIN needle detection system in orderiImage, be denoted as Pi, and by each subdivision
Image PiIt numbers in order and stores；
S3. using PIN needle detection system to the image P of each subdivisioniIn overlapping region pre-processed, obtain respectively
Each subdivision AiOverlapping region BiLocation information of the interior same pixel point in image coordinate system, and establish unified image
Coordinate system；
S4. using PIN needle detection system to the image P of each subdivisioniIn the region of PIN needle pre-processed, obtain
Each subdivision AiIn each PIN needle location information of the central point in unified image coordinate system；
S5. the location information of the first datum mark and the second datum mark in unified image coordinate system is obtained, is created new
The frame of reference；
S6. it calculates separately the X-axis distance DX of each PIN needle central point and the new frame of reference and is sat with new benchmark
The distance DY of mark system Y-axis, when DX and DY meets the numerical value of setting simultaneously, the position degree of corresponding PIN needle is qualified；Otherwise, right
The position degree for the PIN needle answered is unqualified；
Wherein, the PIN needle detection system includes PIN needle detection device and industrial personal computer, the PIN needle detection device packet
Include camera, light source and servo-system；Product to be measured is fixed on the positioning fixture of servo-system, and the light source is arranged described
Above servo-system, the camera is arranged above the light source；Acquiring each subdivision AiImage during, keep phase
The position of machine and light source is constant, and the servo-system drives product to be measured to move along first direction；The industrial personal computer and the phase
Machine connection, for reading the image of the camera acquisition to be handled image and be calculated.
Preferably, S2 includes following sub-step:
S21. product to be measured is fixed on the positioning fixture of the servo-system；
S22. camera and light source are debugged, servo-system drives product to be measured to be successively moved at preset each position, institute
Camera synchronous acquisition image is stated, the image B of each subdivision is respectively obtainedi；
S23. by the image P of each subdivisioniIt is stored in sequence in the industrial personal computer.
Preferably, the step of unified image coordinate system is established in S3 include:
S31. just positioning is carried out to product by edge finding method, to the overlapping region B of each subdivisioniCarry out two-value
Change, after Morphological scale-space, Blob detection is carried out to it, obtains seat of the central point of same pixel point in corresponding overlapping region
Mark；
S32. according to S31 obtain as a result, calculating the image P of each subdivisioniImage coordinate system relative to its latter son
Partial image Pi+1The corresponding image coordinate system of the image of each subdivision is transformed into first by the variable quantity of image coordinate system
The image coordinate system of the image of a subdivision.
Preferably, the calculating process of S32 is as follows:
S321. the image of j-th of subdivision is set as Pj, the image of two subdivisions thereafter is denoted as P respectivelyj+1, Pj+2, the
The image P of j subdivisionjWith the image P of (j+1) a subdivisionj+1Same pixel be denoted as Pa, (j+1) a subdivision
The pixel pixel of image and the image of (j+2) a subdivision is denoted as Pb, and Pa coordinate in j-th of sub-portion partial image is denoted as
(PaX1, PaY1), the coordinate in the image of (j+1) a subdivision are denoted as (PaX2, PaY2)；Pb is in (j+1) a sub-portion
Coordinate is denoted as (PbX1, PbY1) in partial image, and the coordinate in the image of (j+2) a subdivision is denoted as (PbX2, PbY2)；
S322. the coordinate system for calculating the image of (j+1) a subdivision is sat relative to the image of the image of j-th of subdivision
The variable quantity for marking system, is denoted as DX1=PaX1-PaX2；DY1=PaY1-PaY2；Calculate the image of the image of+1 subdivision of jth
The variable quantity of the image coordinate system of coordinate system and the image of+2 subdivisions of jth, is denoted as DX2=PbX1-PbX2；DY2=PbY1-
PbY2；
S323. according to the calculated result of S322, by the image coordinate system and (j+ of the image of (j+1) a subdivision
2) image coordinate system of the image of a subdivision is converted to the image coordinate system of the image of (j) a subdivision；
S324, the image of remaining subdivision is calculated according to S321 to the step of S323, establishes unified image
Coordinate system.
