CN103344648A - Method and system for detecting surface quality of steel sheet based on graphics processing unit (GPU) - Google Patents
Method and system for detecting surface quality of steel sheet based on graphics processing unit (GPU) Download PDFInfo
- Publication number
- CN103344648A CN103344648A CN201310288910XA CN201310288910A CN103344648A CN 103344648 A CN103344648 A CN 103344648A CN 201310288910X A CN201310288910X A CN 201310288910XA CN 201310288910 A CN201310288910 A CN 201310288910A CN 103344648 A CN103344648 A CN 103344648A
- Authority
- CN
- China
- Prior art keywords
- gpu
- image
- purpose computer
- image processing
- processing step
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Abstract
The invention provides a method and a system for detecting surface quality of a steel sheet based on a graphics processing unit (GPU). The system comprises a signal synchronization controller, an encoder, a switch, a linear light source, multiple digital cameras and a universal computer equipped with a GPU board card, wherein CPU and GPU in the universal computer form a high-speed parallel computing processing platform for performing heterogeneous parallel cooperative computing; images acquired by the digital cameras are transmitted into an internal memory of the universal computer, are preliminarily processed by the CPU and transmitted to a GPU calculation module; the acquired images are subjected to real-time parallel processing through the GPU calculation module; the final processing result of the GPU returns to the internal memory of the universal computer; the images and defects of the steel sheet are displayed and saved by the universal computer. Therefore, by utilizing the universal computer, enough high-performance image processing capacity can be obtained, and the system has the advantages of simple and compact structure, high integration level and low cost.
Description
Technical field
The invention belongs to quality testing control field, relate in particular to a kind of method and detection system thereof that the computer realization plate surface quality detection of GPU integrated circuit board is housed of using.
Background technology
Generally adopt multiple cameras to gather the image of fast moving steel plate on the production line in the plate surface quality detection system, this just requires surface detecting system to have high performance image-capable.Usually the graphics processing unit of surface detecting system only adopts a general calculation machine can't have corresponding high-performance image processing power.
In order to have high performance image-capable, from the software and hardware structure of present existing plate surface quality detection system graphics processing unit, adopted two kinds of schemes: a kind of scheme is the switch board of forming with the DSP of one group of special use or FPGA integrated circuit board, in switch board, utilize the supercomputing processing power of DSP or FPGA, collection image to video camera carries out analyzing and processing respectively, in multi-purpose computer the defective of steel plate image and steel plate is shown then and preserves.Another kind of scheme is to use many multi-purpose computers to carry out high-speed dsp or the FPGA integrated circuit board that parallel processing replaces special use, the i.e. scheme of many computing machine parallel processings.In the scheme each ccd video camera is distributed independent client computer, carry out image acquisition and analyzing and processing respectively and detect defective, by main control computer the image of each client computer collection is spliced at last and analysis result gathers and shows.All are the schemes that adopt many computing machine parallel processings as number of patent application 201120264974 and 200920175324.Though above-mentioned two kinds of schemes can both effectively solve the high-performance image processing power problem of plate surface quality detection system, but weak point is: in order to obtain high performance image-capable, no matter be the scheme that adopts DSP or FPGA integrated circuit board to carry out supercomputing, still adopt many computing machines scheme of calculating in parallel, it is huge that the volume of its system all seems, the structure of system is also very complicated, and the cost and price of simultaneity factor is also than higher.
Summary of the invention
The present invention is intended to overcome the defective of prior art, and then a kind of enough high-performance image processing poweies that both can have are provided, can make again system have simple and compact for structure, integrated level is high, with low cost based on GPU(Graphic Processing Unit) plate surface quality detection method and system.
