CN101510295A - Design method for machine vision system based on PCIe and Vision Assistan - Google Patents
Design method for machine vision system based on PCIe and Vision Assistan Download PDFInfo
- Publication number
- CN101510295A CN101510295A CNA2009100261405A CN200910026140A CN101510295A CN 101510295 A CN101510295 A CN 101510295A CN A2009100261405 A CNA2009100261405 A CN A2009100261405A CN 200910026140 A CN200910026140 A CN 200910026140A CN 101510295 A CN101510295 A CN 101510295A
- Authority
- CN
- China
- Prior art keywords
- image
- vision
- pcie
- image processing
- pcie bus
- 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
- 230000004438 eyesight Effects 0.000 title claims abstract description 51
- 238000000034 method Methods 0.000 title claims abstract description 28
- 238000013461 design Methods 0.000 title description 3
- 238000012545 processing Methods 0.000 claims abstract description 23
- 238000001514 detection method Methods 0.000 claims abstract description 10
- 238000003708 edge detection Methods 0.000 claims abstract description 7
- 238000007689 inspection Methods 0.000 claims description 17
- 238000012937 correction Methods 0.000 claims description 6
- 238000003706 image smoothing Methods 0.000 claims description 4
- 238000007781 pre-processing Methods 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 description 7
- 238000004458 analytical method Methods 0.000 description 4
- 238000006243 chemical reaction Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 4
- 230000018109 developmental process Effects 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 238000011160 research Methods 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000003709 image segmentation Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000003801 milling Methods 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 238000012935 Averaging Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 230000001143 conditioned effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000006866 deterioration Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 238000010191 image analysis Methods 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000013441 quality evaluation Methods 0.000 description 1
- 230000005855 radiation Effects 0.000 description 1
- 238000011084 recovery Methods 0.000 description 1
- 230000008054 signal transmission Effects 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Landscapes
- Image Processing (AREA)
Abstract
The invention relates to a designing method of a machine vision system based on PCIe and Vision Assistant. A hardware part comprises an industrial camera, an LED line shaped light source, an image grabbing card, a PCIe bus image processing module, a digital controller and an input/output board, wherein the industrial camera and the LED line shaped light source form a detection device, the LED line shaped light source irradiates on the industrial camera to collect image data which is transmitted to the PCIe bus image processing module by the image collecting card which conforms to PCIe bus standards, the PCIe bus image processing module is installed in an industrial computer, and the result processed by the PCIe bus image processing module is transmitted to the digital controller for carrying out control decision, and a control signal obtained is transmitted to an execution structure by the input/output board; and a Vision Assistant image processing software provides image preprocessing, edge detection and pattern matching. By adopting PCIe bus structure and Vision Assistant process measures, the universality, applicability and reconfigurability of the system are greatly improved, and the throughput bottleneck problem of I/O data of the computer is solved.
Description
Technical field
The present invention relates to a kind of method for designing of the Vision Builder for Automated Inspection based on PCIe bus structure and Vision Assistant image processing software, belong to the machine vision technique field.
Background technology
To be research simulate biological outer showing or the Science and Technology of macroscopical visual performance with computing machine to machine vision, with creation of image and recovery real world model, finally being used for actual detected, measurement and control, is a cross discipline that relates to a plurality of fields such as artificial intelligence, Neurobiology, psychophysics, computer science, Image Processing and Pattern Recognition.
Vision Builder for Automated Inspection generally is made up of video camera, image pick-up card, computing machine, light source etc.Principle of work is: under certain illumination condition, with video camera the target image that is ingested of three-dimensional scenic is collected computer-internal formation original image; Then, the utilization image processing techniques is carried out pre-service to improve picture quality to original image, and partition graph extracts characteristic element, constitutes the description to image; At last, adopt mode identification technology to carry out tagsort, and according to pre-conditioned output result.
Machine vision has with the object that is observed contactless, and to the subject not damaged, observation process is objective, differentiates the high characteristics of result reliability; Simultaneously machine vision has been widened the human vision scope, many human visions can't perception occasion, as the perception of high-risk scene under the industrial environment etc., machine vision has more advantage; And machine vision can obtain bulk information fast, and is easy to automatic processing, also is easy to realize information integration, is the basic technology that realizes computer integrated manufacturing system.