Preferably, each subdivision A is obtained in S4iIn each PIN needle position of the central point in unified image coordinate system
Confidence breath, includes the following steps:
S41. just positioning is carried out to product by edge finding method, to the area in the image of each subdivision including PIN needle
After domain carries out binaryzation, Morphological scale-space, Blob detection is carried out to it, obtains the central point of PIN needle speck in each subdivision
Coordinate in the image coordinate system of image；
S42. by the central point of the speck of the PIN needle in the image of each subdivision in addition to the image of first subdivision
Coordinate transform to first subdivision image image coordinate system.
Preferably, the step of new frame of reference is created in S5 is as follows:
S51. the coordinate of the first datum mark is denoted as (xs1, ys1), the coordinate of the second datum mark is converted to first son
Coordinate under the image coordinate system of partial image is denoted as (xs2, ys2)；
S52. the second datum mark is obtained into third datum mark, coordinate is denoted as relative to the first datum mark rotation alpha angle
(xs3, ys3), wherein
Xs3=(xs2-xs1) * cos α-(ys2-ys1) * sin α+xs1；
Ys3=(ys2-ys1) * cos α+(xs2-xs1) * sin α+ys1；
It S53. will be simultaneously by the straight line of the first datum mark and third datum mark as the X-axis of the new frame of reference；
S54. the second datum mark is obtained into the 4th datum mark, coordinate is denoted as relative to the first datum mark rotation β angle
(xs4, ys4), wherein
Xs4=(xs2-xs1) * cos β-(ys2-ys1) * sin β+xs1；
Ys4=(ys2-ys1) * cos β+(xs2-xs1) * sin β+ys1；
It S55. will be simultaneously by the straight line of the first datum mark and the 4th datum mark as the Y-axis of the new frame of reference；
Wherein, α is equal to 29.1 °, and β is equal to 119.1 °.
Preferably, the PIN needle detection device includes detection support, and the camera and the light source are slidably arranged in described
In detection support；The servo-system includes detection sliding rail and driving cylinder, and the driving cylinder drives the positioning fixture to exist
It is slided on the detection sliding rail.
Preferably, the camera is area array cameras.
Preferably, the PIN needle detection system further includes the detection management module being integrated in the industrial personal computer, the inspection
Management module is surveyed to include user management submodule, image acquisition submodule, image procossing submodule, image preservation submodule, lead to
Module and user interface submodule are interrogated, the user management submodule is used for the permission and pipe of setting operation person and administrator
The switching of role between reason person and operator；Described image acquisition submodule is used to receive the image that the camera transmission comes, and
Image transmitting to described image is saved into submodule；Described image handles submodule and is used to receive described image acquisition submodule
Image carry out image denoising, image enhancement, image restoration, image segmentation and feature extraction processing, determine product whether close
Lattice；Described image saves submodule and is used in order store the image that the transmission of described image acquisition submodule comes, and stores institute
It states image procossing submodule treated image and determine result；The communication module is for realizing industrial personal computer and external circuit
Communication；The user interface submodule is for providing patterned display interface.
The beneficial effects of the present invention are: the PIN needle position degree of the large size product of sub-pixel precision proposed by the present invention is examined
Survey method drives product mobile, product is divided into several sub-portions by the position of fixed camera and light source using servo-system
Point, and the image of each subdivision is acquired respectively, using the common pixel point having in the image of adjacent subsection, by each subdivision
Image unified image coordinate system, while being created that the new frame of reference, finally by the PIN needle needle point being calculated with
The distance between new benchmark is compared with the tolerance value of setting, to distinguish qualified product and non-qualified product.The present invention abandons
The method for obtaining large size product size using image stitching method can greatly reduce splicing and bring error, processing
Pixel has the function of sub-pix.
In addition, camera of the invention uses area array cameras, the time for obtaining single image is extremely short, is not easy to be disturbed, and energy
It is enough applicable in the camera of different brands, system compatibility is strong, meanwhile, the detection system that the present invention uses has the function of data preservation,
It can be realized the storage of image and data, be convenient for follow-up analysis.
