CN104867141B - A kind of non-woven bag automatic positioning method in continuous production - Google Patents
A kind of non-woven bag automatic positioning method in continuous production Download PDFInfo
- Publication number
- CN104867141B CN104867141B CN201510244887.3A CN201510244887A CN104867141B CN 104867141 B CN104867141 B CN 104867141B CN 201510244887 A CN201510244887 A CN 201510244887A CN 104867141 B CN104867141 B CN 104867141B
- Authority
- CN
- China
- Prior art keywords
- line
- woven bag
- point
- realtime graphic
- formula
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0004—Industrial image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/70—Determining position or orientation of objects or cameras
- G06T7/73—Determining position or orientation of objects or cameras using feature-based methods
- G06T7/74—Determining position or orientation of objects or cameras using feature-based methods involving reference images or patches
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30108—Industrial image inspection
- G06T2207/30124—Fabrics; Textile; Paper
Abstract
A kind of non-woven bag automatic positioning method in continuous production passes through the realtime graphic that line-scan digital camera obtains non-woven bag on assembly line first；Then binaryzation operation is carried out according to the threshold value of setting, judging whether there is non-woven bag with the method for statistical pixel point arrives；If non-woven bag arrives, according to the inflection point of pixel statistical series, the position moment q of front end of line is judged；To q+k hereafter1、q+k2The acquisition image at moment carries out lateral first derivative operation respectively, and the left side maximum value position point of acquisition, the point being set as on left end line, the right side maximum value position point of acquisition, the point being set as on right end line；The angle of non-woven bag and flowing water bobbin thread is finally calculated according to the point on left end line and right end line.Calculating speed of the present invention is fast, intelligence degree is high, accurate positioning.
Description
Technical field
That the present invention relates to automatic measurement and control fields more particularly to a kind of non-woven bag in continuous production is real-time,
Automatic positioning method.
Background technology
With the enhancing of people's environmental consciousness, the demand of non-woven bag is more and more.But in existing flow line production mistake
Cheng Zhong, due to the feature of non-woven bag flexibility, it is difficult to machinery mode be accurately positioned, cause its printing and dyeing, paste and
A large amount of artificial progress auxiliary positioning is needed in the production processes such as bonding, not only production efficiency is low, and considerably increases people
Power cost cannot be satisfied quick, high-quality production.Therefore, a kind of fast and accurately non-woven bag of development is automatically positioned
Method is the active demand of current manufacturing enterprise.
With the development of image processing and artificial intelligence technology, the product based on computer vision detects and determines automatically
Position method is gradually developed and applies so that being become by the location information of Computer Image Processing acquisition non-woven bag can
Energy.
Invention content
The quick positioning question that the invention solves non-woven bags in flow line production is provided in a kind of continuous production
Non-woven bag automatic positioning method, this method quickly and accurately can realize automatic positioning to the non-woven bag in continuous production.
To achieve the above object, the present invention uses following technical scheme：
A kind of non-woven bag automatic positioning method in continuous production, comprises the following steps：
Step 1 obtains realtime graphic G from line-scan digital camera；
Step 2 calculates the image of acquisition, to judge whether there is non-woven bag arrival；Steps are as follows for calculating：
Step 2.1 is to image binaryzation, calculation formula：
I is the abscissa of image, and j is the ordinate of image；
X is image pixel, Gij(x) value of realtime graphic x pixels at coordinate (i, j) is indicated；
Wherein 0≤i < W, W are the transverse width of line-scan digital camera；
The line number that 0≤j < H, H are sampled every time for line-scan digital camera, generally 1 or 2；
T is the binary-state threshold of setting；
Step 2.2 counts the number of pixels of binary image, and calculation formula is：
TT is, according to the non-woven bag parameter that lateral proportion is arranged in vision imaging, generally no greater than image is wide
The a quarter of degree, if N1>=TT then determines whether the arrival of woven fabric bag；Otherwise return to step one；
Step 3 obtains subsequent realtime graphic, and according to the computational methods of step 2, obtains corresponding number of pixels successively
Sequence N1, N3,……,Nn；
The parameter that wherein n is arranged for the non-woven bag deviation angle according to permission, sampling interval；
Step 4, sequence of calculation N1, N3,……,NnInflection point, and the detection time at inflection point is set as non-woven bag
The detection moment of front end of line, calculation formula are：
S=Max (2Ni-Ni-1-Ni+1|1<i<n)
Then the corresponding detection times of inflection point S are the detection moment of non-woven bag front end of line, are denoted as q；
Step 5, according to the movement velocity of assembly line, setting delay moment k1, and obtain q+k1The realtime graphic at moment is used
To find 2 points on the end line of left and right；Calculating process is：
Step 5.1 calculates the lateral first derivative of image, and formula is
Step 5.2 seeks the point L on left end line1, formula is
Step 5.3 seeks the point R on right end line1, formula is
Step 6, according to the movement velocity of assembly line, setting delay moment k2, and obtain q+k2The realtime graphic at moment, seeks
2 points on the end line of left and right, calculating process are looked for be：
Step 6.1 calculates the lateral first derivative of image, and formula is
Step 6.2 seeks the point L on left end line2, formula is
Step 6.3 seeks the point R on right end line2, formula is
Step 7, calculates the deflection angle θ of non-woven bag, and formula is：
What although line-scan digital camera obtained is also two dimensional image, but height only has several pixels.Generally coordinate with encoder,
This camera is used in the case of following two：One, image is continuously acquired.Two, image processing speed is required very high.
