CN101276218A - Machine vision system aiming at high real time image collecting and processing - Google Patents
Machine vision system aiming at high real time image collecting and processing Download PDFInfo
- Publication number
- CN101276218A CN101276218A CNA2008100368431A CN200810036843A CN101276218A CN 101276218 A CN101276218 A CN 101276218A CN A2008100368431 A CNA2008100368431 A CN A2008100368431A CN 200810036843 A CN200810036843 A CN 200810036843A CN 101276218 A CN101276218 A CN 101276218A
- Authority
- CN
- China
- Prior art keywords
- image
- module
- processing
- data
- high speed
- 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
Images
Abstract
The present invention provides a machine vision system aiming at the collection and the process of the high real-time image, including a light module, a digital CMOS camera module having a gigabit ethernet interface, a image collecting and processing module, an image display module, a movement control module, an image wireless transmitting module, wherein, the light module irradiates the object image, the digital CMOS camera module having a gigabit ethernet interface collects the object image under the irradiation of the light module, the original image data is obtained, the digital image data is quickly send to the image collecting and processing module by the gigabit net, the image data is output by two paths after quickly processed by the image collecting and processing module, one path output to the image display module to display, the other path transmits to the host computer by the image wireless transmitting module, the control data is transmitted to the movement control module after quickly processed by the image collecting and processing module, for driving the motor. The invention can transmit and process the image data conveniently.
Description
Technical field
What the present invention relates to is the system in a kind of machine vision technique field, specifically is a kind of Vision Builder for Automated Inspection at high real time image collecting and processing.
Background technology
Machine vision technique is an important branch of computing machine subject, it combines the technology of aspects such as optics, machinery, electronics, computer software and hardware, relates to a plurality of fields such as computing machine, Flame Image Process, pattern-recognition, artificial intelligence, signal Processing, optical, mechanical and electronic integration.From the starting development so far, the history in more than 20 year has been arranged, its function and range of application are along with the development of industrial automation is improved gradually and promoted, the fast development of technology such as embedded technology, Flame Image Process and pattern-recognition such as wherein particularly present digital image sensor, CMOS and ccd video camera, DSP, FPGA, ARM has promoted the development of machine vision widely.
In brief, machine vision utilizes machine to replace human eye to do various measurements and judgement exactly.On production line, the people does this type of measurement and judgement meeting and produces the sum of errors mistake because of fatigue, person-to-person difference etc., but machine but can be tirelessly, stably go on.In general, Vision Builder for Automated Inspection has comprised illuminator, camera lens, camera system and image processing system.Use for each, we need, and the travelling speed of taking into account system and image processing velocity, use colour still are that B, the size that detects target still detect target and have that zero defect, visual field needs are much, height more than resolution needs, contrast needs are much etc.On function, typical Vision Builder for Automated Inspection can be divided into: image acquisition part, image processing section and motion control part.
Through the literature search of prior art is found, application (patent) number: described in 200610066957.1 and image acquisition comprise employing CMOS camera sensor photographic subjects image with disposal system, utilize the vision system of FPGA as image processor.It is not that very high occasion can be finished set executing the task really that its image acquisition and processing speed require in some real-time, but require in case improve when real-time, the real-time handling property of this system can not meet the demands naturally, so be necessary to develop the high speed machines vision system that a cover can be competent at the high real-time mission requirements.
Summary of the invention
The objective of the invention is at the deficiencies in the prior art, a kind of high speed robot's embedded vision system based on the Digital Media SOC (system on a chip) is provided.Make its industrial applications that can be applied to high-speed image sampling and processing more easily, carry out image data transmission and processing more masterlyly.
The present invention is achieved through the following technical solutions, the present invention includes: illumination module, the digital CMOS camera model, image acquisition and the processing module that have gigabit ethernet interface, image display, image wireless transport module, motion-control module, wherein: illumination module irradiation target image, for the digital CMOS camera model collection that has gigabit ethernet interface; The digital CMOS camera model that has a gigabit ethernet interface is gathered the target image under the irradiation of illumination module, obtain raw image data, by its gigabit network interface Digital Image Data is sent to image acquisition and processing module fast, view data after image acquisition and processing module high speed processing is divided two-way output, one the tunnel outputs to image display shows, another road sends host computer to by the image wireless transport module, the control data that produces after image acquisition and processing module high speed processing sends to motion-control module, is used for drive motor.
Described illumination module is the key factor that influences the Vision Builder for Automated Inspection input, and it directly influences the quality and the effect of input data.Since there is not general machine vision light fixture, thus at each specific application example, select relevant lighting device, to reach optimum efficiency.
The described digital CMOS camera model that has gigabit ethernet interface is the key equipment that is used for the high-speed transfer view data, and its image sampling rate reached for 200 frame/seconds.For follow-up image acquisition and processing module provide the image information data of magnanimity to be handled.Adopt ICP/IP protocol and image acquisition and processing modules implement real-time Data Transmission at a high speed.