Detailed description of the invention
Fig. 1 is the structural schematic diagram of PIN needle position degree detection device.
Specific embodiment
The technical solution protected below in conjunction with attached drawing to the present invention illustrates.
Please refer to Fig. 1.The PIN needle position degree detection method of the large size product of sub-pixel precision proposed by the present invention, is adopted
It is realized with PIN needle detection system, the PIN needle detection system includes hardware components and software section, and wherein hardware components include
PIN needle detection device and industrial personal computer, software section operate on industrial personal computer, and the industrial personal computer controls the PIN needle detection device
Work, and the image and data of the acquisition of PIN needle detection device are handled, stored and shown.
The PIN needle detection device includes servo-system, light source 12 and camera 11, wherein light source 12 is arranged in servo system
System top, and the camera 11 is arranged above the light source 12, during acquiring image, the servo-system being capable of band
Product to be measured is moved to move in one direction, and the camera 11 and the light source 12 are maintained at same position, so that acquisition every time
The image arrived has the identical pixel in part, ensure that precision；The industrial personal computer can be to camera acquired image at
Reason and operation, therefore, it is determined that whether product to be measured is qualified product.
Specifically, the detection device includes detection support 10, and the camera 11 and the light source 12 are slidably arranged in institute
It states in detection support 10；The servo-system includes detection sliding rail 14 and driving cylinder 15, and the driving cylinder 15 drives described
Positioning fixture 13 slides on the detection sliding rail 14.
Software section is the detection management module being integrated in the industrial personal computer, and the detection management module includes user's pipe
It manages submodule, image acquisition submodule, image procossing submodule, image and saves submodule, communication module and user interface
Module, the user management submodule are used for role between setting operation person and the permission and administrator and operator of administrator
Switching；Described image acquisition submodule is used to receive the image that camera transmission comes, and by image transmitting to described image
Save submodule；Described image handle submodule be used for the received image of described image acquisition submodule carry out image denoising,
Image enhancement, image restoration, image segmentation and feature extraction processing, determine whether product is qualified；Described image saves submodule
Block is used in order store the image that the transmission of described image acquisition submodule comes, and stores described image processing submodule processing
Image and judgement result afterwards；The communication module for realizing industrial personal computer and external circuit communication；User interface
Module is for providing patterned display interface.
Detection method of the invention includes the following steps:
S1. product to be measured is divided into several subdivision A in the longitudinal directioni, and be arranged on product for detecting position
The first datum mark and the second datum mark of degree, wherein the value of i is more than or equal to 1；Adjacent subsection AiBetween have overlapping region
Bi, and the first datum mark on product is located in first subdivision, the second datum mark on product is located at the last one sub-portion
On point；
S2. each subdivision A is successively acquired using PIN needle detection system in orderiImage, be denoted as Pi, and by each subdivision
Image PiIt numbers in order and stores；
S3. using PIN needle detection system to the image P of each subdivisioniIn overlapping region pre-processed, obtain respectively
Each subdivision AiOverlapping region BiLocation information of the interior same pixel point in image coordinate system, and establish unified image
Coordinate system；
S4. using PIN needle detection system to the image P of each subdivisioniIn the region of PIN needle pre-processed, obtain
Each subdivision AiIn each PIN needle location information of the central point in unified image coordinate system；
S5. the location information of the first datum mark and the second datum mark in unified image coordinate system is obtained, is created new
The frame of reference；
S6. it calculates separately the X-axis distance DX of each PIN needle central point and the new frame of reference and is sat with new benchmark
The distance DY of mark system Y-axis, when DX and DY meets the numerical value of setting simultaneously, the position degree of corresponding PIN needle is qualified；Otherwise, right
The position degree for the PIN needle answered is unqualified.
For ease of description, in the present embodiment, product to be measured is divided into three subdivisions, the PIN needle detection system according to
The secondary image for acquiring these three subdivisions, is denoted as three P3 of one P1 of image, two P2 of image and image respectively, below will be to above-mentioned steps
It is described in detail.