Machine vision is a quite new and development research field very rapidly, and becomes one of important research field in computer science.The identification since the 1950's from statistical model, virgin work mainly concentrate on two dimensional image analysis and discern, as the analysis of optical character identification, surface of the work, displaing micro picture and aerial photo and explanation etc.Vision Builder for Automated Inspection generally adopts ccd video camera to gather generation and surveys object image, adopt advanced computer hardware and software engineering that view data is carried out analyzing and processing again, realize multiple function such as pattern-recognition, size or coordinate Calculation, defect analysis etc. according to the result of Treatment Analysis.The design of vision system at present is mainly according to customer demand, and actual system works condition is determined system schema.
Be based at present the reconfigurable Vision Builder for Automated Inspection of PCI and vision bus mostly, form by hardware system and software systems two parts.PCI is based on the signal transmission that bus is shared formula, and PCIe is based on the transportation of serial bag, can realize that a plurality of data sources and processing modules implement are point-to-point to be connected.Machine vision is faced with the too big difficult problem of data volume always; the quantity of information of gray level image, coloured image and degree of depth figure is all very huge; the phenomenon that occurs the bus collapse through regular meeting; solution in the past is the pattern process module card that adopts based on pci bus; by handling the pressure that reduces bus on the plate; but cost can most ofly improve like this, has limited range of application.Two single worker of PCIe connects the transfer rate and the quality that can provide higher, in the middle of the PCIe, because the technology of the difference team of low-voltage has been used in the transmission of Physical layer, so the situation of noiseproof feature and external radiation interference all is greatly improved with respect to PCI.And NI Vision is an instrument that helps quick development machines vision program, comprises a lot of machine vision functions.
Summary of the invention
The objective of the invention is to overcome the deficiency that prior art exists, a kind of method for designing of the Vision Builder for Automated Inspection based on PCIe bus structure and Vision Assistant image processing software is provided.
Purpose of the present invention is achieved through the following technical solutions:
Method for designing based on the Vision Builder for Automated Inspection of PCIe and Vision Assistant, Vision Builder for Automated Inspection comprises hardware components and software section, described hardware components comprises industrial camera, the linear light source of LED, image pick-up card, PCIe bus image processing module, digitial controller and input/output board, industrial camera is made up of line array CCD detecting sensor and vision lens, the linear light source of industrial camera and LED constitutes pick-up unit, the linear light source irradiation of LED acquisition of image data on industrial camera, view data is sent to PCIe bus image processing module by the image pick-up card of following the PCIe bus specification, PCIe bus image processing module is installed in the industrial computer, the result that PCIe bus image processing module is handled gives digitial controller and carries out control decision, and the control signal that obtains is given execution architecture by input/output board; Provide image pre-service, rim detection, pattern match by Vision Assistant image processing software.
Further, the method for designing of above-mentioned Vision Builder for Automated Inspection based on PCIe and Vision Assistan, described image pick-up card and input/output board are all based on the PCIe bus, and all the PCIe slot by industrial computer is inserted on the industrial computer.
Further, the method for designing of above-mentioned Vision Builder for Automated Inspection based on PCIe and Vision Assistan, the image pre-service of described Vision Assistant image processing software comprises gray scale correction, threshold setting and image smoothing, and rim detection comprises by 5 kinds of edge detection operators carries out rim detection to image.
Substantive distinguishing features and obvious improvement that technical solution of the present invention is outstanding are mainly reflected in:
Adopt PCIe bus structure and Vision Assistant to handle versatility, applicability and reconfigurability that means have increased system greatly, solved Computer I/O data throughout bottleneck problem.Be rated as have novelty, creationary good technology, be the new design of a practicality.
Description of drawings
Below in conjunction with accompanying drawing technical solution of the present invention is described further:
Fig. 1: the structural representation of Vision Builder for Automated Inspection of the present invention.