For this reason, the solution taked of the present invention is:
A kind of plate surface quality detection method based on GPU is divided into two groups with many digital cameras, is installed in the above and below of steel plate, respectively steel plate upper surface and lower surface is carried out image acquisition; It is characterized in that, the multi-purpose computer that GPU graphic process unit integrated circuit board is installed is carried out image as image processing terminal handle, every digital camera is carried out communication and control, and the image that digital camera obtains is transferred in the multi-purpose computer internal memory;
CUP in the multi-purpose computer and GPU constitute high-speed parallel computing platform, carry out the isomery concurrent collaborative and calculate; The image that digital camera obtains is transferred to earlier in the internal memory of multi-purpose computer, and after by CPU it being carried out rough handling, be transferred to again in the GPU computing module, by the GPU computing module image that obtains being carried out real-time parallel handles, the last result of GPU transfers back in the multi-purpose computer internal memory again, and the defective of steel plate image and steel plate is shown and is preserved by multi-purpose computer;
Image in the multi-purpose computer is handled and is referred to a series of image processing step, and image processing step has by the order of handling: splicing, pre-service, cut apart, feature extraction, classification of defects; Each image processing step is the input of the result of calculation of last image processing step output as this image processing step, until the result who obtains the final image treatment step; Image splicing in the image processing step is that a plurality of images that many digital cameras are gathered synchronously are spliced into entire image, and this is finished by CPU in multi-purpose computer; The pre-service of image, cut apart, feature extraction, classification of defects step finish in the GPU integrated circuit board, be that GPU is divided into each independent subimage block to entire image, in the GPU integrated circuit board with the form of thread process array to image block parallel computation in corresponding step.
As a further improvement on the present invention, the calculating of described each independent image processing step moves in the parallel computation mode in GPU; Meanwhile, also come parallel running based on the parallel pipeline process mode between each image processing step, i.e. every width of cloth image from gathering, image needs in order successively through splicing, pre-service, cuts apart, feature extraction, each image processing step of classification of defects, up to obtaining net result; In this process, the calculating in each image processing step adopts parallel mode to carry out; From the different width of cloth images of gathering, each image processing step computing module in the synchronization multi-purpose computer also all in parallel running, adopt the principle of first in first out, by the sequencing of image acquisition time different collection images is being carried out image simultaneously and handling.
A kind of plate surface quality detection system based on GPU, carry out communication by Ethernet, it is characterized in that, described system comprises signal isochronous controller, scrambler, switch, multi-purpose computer, LED linear light sorurce and 4-8 platform digital camera, and a GPU graphic process unit integrated circuit board is installed in multi-purpose computer; The signal isochronous controller is connected with two groups of digital cameras that are located at the steel plate upper and lower and the scrambler that is located at conveying roller one side respectively, digital camera connects multi-purpose computer by Ethernet through switch, and two LED linear light sorurces are divided into by two groups of digital cameras of steel plate.
Beneficial effect of the present invention is:
GPU(Graphic Processing Unit) is graphic process unit, in video card, plays the effect of " heart ".Continuous development along with Modern Graphic processor GPU, GPU no longer has been confined to graphics process, high-speed and the concurrency of graphic process unit draw calculation and the programmable functions that development in recent years is got up provide good operation platform for the general-purpose computations beyond the graphics process, make graphic process unit cause more and more widely concern in the general parallel computing such as algebraic manipulation and fluid simulation, database manipulation, frequency spectrum conversion and filtering etc., aspect general parallel computation, and even GPU can provide the performance of tens of times of hundreds of times in CPU.Just for these reasons, the present invention is applied to the video card that the GPU integrated circuit board namely has the general-purpose computations ability in the plate surface quality detection system, realized utilizing a multi-purpose computer that the GPU integrated circuit board is housed both can in the surface quality detection system, carry out the image processing, make the plate surface quality detection system have enough high-performance image processing poweies, simultaneously greatly simplified system architecture again, made system have advantage simple and compact for structure, that integrated level is high and cost is low.
Description of drawings
Fig. 1 is plate surface quality detection system synoptic diagram;
Fig. 2 is CPU and GPU isomery concurrent collaborative computing block diagram;
Fig. 3 is plate surface quality trace routine block diagram.
Among the figure: down shooting unit 1, steel plate 2, on make a video recording unit 3, Ethernet 4, go up LED linear light sorurce 5, switch 6, multi-purpose computer 7, conveying roller 8, scrambler 9, signal isochronous controller 10, LED linear light sorurce 11 down.