Product to be measured is fixed on the positioning fixture of servo-system first, camera and light source is debugged, makes collected figure
As having preferable precision, when the servo-system drives product to move to first position, light source is triggered opening, then camera
The image for collecting the first part of product is denoted as one P1 of image, in the present embodiment, described according to the photo opporunity of setting
Camera uses area array cameras, and the time for obtaining single image is less than 30ms, and is not easy to be disturbed, after the delay of 50ms,
The servo-system drives product to be moved to the second position, collects two P2 of image to the second part of product, postpones 50ms
Afterwards, the servo-system drives product to be moved to the third place, collects three P3 of image, i.e. this hair to the Part III of product
It is bright that large-sized product is divided into three parts, and the image of this three parts is acquired respectively, and guarantees point of three width images of acquisition
Resolution is identical, keeps preferable precision；Simultaneously, it is ensured that there is the region of overlapping, specifically, image on three obtained width images
One has the region that partly overlaps with the collected product section of image two, is denoted as overlapping region B1 and B2, i.e. overlapping region respectively
There is same pixel point, which is denoted as Pa in B1 and overlapping region B2；Similarly, in described image two and image three
With overlapping region, identical pixel is denoted as Pb in the overlapping region of the two.
Then there is image in order in acquired image one, image two and image three to save in submodule, then institute
It states image procossing submodule successively to handle three width images, including image denoising, image enhancement, image restoration and image point
It cuts and feature extraction is handled, obtain the coordinate of the characteristic point for calculating；Specifically, specifically comprise the following steps:
(1) described that just positioning is carried out to product by edge finding method, to overlapping region B1, overlapping region B2, it is overlapped
After region B3 carries out binaryzation, Morphological scale-space, Blob detection is carried out to it, the central point for obtaining corresponding same pixel point exists
Coordinate in the image coordinate system of the image of each subdivision, as coordinate of the Pa in the image coordinate system in one P1 of image is denoted as
(PaX1, PaY1) and its coordinate (PaX2, PaY2) in the image coordinate system in two P2 of image；Meanwhile obtaining two P2 of image
The same pixel point having with three P3 of image respectively the coordinate in the image coordinate system of two P2 of image (PbX1, PbY1) and its
Coordinate (PbX2, PbY2) in the image coordinate system of image three；
(2) variable quantity of the second position relative to first position: DX1=PaX1-PaX2 is calculated；DY1=PaY1-PaY2；
And calculate variable quantity of the third place relative to the second position: DX2=PbX1-PbX2；DY2=PbY1-PbY2；Thus by image
The image coordinate system for being uniformly transformed into one P1 of image of the image coordinate system of three P3 of image coordinate system and image of two P2.
(3) method of (1) and (2) is utilized to obtain in three P3 of one P1 of image, two P2 of image and image in the speck of PIN needle
The coordinate of heart point and the first datum mark and the second datum mark in its correspondence image, creates the new frame of reference；
The process for creating the new frame of reference is as follows:
S51. the coordinate of the first datum mark is denoted as (xs1, ys1), the coordinate of the second datum mark is converted to first son
Coordinate under the image coordinate system of partial image is denoted as (xs2, ys2)；
S52. the second datum mark is obtained into third datum mark, coordinate is denoted as relative to the first datum mark rotation alpha angle
(xs3, ys3), wherein
Xs3=(xs2-xs1) * cos α-(ys2-ys1) * sin α+xs1；
Ys3=(ys2-ys1) * cos α+(xs2-xs1) * sin α+ys1；
It S53. will be simultaneously by the straight line of the first datum mark and third datum mark as the X-axis of the new frame of reference；
S54. the second datum mark is obtained into the 4th datum mark, coordinate is denoted as relative to the first datum mark rotation β angle
(xs4, ys4), wherein
Xs4=(xs2-xs1) * cos β-(ys2-ys1) * sin β+xs1；
Ys4=(ys2-ys1) * cos β+(xs2-xs1) * sin β+ys1；
It S55. will be simultaneously by the straight line of the first datum mark and the 4th datum mark as the Y-axis of the new frame of reference；
Wherein, α is equal to 29.1 °, and β is equal to 119.1 °.
Finally, image procossing submodule handles one P1 of image, two P2 of image and three P3 of image, each PIN needle is calculated
Distance DX and each PIN needle point distance relative to new frame of reference Y-axis of the point relative to the X-axis of the new frame of reference
The value of DX and DY is compared by DY with the tolerance value of setting, when the value of DX and DY tolerance allow range when, be determined as
Otherwise qualification is judged as unqualified, the user interface submodule display result.
The image and data generated in images above acquisition and image processing process is all stored in image and saves submodule
It is interior, it is used convenient for subsequent tracing problem.
The above description is only an embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (9)
1. the PIN needle position degree detection method of the large size product of sub-pixel precision, which comprises the steps of:
S1. product to be measured is divided into several subdivision A in the longitudinal directioni, and be arranged on product for detecting position degree the
One datum mark and the second datum mark, wherein the value of i is more than or equal to 1；Adjacent subsection AiBetween have overlapping region Bi, and produce
The first datum mark on product is located in first subdivision, and the second datum mark on product is located in the last one subdivision；
S2. each subdivision A is successively acquired using PIN needle detection system in orderiImage, be denoted as Pi, and by the figure of each subdivision
As PiIt numbers in order and stores；
S3. using PIN needle detection system to the image P of each subdivisioniIn overlapping region pre-processed, obtain each son respectively
Part AiOverlapping region BiLocation information of the interior same pixel point in image coordinate system, and establish unified image coordinate
System；
S4. using PIN needle detection system to the image P of each subdivisioniIn the region of PIN needle pre-processed, obtain each sub-portion
Divide AiIn each PIN needle location information of the central point in unified image coordinate system；
S5. the location information of the first datum mark and the second datum mark in unified image coordinate system is obtained, new benchmark is created
Coordinate system；
S6. calculate separately each PIN needle central point and the new frame of reference X-axis distance DX and with the new frame of reference
The distance DY of Y-axis, when DX and DY meets the numerical value of setting simultaneously, the position degree of corresponding PIN needle is qualified；Otherwise, corresponding
The position degree of PIN needle is unqualified；
Wherein, the PIN needle detection system includes PIN needle detection device and industrial personal computer, and the PIN needle detection device includes phase
Machine, light source and servo-system；Product to be measured is fixed on the positioning fixture of servo-system, and the light source is arranged in the servo
Above system, the camera is arranged above the light source；Acquiring each subdivision AiImage during, keep camera and
The position of light source is constant, and the servo-system drives product to be measured to move along first direction；The industrial personal computer and the camera connect
It connects, for reading the image of the camera acquisition to be handled image and be calculated.
2. the PIN needle position degree detection method of the large size product of sub-pixel precision according to claim 1, feature exist
In S2 includes following sub-step:
S21. product to be measured is fixed on the positioning fixture of the servo-system；
S22. camera and light source are debugged, servo-system drives product to be measured to be successively moved at preset each position, the phase
Machine synchronous acquisition image respectively obtains the image B of each subdivisioni；
S23. by the image P of each subdivisioniIt is stored in sequence in the industrial personal computer.
3. the PIN needle position degree detection method of the large size product of sub-pixel precision according to claim 1, feature exist
Include: in, the step of unified image coordinate system is established in S3
S31. just positioning is carried out to product by edge finding method, to the overlapping region B of each subdivisioniCarry out binaryzation, form
After processing, Blob detection is carried out to it, obtains coordinate of the central point of same pixel point in corresponding overlapping region；
S32. according to S31 obtain as a result, calculating the image P of each subdivisioniImage coordinate system relative to its latter subdivision
Image Pi+1The corresponding image coordinate system of the image of each subdivision is transformed into first sub-portion by the variable quantity of image coordinate system
The image coordinate system of the image divided.
4. the PIN needle position degree detection method of the large size product of sub-pixel precision according to claim 3, feature exist
In the calculating process of S32 is as follows:
S321. the image of j-th of subdivision is set as Pj, the image of two subdivisions thereafter is denoted as P respectivelyj+1, Pj+2, j-th of son
Partial image PjWith the image P of (j+1) a subdivisionj+1Same pixel be denoted as Pa, the image of (j+1) a subdivision
Be denoted as Pb with the pixel pixel of the image of (j+2) a subdivision, Pa coordinate in j-th of sub-portion partial image be denoted as (PaX1,
PaY1), the coordinate in the image of (j+1) a subdivision is denoted as (PaX2, PaY2)；Pb is in (j+1) a sub- parts of images
Middle coordinate is denoted as (PbX1, PbY1), and the coordinate in the image of (j+2) a subdivision is denoted as (PbX2, PbY2)；
S322. image coordinate system of the coordinate system of the image of calculating (j+1) a subdivision relative to the image of j-th of subdivision
Variable quantity, be denoted as DX1=PaX1-PaX2；DY1=PaY1-PaY2；Calculate the image coordinate of the image of+1 subdivision of jth
The variable quantity of system and the image coordinate system of the image of+2 subdivisions of jth, is denoted as DX2=PbX1-PbX2；DY2=PbY1-
PbY2；
S323. according to the calculated result of S322, the image coordinate system of the image of (j+1) a subdivision and (j+2) is a
The image coordinate system of the image of subdivision is converted to the image coordinate system of the image of (j) a subdivision；
S324, the image of remaining subdivision is calculated according to S321 to the step of S323, establishes unified image coordinate
System.
5. the PIN needle position degree detection method of the large size product of sub-pixel precision according to claim 3, feature exist
In obtaining each subdivision A in S4iIn each PIN needle location information of the central point in unified image coordinate system, including such as
Lower step:
S41. by edge finding method to product carry out just positioning, in the image of each subdivision include PIN needle region into
After row binaryzation, Morphological scale-space, Blob detection is carried out to it, obtains image of the central point in each subdivision of PIN needle speck
Image coordinate system in coordinate；
S42. by the coordinate of the central point of the speck of the PIN needle in the image of each subdivision in addition to the image of first subdivision
It is converted into the image coordinate system of the image of first subdivision.
6. the PIN needle position degree detection method of the large size product of sub-pixel precision according to claim 1, feature exist
In the step of creating the new frame of reference in S5 is as follows:
S51. the coordinate of the first datum mark is denoted as (xs1, ys1), the coordinate of the second datum mark is converted to first subdivision
Image image coordinate system under coordinate be denoted as (xs2, ys2)；
S52. by the second datum mark relative to the first datum mark rotation alpha angle, obtain third datum mark, coordinate be denoted as (xs3,
Ys3), wherein
Xs3=(xs2-xs1) * cos α-(ys2-ys1) * sin α+xs1；
Ys3=(ys2-ys1) * cos α+(xs2-xs1) * sin α+ys1；
It S53. will be simultaneously by the straight line of the first datum mark and third datum mark as the X-axis of the new frame of reference；
S54. by the second datum mark relative to the first datum mark rotation β angle, obtain the 4th datum mark, coordinate be denoted as (xs4,
Ys4), wherein
Xs4=(xs2-xs1) * cos β-(ys2-ys1) * sin β+xs1；
Ys4=(ys2-ys1) * cos β+(xs2-xs1) * sin β+ys1；
It S55. will be simultaneously by the straight line of the first datum mark and the 4th datum mark as the Y-axis of the new frame of reference；
Wherein, α is equal to 29.1 °, and β is equal to 119.1 °.
7. the PIN needle position degree detection method of the large size product of sub-pixel precision according to claim 1, feature exist
In the PIN needle detection device includes detection support, and the camera and the light source are slidably arranged in the detection support；
The servo-system includes detection sliding rail and driving cylinder, and the driving cylinder drives the positioning fixture in the detection sliding rail
Upper sliding.
8. the PIN needle position degree detection method of the large size product of sub-pixel precision according to claim 7, feature exist
In the camera is area array cameras.
9. the PIN needle position degree detection method of the large size product of sub-pixel precision according to claim 1, feature exist
In the PIN needle detection system further includes the detection management module being integrated in the industrial personal computer, the detection management module packet
It includes user management submodule, image acquisition submodule, image procossing submodule, image and saves submodule, communication module and use
Family interface submodule, permission and administrator and operator of the user management submodule for setting operation person and administrator
Between role switching；Described image acquisition submodule is used to receive the image that the camera transmission comes, and extremely by image transmitting
Described image saves submodule；Described image processing submodule is for carrying out figure to the received image of described image acquisition submodule
As denoising, image enhancement, image restoration, image segmentation and feature extraction processing, determine whether product is qualified；Described image is protected
It deposits image of the submodule for carrying out the transmission of described image acquisition submodule to store in order, and stores described image processing submodule
Block treated image and determine result；The communication module for realizing industrial personal computer and external circuit communication；The user
Interface submodule is for providing patterned display interface.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910317864.9A CN110068271B (en) | 2019-04-19 | 2019-04-19 | PIN needle position degree detection method for large-size product with sub-pixel precision |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910317864.9A CN110068271B (en) | 2019-04-19 | 2019-04-19 | PIN needle position degree detection method for large-size product with sub-pixel precision |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110068271A true CN110068271A (en) | 2019-07-30 |
| CN110068271B CN110068271B (en) | 2021-03-30 |
Family
ID=67368050
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910317864.9A Active CN110068271B (en) | 2019-04-19 | 2019-04-19 | PIN needle position degree detection method for large-size product with sub-pixel precision |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110068271B (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111145247A (en) * | 2019-12-18 | 2020-05-12 | 配天机器人技术有限公司 | Vision-based position detection method, robot and computer storage medium |
| CN112577428A (en) * | 2020-12-10 | 2021-03-30 | 苏州凌创电子系统有限公司 | Visual detection equipment based on detection of position degree of servo turntable type PIN needle |
| CN114299026A (en) * | 2021-12-29 | 2022-04-08 | 广东利元亨智能装备股份有限公司 | Detection method, detection device, electronic equipment and readable storage medium |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11132745A (en) * | 1997-11-04 | 1999-05-21 | Nec Corp | Lead bending inspection device |
| CN104483331A (en) * | 2014-12-03 | 2015-04-01 | 东莞市神州视觉科技有限公司 | A three-dimensional detection method, device and system for connector pins |
| CN204705323U (en) * | 2015-07-01 | 2015-10-14 | 江南大学 | A kind of car body controller connector pin normotopia degree pick-up unit |
| CN105678720A (en) * | 2014-11-20 | 2016-06-15 | 深圳英飞拓科技股份有限公司 | Image matching judging method and image matching judging device for panoramic stitching |
| CN106500593A (en) * | 2016-10-31 | 2017-03-15 | 哈尔滨工业大学 | Aviation electric connector contact pin position deviation detection method |
| CN106683043A (en) * | 2015-11-10 | 2017-05-17 | 中国航天科工集团第四研究院指挥自动化技术研发与应用中心 | Parallel image stitching method and device for multi-channel optical detection system |
| CN107478164A (en) * | 2017-08-01 | 2017-12-15 | 成都尊华荣域科技有限公司 | A kind of bonder terminal detection means based on machine vision |
-
2019
- 2019-04-19 CN CN201910317864.9A patent/CN110068271B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11132745A (en) * | 1997-11-04 | 1999-05-21 | Nec Corp | Lead bending inspection device |
| CN105678720A (en) * | 2014-11-20 | 2016-06-15 | 深圳英飞拓科技股份有限公司 | Image matching judging method and image matching judging device for panoramic stitching |
| CN104483331A (en) * | 2014-12-03 | 2015-04-01 | 东莞市神州视觉科技有限公司 | A three-dimensional detection method, device and system for connector pins |
| CN204705323U (en) * | 2015-07-01 | 2015-10-14 | 江南大学 | A kind of car body controller connector pin normotopia degree pick-up unit |
| CN106683043A (en) * | 2015-11-10 | 2017-05-17 | 中国航天科工集团第四研究院指挥自动化技术研发与应用中心 | Parallel image stitching method and device for multi-channel optical detection system |
| CN106500593A (en) * | 2016-10-31 | 2017-03-15 | 哈尔滨工业大学 | Aviation electric connector contact pin position deviation detection method |
| CN107478164A (en) * | 2017-08-01 | 2017-12-15 | 成都尊华荣域科技有限公司 | A kind of bonder terminal detection means based on machine vision |
Non-Patent Citations (1)
| Title |
|---|
| 《兰州大学学报（自然科学版）》: "基于Blob分析的芯片管脚检测方法", 《兰州大学学报（自然科学版）》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111145247A (en) * | 2019-12-18 | 2020-05-12 | 配天机器人技术有限公司 | Vision-based position detection method, robot and computer storage medium |
| CN111145247B (en) * | 2019-12-18 | 2023-07-07 | 配天机器人技术有限公司 | Position degree detection method based on vision, robot and computer storage medium |
| CN112577428A (en) * | 2020-12-10 | 2021-03-30 | 苏州凌创电子系统有限公司 | Visual detection equipment based on detection of position degree of servo turntable type PIN needle |
| CN112577428B (en) * | 2020-12-10 | 2022-05-03 | 苏州凌创电子系统有限公司 | Visual detection equipment based on detection of position degree of servo turntable type PIN needle |
| CN114299026A (en) * | 2021-12-29 | 2022-04-08 | 广东利元亨智能装备股份有限公司 | Detection method, detection device, electronic equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110068271B (en) | 2021-03-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Herráez et al. | 3D modeling by means of videogrammetry and laser scanners for reverse engineering | |
| JP3545558B2 (en) | Method for determining wafer measurement position | |
| DE112014005911T5 (en) | Three-dimensional coordinate scanner and operating procedures | |
| CN110068271A (en) | The PIN needle position degree detection method of the large size product of sub-pixel precision | |
| US8233665B2 (en) | Image measuring apparatus and computer program | |
| KR101638173B1 (en) | Method and apparatus for providing automated detection of calibration | |
| Mi et al. | A vision-based displacement measurement system for foundation pit | |
| KR19990036608A (en) | How to Create Wafer Measurement Information and How to Position Measurement | |
| CN114220757B (en) | Wafer detection alignment method, device and system and computer medium | |
| DE112014001459T5 (en) | Three-dimensional coordinate scanner and operating procedures | |
| CN106705847A (en) | Geometric size measuring method and device for slit inside free-form surface | |
| CN107931012A (en) | A kind of method and dispenser system for extracting dispensing path | |
| JP2018507407A (en) | Image-based tray alignment and tube slot positioning in vision systems | |
| CN109000583B (en) | System and method for efficient surface measurement using laser displacement sensors | |
| CN111707187B (en) | Method and system for measuring large parts | |
| US11562478B2 (en) | Method and system for testing field of view | |
| JPH11118444A (en) | Non-contact image measuring system | |
| KR101670270B1 (en) | System and method for locating fiducials with known shape | |
| CN105423975B (en) | The calibration system and method for a kind of large-scale workpiece | |
| CN113313756B (en) | Camera and laser composite guiding dispensing compensation method and related device | |
| CN110163056B (en) | Intelligent Visual Recognition Vehicle Board Cable Reel Center Coordinate System | |
| Dold | The role of a digital intelligent camera in automating industrial photogrammetry | |
| US20150287177A1 (en) | Image measuring device | |
| CN106645168A (en) | Detection method for surface concave-convex defect of boom cylinder of crane | |
| CN109406545A (en) | A kind of circuit board measuring point automatic station-keeping system based on machine vision |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address | ||
| CP03 | Change of name, title or address |
Address after: Building 4, No. 280, 10th Street, Baiyang Street, Qiantang District, Hangzhou City, Zhejiang Province, 310000 Patentee after: Yinawei (Hangzhou) Intelligent Technology Co.,Ltd. Country or region after: China Address before: 310018 No. 280, No. 10, Hangzhou economic and Technological Development Zone, Zhejiang Patentee before: INTERPLEX ELECTRONIC (HANGZHOU) CO.,LTD. Country or region before: China |