The implication of each Reference numeral sees the following form among the figure:
Reference numeral | Implication | Reference numeral | Implication | | Implication | |
1 | |
2 | The linear light source of LED | 3 | Image pick- |
|
4 | Vision Assistant |
5 | PCIe bus |
6 | |
|
7 | Input/output board | 8 | Execution architecture |
Embodiment
As shown in Figure 1, Vision Builder for Automated Inspection based on PCIe bus structure and Vision Assistant image processing software, comprise hardware components and software section, hardware components comprises industrial camera 1, the linear light source 2 of LED, image pick-up card 3, PCIe bus image processing module 5, with input/output board 7, total system is based on the PCIe bus structure, industrial camera 1 constitutes pick-up unit with the linear light source 2 of LED, industrial camera 1 is made up of line array CCD detecting sensor and vision lens, the linear light source 2 of LED is radiated at acquisition of image data on the industrial camera 1, view data is sent to PCIe bus image processing module 5 by the image pick-up card 3 of following the PCIe bus specification, PCIe bus image processing module 5 is installed in the industrial computer, the result that PCIe bus image processing module 5 is handled gives digitial controller 6 and carries out control decision, and the control signal that obtains is given execution architecture 8 by input/output board 7.Wherein, linear led light source 2 connects light source power by cable, and light source power provides 24V voltage to power to linear led light source.Light source is placed on a side of testee, industrial camera 1 power end connects camera power supply, bus port connects industrial computer by the high speed camera interface cable, and image pick-up card 3 and input/output board 7 are all based on the PCIe bus, and all the PCIe slot by industrial computer is inserted on the industrial computer.
Software configuration is made up of three parts:
1. hardware drive program is finished the hardware components in the system is carried out initialization;
2. system platform;
3. image processing software, the control of some high speed images processing is provided by Vision Assistant image processing software 4, as image pre-service, rim detection, pattern match etc., I. the image preprocessing function comprises gray scale correction, threshold setting and image smoothing, and the index conversion to number conversion, pixel, the square root conversion of gray inversion, pixel carried out in the gray scale correction to image by means of VisionAssistant; Thresholding method has traditional manual threshold method, local threshold method, along with the expansion of level of application, cuts apart robust more in order to make, and system should be able to select threshold value automatically; Image segmentation algorithm based on knowledge such as object, environment and application domains has more ubiquity than based on the fixed threshold algorithm, this method is the adaptive threshold method, the adaptive threshold method comprises classification, according to entropy criterion, measurement technology, momentum apart from principle of invariance, traditional statistical technique interclass variance; The method of image smoothing has: low-pass filter, averaging method, Gaussian filter, median filter.II. rim detection comprises by 5 kinds of edge detection operators image is carried out rim detection, Target Recognition part can the implementation pattern matching feature, object model is set up in object identification exactly, use various matching algorithms to identify the most similar object of object model then from real image, the basic step of object identification is: set up model bank, feature extraction, template matches, suppose the checking of structure etc.; The edge is meant that image local brightness changes the most significant part, and the edge mainly is present between target and target, target and background, zone and the zone, is the important foundation of graphical analyses such as image segmentation, texture feature extraction.Edge detection operator is to utilize the emergent properties of image border to detect the edge.Mainly be divided into two types: a kind of is edge detection operator based on first order derivative, and the Grad by computed image comes the detected image edge, as: Roberts operator, Sobel operator, Prewitt operator; Another kind is the edge detection operator based on second derivative, detects the edge by the zero crossing of seeking in the second derivative, as: Laplacian operator, LOG operator, Canny operator.III. pattern match belongs to a kind of form of object identification, formally being defined as of object identification: a given width of cloth comprises the image of one or more objects and the mark of one group of corresponding object model, and system should correctly distribute to mark object or regional ensemble corresponding in the image.
Adopt PCIe bus structure and Vision Assistant to handle versatility, applicability and reconfigurability that means have increased system greatly, solved Computer I/O data throughout bottleneck problem.Generally speaking, the image that imaging system is obtained often can not directly use in vision system owing to be subjected to all condition restriction and random disturbance, must carry out image pre-service such as gray correction, noise filtering to original image at the commitment of vision.Concerning Vision Builder for Automated Inspection, used image pre-processing method is not considered the image deterioration reason, and is only that interested feature in the image is outstanding selectively, its unwanted feature that decays, and this class image pre-processing method is referred to as the figure image intensifying.From the image quality evaluation viewpoint, the fundamental purpose of figure image intensifying is to improve the intelligibility of image.Image enhancement technique commonly used has gray scale correction, smothing filtering, thresholding etc.
Demand according to the application scenario provides judged result, and this vision system is applied in the milling train automatic centering control system, and judged result is exactly the offset distance of band with respect to the milling train center line.And for example be when being applied in this vision system in the control of the industrial flow-line quality of production, judged result is exactly the similarity marking in the middle of the pattern match.Under the different application scenarios, the form difference of judged result.Carry out the secondary development of practical application based on this system and will accelerate development progress greatly.
What need understand is: above-mentioned explanation is not to be limitation of the present invention, and in the present invention conceived scope, the interpolation of being carried out, conversion, replacement etc. also should belong to protection scope of the present invention.