Embodiment
As seen from Figure 1, the plate surface quality detection system that the present invention is based on GPU mainly by under make a video recording unit 1, on make a video recording unit 3, Ethernet 4, go up LED linear light sorurce 5, switch 6, multi-purpose computer 7, scrambler 9, signal isochronous controller 10 and down LED linear light sorurce 11 formed, a CUDA-enabled(CUDA is installed in multi-purpose computer 7, Compute Unified Device Architecture, namely unifiedly calculate the equipment framework, being NVIDIA company is GPU open platform that oneself GPU provides) GPU graphic process unit integrated circuit board.Make a video recording down unit 1 and last shooting unit 3 is made of 3 CCD digital cameras with express network communication function respectively, make a video recording down unit 1 and last shooting unit 3 is separately positioned on below and the top of steel plate 2, be provided with LED linear light sorurce 11 down on the next door of the unit 1 of making a video recording down, next door at shooting unit 3 is provided with LED linear light sorurce 5, be used for being thrown light in the upper and lower surface of steel plate, with the picture quality that guarantees that digital camera is gathered.Under the unit 1 of making a video recording all be connected with signal isochronous controller 10 with last shooting unit 3, signal isochronous controller 10 is used for guaranteeing that each digital camera gathers carrying out synchronously of image gathering image process.Signal isochronous controller 10 also is connected with scrambler 9, scrambler 9 is located at a side of conveying roller 8, conveying roller 8 is synchronized with the movement with steel plate 2, scrambler 9 flows to signal isochronous controller 10 with the pulse signal that the conveying roller 8 that produces rotates as synchronous control signal, and signal isochronous controller 10 carries out synchronous control signal multichannel again and outputs in each each digital camera.Each digital camera of unit 1 and last shooting unit 3 of making a video recording down is connected multi-purpose computer 7 by Ethernet 4 through switch 6, switch 6 usefulness so that the view data of each digital camera collection be sent in the multi-purpose computer 7 in order to handle by Ethernet 4 communications; Every digital camera is all by multi-purpose computer 7 controls, its image of gathering synchronously at first is transferred in the internal memory of multi-purpose computer 7 of the described GPU of being equipped with plate, through after the CPU rough handling of multi-purpose computer 7, walked abreast by the image of GPU and to handle in real time, at last in multi-purpose computer 7 internal memories that the result of Chu Liing is transmitted again, show and preserve by the image of 7 pairs of steel plates 2 of multi-purpose computer and defective.
As shown in Figure 2, the present invention is based on the plate surface quality detection method of GPU, is to utilize CUP and GPU in the multi-purpose computer 7 to constitute high-speed parallel computing platform, carries out the isomery concurrent collaborative and calculates; The image that digital camera obtains is transferred to earlier in the internal memory of multi-purpose computer 7, and after by CPU it being carried out rough handling, is transferred in the GPU computing module again, by the GPU computing module image that obtains is carried out real-time parallel and handles.
Image processing step in the multi-purpose computer 7 has by the order of handling: splicing, pre-service, cut apart, feature extraction, classification of defects; Each image processing step is the input of the result of calculation of last image processing step output as this image processing step, until the result who obtains the final image treatment step.Image splicing in the image processing step, a plurality of images that each digital camera is gathered synchronously are spliced into entire image exactly, and this is finished by CPU in multi-purpose computer 7.The pre-service of image, cut apart, feature extraction, classification of defects step finish in the GPU integrated circuit board, be that GPU is divided into each independent subimage block to entire image, in the GPU integrated circuit board with the form of thread process array to image block parallel computation in corresponding step.The last result of GPU transfers back in multi-purpose computer 7 internal memories again, and is shown and preserved by the image of 7 pairs of steel plates 2 of multi-purpose computer and defective.Its program circuit as shown in Figure 3.
Simultaneously, the present invention also can be GPU carries out each independent image processing step calculating in the parallel computation mode when, make between each image processing step and also come parallel running based on the parallel pipeline process mode, i.e. every width of cloth image from gathering, image needs in order successively through splicing, pre-service, cuts apart, feature extraction, each image processing step of classification of defects, up to obtaining net result.In this process, the calculating in each image processing step adopts parallel mode to carry out; From the different width of cloth images of gathering, each image processing step computing module in synchronization multi-purpose computer 7 also all in parallel running, adopt the principle of first in first out, by the sequencing of image acquisition time different collection images is carried out image simultaneously and handle.