Described image acquisition and processing module comprise gigabit ethernet interface image transmission module, high speed acquisition module, image pretreatment module, distortion correction module, Region Segmentation module, colour space transformation processing module, target search module, template matches module, multiple image Fusion Module, high speed information communication module, wherein:
Described gigabit ethernet interface image transmission module sends to the high speed acquisition module with the speed acquisition destination image data near gigabit;
The view data that described high speed acquisition module collection gigabit ethernet interface image transmission module is sent also sends to the image pretreatment module;
Described image pretreatment module is carried out the image pre-service, obtains the better view data of visual effect, and sends to the distortion correction module;
Described distortion correction module is carried out after distortion correction handles view data, sends to the pattern recognition process that Region Segmentation module, colour space transformation processing module, target search module, template matches module are carried out image;
Described Region Segmentation module and colour space transformation processing module are transformed into the HIS space with the RGB component value of image and each pixel, finish image segmentation and image recognition in the HIS space, and deliver to target search module and template matches module;
Described target search module and template matches module promptly all find satisfactory pixel with the pixel of template matches with the method for target search, finish the task of pattern-recognition, and the result is delivered to the multiple image Fusion Module;
Described multiple image Fusion Module is used multiframe fusion treatment technology and is restored motion blur image, and the motion control data of the pictorial data that will thoroughly handle well and generation send to the high speed information communication module;
Described high speed information communication module is sent the data of handling well, finishes the task of real-time Communication for Power.
Described image pretreatment module, its pre-service comprises figure image intensifying, image smoothing, image sharpening, wherein: described figure image intensifying, adopt histogram equalization techniques, revise the pixel grey scale of original image with mapping relations, produce one than the more smooth histogram of former side figure, strengthen image effect; Described image smoothing, promptly the denoising of image is handled, and adopts the neighborhood averaging technology, replaces the gray scale of this point with the mean value of adjoint point gray scale; Described image sharpening, promptly the image border enhancement process adopts gradient method with the sharpening by differentiation treatment technology, uses the Grad of each location of pixels.
Relating in the thread that all is embedded in the DSP/BIOS real time operating system in the above each module, utilize pipeline and stream to carry out inter-thread communication, it is very high that it carries out efficient, can satisfy system fully for high speed, the requirement of high real-time.
Image acquisition and processing module can adopt existing techniques in realizing among the present invention, and such as the Digital Media SOC (system on a chip) (DMSoc) that is provided by TexasInstruments company, model is: TMS320DM644x.
Described image display is used to receive the view data after image acquisition and processing module high speed processing, when host CPU is in the IDLE thread (when main frame is idle), being used to show man-machine interface, is that a slice numeral touches color LCD screen, the image of handling well can be shown in real time.
Described image wireless transport module is used to receive the view data after image acquisition and processing module high speed processing, is to be hung on image acquisition and processing module output device outward, by wireless transmission method and host computer real-time exchange data.So that host computer is for the subsequent treatment and the storage of view data.
Described motion-control module is used to receive the control data that produces after image acquisition and processing module high speed processing, promptly utilize the RS485 bus, based on monolithic processor controlled motor drive module, how to control the motion of each motor according to the decision of the view data after above-mentioned processing single-chip microcomputer.
Compared with prior art, the present invention can be applied to the industrial applications of high-speed image sampling and processing more easily, carries out image data transmission and processing more masterlyly.Utilize world today's sophisticated technology, promptly the Digital Media SOC (system on a chip) has realized finishing at a high speed: the clock frequency of ARM9---300MHZ; The clock frequency of C64x+---600MHZ; High real-time---the CPU core employing is grabbed formula and taken the thread mode preferentially to finish the interrupt task that real-time is had relatively high expectations---requires the Vision Builder for Automated Inspection of task.The high speed instruction execution speed of its kernel, again in conjunction with being embedded in optimised program code in the DSP/BIOS real time operating system thread efficiently---based on the RF5 framework---, add the target image picking rate of gigabit network interface, this system has been competent at fully as finishing at a high speed, and high real-time requires this role of task.
Description of drawings
Fig. 1 is a system architecture diagram of the present invention
Embodiment
Below in conjunction with accompanying drawing embodiments of the invention are elaborated: present embodiment is being to implement under the prerequisite with the technical solution of the present invention, provided detailed embodiment and concrete operating process, but protection scope of the present invention is not limited to following embodiment.