The present invention samples assembly line using line-scan digital camera, by the calculating to realtime graphic, obtain front end of line,
Deviation angle of the position and non-woven bag of left end line and right end line relative to flowing water bobbin thread can obtain specific accordingly
The position that process needs.This method can reach 80 per second or more positioning under the auxiliary of high-speed industrial line-scan digital camera
Effect, and position positioning accuracy in 1mm hereinafter, calculation amount is small.
The realtime graphic of non-woven bag is obtained by line-scan digital camera first；Then binaryzation fortune is carried out according to the threshold value of setting
It calculates, judging whether there is non-woven bag with the method for statistical pixel point arrives；If there is non-woven bag arrival, counted according to pixel
The inflection point of sequence judges the position moment q of front end of line；To q+k hereafter1、q+k2The acquisition image at moment carries out horizontal respectively
To first derivative operation, and the left side maximum value position point of acquisition, the point being set as on left end line, the right side maximum of acquisition
It is worth location point, the point being set as on right end line；Non-woven bag and flowing water are finally calculated according to the point on left end line and right end line
The angle of bobbin thread.
The present invention can be realized by C language, C Plus Plus programming, can also be programmed and be realized by Java language.
The present invention can be embedded into the real-time control system of non-woven bag automated production as independent algoritic module,
The control to equipment such as handling machinery arm, dyeing apparatus, stickup and bondings is realized by location information, and it is fast to reach non-woven bag
Speed, the purpose of automated production.
Calculating speed of the present invention is fast, intelligence degree is high, accurate positioning, and the size of locating effect and non-woven bag without
It closes, the location Calculation to different size of non-woven bag may be implemented.
Description of the drawings
Fig. 1 is the work flow diagram of the present invention.
Fig. 2 is the operating diagram of the present invention.
Fig. 3 is the operating diagram for detecting non-woven bag arrival previous moment.
Fig. 4 is the operating diagram for detecting non-woven bag arrival current time.
Fig. 5 is to detect k after non-woven bag arrival1The operating diagram at moment.
Fig. 6 is to detect k after non-woven bag arrival2The operating diagram at moment.
In figure label for：1 non-woven bag, the location point L of 2 left end lines1, the position L of 3 left end lines2, 4 front end line positions, 5 is right
End line position R1, 6 right end line position R2, 7 production lines, 8 be line-scan digital camera imaging region.