Claims (3)
1. the plate surface quality detection method based on GPU is divided into two groups with many digital cameras, is installed in the above and below of steel plate, respectively steel plate upper surface and lower surface is carried out image acquisition; It is characterized in that, the multi-purpose computer that GPU graphic process unit integrated circuit board is installed is carried out image as image processing terminal handle, every digital camera is carried out communication and control, and the image that digital camera obtains is transferred in the multi-purpose computer internal memory;
CUP in the multi-purpose computer and GPU constitute high-speed parallel computing platform, carry out the isomery concurrent collaborative and calculate; The image that digital camera obtains is transferred to earlier in the internal memory of multi-purpose computer, and after by CPU it being carried out rough handling, be transferred to again in the GPU computing module, by the GPU computing module image that obtains being carried out real-time parallel handles, the last result of GPU transfers back in the multi-purpose computer internal memory again, and the defective of steel plate image and steel plate is shown and is preserved by multi-purpose computer;
Image in the multi-purpose computer is handled and is referred to a series of image processing step, and image processing step has by the order of handling: splicing, pre-service, cut apart, feature extraction, classification of defects; Each image processing step is the input of the result of calculation of last image processing step output as this image processing step, until the result who obtains the final image treatment step; Image splicing in the image processing step is that a plurality of images that many digital cameras are gathered synchronously are spliced into entire image, and this is finished by CPU in multi-purpose computer; The pre-service of image, cut apart, feature extraction, classification of defects step finish in the GPU integrated circuit board, be that GPU is divided into each independent subimage block to entire image, in the GPU integrated circuit board with the form of thread process array to image block parallel computation in corresponding step.
2. the plate surface quality detection method based on GPU according to claim 1 is characterized in that the calculating of described each independent image processing step moves in the parallel computation mode in GPU; Meanwhile, also come parallel running based on the parallel pipeline process mode between each image processing step, i.e. every width of cloth image from gathering, image needs in order successively through splicing, pre-service, cuts apart, feature extraction, each image processing step of classification of defects, up to obtaining net result; In this process, the calculating in each image processing step adopts parallel mode to carry out; From the different width of cloth images of gathering, each image processing step computing module in the synchronization multi-purpose computer also all in parallel running, adopt the principle of first in first out, by the sequencing of image acquisition time different collection images is being carried out image simultaneously and handling.
3. an application rights requires the system of 1 described plate surface quality detection method based on GPU, carry out communication by Ethernet, it is characterized in that, described system comprises signal isochronous controller, scrambler, switch, multi-purpose computer, LED linear light sorurce and 4-8 platform digital camera, and a GPU graphic process unit integrated circuit board is installed in multi-purpose computer; The signal isochronous controller is connected with two groups of digital cameras that are located at the steel plate upper and lower and the scrambler that is located at conveying roller one side respectively, digital camera connects multi-purpose computer by Ethernet through switch, and two LED linear light sorurces are divided into by two groups of digital cameras of steel plate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310288910XA CN103344648A (en) | 2013-07-10 | 2013-07-10 | Method and system for detecting surface quality of steel sheet based on graphics processing unit (GPU) |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310288910XA CN103344648A (en) | 2013-07-10 | 2013-07-10 | Method and system for detecting surface quality of steel sheet based on graphics processing unit (GPU) |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103344648A true CN103344648A (en) | 2013-10-09 |
Family
ID=49279462