As shown in Figure 1, present embodiment comprises: illumination module, the digital CMOS camera model, image acquisition and the processing module that have gigabit ethernet interface, image display, motion-control module, image wireless transport module.The digital CMOS camera model that has gigabit ethernet interface, under the irradiation of illumination module, obtain more satisfactory original data, after image acquisition and processing module, pretreated image one road blit is shown as display module that another road sends to host computer through the image wireless transport module and handles and preserve.The control data that obtains after image acquisition and processing module processing phoresys moving control module and carries out motion of mechanism control.
1. illumination module.The illumination module is the key factor that influences the Vision Builder for Automated Inspection input, and it directly influences the quality and the effect of input data.The view data that obtains after the illumination module in the present embodiment has guaranteed the quality of original data again by the collection of digital CMOS camera.
The illumination module is the key factor that influences the Vision Builder for Automated Inspection input, and it directly influences the quality and the effect of input data.Since there is not general machine vision light fixture, thus at each specific application example, select relevant lighting device, to reach optimum efficiency.Light source can be visible light and invisible light.Several visible light sources commonly used are white flag lamp, daylight lamp, mercury vapor lamp and sodium lamp.It is stable that the shortcoming of visible light is that luminous energy can not keep.How making luminous energy keep stable on certain degree, is the problem that urgent need will solve in the practicability process.On the other hand, surround lighting might influence the quality of image, so can adopt the method that adds protecting screen to reduce the influence of surround lighting.Illuminator can be divided into by its illuminating method: illumination dorsad, front illumination, structured light and strobe light illumination etc.Wherein, illumination is that measured object is placed between light source and the video camera dorsad, and its advantage is the image that can obtain high-contrast.Front illumination be light source and position for video camera in the homonymy of measured object, this mode is convenient to install.Structured Illumination is that grating or line source etc. is projected on the measured object, according to the distortion that they produce, demodulates the three-dimensional information of measured object.Strobe light illumination be with high-frequency optical pulse irradiation to object, video camera photographing request and light source are synchronous.
2. the digital CMOS camera model that has gigabit ethernet interface.Its advantage of digital CMOS camera of Ethernet interface is an image sampling rate height, and transmission speed is big, and the real time data handling capacity that it is huge has satisfied the requirement of the high-speed real-time of present embodiment.
3. image acquisition and processing module.In the present embodiment, image acquisition and processing module are to be (DMSoc) on a Digital Media sheet that is provided by TexasInstruments company.Model is: TMS320DM644x.Consist of the following components: the gigabit ethernet interface image transmission module, the high speed acquisition module, the image pretreatment module, the distortion correction module, Region Segmentation module, colour space transformation processing module, the target search module, the template matches module, multiple image Fusion Module, high speed information communication module etc.As shown in Figure 1.
A). gigabit ethernet interface image transmission module, this module are used to receive the next view data of digital CMOS camera collection of Ethernet interface, utilize this interface can realize the data transmission of high-speed real-time.
B). the high speed acquisition module, this module is the enhancement mode direct memory access mode of utilizing on the TMS320DM644x chip slapper i.e. (EDMA), and the raw image data that the collection of gigabit ethernet interface image transmission module is come is moved and carried out successive image in the kernel of TMS320DM644x chip and handle and pattern-recognition.
C). the image pretreatment module, the function of this module is that original data is processed processing, to obtain the more desirable visual pattern of effect, preprocessing process is divided into following three parts:
1). the figure image intensifying
Histogram equalization techniques is generally adopted in the figure image intensifying, with the pixel grey scale of certain mapping relations modification original image, produces one than the more smooth histogram of former side figure, and image is had obvious enhancing effect.
2). image smoothing
Image smoothing is called the denoising of image again to be handled, and generally adopts the neighborhood averaging technology, replaces the gray scale of this point, i.e. mould plate technique with the mean value of adjoint point gray scale.
3). image sharpening
Image sharpening is called the image border enhancement process again, generally adopts gradient method with the sharpening by differentiation treatment technology, uses the Grad of each location of pixels.
Except that above-mentioned several preconditioning techniques, consider that the robot system real-time has relatively high expectations, environment is variable, can adjust the capacity and the quality of institute's pickup image, comprises image adjustment and compression.Satisfying under the prerequisite of precision, can adopt " field " mode or " TARGET " acquisition mode, reducing image volume, improving picking rate.
D). the distortion correction module.Pattern distortion and brightness variation extensively are present in the imaging system of using wide-angle lens.In large visual field optical system, adopt Gauss's imaging formula can have nonlinearity erron; Because technological level restriction, optical system may be brought deformation adding man-hour; Detector itself is arranged just irregular; All these all can cause pattern distortion, and its classics show as object distortion in the image, and far and near ratio is inharmonious etc.The method that solves this class problem of dtmf distortion DTMF is called geometric distortion correction.Distortion can increase and increase rapidly with the visual field.Though do not influence image definition, optical system has distortion but directly to influence the geometric position precision of imaging.Because the existence of distortion, the straight line of object space has just become a curve in picture side, caused the distortion of picture.It is not remarkable to distort in the smaller optical system in visual field, but large visual field optical system just must take measures to eliminate the influence that distortion brings.The existence of distortion is unfavorable for identification, analysis and the judgement of image.In some quantitative test fields, need proofread and correct distortion, correction accuracy will directly influence the precision of quantitative test.The geometric distortion of imaging system is divided into two classes, i.e. linear geometry distortion and nonlinear geometry distortion.The correction of linear geometry distortion has obtained reasonable solution, the solution but the correction of nonlinear geometry distortion also fails.