Specific implementation mode
With reference to attached drawing, the non-woven bag automatic positioning method in a kind of continuous production comprises the following steps：
Step 1 obtains real-time gray level image G from line-scan digital camera, and size is 800 × 2, and width is 800 pixels, height
For 2 pixels；
Step 2 calculates the image of acquisition, to judge whether there is non-woven bag arrival；Steps are as follows for calculating：
Step 2.1 sets binary-state threshold as 100, calculates image binaryzation, and formula is：
I is the abscissa of image, and j is the ordinate of image；
X is image pixel, Gij(x) value of realtime graphic x pixels at coordinate (i, j) is indicated；
Wherein 0≤i 8000≤j of < < 2；
Step 2.2 counts the number of pixels of binary image, and calculation formula is：
If judging that the threshold value that non-woven bag arrives is set as 150, i.e., according to non-woven bag in vision imaging lateral institute's accounting
Example and be arranged parameter be 150, according to above formula, acquire N1=180, N1More than 150, therefore it is determined with the arrival of non-woven bag；
Step 3 obtains successively if the parameter n being arranged according to non-woven bag deviation angle, the sampling interval of permission is 50
50 subsequent realtime graphics are taken, and according to the computational methods of step 2, obtain corresponding number of pixels sequence 160,170 ...,
400；
Step 4, calculates the inflection point for the sequence that step 3 obtains, and the detection time at inflection point is set as non-woven bag
The detection moment of front end of line, calculation formula are：
S=Max (2Ni-Ni-1-Ni+1|1<i<50)
The detection moment i of the inflection point S acquired is 30, then it is 30 to acquire front end of line detection moment；
Step 5, according to the movement velocity of assembly line, if delay moment k1It is 10, then obtains the real-time figure at 30+10 moment
Picture, to find 2 points on the end line of left and right, calculating process is：
Step 5.1 calculates the lateral first derivative of image, and formula is
D40 i,j(x)=| G40 i+1,j(x)-G40 i,j(x)|,0≤i<799,0≤j<2
Step 5.2 seeks the point L on left end line1, formula is
If result of calculation is：DL1It is 8000, L1It is 80；
Step 5.3 seeks the point R on right end line1, formula is
If result of calculation is：DR1It is 8100, R1It is 720；
Step 6, according to the movement velocity of assembly line, if delay moment k2It is 60, then obtains the real-time figure at 30+60 moment
Picture, to find 2 points on the end line of left and right, calculating process is：
Step 6.1 calculates the lateral first derivative of image, and formula is
D90 i,j(x)=| D90 i+1,j(x)-D90 i,j(x)|,0≤i<799,0≤j<2
Step 6.2 seeks the point L on left end line2, formula is
If result of calculation is：DL2It is 7900, L1It is 60；
Step 6.3 seeks the point R on right end line2, formula is
If result of calculation is：DR2It is 8300, R2It is 700；
Step 7, calculates the deflection angle θ of non-woven bag, and formula is：
The final front end line position for obtaining non-woven bag is 30, and the position that 2 points of left end line is 80,60,2 points of right end line
Position is 720,700, and non-woven fabrics deflection angle is 21.8 °.
Claims (1)
1. the non-woven bag automatic positioning method in a kind of continuous production, comprises the following steps：
Step 1 obtains realtime graphic G from line-scan digital camera；
Step 2 calculates the image of acquisition, to judge whether there is non-woven bag arrival；Steps are as follows for calculating：
2.1 pairs of image binaryzations, calculation formula are：
I is the abscissa of image, and j is the ordinate of image, and x is image pixel；Gi,j(x) indicate realtime graphic at coordinate (i, j)
Locate the value of x pixels；
0≤i < W, W are the transverse width of line-scan digital camera；
0≤j < H, H are the line number that line-scan digital camera samples every time, are 1 or 2；
T is the binary-state threshold of setting；
The number of pixels of 2.2 statistics binary images, calculation formula are：
If N1>=TT then determines whether the arrival of woven fabric bag, and TT is lateral proportion is set in vision imaging according to non-woven bag
The parameter set is not more than a quarter of the realtime graphic width；Otherwise return to step one；
Step 3 obtains subsequent realtime graphic, and according to the computational methods of step 2, obtains corresponding number of pixels sequence successively
N2,N3,…,Nn, wherein n for according to allow non-woven bag deviation angle, the parameter that is arranged of sampling interval；
Step 4, sequence of calculation N1,N2,…,NnInflection point, and the detection time at inflection point is set as non-woven bag front end of line
Detection moment, calculation formula is：
S=Max (2Nt-Nt-1-Nt+1| 1 < t < n)
Then the corresponding location point of S points is the detection moment of non-woven bag front end of line, is denoted as q；
Step 5, according to the movement velocity of realtime graphic, setting delay moment k1, and obtain q+k1The realtime graphic at moment is found
The point on left and right two outer contours of non-woven fabrics in the realtime graphic, calculating process are：
5.1 calculate the lateral first derivative of realtime graphic, and formula is
5.2 seek the point L on left end line1, formula is
5.3 seek the point R on right end line1, formula is
Step 6, according to the movement velocity of assembly line, setting delay moment k2, and obtain q+k2The realtime graphic at moment, finding should