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310288910XA Pending CN103344648A (en) | 2013-07-10 | 2013-07-10 | Method and system for detecting surface quality of steel sheet based on graphics processing unit (GPU) |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103344648A (en) |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104198494A (en) * | 2014-08-18 | 2014-12-10 | 苏州克兰兹电子科技有限公司 | On-line detection system for surface defects of plate strips |
| CN105606625A (en) * | 2016-02-03 | 2016-05-25 | 宁波韵升智能技术有限公司 | Appearance defect detection equipment for flake strip-shaped products |
| CN106124515A (en) * | 2016-07-04 | 2016-11-16 | 佛山科学技术学院 | A kind of air spring bar surface defects detection system and detection method thereof |
| CN106970090A (en) * | 2017-04-27 | 2017-07-21 | 佛山市南海区广工大数控装备协同创新研究院 | Embryo cloth defective vision detection device and method |
| CN107179324A (en) * | 2017-05-17 | 2017-09-19 | 珠海格力电器股份有限公司 | Detect the methods, devices and systems of product packaging |
| CN108760767A (en) * | 2018-05-31 | 2018-11-06 | 电子科技大学 | Large-size LCD Screen defect inspection method based on machine vision |
| CN110781849A (en) * | 2019-10-30 | 2020-02-11 | 北京锐安科技有限公司 | Image processing method, device, equipment and storage medium |
| CN111044522A (en) * | 2019-12-14 | 2020-04-21 | 中国科学院深圳先进技术研究院 | Defect detection method and device and terminal equipment |
| CN111462060A (en) * | 2020-03-24 | 2020-07-28 | 湖南大学 | Method and device for detecting standard section image in fetal ultrasonic image |
| CN111753707A (en) * | 2020-06-19 | 2020-10-09 | 上海交通大学 | Method and system for detecting imperfect grains of granular crops |
| CN111984417A (en) * | 2020-08-26 | 2020-11-24 | 展讯通信(天津)有限公司 | Image processing method and device for mobile terminal, storage medium and terminal |
| CN114312060A (en) * | 2021-12-31 | 2022-04-12 | 深圳市泰力格打印技术有限公司 | Processing system for printing defects |
| CN115290662A (en) * | 2022-09-29 | 2022-11-04 | 南京原觉信息科技有限公司 | Multi-vision surface defect detection system and detection method thereof |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7693318B1 (en) * | 2004-01-12 | 2010-04-06 | Pme Ip Australia Pty Ltd | Method and apparatus for reconstruction of 3D image volumes from projection images |
| CN102169093A (en) * | 2010-12-20 | 2011-08-31 | 湖南大学 | Multi-station machine vision imaging detection method and system based on graphics processor |
| WO2012115819A1 (en) * | 2011-02-24 | 2012-08-30 | 3M Innovative Properties Company | System for detection of non-uniformities in web-based materials |
| CN102680495A (en) * | 2011-03-15 | 2012-09-19 | 上海赫立电子科技有限公司 | Device and method for automatic optical detection |
| CN102759530A (en) * | 2012-07-03 | 2012-10-31 | 湖南镭目科技有限公司 | Online detection device for surface quality image |
| CN102937599A (en) * | 2012-10-25 | 2013-02-20 | 中国科学院自动化研究所 | Non-destructive testing systems and method used for detecting a metal-containing object through X-ray detection |
| CN202921575U (en) * | 2012-05-18 | 2013-05-08 | 江苏大学 | Cotton foreign fiber removing device |
| CN103163141A (en) * | 2011-12-14 | 2013-06-19 | 鞍钢股份有限公司 | Strip steel surface on-line inspection system and method based on embedded image processing system |
-
2013
- 2013-07-10 CN CN201310288910XA patent/CN103344648A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7693318B1 (en) * | 2004-01-12 | 2010-04-06 | Pme Ip Australia Pty Ltd | Method and apparatus for reconstruction of 3D image volumes from projection images |
| US20100215240A1 (en) * | 2004-01-12 | 2010-08-26 | Detlev Stalling | Method and apparatus for reconstruction of 3d image volumes from projection images |
| CN102169093A (en) * | 2010-12-20 | 2011-08-31 | 湖南大学 | Multi-station machine vision imaging detection method and system based on graphics processor |
| WO2012115819A1 (en) * | 2011-02-24 | 2012-08-30 | 3M Innovative Properties Company | System for detection of non-uniformities in web-based materials |
| CN102680495A (en) * | 2011-03-15 | 2012-09-19 | 上海赫立电子科技有限公司 | Device and method for automatic optical detection |
| CN103163141A (en) * | 2011-12-14 | 2013-06-19 | 鞍钢股份有限公司 | Strip steel surface on-line inspection system and method based on embedded image processing system |
| CN202921575U (en) * | 2012-05-18 | 2013-05-08 | 江苏大学 | Cotton foreign fiber removing device |
| CN102759530A (en) * | 2012-07-03 | 2012-10-31 | 湖南镭目科技有限公司 | Online detection device for surface quality image |
| CN102937599A (en) * | 2012-10-25 | 2013-02-20 | 中国科学院自动化研究所 | Non-destructive testing systems and method used for detecting a metal-containing object through X-ray detection |
Non-Patent Citations (1)
| Title |
|---|
| 王成顺: "表面缺陷检测GPU并行图像处理技术", 《中国优秀硕士学位论文全文数据库》, no. 3, 15 March 2013 (2013-03-15) * |
Cited By (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104198494A (en) * | 2014-08-18 | 2014-12-10 | 苏州克兰兹电子科技有限公司 | On-line detection system for surface defects of plate strips |
| CN105606625A (en) * | 2016-02-03 | 2016-05-25 | 宁波韵升智能技术有限公司 | Appearance defect detection equipment for flake strip-shaped products |