Present embodiment has been selected a kind of generation principle according to distortion, can restore image by existing software approach, deformation pattern is carried out geometry correction, comprising spatial alternation and two parts of gray-level interpolation.When utilization polynomial expression deformation technology carries out spatial alternation,, use the polynomial expression of appropriate number of times that the every bit on the image is carried out spatial alternation by choosing the reference mark.This module can be finished these functions.
E). Region Segmentation module and colour space transformation processing module.In image recognition processes, its colouring information is main basis of characterization, and choosing of colour model has very big influence to correct identification colors, and colour model commonly used at present has RGB and HIS.The RGB model is the linear expression system, and its advantage is simple, directly perceived.But practice result shows, to same color attribute object, under different condition (illumination, light source kind, brightness, object reflection characteristic etc.), the RGB color distribution that it records is disperseed very much, 3 interrelated variation wave bands of component are very wide, and the ratio that takes up space is very big, are difficult to determine the threshold range of identification RGB, very easy handle is not that the object of designated color is included, and misses the part object that discern.
The HSI model is based on the model of visual theory, it has defined the color attribute of 3 mutual uncorrelated, easy predictions: colourity (Hue), saturation degree (Saturation) and lightness (Illumination), chrominance properties wherein can reflect color category more exactly, and the variation sensitivity of illumination condition is low to external world.To same color attribute object, have stable and narrower numerical value change scope.Saturation degree S can be used as the auxiliary judgment condition, and brightness I does not generally judge.So system adopts the HIS model.
Rgb space is as follows to the transformation for mula in HSI space:
Wherein: the H span is [0 a °, 180 °], and when G＜B, the H span is greater than 180 °.Can make H=360 °-H, H is transformed into [180 °, 360 °], above-mentioned 2 kinds of information summaries are considered, the scope that can get H is [0 °, 360 °], and formula is as follows:
By above-mentioned formula, the RGB component value of image and each pixel is transformed into the HIS space, finish in the HIS space image segmentation and image recognition etc. work.
F). target search module and template matches module.Order network and seed filling that Target Searching Method is based on the consecutive image correlativity combine.So-called order grid is divided into some, equal-sized square zonule by certain criterion artificially with the region of search exactly, and scans target in sequence in this zonule, searches out the Position Approximate of target object.Seed filling is to be seed points with this point, with certain colouring information be standard to around diffusion, all find up to all pixels of will meet the demands (being template matches).
G). the multiple image Fusion Module, use multiframe fusion treatment technology and restore motion blur image.At last view data and the motion control data handled well are transferred to the high speed information communication module.
H). the high speed information communication module, this module links to each other with the output peripheral hardware: chromatic liquid crystal screen, host computer, and RS485 bus.The data of handling well are sent by EDMA.
TMS320DM644x is the dual microprocessors that a slice kernel is made up of ARM926EJ-S stone and TMS320C64X+DSP stone.Its processing speed is up to the clock frequency of ARM9---300MHZ; The clock frequency of C64x+---600MHZ.And it offers the Peripheral Interface that the user enriches, can be directly and digital CMOS camera (IMAGE INPUT) and digital liquid crystal screen (IMAGE OUTPUT) do interface, nearly 2 tunnel video window output can be provided.This processor provides multiple load mode (BOOTLOAD MODE), for user (USER) programming program provides multiple channel.
So this chip of TMS320DM644x can be competent at this task of CPU of high speed robot's embedded vision system fully, and can predict, the hardware of this system can not run into substantial difficulty in realization, and this mainly gives the credit to the kernel of this chip and provides sufficient consideration with the exploitation that is made as portable media device (PDA) outward.
4. image display, this module is used to show man-machine interface and image, is that a slice numeral touches color LCD screen.The image of handling well can be shown in real time, and Flame Image Process application program and image wireless transmission procedure and motion control application program etc. that the ARM926EJ-S stone that utilizes TMS320DM644x will be embedded in wherein show and the WINCE desktop, so that the management of system-level man-machine interface.
5. motion-control module, this module connects motor by the RS485 bus, how to control the motion of each motor according to the decision of the view data after above-mentioned processing single-chip microcomputer.
6. image wireless transport module, this module is hung on the output device of TMS320DM644x outward, by wireless transmission method, with host computer real-time exchange data.So that host computer is for the subsequent treatment and the storage of view data.
The present invention can finish at a high speed: the clock frequency of ARM9---300MHZ; The clock frequency of C64x+---600MHZ; High real-time---the CPU core employing is grabbed formula and taken the thread mode preferentially to finish the interrupt task that real-time is had relatively high expectations---requires the Vision Builder for Automated Inspection of task.The high speed instruction execution speed of its kernel, again in conjunction with being embedded in optimised program code in the DSP/BIOS real time operating system thread efficiently---based on the RF5 framework---, add the target image picking rate of gigabit network interface, this system has been competent at fully as finishing at a high speed, and high real-time requires this role of task.
Claims (7)
1. Vision Builder for Automated Inspection at high real time image collecting and processing, it is characterized in that, comprise: illumination module, the digital CMOS camera model, image acquisition and the processing module that have gigabit ethernet interface, image display, motion-control module, image wireless transport module, wherein: illumination module irradiation target image, for the digital CMOS camera model collection that has gigabit ethernet interface; The digital CMOS camera model that has a gigabit ethernet interface is gathered the target image under the irradiation of illumination module, obtain raw image data, by its gigabit network interface Digital Image Data is sent to image acquisition and processing module fast, view data after image acquisition and processing module high speed processing is divided two-way output, one the tunnel outputs to image display shows, another road sends host computer to by the image wireless transport module, the control data that produces after image acquisition and processing module high speed processing sends to motion-control module, is used for drive motor.
2. the Vision Builder for Automated Inspection at high real time image collecting and processing according to claim 1, it is characterized in that, the described digital CMOS camera model that has gigabit ethernet interface, its image sampling rate reached for 200 frame/seconds, for follow-up image acquisition and processing module provide the image information data of magnanimity to be handled, adopt the real-time Data Transmission of ICP/IP protocol and image acquisition and processing modules implement high speed.
3. the Vision Builder for Automated Inspection at high real time image collecting and processing according to claim 1, it is characterized in that, described image acquisition and processing module comprise gigabit ethernet interface image transmission module, high speed acquisition module, image pretreatment module, distortion correction module, Region Segmentation module, colour space transformation processing module, target search module, template matches module, multiple image Fusion Module, high speed information communication module, wherein:
Described gigabit ethernet interface image transmission module sends to the high speed acquisition module with the speed acquisition destination image data near gigabit;
The view data that described high speed acquisition module collection gigabit ethernet interface image transmission module is sent also sends to the image pretreatment module;
Described image pretreatment module is carried out the image pre-service, obtains the better view data of visual effect, and sends to the distortion correction module;
Described distortion correction module is carried out after distortion correction handles view data, sends to the pattern recognition process that Region Segmentation module, colour space transformation processing module, target search module, template matches module are carried out image;
Described Region Segmentation module and colour space transformation processing module are transformed into the HIS space with the RGB component value of image and each pixel, finish image segmentation and image recognition in the HIS space, and deliver to target search module and template matches module;
Described target search module and template matches module will all find with the pixel of template matches with the method for target search, finish the task of pattern-recognition, and the result is delivered to the multiple image Fusion Module;
Described multiple image Fusion Module is used multiframe fusion treatment technology and is restored motion blur image, and the motion control data of the pictorial data that will thoroughly handle well and generation send to the high speed information communication module;
Described high speed information communication module is sent the data of handling well, finishes the task of real-time Communication for Power.
4. the Vision Builder for Automated Inspection at high real time image collecting and processing according to claim 3 is characterized in that, described image pretreatment module, and its pre-service comprises figure image intensifying, image smoothing, image sharpening, wherein:
Histogram equalization techniques is adopted in described figure image intensifying, with the pixel grey scale of mapping relations modification original image, produces one than the more smooth histogram of former side figure, strengthens image effect;
Described image smoothing, promptly the denoising of image is handled, and adopts the neighborhood averaging technology, replaces the gray scale of this point with the mean value of adjoint point gray scale;
Described image sharpening, promptly the image border enhancement process adopts gradient method with the sharpening by differentiation treatment technology, uses the Grad of each location of pixels.
5. the Vision Builder for Automated Inspection at high real time image collecting and processing according to claim 1, it is characterized in that, described image display is used to show man-machine interface and image, is that a slice numeral touches color LCD screen, and the image of handling well is shown in real time.
6. the Vision Builder for Automated Inspection at high real time image collecting and processing according to claim 1, it is characterized in that, described image wireless transport module is the outer output device that is hung on image acquisition and processing module, by wireless transmission method and host computer real-time exchange data, so that host computer is for the subsequent treatment and the storage of view data.
7. the Vision Builder for Automated Inspection at high real time image collecting and processing according to claim 1, it is characterized in that, described motion-control module is to utilize the RS485 bus, based on monolithic processor controlled motor drive module, how to control the motion of each motor according to the decision of the view data after above-mentioned processing single-chip microcomputer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200810036843A CN100587638C (en) | 2008-04-29 | 2008-04-29 | Machine vision system aiming at high real time image collecting and processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200810036843A CN100587638C (en) | 2008-04-29 | 2008-04-29 | Machine vision system aiming at high real time image collecting and processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101276218A true CN101276218A (en) | 2008-10-01 |
| CN100587638C CN100587638C (en) | 2010-02-03 |
Family
ID=39995717
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200810036843A Active CN100587638C (en) | 2008-04-29 | 2008-04-29 | Machine vision system aiming at high real time image collecting and processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN100587638C (en) |
Cited By (28)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102044063A (en) * | 2010-12-23 | 2011-05-04 | 中国科学院自动化研究所 | FPGA (Field Programmable Gate Array) and DSP (Digital Signal Processor) based machine vision system |
| CN101576956B (en) * | 2009-05-11 | 2011-08-31 | 天津普达软件技术有限公司 | On-line character detection method based on machine vision and system thereof |
| CN102412627A (en) * | 2011-11-29 | 2012-04-11 | 安徽继远电网技术有限责任公司 | Image identification-based intelligent transformer substation state monitoring system |
| CN102521823A (en) * | 2011-11-08 | 2012-06-27 | 中国科学院深圳先进技术研究院 | Image processing method and system on basis of elastic imaging |
| CN102792124A (en) * | 2009-10-17 | 2012-11-21 | 荷马里光电子公司 | Enhanced imaging method and apparatus |
| CN102912714A (en) * | 2012-10-24 | 2013-02-06 | 华东交通大学 | Machine vision system used for acquiring and processing road crack images |
| CN103108131A (en) * | 2013-03-11 | 2013-05-15 | 深圳华用科技有限公司 | Industrial camera |
| CN103217929A (en) * | 2013-03-12 | 2013-07-24 | 河南科技大学 | Cotton foreign fiber sorting machine control system |
| CN103338191A (en) * | 2013-06-14 | 2013-10-02 | 誉阵电子科技（上海）有限公司 | Discrete machine vision device based on TCP/IP networking protocol and control method thereof |
| CN103685884A (en) * | 2013-10-22 | 2014-03-26 | 中国科学院半导体研究所 | Intelligent camera based on on-chip visual system |
| CN104647388A (en) * | 2014-12-30 | 2015-05-27 | 东莞市三瑞自动化科技有限公司 | Machine vision-based intelligent control method and machine vision-based intelligent control system for industrial robot |
| CN105023262A (en) * | 2014-04-23 | 2015-11-04 | 苏州瑞森特信息科技有限公司 | Visual detection controller |
| US9200890B2 (en) | 2012-05-22 | 2015-12-01 | Cognex Corporation | Machine vision systems and methods with predictive motion control |
| CN105830429A (en) * | 2013-12-09 | 2016-08-03 | 微软技术许可有限责任公司 | Handling video frames compromised by camera motion |
| CN105981364A (en) * | 2014-02-19 | 2016-09-28 | 索尼公司 | Image pickup apparatus, image pickup method and image pickup system |
| CN107197239A (en) * | 2017-07-06 | 2017-09-22 | 杭州柴滕自动化科技有限公司 | One kind based on taking the photograph IMAQ test device Ethernet optical fiber more |
| CN107205148A (en) * | 2017-07-06 | 2017-09-26 | 杭州柴滕自动化科技有限公司 | It is a kind of to take the photograph IMAQ test device based on cloud processing more |
| CN107529087A (en) * | 2017-09-29 | 2017-12-29 | 孔华 | Box programming statistics platform on piece |
| CN108169793A (en) * | 2017-12-27 | 2018-06-15 | 国家海洋局第海洋研究所 | A kind of earthquake data acquisition multi-protocols real-time transmission system |
| US10083496B2 (en) | 2012-05-22 | 2018-09-25 | Cognex Corporation | Machine vision systems and methods with predictive motion control |
| CN109000738A (en) * | 2018-09-27 | 2018-12-14 | 张浩然 | A kind of environmental monitoring system based on big data |
| CN109568751A (en) * | 2019-01-16 | 2019-04-05 | 傅新镇 | The in due course switching platform of instrument mode |
| CN109596066A (en) * | 2018-12-24 | 2019-04-09 | 欣辰卓锐（苏州）智能装备有限公司 | A kind of vision detection system of 3-D scanning imaging |
| CN109890005A (en) * | 2019-03-25 | 2019-06-14 | 王洁 | Multi-functional big data communication system |
| WO2020062263A1 (en) * | 2018-09-30 | 2020-04-02 | 北京比特大陆科技有限公司 | Box device, method, and system for use in image recognition, and storage medium |
| CN111186769A (en) * | 2019-12-05 | 2020-05-22 | 靳霞 | Triangular support data search platform and method for balance |
| CN113596344A (en) * | 2021-07-26 | 2021-11-02 | 艾酷软件技术(上海)有限公司 | Shooting processing method and device, electronic equipment and readable storage medium |
| CN115610739A (en) * | 2022-09-26 | 2023-01-17 | 江阴瑞兴塑料玻璃制品有限公司 | Bubble state detection platform for glass film pasting machine |
-
2008
- 2008-04-29 CN CN200810036843A patent/CN100587638C/en active Active
Cited By (37)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101576956B (en) * | 2009-05-11 | 2011-08-31 | 天津普达软件技术有限公司 | On-line character detection method based on machine vision and system thereof |
| CN102792124B (en) * | 2009-10-17 | 2016-12-28 | 荷马里光电子公司 | The formation method strengthened and device |
| CN102792124A (en) * | 2009-10-17 | 2012-11-21 | 荷马里光电子公司 | Enhanced imaging method and apparatus |
| CN102044063A (en) * | 2010-12-23 | 2011-05-04 | 中国科学院自动化研究所 | FPGA (Field Programmable Gate Array) and DSP (Digital Signal Processor) based machine vision system |
| CN102044063B (en) * | 2010-12-23 | 2012-11-21 | 中国科学院自动化研究所 | FPGA (Field Programmable Gate Array) and DSP (Digital Signal Processor) based machine vision system |
| CN102521823A (en) * | 2011-11-08 | 2012-06-27 | 中国科学院深圳先进技术研究院 | Image processing method and system on basis of elastic imaging |
| CN102521823B (en) * | 2011-11-08 | 2013-12-11 | 中国科学院深圳先进技术研究院 | Image processing method and system on basis of elastic imaging |
| CN102412627B (en) * | 2011-11-29 | 2013-08-28 | 安徽继远电网技术有限责任公司 | Image identification-based intelligent transformer substation state monitoring system |
| CN102412627A (en) * | 2011-11-29 | 2012-04-11 | 安徽继远电网技术有限责任公司 | Image identification-based intelligent transformer substation state monitoring system |
| US10083496B2 (en) | 2012-05-22 | 2018-09-25 | Cognex Corporation | Machine vision systems and methods with predictive motion control |
| US9200890B2 (en) | 2012-05-22 | 2015-12-01 | Cognex Corporation | Machine vision systems and methods with predictive motion control |
| CN102912714A (en) * | 2012-10-24 | 2013-02-06 | 华东交通大学 | Machine vision system used for acquiring and processing road crack images |
| CN103108131A (en) * | 2013-03-11 | 2013-05-15 | 深圳华用科技有限公司 | Industrial camera |
| CN103217929A (en) * | 2013-03-12 | 2013-07-24 | 河南科技大学 | Cotton foreign fiber sorting machine control system |
| CN103217929B (en) * | 2013-03-12 | 2016-02-17 | 河南科技大学 | Control system of foreign cotton fiber sorting machine |
| CN103338191A (en) * | 2013-06-14 | 2013-10-02 | 誉阵电子科技（上海）有限公司 | Discrete machine vision device based on TCP/IP networking protocol and control method thereof |
| CN103685884A (en) * | 2013-10-22 | 2014-03-26 | 中国科学院半导体研究所 | Intelligent camera based on on-chip visual system |
| CN105830429A (en) * | 2013-12-09 | 2016-08-03 | 微软技术许可有限责任公司 | Handling video frames compromised by camera motion |
| CN105981364A (en) * | 2014-02-19 | 2016-09-28 | 索尼公司 | Image pickup apparatus, image pickup method and image pickup system |
| CN105023262A (en) * | 2014-04-23 | 2015-11-04 | 苏州瑞森特信息科技有限公司 | Visual detection controller |
| CN104647388A (en) * | 2014-12-30 | 2015-05-27 | 东莞市三瑞自动化科技有限公司 | Machine vision-based intelligent control method and machine vision-based intelligent control system for industrial robot |
| CN107197239A (en) * | 2017-07-06 | 2017-09-22 | 杭州柴滕自动化科技有限公司 | One kind based on taking the photograph IMAQ test device Ethernet optical fiber more |
| CN107205148A (en) * | 2017-07-06 | 2017-09-26 | 杭州柴滕自动化科技有限公司 | It is a kind of to take the photograph IMAQ test device based on cloud processing more |
| CN107529087A (en) * | 2017-09-29 | 2017-12-29 | 孔华 | Box programming statistics platform on piece |
| CN108169793A (en) * | 2017-12-27 | 2018-06-15 | 国家海洋局第海洋研究所 | A kind of earthquake data acquisition multi-protocols real-time transmission system |
| CN109000738A (en) * | 2018-09-27 | 2018-12-14 | 张浩然 | A kind of environmental monitoring system based on big data |
| WO2020062263A1 (en) * | 2018-09-30 | 2020-04-02 | 北京比特大陆科技有限公司 | Box device, method, and system for use in image recognition, and storage medium |
| CN109596066A (en) * | 2018-12-24 | 2019-04-09 | 欣辰卓锐（苏州）智能装备有限公司 | A kind of vision detection system of 3-D scanning imaging |
| CN109568751A (en) * | 2019-01-16 | 2019-04-05 | 傅新镇 | The in due course switching platform of instrument mode |
| CN109890005A (en) * | 2019-03-25 | 2019-06-14 | 王洁 | Multi-functional big data communication system |
| CN109890005B (en) * | 2019-03-25 | 2020-08-11 | 岳阳县辉通物联网科技有限公司 | Multifunctional big data communication system |
| CN111186769A (en) * | 2019-12-05 | 2020-05-22 | 靳霞 | Triangular support data search platform and method for balance |
| CN111186769B (en) * | 2019-12-05 | 2021-12-14 | 珠海市华兴软件信息服务有限公司 | Triangular support data search platform and method for balance |
| CN113596344A (en) * | 2021-07-26 | 2021-11-02 | 艾酷软件技术(上海)有限公司 | Shooting processing method and device, electronic equipment and readable storage medium |
| CN113596344B (en) * | 2021-07-26 | 2023-10-24 | 艾酷软件技术(上海)有限公司 | Shooting processing method, shooting processing device, electronic equipment and readable storage medium |
| CN115610739A (en) * | 2022-09-26 | 2023-01-17 | 江阴瑞兴塑料玻璃制品有限公司 | Bubble state detection platform for glass film pasting machine |
| CN115610739B (en) * | 2022-09-26 | 2023-05-16 | 江阴瑞兴塑料玻璃制品有限公司 | Glass film pasting machinery bubble state detection platform |
Also Published As
| Publication number | Publication date |
|---|---|
| CN100587638C (en) | 2010-02-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN100587638C (en) | Machine vision system aiming at high real time image collecting and processing | |
| CN103424409B (en) | Vision detecting system based on DSP | |
| CN106896069B (en) | A kind of spectrum reconstruction method based on color digital camera single width RGB image | |
| WO2023134793A2 (en) | Machine vision-based machine tool part online inspection method | |
| CN105538345B (en) | A kind of puma manipulator and positioning assembly method based on many camera lenses | |
| CN107635129B (en) | Three-dimensional trinocular camera device and depth fusion method | |
| CN110390691A (en) | A kind of ore scale measurement method and application system based on deep learning | |
| CN100483446C (en) | Non-contact optical fingerprint image collecting method and system | |
| CN102704215B (en) | Automatic cutting method of embroidery cloth based on combination of DST file parsing and machine vision | |
| CN103714345B (en) | A kind of method and system of binocular stereo vision detection finger fingertip locus | |
| WO2018120446A1 (en) | Parallel and coordinated processing method for real-time target recognition-oriented heterogeneous processor | |
| CN109886312A (en) | A kind of bridge wheel of vehicle detection method based on multilayer feature fused neural network model | |
| CN104568981A (en) | Building wall defect measurement method based on image and system thereof | |
| CN102912714A (en) | Machine vision system used for acquiring and processing road crack images | |
| CN102855626A (en) | Methods and devices for light source direction calibration and human information three-dimensional collection | |
| CN101477062A (en) | Recognition method and device for chopped fiber microscopic structural parameters in rubber based material | |
| CN109767428A (en) | A kind of dirty detection method of camera module | |
| CN102637301A (en) | Method for automatically evaluating color quality of image during aerial photography in real time | |
| CN109949231A (en) | A kind of method and device for urban managing information acquiring and processing | |
| CN109738448A (en) | A kind of industrial products intelligent detection device and method | |
| CN101599172A (en) | The illumination compensation splitting method of the text image of inhomogeneous illumination | |
| CN105631799A (en) | Moving platform laser infrared fusion detection and recognition system | |
| CN1303574C (en) | Realp-time 3-D image processing device | |
| CN107300360A (en) | A kind of shaft size fast algorithm of detecting of rain fed crops seed three | |
| CN107680079B (en) | The high-speed parallel visible detection method of visible foreign matters in a kind of medical pharmacy |
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: 20170531 Address after: No. 3689 road Anhui Wuhu Economic Development Zone 241000 Anhui County of Wuhu Province Patentee after: Ke Shuo (Wuhu) Co. Ltd. Intelligent Technology Address before: 200240 Dongchuan Road, Shanghai, No. 800, No. Patentee before: Shanghai Jiao Tong University |