Claims (3)
1. based on the method for designing of the Vision Builder for Automated Inspection of PCIe and Vision Assistant, Vision Builder for Automated Inspection comprises hardware components and software section, it is characterized in that: described hardware components comprises industrial camera, the linear light source of LED, image pick-up card, PCIe bus image processing module, digitial controller and input/output board, industrial camera is made up of line array CCD detecting sensor and vision lens, the linear light source of industrial camera and LED constitutes pick-up unit, the linear light source irradiation of LED acquisition of image data on industrial camera, view data is sent to PCIe bus image processing module by the image pick-up card of following the PCIe bus specification, PCIe bus image processing module is installed in the industrial computer, the result that PCIe bus image processing module is handled gives digitial controller and carries out control decision, and the control signal that obtains is given execution architecture by input/output board; Provide image pre-service, rim detection, pattern match by Vision Assistant image processing software.
2. the method for designing of the Vision Builder for Automated Inspection based on PCIe and Vision Assistan according to claim 1, it is characterized in that: described image pick-up card and input/output board are all based on the PCIe bus, and all the PCIe slot by industrial computer is inserted on the industrial computer.
3. the method for designing of the Vision Builder for Automated Inspection based on PCIe and Vision Assistan according to claim 1, it is characterized in that: the image pre-service of described Vision Assistant image processing software comprises gray scale correction, threshold setting and image smoothing, and rim detection comprises by 5 kinds of edge detection operators carries out rim detection to image.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 200910026140 CN101510295B (en) | 2009-04-01 | 2009-04-01 | Design method for machine vision system based on PCIe and Vision Assistan |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN 200910026140 CN101510295B (en) | 2009-04-01 | 2009-04-01 | Design method for machine vision system based on PCIe and Vision Assistan |
Publications (2)
Publication Number | Publication Date |
---|---|
CN101510295A true CN101510295A (en) | 2009-08-19 |
CN101510295B CN101510295B (en) | 2013-01-23 |
Family
ID=41002688
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN 200910026140 Active CN101510295B (en) | 2009-04-01 | 2009-04-01 | Design method for machine vision system based on PCIe and Vision Assistan |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN101510295B (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102735690A (en) * | 2012-06-26 | 2012-10-17 | 东莞市三瑞自动化科技有限公司 | Intelligent high speed online automation detection method based on machine vision, and system thereof |
CN102981520A (en) * | 2012-11-30 | 2013-03-20 | 苏州有色金属研究院有限公司 | Method for controlling synchronous acquisition of multiple cameras |
CN105405141A (en) * | 2015-11-11 | 2016-03-16 | 佛山轻子精密测控技术有限公司 | Method for automatically identifying edge of concave-convex stage of workpiece |
CN105718271A (en) * | 2016-02-15 | 2016-06-29 | 福州觉感视觉软件科技有限公司 | Machine vision intelligent detection system |
CN106340026A (en) * | 2016-08-16 | 2017-01-18 | 成都市和平科技有限责任公司 | Low-light environment item screening system based on image processing technology and low-light environment item screening method thereof |
CN110352124A (en) * | 2017-02-08 | 2019-10-18 | 克里奥瓦克公司 | Method and system for on-line inspection of functional thin film layers containing detectable components |
CN110473281A (en) * | 2018-05-09 | 2019-11-19 | 网易(杭州)网络有限公司 | Threedimensional model retouches side processing method, device, processor and terminal |
CN114286035A (en) * | 2021-12-29 | 2022-04-05 | 杭州海康机器人技术有限公司 | Image acquisition card, image acquisition method and image acquisition system |
Family Cites Families (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1170232C (en) * | 2002-10-16 | 2004-10-06 | 西安交通大学 | Machine vision system based on PCI and vision bus and capable of being reconfigurated |
CN100444803C (en) * | 2006-09-27 | 2008-12-24 | 北京航空航天大学 | Three-dimensional type-B ultrasonic diagnostic apparatus based on stereoscopic vision |
CN201145218Y (en) * | 2007-12-28 | 2008-11-05 | 东莞市奥普特自动化科技有限公司 | Multiple color LED light source for detection |
-
2009
- 2009-04-01 CN CN 200910026140 patent/CN101510295B/en active Active
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN102735690A (en) * | 2012-06-26 | 2012-10-17 | 东莞市三瑞自动化科技有限公司 | Intelligent high speed online automation detection method based on machine vision, and system thereof |
CN102981520A (en) * | 2012-11-30 | 2013-03-20 | 苏州有色金属研究院有限公司 | Method for controlling synchronous acquisition of multiple cameras |
CN105405141A (en) * | 2015-11-11 | 2016-03-16 | 佛山轻子精密测控技术有限公司 | Method for automatically identifying edge of concave-convex stage of workpiece |
CN105405141B (en) * | 2015-11-11 | 2018-05-29 | 佛山轻子精密测控技术有限公司 | A kind of method of automatic identification workpiece bumps edge of table |
CN105718271A (en) * | 2016-02-15 | 2016-06-29 | 福州觉感视觉软件科技有限公司 | Machine vision intelligent detection system |
CN106340026A (en) * | 2016-08-16 | 2017-01-18 | 成都市和平科技有限责任公司 | Low-light environment item screening system based on image processing technology and low-light environment item screening method thereof |
CN110352124A (en) * | 2017-02-08 | 2019-10-18 | 克里奥瓦克公司 | Method and system for on-line inspection of functional thin film layers containing detectable components |
CN110473281A (en) * | 2018-05-09 | 2019-11-19 | 网易(杭州)网络有限公司 | Threedimensional model retouches side processing method, device, processor and terminal |
CN114286035A (en) * | 2021-12-29 | 2022-04-05 | 杭州海康机器人技术有限公司 | Image acquisition card, image acquisition method and image acquisition system |
CN114286035B (en) * | 2021-12-29 | 2024-01-05 | 杭州海康机器人股份有限公司 | Image acquisition card, image acquisition method and image acquisition system |
Also Published As
Publication number | Publication date |
---|---|
CN101510295B (en) | 2013-01-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101510295B (en) | Design method for machine vision system based on PCIe and Vision Assistan | |
CN110314854B (en) | Workpiece detecting and sorting device and method based on visual robot | |
Song et al. | Real-time tunnel crack analysis system via deep learning | |
CN107941808B (en) | 3D printing forming quality detection system and method based on machine vision | |
CN103913468B (en) | Many defects of vision checkout equipment and the method for large-scale LCD glass substrate on production line | |
CN104112269B (en) | A kind of solar battery laser groove parameter detection method and system based on machine vision | |
CN103530878B (en) | A kind of edge extracting method based on convergence strategy | |
CN110473184A (en) | A kind of pcb board defect inspection method | |
CN102175692A (en) | System and method for detecting defects of fabric gray cloth quickly | |
CN107014819A (en) | A kind of solar panel surface defects detection system and method | |
CN105279756A (en) | Notch circular arc part dimension visual detection method based on self-adapting region division | |
CN109584215A (en) | A kind of online vision detection system of circuit board | |
CN113252568A (en) | Lens surface defect detection method, system, product and terminal based on machine vision | |
Keser et al. | Intelligent machine vision system for automated quality control in ceramic tiles industry | |
Sansoni et al. | Optoranger: A 3D pattern matching method for bin picking applications | |
CN104200215A (en) | Method for identifying dust and pocking marks on surface of big-caliber optical element | |
CN103091330A (en) | Copper strip surface defect identifying device for simulating human visual perception mechanism and method thereof | |
CN108582075A (en) | A kind of intelligent robot vision automation grasping system | |
CN106290379A (en) | Rail surface defects based on Surface scan camera detection device and method | |
Zhao et al. | Recognition of flooding and sinking conditions in flotation process using soft measurement of froth surface level and QTA | |
CN115597494B (en) | Precision detection method and system for prefabricated part preformed hole based on point cloud | |
Hongxun et al. | Pavement crack detection by ridge detection on fractional calculus and dual-thresholds | |
CN104715250A (en) | Cross laser detection method and device | |
CN106650735B (en) | A kind of LED character automatic positioning recognition methods | |
CN114821274A (en) | Method and device for identifying state of split and combined indicator |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C14 | Grant of patent or utility model | ||
GR01 | Patent grant | ||
TR01 | Transfer of patent right |
Effective date of registration: 20171017 Address after: 471000 Henan Province, Luoyang city high tech Development Zone middle Ling Road Patentee after: China Nonferrous Metals Processing Technology Co., Ltd. Address before: Suzhou City, Jiangsu province 215021 Industrial Park No. 200 Shen Hu Road Patentee before: Suzhou Non-ferrous Metal academy Co., Ltd. |
|
TR01 | Transfer of patent right |