| CN105606625B (en) * | 2016-02-03 | 2018-06-26 | 宁波韵升智能技术有限公司 | A kind of appearance defect detection device of thin slice band-type product |
| CN106124515A (en) * | 2016-07-04 | 2016-11-16 | 佛山科学技术学院 | A kind of air spring bar surface defects detection system and detection method thereof |
| CN106970090A (en) * | 2017-04-27 | 2017-07-21 | 佛山市南海区广工大数控装备协同创新研究院 | Embryo cloth defective vision detection device and method |
| CN107179324A (en) * | 2017-05-17 | 2017-09-19 | 珠海格力电器股份有限公司 | Detect the methods, devices and systems of product packaging |
| CN107179324B (en) * | 2017-05-17 | 2019-01-01 | 珠海格力电器股份有限公司 | The methods, devices and systems of testing product packaging |
| CN108760767B (en) * | 2018-05-31 | 2020-07-17 | 电子科技大学 | Large-size liquid crystal display defect detection method based on machine vision |
| CN108760767A (en) * | 2018-05-31 | 2018-11-06 | 电子科技大学 | Large-size LCD Screen defect inspection method based on machine vision |
| CN110781849A (en) * | 2019-10-30 | 2020-02-11 | 北京锐安科技有限公司 | Image processing method, device, equipment and storage medium |
| CN111044522A (en) * | 2019-12-14 | 2020-04-21 | 中国科学院深圳先进技术研究院 | Defect detection method and device and terminal equipment |
| CN111044522B (en) * | 2019-12-14 | 2022-03-11 | 中国科学院深圳先进技术研究院 | Defect detection method and device and terminal equipment |
| CN111462060A (en) * | 2020-03-24 | 2020-07-28 | 湖南大学 | Method and device for detecting standard section image in fetal ultrasonic image |
| CN111753707A (en) * | 2020-06-19 | 2020-10-09 | 上海交通大学 | Method and system for detecting imperfect grains of granular crops |
| CN111984417A (en) * | 2020-08-26 | 2020-11-24 | 展讯通信(天津)有限公司 | Image processing method and device for mobile terminal, storage medium and terminal |
| WO2022042587A1 (en) * | 2020-08-26 | 2022-03-03 | 展讯通信(天津)有限公司 | Image processing method and apparatus for mobile terminal, and storage medium and terminal |
| CN114312060A (en) * | 2021-12-31 | 2022-04-12 | 深圳市泰力格打印技术有限公司 | Processing system for printing defects |
| CN115290662A (en) * | 2022-09-29 | 2022-11-04 | 南京原觉信息科技有限公司 | Multi-vision surface defect detection system and detection method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103344648A (en) | Method and system for detecting surface quality of steel sheet based on graphics processing unit (GPU) | |
| CN204924967U (en) | Image acquisition mechanism of full -automatic AOI complete machine | |
| CN102169093B (en) | Multi-station machine vision imaging detection method and system based on graphics processor | |
| CN112871703B (en) | Intelligent management coal preparation platform and method thereof | |
| CN103442174B (en) | A kind of many CIS splicing smart camera realizing large format on-line checking and method | |
| CN105044126A (en) | Visual detection system for large-width continuous surface defects | |
| CN103163141A (en) | Strip steel surface on-line inspection system and method based on embedded image processing system | |
| CN103399016A (en) | Online detection system for surface defects of coldly-rolled aluminum plate and detection method of online detection system | |
| CN102759530B (en) | A kind of surface quality image on-line measuring device | |
| CN101482518A (en) | On-line quality detection system for movable band-shaped material | |
| CN101221439B (en) | Embedded system for high speed parallel duplex digital image capturing and processing | |
| CN107274368B (en) | Compatible vision processing system and method | |
| CN103325116A (en) | Printing product image detection system and method | |
| CN101216438B (en) | Printed circuit boards coarse defect image detection method based on FPGA | |
| CN103090946B (en) | Method and system for measuring single fruit tree yield | |
| CN105548950A (en) | Device and method of on-line detection of intelligent ammeter | |
| CN106412474B (en) | A kind of high-speed lossless ultra high-definition industrial vision detection method and system | |
| CN103617592A (en) | Hyperspectral image high-speed parallel processing system and method based on FPGA and multiple DSPs | |
| CN108509696A (en) | Ancient building health monitor method based on three-dimensional laser scanning technique and device | |
| CN202433316U (en) | Device for detecting surface defects of plastic sheets on line | |
| CN104833925A (en) | Fuel cell bipolar plate detection method and system based on machine vision | |
| CN105023262A (en) | Visual detection controller | |
| CN204216935U (en) | Based on the mass data collection communication platform of frame-type | |
| CN203241148U (en) | Device for monitoring wind turbine real-time vibration faults | |
| CN103543157B (en) | Off-line strip surface image simulation dynamic collecting method and device |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20131009 |