The point on left and right two outer contours of non-woven fabrics in realtime graphic, calculating process are：
6.1 calculate the lateral first derivative of realtime graphic, and formula is
6.2 seek the point L on left end line2, formula is
6.3 seek the point R on right end line2, formula is
Step 7, calculates the deflection angle θ of non-woven bag, and formula is：
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510244887.3A CN104867141B (en) | 2015-05-14 | 2015-05-14 | A kind of non-woven bag automatic positioning method in continuous production |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510244887.3A CN104867141B (en) | 2015-05-14 | 2015-05-14 | A kind of non-woven bag automatic positioning method in continuous production |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104867141A CN104867141A (en) | 2015-08-26 |
| CN104867141B true CN104867141B (en) | 2018-11-09 |
Family
ID=53912956
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510244887.3A Active CN104867141B (en) | 2015-05-14 | 2015-05-14 | A kind of non-woven bag automatic positioning method in continuous production |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104867141B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2468044Y (en) * | 2000-11-15 | 2001-12-26 | 上海印钞厂 | Printing quality on-line investigating apparatus for Renminbi (RMB) |
| WO2012002335A1 (en) * | 2010-06-30 | 2012-01-05 | 株式会社オプトエレクトロニクス | Decoding method and decoding processing device |
| CN102615052A (en) * | 2012-02-21 | 2012-08-01 | 上海大学 | Machine visual identification method for sorting products with corner point characteristics |
| CN104001676A (en) * | 2014-05-04 | 2014-08-27 | 广东都市丽人实业有限公司 | Automatic sorting method and production line for large-scale multi-variety mixed-match underwear |
-
2015
- 2015-05-14 CN CN201510244887.3A patent/CN104867141B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN2468044Y (en) * | 2000-11-15 | 2001-12-26 | 上海印钞厂 | Printing quality on-line investigating apparatus for Renminbi (RMB) |
| WO2012002335A1 (en) * | 2010-06-30 | 2012-01-05 | 株式会社オプトエレクトロニクス | Decoding method and decoding processing device |
| CN102615052A (en) * | 2012-02-21 | 2012-08-01 | 上海大学 | Machine visual identification method for sorting products with corner point characteristics |
| CN104001676A (en) * | 2014-05-04 | 2014-08-27 | 广东都市丽人实业有限公司 | Automatic sorting method and production line for large-scale multi-variety mixed-match underwear |
Non-Patent Citations (2)
| Title |
|---|
| SPARTAN Project: Efficient Implementation of Computer Vision Algorithms onto Reconfigurable Platform Targeting to Space Applications;K. Siozios 等;《Reconfigurable Communication-centric Systems-on-Chip（ReCoSoC），2011 6th International Workshop on》;20110620;第1-8页 * |
| 一种码垛视觉系统中物料袋的识别与定位方法;陈州尧 等;《制造业自动化》;20150228;第37卷(第2期);第47-49页、第59页 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104867141A (en) | 2015-08-26 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104282020B (en) | A kind of vehicle speed detection method based on target trajectory | |
| CN108827316B (en) | Mobile robot visual positioning method based on improved Apriltag | |
| CN105069799B (en) | Angular point positioning method and apparatus | |
| CN109969736B (en) | Intelligent detection method for deviation fault of large carrying belt | |
| CN106446894B (en) | A method of based on outline identification ball-type target object location | |
| CN107992881A (en) | A kind of Robotic Dynamic grasping means and system | |
| CN104217441A (en) | Mechanical arm positioning fetching method based on machine vision | |
| CN105404874B (en) | A kind of vehicle window identifying system based on projection and hough straight-line detections | |
| CN108090434B (en) | Rapid ore identification method | |
| CN105718964B (en) | A kind of visible detection method of power transmission line damper | |
| CN110991360B (en) | Robot inspection point position intelligent configuration method based on visual algorithm | |
| CN108921819A (en) | A kind of cloth examination device and method based on machine vision | |
| CN110782436A (en) | Conveyor belt material state detection method based on computer vision | |
| CN110287907A (en) | A kind of method for checking object and device | |
| CN110880184A (en) | Method and device for carrying out automatic camera inspection based on optical flow field | |
| CN113822810A (en) | Method for positioning workpiece in three-dimensional space based on machine vision | |
| CN114581760B (en) | Equipment fault detection method and system for machine room inspection | |
| CN103699876A (en) | Method and device for identifying vehicle number based on linear array CCD (Charge Coupled Device) images | |
| CN104835156B (en) | A kind of non-woven bag automatic positioning method based on computer vision | |
| CN109583306B (en) | Bobbin residual yarn detection method based on machine vision | |
| Xia et al. | Moving targets detection algorithm based on background subtraction and frames subtraction | |
| Xiaohu et al. | Research on steel bar detection and counting method based on contours | |
| CN104867141B (en) | A kind of non-woven bag automatic positioning method in continuous production | |
| CN110675393B (en) | Blank specification detection method based on machine vision | |
| CN114581447B (en) | Conveying belt deviation identification method and device based on machine vision |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |